This research is developing an incubator system that integrates the internet of things and artificial intelligence to improve care for premature babies. The system workflow starts with sensors that collect data from the incubator. Then, the data is sent in real-time to the internet of things (IoT) broker eclipse mosquito using the message queue telemetry transport (MQTT) protocol version 5.0. After that, the data is stored in a database for analysis using the long short-term memory network (LSTM) method and displayed in a web application using an application programming interface (API) service. Furthermore, the experimental results produce as many as 2,880 rows of data stored in the database. The correlation coefficient between the target attribute and other attributes ranges from 0.23 to 0.48. Next, several experiments were conducted to evaluate the model-predicted value on the test data. The best results are obtained using a two-layer LSTM configuration model, each with 60 neurons and a lookback setting 6. This model produces an R 2 value of 0.934, with a root mean square error (RMSE) value of 0.015 and a mean absolute error (MAE) of 0.008. In addition, the R 2 value was also evaluated for each attribute used as input, with a result of values between 0.590 and 0.845.
Real-time wireless temperature measurement system of infant incubatorIJECEIAES
The internet of things (IoT) has allowed for ubiquitous measurement. Infant incubator temperature is one of crucial parts that need to be measured, especially for the stability and uniformity temperature. Based on the interpretation of IEC 60601-2-19, we proposed measurement method using IoT with the message queue telemetry transport (MQTT). In the 10,000 packet, the result shows the quality of service (QoS) level 2 of the system has the highest delay, however it has the lowest packet loss data than the other QoS. For 1 hour, the uniformity result and stability can fulfill the standards. Uniformity of 32°C, the lowest difference is point C with 0.32 °C, and the highest difference is point B with 0.75 °C. Uniformity of 36 °C, the lowest difference is point B with 0.27 °C, and the highest difference is point C with 0.79 °C. The stability of 32 °C and 36 °C is 0.32 °C and 0.44 °C, respectively. Moreover, the Kruskal Wallis test shows the highest difference average from point M is point A and B. It occurred because of the point A and B located far from the heater part, so the point A and B colder than point C.
IRJET- Monitoring of Incubator using IotIRJET Journal
This document describes a project to monitor neonatal incubators using IoT technology. Sensors are connected to a NodeMCU to measure parameters like temperature, humidity, light levels, gas levels, and pulse rate of babies in incubators. If any parameters exceed safe levels, a notification is sent to doctors and nurses via an Ubidots cloud platform. This allows for remote monitoring of incubators and addresses issues like overheating or gas leaks that could endanger premature infants' lives. The goal is to provide safe, low-cost monitoring and reduce infant mortality rates.
INTERNET OF THINGS BASED MODEL FOR IDENTIFYING PEDIATRIC EMERGENCY CASESpijans
Pediatric emergency cases need rapid systems that measure vital body parameters data, analyze and
categorize emergency cases for precise action. Current systems use manual examination resulting in
delayed medication, death, or other severe medical conditions.In this paper, we propose a Internet of
Things (IoT) based model, created using Balena fin with Raspberry pi compute module. It is used for
determining emergency cases, in pediatric section, specifically the triage section. It is later tested using
hospital data that represents the vital parameters in pediatric. Our approach entails designing and setting
up the hardware and software infrastructure, to accommodate data via Bluetooth protocol, and transmit it
to the cloud server database via Message Queuing Telemetry Transport (MQTT). Later, we perform
machine learning on the data by training a model and finally develop a Plotly Dash analytical application
integrating the model for visualization near real-time.Findings show that emergency cases are detected
using vital body parameters which include the body temperature, oxygen levels, heart rate and the age. The
model indicates a 97% accuracy.In conclusion, children’s emergency cases are detected in time using IoT
gadgets and machine learning classification.
INTERNET OF THINGS BASED MODEL FOR IDENTIFYING PEDIATRIC EMERGENCY CASESpijans
This document proposes an IoT-based model for identifying pediatric emergency cases using vital body parameters data collected from Bluetooth sensors. The model uses a Raspberry Pi device to collect temperature, oxygen, heart rate, and blood pressure data and transmit it via MQTT to an AWS cloud database. A machine learning model is trained on historical hospital data and achieves 97% accuracy in classifying cases as emergency, non-emergency, or moderate emergency. The model provides a way to rapidly identify pediatric emergency cases using wireless sensors and cloud-based analytics.
INTERNET OF THINGS BASED MODEL FOR IDENTIFYING PEDIATRIC EMERGENCY CASESamsjournal
Pediatric emergency cases need rapid systems that measure vital body parameters data, analyze and
categorize emergency cases for precise action. Current systems use manual examination resulting in
delayed medication, death, or other severe medical conditions.In this paper, we propose a Internet of
Things (IoT) based model, created using Balena fin with Raspberry pi compute module. It is used for
determining emergency cases, in pediatric section, specifically the triage section. It is later tested using
hospital data that represents the vital parameters in pediatric. Our approach entails designing and setting
up the hardware and software infrastructure, to accommodate data via Bluetooth protocol, and transmit it
to the cloud server database via Message Queuing Telemetry Transport (MQTT). Later, we perform
machine learning on the data by training a model and finally develop a Plotly Dash analytical application
integrating the model for visualization near real-time.Findings show that emergency cases are detected
using vital body parameters which include the body temperature, oxygen levels, heart rate and the age. The
model indicates a 97% accuracy.In conclusion, children’s emergency cases are detected in time using IoT
gadgets and machine learning classification.
INTERNET OF THINGS BASED MODEL FOR IDENTIFYING PEDIATRIC EMERGENCY CASES pijans
Pediatric emergency cases need rapid systems that measure vital body parameters data, analyze and
categorize emergency cases for precise action. Current systems use manual examination resulting in
delayed medication, death, or other severe medical conditions.In this paper, we propose a Internet of
Things (IoT) based model, created using Balena fin with Raspberry pi compute module. It is used for
determining emergency cases, in pediatric section, specifically the triage section. It is later tested using
hospital data that represents the vital parameters in pediatric. Our approach entails designing and setting
up the hardware and software infrastructure, to accommodate data via Bluetooth protocol, and transmit it
to the cloud server database via Message Queuing Telemetry Transport (MQTT)
IRJET- Smart and Secure IoT based Child Monitoring SystemIRJET Journal
The document describes a proposed smart and secure IoT-based child monitoring system. The system uses radar devices and obstacle sensors to detect when a child enters a danger zone or approaches a harmful object, then alerts the caregiver via mobile notification or alarm. Waterproof ultrasonic sensors placed in a locket worn by the baby would detect dangers and alert the caregiver's mobile device. The system aims to solve problems for baby guardians and secure babies from dangers, notifying guardians when hazards are near. It also reviews several related works on child monitoring systems and IoT applications and their methodologies and findings.
This document discusses a proposed system for warehouse management using IoT. The system would use sensors like DHT11 (for temperature and humidity), a flame detector, and an ADXL335 accelerometer to continuously monitor the environment in a warehouse for factors like temperature, moisture, fire, and earthquakes. If any emergency events are detected, such as a fire or earthquake, the system would send alert messages via GSM to notify warehouse officials, emergency services, and hospitals so they can respond quickly. The system aims to automate environmental monitoring and alerting to improve safety and efficiency over manual methods, while using low-cost, low-power components suitable for rural areas.
Real-time wireless temperature measurement system of infant incubatorIJECEIAES
The internet of things (IoT) has allowed for ubiquitous measurement. Infant incubator temperature is one of crucial parts that need to be measured, especially for the stability and uniformity temperature. Based on the interpretation of IEC 60601-2-19, we proposed measurement method using IoT with the message queue telemetry transport (MQTT). In the 10,000 packet, the result shows the quality of service (QoS) level 2 of the system has the highest delay, however it has the lowest packet loss data than the other QoS. For 1 hour, the uniformity result and stability can fulfill the standards. Uniformity of 32°C, the lowest difference is point C with 0.32 °C, and the highest difference is point B with 0.75 °C. Uniformity of 36 °C, the lowest difference is point B with 0.27 °C, and the highest difference is point C with 0.79 °C. The stability of 32 °C and 36 °C is 0.32 °C and 0.44 °C, respectively. Moreover, the Kruskal Wallis test shows the highest difference average from point M is point A and B. It occurred because of the point A and B located far from the heater part, so the point A and B colder than point C.
IRJET- Monitoring of Incubator using IotIRJET Journal
This document describes a project to monitor neonatal incubators using IoT technology. Sensors are connected to a NodeMCU to measure parameters like temperature, humidity, light levels, gas levels, and pulse rate of babies in incubators. If any parameters exceed safe levels, a notification is sent to doctors and nurses via an Ubidots cloud platform. This allows for remote monitoring of incubators and addresses issues like overheating or gas leaks that could endanger premature infants' lives. The goal is to provide safe, low-cost monitoring and reduce infant mortality rates.
INTERNET OF THINGS BASED MODEL FOR IDENTIFYING PEDIATRIC EMERGENCY CASESpijans
Pediatric emergency cases need rapid systems that measure vital body parameters data, analyze and
categorize emergency cases for precise action. Current systems use manual examination resulting in
delayed medication, death, or other severe medical conditions.In this paper, we propose a Internet of
Things (IoT) based model, created using Balena fin with Raspberry pi compute module. It is used for
determining emergency cases, in pediatric section, specifically the triage section. It is later tested using
hospital data that represents the vital parameters in pediatric. Our approach entails designing and setting
up the hardware and software infrastructure, to accommodate data via Bluetooth protocol, and transmit it
to the cloud server database via Message Queuing Telemetry Transport (MQTT). Later, we perform
machine learning on the data by training a model and finally develop a Plotly Dash analytical application
integrating the model for visualization near real-time.Findings show that emergency cases are detected
using vital body parameters which include the body temperature, oxygen levels, heart rate and the age. The
model indicates a 97% accuracy.In conclusion, children’s emergency cases are detected in time using IoT
gadgets and machine learning classification.
INTERNET OF THINGS BASED MODEL FOR IDENTIFYING PEDIATRIC EMERGENCY CASESpijans
This document proposes an IoT-based model for identifying pediatric emergency cases using vital body parameters data collected from Bluetooth sensors. The model uses a Raspberry Pi device to collect temperature, oxygen, heart rate, and blood pressure data and transmit it via MQTT to an AWS cloud database. A machine learning model is trained on historical hospital data and achieves 97% accuracy in classifying cases as emergency, non-emergency, or moderate emergency. The model provides a way to rapidly identify pediatric emergency cases using wireless sensors and cloud-based analytics.
INTERNET OF THINGS BASED MODEL FOR IDENTIFYING PEDIATRIC EMERGENCY CASESamsjournal
Pediatric emergency cases need rapid systems that measure vital body parameters data, analyze and
categorize emergency cases for precise action. Current systems use manual examination resulting in
delayed medication, death, or other severe medical conditions.In this paper, we propose a Internet of
Things (IoT) based model, created using Balena fin with Raspberry pi compute module. It is used for
determining emergency cases, in pediatric section, specifically the triage section. It is later tested using
hospital data that represents the vital parameters in pediatric. Our approach entails designing and setting
up the hardware and software infrastructure, to accommodate data via Bluetooth protocol, and transmit it
to the cloud server database via Message Queuing Telemetry Transport (MQTT). Later, we perform
machine learning on the data by training a model and finally develop a Plotly Dash analytical application
integrating the model for visualization near real-time.Findings show that emergency cases are detected
using vital body parameters which include the body temperature, oxygen levels, heart rate and the age. The
model indicates a 97% accuracy.In conclusion, children’s emergency cases are detected in time using IoT
gadgets and machine learning classification.
INTERNET OF THINGS BASED MODEL FOR IDENTIFYING PEDIATRIC EMERGENCY CASES pijans
Pediatric emergency cases need rapid systems that measure vital body parameters data, analyze and
categorize emergency cases for precise action. Current systems use manual examination resulting in
delayed medication, death, or other severe medical conditions.In this paper, we propose a Internet of
Things (IoT) based model, created using Balena fin with Raspberry pi compute module. It is used for
determining emergency cases, in pediatric section, specifically the triage section. It is later tested using
hospital data that represents the vital parameters in pediatric. Our approach entails designing and setting
up the hardware and software infrastructure, to accommodate data via Bluetooth protocol, and transmit it
to the cloud server database via Message Queuing Telemetry Transport (MQTT)
IRJET- Smart and Secure IoT based Child Monitoring SystemIRJET Journal
The document describes a proposed smart and secure IoT-based child monitoring system. The system uses radar devices and obstacle sensors to detect when a child enters a danger zone or approaches a harmful object, then alerts the caregiver via mobile notification or alarm. Waterproof ultrasonic sensors placed in a locket worn by the baby would detect dangers and alert the caregiver's mobile device. The system aims to solve problems for baby guardians and secure babies from dangers, notifying guardians when hazards are near. It also reviews several related works on child monitoring systems and IoT applications and their methodologies and findings.
This document discusses a proposed system for warehouse management using IoT. The system would use sensors like DHT11 (for temperature and humidity), a flame detector, and an ADXL335 accelerometer to continuously monitor the environment in a warehouse for factors like temperature, moisture, fire, and earthquakes. If any emergency events are detected, such as a fire or earthquake, the system would send alert messages via GSM to notify warehouse officials, emergency services, and hospitals so they can respond quickly. The system aims to automate environmental monitoring and alerting to improve safety and efficiency over manual methods, while using low-cost, low-power components suitable for rural areas.
Smart internet of things kindergarten garbage observation system using Ardui...IJECEIAES
Increase the in population and kindergarten number, especially in urban areas made it difficult to properly manage waste. Thus, this paper proposed a system dedicated to kindergartens to manage to dispose of waste, the system can be called smart garbage based on internet of things (SGI). To ensure a healthy environment and an intelligent waste in the kindergarten management system in an integrated manner and supported by the internet of things (IoT), we presented it in detail identification, the SGI system includes details like a display system, an automatic lid system, and a communication system. This system supplied capabilities to monitor the status of waste continuously and on IoT website can show the percentage of waste placed inside the bin. And by using a Wi-Fi communication system, between the system unit and the monitoring body, to collect waste when the trash is full. The smart system proposed in this paper is the most efficient system of traditional waste management systems because it reduces the use of manpower and significantly limits the spread of waste and fully controls it. Additionally, it can be linked via the IoT to the mobile, thus forming an integrated monitoring system.
This document proposes an IoT-based monitoring system for smart home services using a tri-level context making model. The system includes sensor nodes with various sensors that collect environmental data and send it wirelessly to an ARM microcontroller connected to the internet. The microcontroller analyzes the data using the tri-level context model to generate high-level contexts and determine appropriate actions. This allows users to monitor parameters and control devices via the internet. The system was prototyped and tested through scenarios like disaster management and health care services.
IRJET- Health Monitoring system using IoTIRJET Journal
This document summarizes a research paper on a health monitoring system using IoT. The system measures body temperature and heart rate using sensors connected to an Arduino board. The Arduino transmits the sensor data wirelessly to a ThingSpeak platform using an ESP8266 WiFi module. This allows the sensor data to be stored, visualized, and accessed over time on the ThingSpeak server. The system aims to provide convenient remote health monitoring and storage of vital sign data over periods of time using IoT technology.
IRJET - Poultry Farm Controlling based on IoTIRJET Journal
This document describes a poultry farm monitoring system using IoT technology. The system uses sensors to monitor temperature, humidity, gas levels and food levels in the farm. An Arduino Mega controller collects data from the sensors and sends it to the cloud. Users can then view the sensor data through a mobile app, which will also notify them of any abnormal conditions. The system aims to automate 80% of the farm monitoring process and remotely manage conditions in the poultry house.
Smart health monitoring system using IoT based smart fitness mirrorTELKOMNIKA JOURNAL
The smart fitness mirror proposed in this researchaims to provide the users with a platform to monitor their health and fitness status on a daily basis. The system employs a number of sensors to monitor the body mass index (BMI) and amount of body fat present in the user’s body. A weight scale consisting of four load sensors has been implemented to obtain the weight of the user whereas an ultrasonic sensor has been used to measure the height of the user. In addition, four electrode plates have been implemented on the foot weight scale to infuse a small amount of electric current (1mA) for BIA (bioelectrical impedance analysis) to estimate the amount of body fat percentage, lean body mass and total body water. An IR temperature sensor has been implemented in the research to measure the temperature of the user’s body from the forehead. Tests conducted on the system illustrate that it is able to accurately compute the body mass index and perform a bioelectrical impedance analysis on the user. The system is able to achieve a 92.5 % and 93.7 % accuracy in determining the body mass index and body fat percentage respectively. An accuracy of 95.3 % was observed in the determination of the body temperature.
Real-time monitoring system for weather and air pollutant measurement with HT...journalBEEI
This system summarizes the development of a real-time monitoring system for weather and air pollutant measurement with an HTML-based user interface application. The system includes sensors to measure weather parameters like wind, rain, temperature, and humidity, as well as air pollutants. A microcontroller collects and transmits the sensor data to a cloud database in real-time. A web application then displays the data for users. Field testing showed the sensors accurately measured various weather and pollution levels over a day. The HTML interface provided an informative display of the real-time environmental information.
IRJET- Review Paper on –Baby Cradle Monitoring SystemIRJET Journal
This document describes a proposed baby cradle monitoring system that uses various sensors to monitor babies and update parents. It discusses designing a smart baby cradle with features like camera monitoring, automatic swinging when the baby cries, sensing wetness in the baby's bed, monitoring the baby's presence in the cradle, and sending SMS messages to parents' phones to notify them about the baby's status. The proposed system aims to help busy working parents remotely monitor their babies using new technologies while alleviating their stress and anxiety. It outlines the existing limitations and proposes a new architecture using sensors, microcontrollers, and wireless communication.
This document describes an IoT-based patient monitoring system that collects a patient's vital signs like heartbeat, temperature, ECG, oxygen level, and other data using sensors. The data is sent to a cloud platform called ThingSpeak and can be accessed through a mobile application. This allows medical staff to remotely monitor patients in real-time. Key benefits of the system include reduced errors, decreased costs by reducing visits, better patient experience through continuous monitoring, and ability to provide quick treatment if abnormalities are detected. The system uses a NodeMCU microcontroller along with sensors like a pulse oximeter, temperature sensor, and ECG sensor to collect and transmit the health data.
SMART INCUBATOR FOR INFANT MONITORING.pptxNANDHAKUMARA10
to build the prototype of a smart incubator to monitor the vital parameters of the newborns in their neonatal period (First 4 weeks after birth). The smart incubator is capable of monitoring the baby’s body temperature and other vital parameters required by the doctor for examining the newborn. The incubator is based on IoT and other edge computing techniques
Smart management system for monitoring and control of infant baby bed IJECEIAES
Step by step the innovation likewise becomes exceptionally quick and the human makes it. Thus, it is imperative to take care of the people to come, a unique consideration ought to be appeared to them particularly indulges. This paper manages plan and usage of intelligent child support framework which is extraordinary blessing to guardians in this century In this work a baby bed with intelligent system was be designed and implemented. Many sensors where be used to monitor the baby behavior. The component of this project consist of a smart camera, moisture sensor, sensitive Dc Motor and WiFi system.
The document describes a proposed IoT-based smart cradle system for baby monitoring. The system would use sensors to monitor a baby's vital signs and movements in the cradle. It would automatically rock the cradle in response to crying or discomfort. Parents could monitor the baby remotely through a mobile app that displays sensor data and sends alerts. The goal is to enhance parental care and safety by reducing the need for constant physical intervention through automated responses and remote monitoring capabilities enabled by IoT technologies.
IoT based temperature and humidity monitoring frameworkjournalBEEI
This study explored the use of Internet of Things (IoT) in monitoring the temperature and humidity of a data centre in real-time using a simple monitoring system to determine the relationship and difference between temperature and humidity with respect to the different locations of measurements. The development of temperature and humidity monitoring system was accomplished using the proposed framework and has been deployed at the data centre of Politeknik Muadzam Shah, where the readings were recorded and sent to an IoT platform of AT&T M2X to be stored. The data was then retrieved and analysed showing that there was a significant difference in temperature and humidity measured at different locations. X The monitoring system was also successful in detecting extreme changes in temperature and humidity and automatically send a notification to IT personnel via e-mail, short messaging service (SMS) and mobile push notification for further action.
GPS BASED VULNERABLE CHILD TRACKING SYSTEMIRJET Journal
This document describes a GPS-based vulnerable child tracking system. The system uses sensors attached to the child to track their location and activities. A mobile application allows parents to view the child's location in real-time using GPS and see video of the child's activities at school that is captured by a camera and sent to the parents' phones. The system is designed to help working parents monitor their child's safety and activities even when away from home through remote tracking and video monitoring using sensors, GPS, and an IoT-based cloud computing system.
An intelligent irrigation system based on internet of things (IoT) to minimiz...nooriasukmaningtyas
This paper proposes a comparison of three machine learning algorithms for a better intelligent irrigation system based on internet of things (IoT) for differents products. This work's major contribution is to specify the most accurate algorithm among the three machine learning algorithms (k-nearest neighbors (KNN), support vector machine (SVM), artificial neural network (ANN)). This is achieved by collecting irrigation data of a specific products and split it into training data and test data then compare the accuracy of the three algorithms. To evaluate the performance of our algorithm we built a system of IoT devices. The temperature and humidity sensors are installed in the field interact with the Arduino microcontroller. The Arduino is connected to Raspberry Pi3, which holds the machine learning algorithm. It turned out to be ANN algorithm is the most accurate for such system of irrigation. The ANN algorithm is the best choice for an intelligent system to minimize water loss for some products.
Low-cost real-time internet of things-based monitoring system for power grid ...IJECEIAES
This system creates a low-cost IoT-based monitoring system for power grid transformers to monitor their status in real-time. Sensors measure temperature, humidity, oil level, voltage, vibration, and pressure and send the data via ESP32 to a cloud interface. This allows maintenance centers to detect abnormalities before failures and improve transformer efficiency in smart grids. The low-cost system was built for under $23 using inexpensive and accessible components like an ESP32 board, DHT22 sensor, and ultrasonic sensor. It demonstrates the feasibility of remotely monitoring transformers to extend their lifetimes.
This document describes an Internet of Things (IoT) based greenhouse monitoring system that monitors temperature and soil moisture using sensors. The sensor data is sent over WiFi to a cloud server every 3 hours using MQTT protocol. Users can access the sensor data from anywhere using an internet connection and control greenhouse parameters remotely. The system aims to provide low-cost and flexible monitoring of greenhouse conditions without needing a dedicated server. It demonstrates monitoring temperature and soil moisture to evaluate the feasibility of the IoT-enabled smart greenhouse.
A Review Paper on Doctorless Intelligent Covid CenterIRJET Journal
This document reviews a proposed contactless patient health monitoring system for COVID centers. The system would employ touchless technology to prevent infection spread by avoiding direct contact with patients. Sensors would collect patient data like temperature and oxygen levels and transmit it to a microcontroller. The data would be stored in LabVIEW on a server. Applications like paramedic robots would be used to deliver meals and medicine to eliminate personal contact between patients and healthcare providers. The goal is to minimize physical contact with COVID patients and allow remote monitoring by doctors.
This document summarizes literature on health care monitoring systems using wireless sensors and cloud storage. It discusses technologies like ZigBee, embedded microcontrollers, and Bluetooth that are used in wireless sensor networks to monitor patient vitals. The data collected is stored in the cloud and can be accessed by doctors. Challenges discussed include ensuring reliability, quality of service, security, and privacy of patient data. The literature proposes systems for continuous remote patient monitoring, early warning systems, and alerting doctors and caregivers of any issues.
IRJET-Experimental Investigation on the Effect of TiO2 Particles on MortarsIRJET Journal
This document describes a proposed system to monitor patient body temperature using IoT and a microservices architecture. An Arduino device with temperature sensor would collect body temperature data and send it over WiFi to a cloud system. The cloud system would use a microservices architecture with three main services: 1) an API to receive temperature data, 2) a queue to store incoming data, and 3) a computation service to analyze data for anomalies and send alerts. The system is designed to be horizontally scalable and fault tolerant to reliably process large amounts of patient monitoring data.
This document summarizes a seminar topic on animal monitoring using the Internet of Things. It discusses using sensors on animal collars to monitor body temperature, rumination, heart rate, and location. The hardware architecture uses collars on animals to collect sensor data and beacons to track location. A cloud platform analyzes the collected data to provide information to farmers on animal behavior and health. Potential applications include early detection of health issues in animals and understanding animal movement patterns. Future areas of research may involve using satellite tracking and camera traps to monitor wild animals. The conclusion evaluates machine learning algorithms for categorizing animal posture data collected from sensor collars.
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Contenu connexe
Similaire à Developing a smart system for infant incubators using the internet of things and artificial intelligence
Smart internet of things kindergarten garbage observation system using Ardui...IJECEIAES
Increase the in population and kindergarten number, especially in urban areas made it difficult to properly manage waste. Thus, this paper proposed a system dedicated to kindergartens to manage to dispose of waste, the system can be called smart garbage based on internet of things (SGI). To ensure a healthy environment and an intelligent waste in the kindergarten management system in an integrated manner and supported by the internet of things (IoT), we presented it in detail identification, the SGI system includes details like a display system, an automatic lid system, and a communication system. This system supplied capabilities to monitor the status of waste continuously and on IoT website can show the percentage of waste placed inside the bin. And by using a Wi-Fi communication system, between the system unit and the monitoring body, to collect waste when the trash is full. The smart system proposed in this paper is the most efficient system of traditional waste management systems because it reduces the use of manpower and significantly limits the spread of waste and fully controls it. Additionally, it can be linked via the IoT to the mobile, thus forming an integrated monitoring system.
This document proposes an IoT-based monitoring system for smart home services using a tri-level context making model. The system includes sensor nodes with various sensors that collect environmental data and send it wirelessly to an ARM microcontroller connected to the internet. The microcontroller analyzes the data using the tri-level context model to generate high-level contexts and determine appropriate actions. This allows users to monitor parameters and control devices via the internet. The system was prototyped and tested through scenarios like disaster management and health care services.
IRJET- Health Monitoring system using IoTIRJET Journal
This document summarizes a research paper on a health monitoring system using IoT. The system measures body temperature and heart rate using sensors connected to an Arduino board. The Arduino transmits the sensor data wirelessly to a ThingSpeak platform using an ESP8266 WiFi module. This allows the sensor data to be stored, visualized, and accessed over time on the ThingSpeak server. The system aims to provide convenient remote health monitoring and storage of vital sign data over periods of time using IoT technology.
IRJET - Poultry Farm Controlling based on IoTIRJET Journal
This document describes a poultry farm monitoring system using IoT technology. The system uses sensors to monitor temperature, humidity, gas levels and food levels in the farm. An Arduino Mega controller collects data from the sensors and sends it to the cloud. Users can then view the sensor data through a mobile app, which will also notify them of any abnormal conditions. The system aims to automate 80% of the farm monitoring process and remotely manage conditions in the poultry house.
Smart health monitoring system using IoT based smart fitness mirrorTELKOMNIKA JOURNAL
The smart fitness mirror proposed in this researchaims to provide the users with a platform to monitor their health and fitness status on a daily basis. The system employs a number of sensors to monitor the body mass index (BMI) and amount of body fat present in the user’s body. A weight scale consisting of four load sensors has been implemented to obtain the weight of the user whereas an ultrasonic sensor has been used to measure the height of the user. In addition, four electrode plates have been implemented on the foot weight scale to infuse a small amount of electric current (1mA) for BIA (bioelectrical impedance analysis) to estimate the amount of body fat percentage, lean body mass and total body water. An IR temperature sensor has been implemented in the research to measure the temperature of the user’s body from the forehead. Tests conducted on the system illustrate that it is able to accurately compute the body mass index and perform a bioelectrical impedance analysis on the user. The system is able to achieve a 92.5 % and 93.7 % accuracy in determining the body mass index and body fat percentage respectively. An accuracy of 95.3 % was observed in the determination of the body temperature.
Real-time monitoring system for weather and air pollutant measurement with HT...journalBEEI
This system summarizes the development of a real-time monitoring system for weather and air pollutant measurement with an HTML-based user interface application. The system includes sensors to measure weather parameters like wind, rain, temperature, and humidity, as well as air pollutants. A microcontroller collects and transmits the sensor data to a cloud database in real-time. A web application then displays the data for users. Field testing showed the sensors accurately measured various weather and pollution levels over a day. The HTML interface provided an informative display of the real-time environmental information.
IRJET- Review Paper on –Baby Cradle Monitoring SystemIRJET Journal
This document describes a proposed baby cradle monitoring system that uses various sensors to monitor babies and update parents. It discusses designing a smart baby cradle with features like camera monitoring, automatic swinging when the baby cries, sensing wetness in the baby's bed, monitoring the baby's presence in the cradle, and sending SMS messages to parents' phones to notify them about the baby's status. The proposed system aims to help busy working parents remotely monitor their babies using new technologies while alleviating their stress and anxiety. It outlines the existing limitations and proposes a new architecture using sensors, microcontrollers, and wireless communication.
This document describes an IoT-based patient monitoring system that collects a patient's vital signs like heartbeat, temperature, ECG, oxygen level, and other data using sensors. The data is sent to a cloud platform called ThingSpeak and can be accessed through a mobile application. This allows medical staff to remotely monitor patients in real-time. Key benefits of the system include reduced errors, decreased costs by reducing visits, better patient experience through continuous monitoring, and ability to provide quick treatment if abnormalities are detected. The system uses a NodeMCU microcontroller along with sensors like a pulse oximeter, temperature sensor, and ECG sensor to collect and transmit the health data.
SMART INCUBATOR FOR INFANT MONITORING.pptxNANDHAKUMARA10
to build the prototype of a smart incubator to monitor the vital parameters of the newborns in their neonatal period (First 4 weeks after birth). The smart incubator is capable of monitoring the baby’s body temperature and other vital parameters required by the doctor for examining the newborn. The incubator is based on IoT and other edge computing techniques
Smart management system for monitoring and control of infant baby bed IJECEIAES
Step by step the innovation likewise becomes exceptionally quick and the human makes it. Thus, it is imperative to take care of the people to come, a unique consideration ought to be appeared to them particularly indulges. This paper manages plan and usage of intelligent child support framework which is extraordinary blessing to guardians in this century In this work a baby bed with intelligent system was be designed and implemented. Many sensors where be used to monitor the baby behavior. The component of this project consist of a smart camera, moisture sensor, sensitive Dc Motor and WiFi system.
The document describes a proposed IoT-based smart cradle system for baby monitoring. The system would use sensors to monitor a baby's vital signs and movements in the cradle. It would automatically rock the cradle in response to crying or discomfort. Parents could monitor the baby remotely through a mobile app that displays sensor data and sends alerts. The goal is to enhance parental care and safety by reducing the need for constant physical intervention through automated responses and remote monitoring capabilities enabled by IoT technologies.
IoT based temperature and humidity monitoring frameworkjournalBEEI
This study explored the use of Internet of Things (IoT) in monitoring the temperature and humidity of a data centre in real-time using a simple monitoring system to determine the relationship and difference between temperature and humidity with respect to the different locations of measurements. The development of temperature and humidity monitoring system was accomplished using the proposed framework and has been deployed at the data centre of Politeknik Muadzam Shah, where the readings were recorded and sent to an IoT platform of AT&T M2X to be stored. The data was then retrieved and analysed showing that there was a significant difference in temperature and humidity measured at different locations. X The monitoring system was also successful in detecting extreme changes in temperature and humidity and automatically send a notification to IT personnel via e-mail, short messaging service (SMS) and mobile push notification for further action.
GPS BASED VULNERABLE CHILD TRACKING SYSTEMIRJET Journal
This document describes a GPS-based vulnerable child tracking system. The system uses sensors attached to the child to track their location and activities. A mobile application allows parents to view the child's location in real-time using GPS and see video of the child's activities at school that is captured by a camera and sent to the parents' phones. The system is designed to help working parents monitor their child's safety and activities even when away from home through remote tracking and video monitoring using sensors, GPS, and an IoT-based cloud computing system.
An intelligent irrigation system based on internet of things (IoT) to minimiz...nooriasukmaningtyas
This paper proposes a comparison of three machine learning algorithms for a better intelligent irrigation system based on internet of things (IoT) for differents products. This work's major contribution is to specify the most accurate algorithm among the three machine learning algorithms (k-nearest neighbors (KNN), support vector machine (SVM), artificial neural network (ANN)). This is achieved by collecting irrigation data of a specific products and split it into training data and test data then compare the accuracy of the three algorithms. To evaluate the performance of our algorithm we built a system of IoT devices. The temperature and humidity sensors are installed in the field interact with the Arduino microcontroller. The Arduino is connected to Raspberry Pi3, which holds the machine learning algorithm. It turned out to be ANN algorithm is the most accurate for such system of irrigation. The ANN algorithm is the best choice for an intelligent system to minimize water loss for some products.
Low-cost real-time internet of things-based monitoring system for power grid ...IJECEIAES
This system creates a low-cost IoT-based monitoring system for power grid transformers to monitor their status in real-time. Sensors measure temperature, humidity, oil level, voltage, vibration, and pressure and send the data via ESP32 to a cloud interface. This allows maintenance centers to detect abnormalities before failures and improve transformer efficiency in smart grids. The low-cost system was built for under $23 using inexpensive and accessible components like an ESP32 board, DHT22 sensor, and ultrasonic sensor. It demonstrates the feasibility of remotely monitoring transformers to extend their lifetimes.
This document describes an Internet of Things (IoT) based greenhouse monitoring system that monitors temperature and soil moisture using sensors. The sensor data is sent over WiFi to a cloud server every 3 hours using MQTT protocol. Users can access the sensor data from anywhere using an internet connection and control greenhouse parameters remotely. The system aims to provide low-cost and flexible monitoring of greenhouse conditions without needing a dedicated server. It demonstrates monitoring temperature and soil moisture to evaluate the feasibility of the IoT-enabled smart greenhouse.
A Review Paper on Doctorless Intelligent Covid CenterIRJET Journal
This document reviews a proposed contactless patient health monitoring system for COVID centers. The system would employ touchless technology to prevent infection spread by avoiding direct contact with patients. Sensors would collect patient data like temperature and oxygen levels and transmit it to a microcontroller. The data would be stored in LabVIEW on a server. Applications like paramedic robots would be used to deliver meals and medicine to eliminate personal contact between patients and healthcare providers. The goal is to minimize physical contact with COVID patients and allow remote monitoring by doctors.
This document summarizes literature on health care monitoring systems using wireless sensors and cloud storage. It discusses technologies like ZigBee, embedded microcontrollers, and Bluetooth that are used in wireless sensor networks to monitor patient vitals. The data collected is stored in the cloud and can be accessed by doctors. Challenges discussed include ensuring reliability, quality of service, security, and privacy of patient data. The literature proposes systems for continuous remote patient monitoring, early warning systems, and alerting doctors and caregivers of any issues.
IRJET-Experimental Investigation on the Effect of TiO2 Particles on MortarsIRJET Journal
This document describes a proposed system to monitor patient body temperature using IoT and a microservices architecture. An Arduino device with temperature sensor would collect body temperature data and send it over WiFi to a cloud system. The cloud system would use a microservices architecture with three main services: 1) an API to receive temperature data, 2) a queue to store incoming data, and 3) a computation service to analyze data for anomalies and send alerts. The system is designed to be horizontally scalable and fault tolerant to reliably process large amounts of patient monitoring data.
This document summarizes a seminar topic on animal monitoring using the Internet of Things. It discusses using sensors on animal collars to monitor body temperature, rumination, heart rate, and location. The hardware architecture uses collars on animals to collect sensor data and beacons to track location. A cloud platform analyzes the collected data to provide information to farmers on animal behavior and health. Potential applications include early detection of health issues in animals and understanding animal movement patterns. Future areas of research may involve using satellite tracking and camera traps to monitor wild animals. The conclusion evaluates machine learning algorithms for categorizing animal posture data collected from sensor collars.
Similaire à Developing a smart system for infant incubators using the internet of things and artificial intelligence (20)
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Advanced control scheme of doubly fed induction generator for wind turbine us...IJECEIAES
This paper describes a speed control device for generating electrical energy on an electricity network based on the doubly fed induction generator (DFIG) used for wind power conversion systems. At first, a double-fed induction generator model was constructed. A control law is formulated to govern the flow of energy between the stator of a DFIG and the energy network using three types of controllers: proportional integral (PI), sliding mode controller (SMC) and second order sliding mode controller (SOSMC). Their different results in terms of power reference tracking, reaction to unexpected speed fluctuations, sensitivity to perturbations, and resilience against machine parameter alterations are compared. MATLAB/Simulink was used to conduct the simulations for the preceding study. Multiple simulations have shown very satisfying results, and the investigations demonstrate the efficacy and power-enhancing capabilities of the suggested control system.
Neural network optimizer of proportional-integral-differential controller par...IJECEIAES
Wide application of proportional-integral-differential (PID)-regulator in industry requires constant improvement of methods of its parameters adjustment. The paper deals with the issues of optimization of PID-regulator parameters with the use of neural network technology methods. A methodology for choosing the architecture (structure) of neural network optimizer is proposed, which consists in determining the number of layers, the number of neurons in each layer, as well as the form and type of activation function. Algorithms of neural network training based on the application of the method of minimizing the mismatch between the regulated value and the target value are developed. The method of back propagation of gradients is proposed to select the optimal training rate of neurons of the neural network. The neural network optimizer, which is a superstructure of the linear PID controller, allows increasing the regulation accuracy from 0.23 to 0.09, thus reducing the power consumption from 65% to 53%. The results of the conducted experiments allow us to conclude that the created neural superstructure may well become a prototype of an automatic voltage regulator (AVR)-type industrial controller for tuning the parameters of the PID controller.
An improved modulation technique suitable for a three level flying capacitor ...IJECEIAES
This research paper introduces an innovative modulation technique for controlling a 3-level flying capacitor multilevel inverter (FCMLI), aiming to streamline the modulation process in contrast to conventional methods. The proposed
simplified modulation technique paves the way for more straightforward and
efficient control of multilevel inverters, enabling their widespread adoption and
integration into modern power electronic systems. Through the amalgamation of
sinusoidal pulse width modulation (SPWM) with a high-frequency square wave
pulse, this controlling technique attains energy equilibrium across the coupling
capacitor. The modulation scheme incorporates a simplified switching pattern
and a decreased count of voltage references, thereby simplifying the control
algorithm.
A review on features and methods of potential fishing zoneIJECEIAES
This review focuses on the importance of identifying potential fishing zones in seawater for sustainable fishing practices. It explores features like sea surface temperature (SST) and sea surface height (SSH), along with classification methods such as classifiers. The features like SST, SSH, and different classifiers used to classify the data, have been figured out in this review study. This study underscores the importance of examining potential fishing zones using advanced analytical techniques. It thoroughly explores the methodologies employed by researchers, covering both past and current approaches. The examination centers on data characteristics and the application of classification algorithms for classification of potential fishing zones. Furthermore, the prediction of potential fishing zones relies significantly on the effectiveness of classification algorithms. Previous research has assessed the performance of models like support vector machines, naïve Bayes, and artificial neural networks (ANN). In the previous result, the results of support vector machine (SVM) were 97.6% more accurate than naive Bayes's 94.2% to classify test data for fisheries classification. By considering the recent works in this area, several recommendations for future works are presented to further improve the performance of the potential fishing zone models, which is important to the fisheries community.
Electrical signal interference minimization using appropriate core material f...IJECEIAES
As demand for smaller, quicker, and more powerful devices rises, Moore's law is strictly followed. The industry has worked hard to make little devices that boost productivity. The goal is to optimize device density. Scientists are reducing connection delays to improve circuit performance. This helped them understand three-dimensional integrated circuit (3D IC) concepts, which stack active devices and create vertical connections to diminish latency and lower interconnects. Electrical involvement is a big worry with 3D integrates circuits. Researchers have developed and tested through silicon via (TSV) and substrates to decrease electrical wave involvement. This study illustrates a novel noise coupling reduction method using several electrical involvement models. A 22% drop in electrical involvement from wave-carrying to victim TSVs introduces this new paradigm and improves system performance even at higher THz frequencies.
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...IJECEIAES
Climate change's impact on the planet forced the United Nations and governments to promote green energies and electric transportation. The deployments of photovoltaic (PV) and electric vehicle (EV) systems gained stronger momentum due to their numerous advantages over fossil fuel types. The advantages go beyond sustainability to reach financial support and stability. The work in this paper introduces the hybrid system between PV and EV to support industrial and commercial plants. This paper covers the theoretical framework of the proposed hybrid system including the required equation to complete the cost analysis when PV and EV are present. In addition, the proposed design diagram which sets the priorities and requirements of the system is presented. The proposed approach allows setup to advance their power stability, especially during power outages. The presented information supports researchers and plant owners to complete the necessary analysis while promoting the deployment of clean energy. The result of a case study that represents a dairy milk farmer supports the theoretical works and highlights its advanced benefits to existing plants. The short return on investment of the proposed approach supports the paper's novelty approach for the sustainable electrical system. In addition, the proposed system allows for an isolated power setup without the need for a transmission line which enhances the safety of the electrical network
Bibliometric analysis highlighting the role of women in addressing climate ch...IJECEIAES
Fossil fuel consumption increased quickly, contributing to climate change
that is evident in unusual flooding and draughts, and global warming. Over
the past ten years, women's involvement in society has grown dramatically,
and they succeeded in playing a noticeable role in reducing climate change.
A bibliometric analysis of data from the last ten years has been carried out to
examine the role of women in addressing the climate change. The analysis's
findings discussed the relevant to the sustainable development goals (SDGs),
particularly SDG 7 and SDG 13. The results considered contributions made
by women in the various sectors while taking geographic dispersion into
account. The bibliometric analysis delves into topics including women's
leadership in environmental groups, their involvement in policymaking, their
contributions to sustainable development projects, and the influence of
gender diversity on attempts to mitigate climate change. This study's results
highlight how women have influenced policies and actions related to climate
change, point out areas of research deficiency and recommendations on how
to increase role of the women in addressing the climate change and
achieving sustainability. To achieve more successful results, this initiative
aims to highlight the significance of gender equality and encourage
inclusivity in climate change decision-making processes.
Voltage and frequency control of microgrid in presence of micro-turbine inter...IJECEIAES
The active and reactive load changes have a significant impact on voltage
and frequency. In this paper, in order to stabilize the microgrid (MG) against
load variations in islanding mode, the active and reactive power of all
distributed generators (DGs), including energy storage (battery), diesel
generator, and micro-turbine, are controlled. The micro-turbine generator is
connected to MG through a three-phase to three-phase matrix converter, and
the droop control method is applied for controlling the voltage and
frequency of MG. In addition, a method is introduced for voltage and
frequency control of micro-turbines in the transition state from gridconnected mode to islanding mode. A novel switching strategy of the matrix
converter is used for converting the high-frequency output voltage of the
micro-turbine to the grid-side frequency of the utility system. Moreover,
using the switching strategy, the low-order harmonics in the output current
and voltage are not produced, and consequently, the size of the output filter
would be reduced. In fact, the suggested control strategy is load-independent
and has no frequency conversion restrictions. The proposed approach for
voltage and frequency regulation demonstrates exceptional performance and
favorable response across various load alteration scenarios. The suggested
strategy is examined in several scenarios in the MG test systems, and the
simulation results are addressed.
Enhancing battery system identification: nonlinear autoregressive modeling fo...IJECEIAES
Precisely characterizing Li-ion batteries is essential for optimizing their
performance, enhancing safety, and prolonging their lifespan across various
applications, such as electric vehicles and renewable energy systems. This
article introduces an innovative nonlinear methodology for system
identification of a Li-ion battery, employing a nonlinear autoregressive with
exogenous inputs (NARX) model. The proposed approach integrates the
benefits of nonlinear modeling with the adaptability of the NARX structure,
facilitating a more comprehensive representation of the intricate
electrochemical processes within the battery. Experimental data collected
from a Li-ion battery operating under diverse scenarios are employed to
validate the effectiveness of the proposed methodology. The identified
NARX model exhibits superior accuracy in predicting the battery's behavior
compared to traditional linear models. This study underscores the
importance of accounting for nonlinearities in battery modeling, providing
insights into the intricate relationships between state-of-charge, voltage, and
current under dynamic conditions.
Smart grid deployment: from a bibliometric analysis to a surveyIJECEIAES
Smart grids are one of the last decades' innovations in electrical energy.
They bring relevant advantages compared to the traditional grid and
significant interest from the research community. Assessing the field's
evolution is essential to propose guidelines for facing new and future smart
grid challenges. In addition, knowing the main technologies involved in the
deployment of smart grids (SGs) is important to highlight possible
shortcomings that can be mitigated by developing new tools. This paper
contributes to the research trends mentioned above by focusing on two
objectives. First, a bibliometric analysis is presented to give an overview of
the current research level about smart grid deployment. Second, a survey of
the main technological approaches used for smart grid implementation and
their contributions are highlighted. To that effect, we searched the Web of
Science (WoS), and the Scopus databases. We obtained 5,663 documents
from WoS and 7,215 from Scopus on smart grid implementation or
deployment. With the extraction limitation in the Scopus database, 5,872 of
the 7,215 documents were extracted using a multi-step process. These two
datasets have been analyzed using a bibliometric tool called bibliometrix.
The main outputs are presented with some recommendations for future
research.
Use of analytical hierarchy process for selecting and prioritizing islanding ...IJECEIAES
One of the problems that are associated to power systems is islanding
condition, which must be rapidly and properly detected to prevent any
negative consequences on the system's protection, stability, and security.
This paper offers a thorough overview of several islanding detection
strategies, which are divided into two categories: classic approaches,
including local and remote approaches, and modern techniques, including
techniques based on signal processing and computational intelligence.
Additionally, each approach is compared and assessed based on several
factors, including implementation costs, non-detected zones, declining
power quality, and response times using the analytical hierarchy process
(AHP). The multi-criteria decision-making analysis shows that the overall
weight of passive methods (24.7%), active methods (7.8%), hybrid methods
(5.6%), remote methods (14.5%), signal processing-based methods (26.6%),
and computational intelligent-based methods (20.8%) based on the
comparison of all criteria together. Thus, it can be seen from the total weight
that hybrid approaches are the least suitable to be chosen, while signal
processing-based methods are the most appropriate islanding detection
method to be selected and implemented in power system with respect to the
aforementioned factors. Using Expert Choice software, the proposed
hierarchy model is studied and examined.
Enhancing of single-stage grid-connected photovoltaic system using fuzzy logi...IJECEIAES
The power generated by photovoltaic (PV) systems is influenced by
environmental factors. This variability hampers the control and utilization of
solar cells' peak output. In this study, a single-stage grid-connected PV
system is designed to enhance power quality. Our approach employs fuzzy
logic in the direct power control (DPC) of a three-phase voltage source
inverter (VSI), enabling seamless integration of the PV connected to the
grid. Additionally, a fuzzy logic-based maximum power point tracking
(MPPT) controller is adopted, which outperforms traditional methods like
incremental conductance (INC) in enhancing solar cell efficiency and
minimizing the response time. Moreover, the inverter's real-time active and
reactive power is directly managed to achieve a unity power factor (UPF).
The system's performance is assessed through MATLAB/Simulink
implementation, showing marked improvement over conventional methods,
particularly in steady-state and varying weather conditions. For solar
irradiances of 500 and 1,000 W/m2
, the results show that the proposed
method reduces the total harmonic distortion (THD) of the injected current
to the grid by approximately 46% and 38% compared to conventional
methods, respectively. Furthermore, we compare the simulation results with
IEEE standards to evaluate the system's grid compatibility.
Enhancing photovoltaic system maximum power point tracking with fuzzy logic-b...IJECEIAES
Photovoltaic systems have emerged as a promising energy resource that
caters to the future needs of society, owing to their renewable, inexhaustible,
and cost-free nature. The power output of these systems relies on solar cell
radiation and temperature. In order to mitigate the dependence on
atmospheric conditions and enhance power tracking, a conventional
approach has been improved by integrating various methods. To optimize
the generation of electricity from solar systems, the maximum power point
tracking (MPPT) technique is employed. To overcome limitations such as
steady-state voltage oscillations and improve transient response, two
traditional MPPT methods, namely fuzzy logic controller (FLC) and perturb
and observe (P&O), have been modified. This research paper aims to
simulate and validate the step size of the proposed modified P&O and FLC
techniques within the MPPT algorithm using MATLAB/Simulink for
efficient power tracking in photovoltaic systems.
Adaptive synchronous sliding control for a robot manipulator based on neural ...IJECEIAES
Robot manipulators have become important equipment in production lines, medical fields, and transportation. Improving the quality of trajectory tracking for
robot hands is always an attractive topic in the research community. This is a
challenging problem because robot manipulators are complex nonlinear systems
and are often subject to fluctuations in loads and external disturbances. This
article proposes an adaptive synchronous sliding control scheme to improve trajectory tracking performance for a robot manipulator. The proposed controller
ensures that the positions of the joints track the desired trajectory, synchronize
the errors, and significantly reduces chattering. First, the synchronous tracking
errors and synchronous sliding surfaces are presented. Second, the synchronous
tracking error dynamics are determined. Third, a robust adaptive control law is
designed,the unknown components of the model are estimated online by the neural network, and the parameters of the switching elements are selected by fuzzy
logic. The built algorithm ensures that the tracking and approximation errors
are ultimately uniformly bounded (UUB). Finally, the effectiveness of the constructed algorithm is demonstrated through simulation and experimental results.
Simulation and experimental results show that the proposed controller is effective with small synchronous tracking errors, and the chattering phenomenon is
significantly reduced.
Remote field-programmable gate array laboratory for signal acquisition and de...IJECEIAES
A remote laboratory utilizing field-programmable gate array (FPGA) technologies enhances students’ learning experience anywhere and anytime in embedded system design. Existing remote laboratories prioritize hardware access and visual feedback for observing board behavior after programming, neglecting comprehensive debugging tools to resolve errors that require internal signal acquisition. This paper proposes a novel remote embeddedsystem design approach targeting FPGA technologies that are fully interactive via a web-based platform. Our solution provides FPGA board access and debugging capabilities beyond the visual feedback provided by existing remote laboratories. We implemented a lab module that allows users to seamlessly incorporate into their FPGA design. The module minimizes hardware resource utilization while enabling the acquisition of a large number of data samples from the signal during the experiments by adaptively compressing the signal prior to data transmission. The results demonstrate an average compression ratio of 2.90 across three benchmark signals, indicating efficient signal acquisition and effective debugging and analysis. This method allows users to acquire more data samples than conventional methods. The proposed lab allows students to remotely test and debug their designs, bridging the gap between theory and practice in embedded system design.
Detecting and resolving feature envy through automated machine learning and m...IJECEIAES
Efficiently identifying and resolving code smells enhances software project quality. This paper presents a novel solution, utilizing automated machine learning (AutoML) techniques, to detect code smells and apply move method refactoring. By evaluating code metrics before and after refactoring, we assessed its impact on coupling, complexity, and cohesion. Key contributions of this research include a unique dataset for code smell classification and the development of models using AutoGluon for optimal performance. Furthermore, the study identifies the top 20 influential features in classifying feature envy, a well-known code smell, stemming from excessive reliance on external classes. We also explored how move method refactoring addresses feature envy, revealing reduced coupling and complexity, and improved cohesion, ultimately enhancing code quality. In summary, this research offers an empirical, data-driven approach, integrating AutoML and move method refactoring to optimize software project quality. Insights gained shed light on the benefits of refactoring on code quality and the significance of specific features in detecting feature envy. Future research can expand to explore additional refactoring techniques and a broader range of code metrics, advancing software engineering practices and standards.
Smart monitoring technique for solar cell systems using internet of things ba...IJECEIAES
Rapidly and remotely monitoring and receiving the solar cell systems status parameters, solar irradiance, temperature, and humidity, are critical issues in enhancement their efficiency. Hence, in the present article an improved smart prototype of internet of things (IoT) technique based on embedded system through NodeMCU ESP8266 (ESP-12E) was carried out experimentally. Three different regions at Egypt; Luxor, Cairo, and El-Beheira cities were chosen to study their solar irradiance profile, temperature, and humidity by the proposed IoT system. The monitoring data of solar irradiance, temperature, and humidity were live visualized directly by Ubidots through hypertext transfer protocol (HTTP) protocol. The measured solar power radiation in Luxor, Cairo, and El-Beheira ranged between 216-1000, 245-958, and 187-692 W/m 2 respectively during the solar day. The accuracy and rapidity of obtaining monitoring results using the proposed IoT system made it a strong candidate for application in monitoring solar cell systems. On the other hand, the obtained solar power radiation results of the three considered regions strongly candidate Luxor and Cairo as suitable places to build up a solar cells system station rather than El-Beheira.
An efficient security framework for intrusion detection and prevention in int...IJECEIAES
Over the past few years, the internet of things (IoT) has advanced to connect billions of smart devices to improve quality of life. However, anomalies or malicious intrusions pose several security loopholes, leading to performance degradation and threat to data security in IoT operations. Thereby, IoT security systems must keep an eye on and restrict unwanted events from occurring in the IoT network. Recently, various technical solutions based on machine learning (ML) models have been derived towards identifying and restricting unwanted events in IoT. However, most ML-based approaches are prone to miss-classification due to inappropriate feature selection. Additionally, most ML approaches applied to intrusion detection and prevention consider supervised learning, which requires a large amount of labeled data to be trained. Consequently, such complex datasets are impossible to source in a large network like IoT. To address this problem, this proposed study introduces an efficient learning mechanism to strengthen the IoT security aspects. The proposed algorithm incorporates supervised and unsupervised approaches to improve the learning models for intrusion detection and mitigation. Compared with the related works, the experimental outcome shows that the model performs well in a benchmark dataset. It accomplishes an improved detection accuracy of approximately 99.21%.
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Sinan KOZAK
Sinan from the Delivery Hero mobile infrastructure engineering team shares a deep dive into performance acceleration with Gradle build cache optimizations. Sinan shares their journey into solving complex build-cache problems that affect Gradle builds. By understanding the challenges and solutions found in our journey, we aim to demonstrate the possibilities for faster builds. The case study reveals how overlapping outputs and cache misconfigurations led to significant increases in build times, especially as the project scaled up with numerous modules using Paparazzi tests. The journey from diagnosing to defeating cache issues offers invaluable lessons on maintaining cache integrity without sacrificing functionality.
Applications of artificial Intelligence in Mechanical Engineering.pdfAtif Razi
Historically, mechanical engineering has relied heavily on human expertise and empirical methods to solve complex problems. With the introduction of computer-aided design (CAD) and finite element analysis (FEA), the field took its first steps towards digitization. These tools allowed engineers to simulate and analyze mechanical systems with greater accuracy and efficiency. However, the sheer volume of data generated by modern engineering systems and the increasing complexity of these systems have necessitated more advanced analytical tools, paving the way for AI.
AI offers the capability to process vast amounts of data, identify patterns, and make predictions with a level of speed and accuracy unattainable by traditional methods. This has profound implications for mechanical engineering, enabling more efficient design processes, predictive maintenance strategies, and optimized manufacturing operations. AI-driven tools can learn from historical data, adapt to new information, and continuously improve their performance, making them invaluable in tackling the multifaceted challenges of modern mechanical engineering.
Comparative analysis between traditional aquaponics and reconstructed aquapon...bijceesjournal
The aquaponic system of planting is a method that does not require soil usage. It is a method that only needs water, fish, lava rocks (a substitute for soil), and plants. Aquaponic systems are sustainable and environmentally friendly. Its use not only helps to plant in small spaces but also helps reduce artificial chemical use and minimizes excess water use, as aquaponics consumes 90% less water than soil-based gardening. The study applied a descriptive and experimental design to assess and compare conventional and reconstructed aquaponic methods for reproducing tomatoes. The researchers created an observation checklist to determine the significant factors of the study. The study aims to determine the significant difference between traditional aquaponics and reconstructed aquaponics systems propagating tomatoes in terms of height, weight, girth, and number of fruits. The reconstructed aquaponics system’s higher growth yield results in a much more nourished crop than the traditional aquaponics system. It is superior in its number of fruits, height, weight, and girth measurement. Moreover, the reconstructed aquaponics system is proven to eliminate all the hindrances present in the traditional aquaponics system, which are overcrowding of fish, algae growth, pest problems, contaminated water, and dead fish.
artificial intelligence and data science contents.pptxGauravCar
What is artificial intelligence? Artificial intelligence is the ability of a computer or computer-controlled robot to perform tasks that are commonly associated with the intellectual processes characteristic of humans, such as the ability to reason.
› ...
Artificial intelligence (AI) | Definitio
Null Bangalore | Pentesters Approach to AWS IAMDivyanshu
#Abstract:
- Learn more about the real-world methods for auditing AWS IAM (Identity and Access Management) as a pentester. So let us proceed with a brief discussion of IAM as well as some typical misconfigurations and their potential exploits in order to reinforce the understanding of IAM security best practices.
- Gain actionable insights into AWS IAM policies and roles, using hands on approach.
#Prerequisites:
- Basic understanding of AWS services and architecture
- Familiarity with cloud security concepts
- Experience using the AWS Management Console or AWS CLI.
- For hands on lab create account on [killercoda.com](https://killercoda.com/cloudsecurity-scenario/)
# Scenario Covered:
- Basics of IAM in AWS
- Implementing IAM Policies with Least Privilege to Manage S3 Bucket
- Objective: Create an S3 bucket with least privilege IAM policy and validate access.
- Steps:
- Create S3 bucket.
- Attach least privilege policy to IAM user.
- Validate access.
- Exploiting IAM PassRole Misconfiguration
-Allows a user to pass a specific IAM role to an AWS service (ec2), typically used for service access delegation. Then exploit PassRole Misconfiguration granting unauthorized access to sensitive resources.
- Objective: Demonstrate how a PassRole misconfiguration can grant unauthorized access.
- Steps:
- Allow user to pass IAM role to EC2.
- Exploit misconfiguration for unauthorized access.
- Access sensitive resources.
- Exploiting IAM AssumeRole Misconfiguration with Overly Permissive Role
- An overly permissive IAM role configuration can lead to privilege escalation by creating a role with administrative privileges and allow a user to assume this role.
- Objective: Show how overly permissive IAM roles can lead to privilege escalation.
- Steps:
- Create role with administrative privileges.
- Allow user to assume the role.
- Perform administrative actions.
- Differentiation between PassRole vs AssumeRole
Try at [killercoda.com](https://killercoda.com/cloudsecurity-scenario/)
Software Engineering and Project Management - Introduction, Modeling Concepts...Prakhyath Rai
Introduction, Modeling Concepts and Class Modeling: What is Object orientation? What is OO development? OO Themes; Evidence for usefulness of OO development; OO modeling history. Modeling
as Design technique: Modeling, abstraction, The Three models. Class Modeling: Object and Class Concept, Link and associations concepts, Generalization and Inheritance, A sample class model, Navigation of class models, and UML diagrams
Building the Analysis Models: Requirement Analysis, Analysis Model Approaches, Data modeling Concepts, Object Oriented Analysis, Scenario-Based Modeling, Flow-Oriented Modeling, class Based Modeling, Creating a Behavioral Model.
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...shadow0702a
This document serves as a comprehensive step-by-step guide on how to effectively use PyCharm for remote debugging of the Windows Subsystem for Linux (WSL) on a local Windows machine. It meticulously outlines several critical steps in the process, starting with the crucial task of enabling permissions, followed by the installation and configuration of WSL.
The guide then proceeds to explain how to set up the SSH service within the WSL environment, an integral part of the process. Alongside this, it also provides detailed instructions on how to modify the inbound rules of the Windows firewall to facilitate the process, ensuring that there are no connectivity issues that could potentially hinder the debugging process.
The document further emphasizes on the importance of checking the connection between the Windows and WSL environments, providing instructions on how to ensure that the connection is optimal and ready for remote debugging.
It also offers an in-depth guide on how to configure the WSL interpreter and files within the PyCharm environment. This is essential for ensuring that the debugging process is set up correctly and that the program can be run effectively within the WSL terminal.
Additionally, the document provides guidance on how to set up breakpoints for debugging, a fundamental aspect of the debugging process which allows the developer to stop the execution of their code at certain points and inspect their program at those stages.
Finally, the document concludes by providing a link to a reference blog. This blog offers additional information and guidance on configuring the remote Python interpreter in PyCharm, providing the reader with a well-rounded understanding of the process.
Introduction- e - waste – definition - sources of e-waste– hazardous substances in e-waste - effects of e-waste on environment and human health- need for e-waste management– e-waste handling rules - waste minimization techniques for managing e-waste – recycling of e-waste - disposal treatment methods of e- waste – mechanism of extraction of precious metal from leaching solution-global Scenario of E-waste – E-waste in India- case studies.
Batteries -Introduction – Types of Batteries – discharging and charging of battery - characteristics of battery –battery rating- various tests on battery- – Primary battery: silver button cell- Secondary battery :Ni-Cd battery-modern battery: lithium ion battery-maintenance of batteries-choices of batteries for electric vehicle applications.
Fuel Cells: Introduction- importance and classification of fuel cells - description, principle, components, applications of fuel cells: H2-O2 fuel cell, alkaline fuel cell, molten carbonate fuel cell and direct methanol fuel cells.
Developing a smart system for infant incubators using the internet of things and artificial intelligence
1. International Journal of Electrical and Computer Engineering (IJECE)
Vol. 14, No. 2, April 2024, pp. 2293~2312
ISSN: 2088-8708, DOI: 10.11591/ijece.v14i2.pp2293-2312 2293
Journal homepage: http://ijece.iaescore.com
Developing a smart system for infant incubators using the
internet of things and artificial intelligence
I Komang Agus Ady Aryanto1
, Dechrit Maneetham1
, Evi Triandini2
1
Department of Mechatronics Engineering, Faculty of Technical Education, Rajamangala University of Technology Thanyaburi,
Pathum Thani, Thailand
2
Department of Information Systems, Faculty of Informatics and Computers, Institute of Technology and Business STIKOM Bali,
Bali, Indonesia
Article Info ABSTRACT
Article history:
Received Sep 20, 2023
Revised Oct 11, 2023
Accepted Dec 5, 2023
This research is developing an incubator system that integrates the internet
of things and artificial intelligence to improve care for premature babies. The
system workflow starts with sensors that collect data from the incubator.
Then, the data is sent in real-time to the internet of things (IoT) broker
eclipse mosquito using the message queue telemetry transport (MQTT)
protocol version 5.0. After that, the data is stored in a database for analysis
using the long short-term memory network (LSTM) method and displayed in
a web application using an application programming interface (API) service.
Furthermore, the experimental results produce as many as 2,880 rows of data
stored in the database. The correlation coefficient between the target
attribute and other attributes ranges from 0.23 to 0.48. Next, several
experiments were conducted to evaluate the model-predicted value on the
test data. The best results are obtained using a two-layer LSTM
configuration model, each with 60 neurons and a lookback setting 6. This
model produces an R2
value of 0.934, with a root mean square error (RMSE)
value of 0.015 and a mean absolute error (MAE) of 0.008. In addition, the R2
value was also evaluated for each attribute used as input, with a result of
values between 0.590 and 0.845.
Keywords:
Artificial intelligence
Infant incubator
Internet of things
Long short-term memory
network
Message queue telemetry
transport
This is an open access article under the CC BY-SA license.
Corresponding Author:
Dechrit Maneetham
Department of Mechatronics Engineering, Faculty of Technical Education, Rajamangala University of
Technology Thanyaburi
39 Village No. 1 Rangsit - Nakhon Nayok Road, Tambon Khlong Hok, Amphoe Thanyaburi Pathum Thani
12110, Thailand
Email: dechrit_m@rmutt.ac.th
1. INTRODUCTION
Infant incubators are important devices used to provide a controlled and stable environment for
premature babies or babies with certain health conditions [1]. The incubator can maintain environmental
conditions from outside conditions so that the baby becomes safe in the incubator [2], [3]. In the incubator,
several important parameters must be closely monitored so that it requires more attention to care for babies in
the incubator. These parameters include the baby's body temperature, incubator temperature, oxygen level, and
heart rate [4]. All of these parameters are monitored to ensure that the baby receives appropriate care and that
the environmental conditions in the incubator remain optimal.
However, the problem is monitoring the infant’s condition and manually adjusting the incubator's
environmental parameters, which can be a challenge. This requires medical personnel to constantly monitor and
adapt to environmental conditions for each baby, which can be very tiring and increases the risk of human error.
2. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2293-2312
2294
Another problem often encountered is temperature instability inside the incubator because the incubator is often
opened and closed for baby care and examination. As a result, the incubator's temperature conditions may differ
now and, in the future, placing the baby at risk of hypothermia or hyperthermia. This incubator temperature
condition that is not optimal can have a negative impact on health and affect the baby's healing process.
Based on these problems, we offer updates in conducting novel research on using automation
technology in infant incubators enhanced by integrating internet of things (IoT) and artificial intelligence (AI)
technologies. In particular, artificial intelligence technology uses the long short-term memory (LSTM) method
to predict future incubator temperature conditions. This research is the first step for us in developing an
incubator equipped with a combination of the internet of things and artificial intelligence models. The AI model
is created using sensor data obtained at the incubator with the IoT concept. Thus, it is hoped that this research
will improve the quality of care, especially for babies, and provide new insights regarding health technology
development using IoT and AI artificial intelligence.
The internet of things is a concept that describes a physical device connected to the internet that can
communicate with each other to collect and exchange data without involving human interaction [5]. So, in this
study, internet of things technology is used to collect data in real-time from various sensors installed in the
incubator. The system uses several types of sensors, including body temperature, incubator temperature, heart
rate, and oxygen sensors that collect real-time data about the infant's physical condition and environment inside
the incubator.
Then, for network communication devices, use the Wi-Fi module, which functions as a liaison
between the incubator and the IoT broker so that sensor data measured in the incubator can be transmitted to the
IoT broker with the message queue telemetry transport (MQTT) protocol. MQTT is a communication protocol
used on the internet of things to send messages between devices with a publish (sender) and subscribe
(recipient) mechanism. In addition, MQTT also supports quality of service (QoS) settings that allow users to
determine the reliability level of message delivery [6].
Meanwhile, the microcontroller chip controls all sensor measurement processes and data transmission,
which is the core brain of all hardware. The microcontroller used ATMega256 on the Arduino Mega board,
with a large number of input/output pins and a large memory capacity compared to other Arduino-type boards,
which allows reading data from various sensors and controlling other devices, such as relay actuators and
communication modules. The Arduino Mega operates on 5 V, making it suitable for multiple sensor modules.
The programming language used is wiring, which makes it easy to write program code for the various functions
needed [7].
Furthermore, the data transmitted to the IoT broker is collected and processed by the server service to
be stored in the database. The process of storing data received from the incubator in the database is adjusted to
the database structure. The design of this database is based on data patterns obtained from sensor data in the
incubator so that the stored data becomes structured and efficient to access and analyze. After the data is stored
in the database, through the web application, the data is accessed and displayed on web pages in real-time so
that medical staff can monitor the infant's condition directly if special attention is needed. The standard
temperature setting in the incubator is 32 °
C to 35 °
C, depending on the baby's age [8].
Meanwhile, the LSTM-based deep learning model is used for the data analysis. LSTM are a particular
type of recurrent neural networks (RNN) designed to learn and understand long-term dependencies in data.
Through the analysis performed by the LSTM model, certain patterns in the data can be identified and predicted
[9], [10]. Therefore, this study uses LSTM to analyze data from various sensors in the incubator collected in a
database.
2. RELATED WORKS
In this section, we provide an overview of necessary research conducted in this field. As a basic
framework, these studies have provided essential and in-depth insights into relevant methods, techniques, and
approaches, all of which have become references in the planning and implementation of research conducted.
The following are some of the studies that formed the basis for this research.
The first study we discussed concerned a real-time wireless temperature measurement system for
infant incubators. This research in 2023 explains the implementation of the MQTT protocol in transmitting
temperature data from the incubator to the server. In addition, perform an analysis of the QoS provided by
MQTT and evaluate the overall performance of this system Sukma et al. [11]. Subsequent research focuses
on developing incubators designed to read fingerprints for infant identification. In addition, this incubator is
equipped with a monitoring system to monitor the infant's temperature and heart rate via the global system
for mobile (GSM) communications network, which is integrated with IoT based applications Kapen et al.
[12]. Subsequent research discusses the development of an incubator that can monitor the baby's temperature
and heart rate on the liquid crystal display (LCD) module and web applications via the hypertext transfer
3. Int J Elec & Comp Eng ISSN: 2088-8708
Developing a smart system for infant incubators using the internet of … (I Komang Agus Ady Aryanto)
2295
protocol (HTTP) protocol with an ethernet shield device Irmansyah et al. [13]. Next is research that discusses
the control system in the incubator by combining fuzzy-proportional integral derivative (fuzzy-PID) to
regulate temperature and humidity in the incubator Alimuddin et al. [14]. Subsequent research regarding
developing an incubator system to monitor temperature and humidity through a web application. The system
uses a Wi-Fi network and MQTT protocol to send data to the broker service at node-RED Parra et al. [15].
Then, research on developing a system to monitor the respiratory rate and detect the incidence of apnea in
premature babies with the internet of things concept. The system developed uses the ESP32 microcontroller,
sensors, edge computing device (ECD) devices, and the MQTT protocol. It can be described in general that
this system uses the internet of things architecture with the MQTT protocol to connect a wireless embedded
system (WES) system or sensor with an ECD Cay et al. [16]. Subsequent research discusses the development
of a model to detect system errors in reading sensor values in incubators. The model developed uses a
classification method, namely support vector machine (SVM), decision tree (DT), and artificial neural
network (ANN). The results of these three methods are compared to get the model with the best method. The
dataset has four features: temperature, humidity, fan electric current, and heating electric current. The value
of this dataset feature is obtained from the sensors attached to the incubator. In addition, the system also uses
services from the Blynk application Mahdi et al. [17]. In Table 1, a summary of the state-of-the-art references
related to the latest research conducted is presented for comparison.
Table 1. State-of-the-art of the existing works
Reference
Microcontroller
Microcomputer
Sensor
Communication
protocol
Network
Broker
IoT
Data
process
Application
interface
Programming
Data
analytics
[11]
ESP32
Raspberry
Pi
Temperature MQTT Wi-Fi Node-Red Node-Red Web Node-Red -
[12]
ATMega
328
-
Phototherapy,
Temperature,
Humidity,
Fingerprint,
Heart Rate,
Camera
HTTP GSM - MySQL
Mobile
Android
C++, PHP,
Java
-
[13]
ATMega
2560
-
Heart rate,
Weight
HTTP Ethernet - - Web C++ -
[14]
ATMega
16
-
Temperature,
Humidity
- - - -
LCD,
Desktop
C++,
VB.Net
Fuzzy-
PID
[15]
ESP32
-
Temperature,
Humidity,
Sound
MQTT Wi-Fi Node-Red MySQL Web
Node.js,
PHP,
JavaScript,
C++
-
[16]
ESP32
Raspberry
Pi
Respiration MQTT Wi-Fi Mosquitto
Data filter,
Peak
Detection,
Feature
extraction
LCD,
Desktop
Python
-
[17]
ESP8266
Raspberry
Pi
Temperature,
Humidity, Fan
Current,
Heater
Current
- Wi-Fi - -
Blynk
Platform
C++
Decision
Tree,
SVM,
Neural
Network
Our
work
ATMega
2560
Raspberry
Pi
Temperature
Incubator,
Humidity
Incubator,
Body
Temperature,
Heart Rate,
Saturation
MQTT
and
HTTP
Wi-Fi Mosquitto
Data
aggregator,
Data filter,
MySQL
Web,
Mobile,
Notification,
LCD
C++,
Python,
PHP,
JavaScript,
CSS
LSTM,
RMSE,
MAE,
MAPE,
R2
4. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2293-2312
2296
Based on previous research, we developed an incubator system with the internet of things concept to
combine artificial intelligence, hardware, network, database management, and software. In terms of
hardware, the system is designed using various sensors and actuators and is supported by a microcontroller
and microcomputer. Furthermore, the communication network developed in this system uses the MQTT and
HTTP protocols, which enable an efficient data transmission process according to its QoS. In addition, data is
directly stored in the database according to the schema to facilitate analysis. The analysis process in this
study utilizes the LSTM method to create a learning model. This study also developed a web application for
monitoring, controlling, and providing real-time notifications regarding the condition of the incubator.
3. METHOD
3.1. System overview
Figure 1 shows an overview of the system design in this study. This innovation applies the latest
technology to improve baby care, especially for premature babies and babies with certain health conditions
requiring intensive monitoring. This system is centered on a baby incubator with various sensors, including
sensors for the infant's body temperature, temperature inside the incubator, heart rate, and oxygen level.
These sensors continuously collect data in real-time, providing a real-time picture of the infant's condition
and the environment inside the incubator.
The microcontroller then handles the data measured by these sensors [18]. The microcontroller
functions as a data collector from various sensors and as an actuator controller whose job is to regulate the
temperature in the incubator. These data and control instructions are sent to the IoT broker via the network,
making this system part of the internet of things scope. Sending data to the IoT broker uses the MQTT
protocol and Wi-Fi network [19].
The data collected in the IoT broker is then processed and stored in the database through data
processing stages such as screening and data filtering. The data storage process is adjusted to the database
schema, such as attributes and data types. This approach also enables large-scale and systematic collection of
medical data. These data are invaluable for further research and development in neonatal care.
After that, the data is analyzed using a learning method based on deep learning LSTM to produce a
model that can predict future incubator temperature values. LSTM is an artificial neural network method for
pattern processing in sequential datasets [20]. This model is designed to learn from the incubator dataset
collected in the database, understand the patterns that emerge from the data, and then make accurate
predictions about future incubator temperature conditions.
Furthermore, in the data output process, a web based IoT application plays an essential role in
making it easier for users to monitor and control the condition of the incubator. The web application is
developed using modern web technology with a responsive design and is equipped with various features,
making it easier for users to understand and operate this system. In addition, the web application also has a
notification feature that provides a warning if an event occurs.
Then, the data displayed on the web application is obtained in real-time from the database through
the application programming interface (API) and the POST method. API allows programmatic access to data
stored in the database. In addition, this application also uses asynchronous JavaScript and XML (AJAX) and
JavaScript object notation (JSON) technology, and AJAX is used to send asynchronous requests to the server
to retrieve data from the database [21]. Meanwhile, JSON is used as a data format that is lightweight and
easy for software to understand, allowing data to be transmitted quickly and efficiently between servers and
applications [22]. After the data is received in JSON format, the application can parse and process it to
display it in a graphical and tabular interface.
3.2. Software design
In Figure 2, the software design is shown. This design describes the process of data from sensors in
the incubator being sent to the IoT broker. Next, on the client side, a service is created that runs continuously
through a looping process. In this process, sensor data on the broker is taken in real-time and displayed on a
web page. The process of showing this data is carried out automatically without the need to refresh the web
page. Thus, sensor data from the incubator is displayed in real-time in a web interface without requiring
manual intervention for refreshing.
3.3. Hardware design
The hardware schematic design is shown as shown in Figure 3. After completing the schematic
design, we continued with making a printed circuit board (PCB) to connect the microcontroller, sensor, and
actuator hardware on one board [23]. The PCB design is shown in Figure 4, and information about the
hardware used is shown in Table 2.
5. Int J Elec & Comp Eng ISSN: 2088-8708
Developing a smart system for infant incubators using the internet of … (I Komang Agus Ady Aryanto)
2297
The microcontroller used is the Arduino Mega board; this device was chosen because of its ability to
interact with various sensors and actuators simultaneously. This board has 54 digital input/output pins, of
which 15 provide pulse width modulation (PWM) outputs and 16 analog input pins. Each input/output pin
can supply 20 mA of current. Then, the Arduino Mega is equipped with 256 KB of flash memory, of which
the bootloader uses 8 KB. Arduino Mega operates at a clock speed of 16 MHz, which allows fast processing
of instructions [24], [25]. In this research, Arduino Mega is used to read data from DHT22, MLX90614, and
MAX30102 sensors, each of which measures parameters such as temperature, heart rate, and blood oxygen
level [26]–[28]. In the system configuration process, the DHT22 sensor is connected to the Arduino Mega via
a digital pin, enabling data communication between the two. Meanwhile, the MLX90614 and MAX30102
sensors are connected to the Arduino Mega using the inter-integrated circuit (I2C) communication bus, an
efficient and reliable two-way communication system for exchanging data between devices. Arduino Mega is
also used to control actuator devices based on data from these sensors.
In addition, we also use the DS3231 real-time clock (RTC) module to provide a time marker for data
taken from the sensor. This tracks parameter changes over time and aids in data analysis. Next, we use the
ESP8266 Wi-Fi module for wireless communication, which is connected to the Arduino Mega using serial
(TX/RX). This module provides IoT capabilities for Arduino Mega to send data to the Raspberry Pi via a
Wi-Fi network.
Raspberry Pi is a microcomputer that has more than 2GB of random-access memory (RAM) with a
quad-core cortex-A72 64-bit processor with a speed of 1.5GHz, equipped with IEEE 802.11ac wireless
connectivity at a frequency of 2.4 and 5.0 GHz, Bluetooth 5.0, and also ethernet. Raspberry Pi can also be
referred to as a low-cost computer [29]. Then, in this study, the Raspberry Pi functions as an IoT broker in
the system, processing and forwarding data from Arduino Mega to the server. The Raspberry Pi is designed
to communicate with the Arduino Mega using the MQTT protocol. In addition, the Raspberry Pi also
functions as a server, storing sensor data in a database and serving data requests from other devices or users.
This design structure combines sensor devices, actuators, network modules, microcontrollers, and
microcomputers to create an incubator IoT system. The process of how integration programs from various
hardware devices can form an IoT system is shown in Algorithm 1.
Figure 1. System design overview
6. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2293-2312
2298
Figure 2. Software design
Figure 3. Hardware design
Figure 4. Schematic design of the PCB
7. Int J Elec & Comp Eng ISSN: 2088-8708
Developing a smart system for infant incubators using the internet of … (I Komang Agus Ady Aryanto)
2299
Table 2. Module bill of materials
Product/Module Qty. Unit price ($) Total ($)
Board Arduino Mega 1 37.75 37.75
Board Raspberry Pi 1 80.95 80.95
DHT22 1 4.49 4.49
MLX90614 1 22.4 22.4
MAX30102 1 11.16 11.16
ESP8266 1 1.05 1.05
RTC DS3231 1 2.05 2.05
Relay 1 2.88 2.88
LCD 1 1.08 1.08
Light emitting diode (LED) 2 0.13 0.26
Buzzer 1 0.40 0.40
Power Supply 5V 2A 1 9.59 9.59
Total 174.06
Algorithm 1. Integrating hardware into the system
Input: hardware components
Output: sensor data is transmitted to the IoT Broker using the MQTT protocol.
Description:
connect A to sensor dht, mxl, max, esp, rtc
connect esp, rasp to network
while the system microcontroller is running:
read data[ ] = dht, mxl, max,
read data[time] = rtc
send data[ ] to microcomputer via network using MQTT protocol
if response from microcomputer == true:
process response
end
end
while the system microcomputer is running:
if data[ ] from microcontroller == true:
analysis data[ ]
process store data[ ] into the database
end
if data[ ] request from the server or other devices == true:
send data[ ] to the requesting device
end
end
3.4. Design network and server
This section discusses how the network design is used in communication in the baby incubator
system. Wi-Fi networks are used as a means of wireless connection between IoT devices. Wi-Fi works by
using radio waves to send and receive data between devices. This is an advantage of using Wi-Fi as devices
can easily connect, allowing for greater mobility compared to wired networks. The IEEE developed the Wi-
Fi standards, starting with the number 802.11 [30]. Through Wi-Fi, IoT devices such as sensors or actuators
in incubators can connect to the Internet, allowing them to send and receive data with the MQTT
communication protocol.
MQTT is a lightweight communication protocol for exchanging data in IoT devices on incubators.
MQTT is designed for efficient two-way communication and reliable message delivery, even in unstable
network conditions. In addition, MQTT also supports QoS mechanisms up to level three, which enables
reliable message delivery. The MQTT architecture has two types of entities, namely, publisher and
subscriber. The publisher sends a message to the broker IoT, which then distributes the message to
subscribers who are subscribed to the relevant topic of the message. The Broker acts as a message handler
and ensures the messages arrive at the right destination [31], [32].
This study uses the Eclipse Mosquitto application as an IoT broker, which is open-source software
that facilitates the implementation of the MQTT protocol [33]. For this broker installation, configuration
involves address and port settings, authentication and authorization, and QoS. Configuration is done on the
client side using the Paho-MQTT library [34]. The IoT broker configuration is illustrated in Figure 5, which
illustrates the configuration process flowchart.
Meanwhile, the gateway application functions as an access point between IoT devices and servers
via the network, also carrying out processes such as light data processing, filtering, and security. Then, the
server is used for data processing and control in IoT devices. This server is implemented on the Raspberry Pi
microcomputer module. Application services running on this server are responsible for collecting, storing,
and analyzing data from IoT devices and sending instructions back to the device based on data processing
results.
8. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2293-2312
2300
Figure 5. The flow of IoT broker configuration
3.5. Design data process
3.5.1. Data aggregator
Collecting data from the internet of things devices in the incubator uses a data aggregator service.
This service is needed because of the number and variety of IoT devices that can connect to the network at
one time, so it is essential to manage the flow of information and ensure data originating from various IoT
devices can be analyzed and utilized effectively. The processes carried out on the data aggregator are:
i) collecting data from various sensor devices installed in the incubator; ii) normalizing data by converting
sensor data into a consistent format so that it can be processed; iii) simple data processing to identify
patterns or detecting data anomalies obtained on sensor and iv) presenting the final data. The following
Algorithm 2 shows the procedure for the data aggregator.
Algorithm 2. data aggregator service
INPUT: Sensor data from IoT devices
OUTPUT: Sensor data is shaped according to the format of the system
Description:
data_store = {
JSON_object: []
}
handle_sensor_data(data):
normalized_data = normalize(data)
data_store[sensor_id].append(normalized_data)
end
receive_sensor_data(device_type, data):
for each_item_sensor in id_sensor do
if device_type == sensor_id:
handle_sensor_data(data)
end
end
end
analyze_sensor_data():
result = analyze_process (data_store[sensor_id])
return:
result
end
end
3.5.2. Data filtering
In this research, the data filtering process needs to be done because the data generated by internet
of things devices is extensive and varied. By implementing data filtering, the system can enhance the
quality of sensor device data and bolster cybersecurity by mitigating potential cyberattacks [35]. There are
two types of applications of the data filtering process carried out on the system, namely: i) Noise reduction
because the data generated by IoT devices can contain noise or interference that can affect the accuracy of
the data; the process is carried out by calculating the average number of data points in a row in a data; and
ii) Outlier detection because the data obtained from the sensor may have a value that is much different
from other values and can be caused by various factors such as measurement errors from the sensor or
abnormal conditions. The process is carried out by determining the upper and lower limits of the data and
identifying any values outside these limits as outliers. Algorithm 3 shows the procedure of the data filter
module.
9. Int J Elec & Comp Eng ISSN: 2088-8708
Developing a smart system for infant incubators using the internet of … (I Komang Agus Ady Aryanto)
2301
Algorithm 3. Data filter
Input: Sensor data
Output: Filtered sensor data of the system
Description:
data = data_sensor
noise (data, size):
results []
for i in range(len(data) - size + 1):
x = sum(data[i:i+size])/ size
results[] = x
end
return:
results[]
end
end
detect_outliers(data):
low = set_lower_bound
high = set_upper_bound
for x in data:
if data < low:
outliers = data
end
elseif data > high:
outliers = data
end
end
return:
outliers
end
end
3.5.3. Data storage
In this study, sensor devices are used to collect data from the incubator environment through
connected sensors, then send this data to a database by passing through a filtering process. Data storage in the
database requires several tables related to each other to enable efficient access and further data analysis. The
design of the database schema on the system defines the characteristics of the data stored in the database,
including the type of data as shown in Table 3.
Table 3 describes the sensor data, namely, the incubator temperature, measured in degrees Celsius,
as a parameter stored with the float data type in the database so that it has a high precision value in
representing temperature. Furthermore, body temperature is monitored and recorded. Like the incubator
temperature, the database stores body temperature as a float data type. Meanwhile, heart rate is another vital
parameter monitored, stored as an Integer data type in the database. Next, the oxygen saturation level in the
blood is expressed as a percentage. Oxygen saturation is stored as a decimal data type in the database. In
addition to these parameter data, records of data retrieval times are stored as the Timestamp data type in the
database. Thus, these various types of data can be stored efficiently in the database, facilitating the analysis
process.
Table 3. Data description for sensor devices
Device Data variable Example value Unit Data type
DHT22 Incubator temperature 33.00 ℃ Float
MLX90614 Body temperature 37.00 ℃ Float
MAX30102 Heart rate 150 Beats per minute (BPM) Integer
MAX30102 Saturation 99 SpO2 Decimal
RTC Real-time Date-time 2023-07-21 10:00:00 yyyy-mm-dd hh:mm:ss Timestamp
3.5.4. Dataset
In this study, the data set in the database was organized to become the dataset used for modeling
analysis. This dataset consists of features retrieved from database columns. The features of the dataset are
incubator temperature (T_i), body temperature (T_i), heart rate (HR), and saturation peripheral oxygen
(SPO), as shown in Table 4. Then, each row of data will include values for each feature, which are used to
determine the infant's condition from time to time based on model training to produce predictive values or
patterns of incubator temperature conditions. In addition, given the complexity and sensitivity of health data,
we are also aware of handling this dataset with care, ensuring data privacy and security, and only using data
for legal and ethical purposes.
10. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2293-2312
2302
Table 4. Dataset attribute
Attribute Unit Descriptions
T_b ℃ Body temperature
T_i ℃ Temperature around the incubator environment
HR BPM Heart rate in infants
SPO SpO2 Saturation (oxygen level)
Next, we use this dataset to calculate the correlation value between the attributes. The target or label
chosen in this dataset is the incubator temperature or T_i. Selecting attributes that correlate with the target
can increase the effectiveness of the model training process. The correlation equation r uses the formula
shown in (1). This equation can be used if the dataset has a sequential time series with vector
X= (x1,x2,x3,…,xn), and there must also be vector Y=( y1,y2,y3,…,yn). Then, the results of the value of r are
considered to have a positive correlation if the attribute value is in the range 0 < r < 1, while it is considered
to have a negative correlation if the attribute value is in the range -1 < r < 0 [36].
𝑟 =
𝑛 ∑ 𝑥𝑖 𝑦𝑖− ∑ 𝑥𝑖 ∑ 𝑦𝑖
𝑛
𝑖=1
𝑛
𝑖=1
𝑛
𝑖=1
√𝑛 ∑ 𝑥𝑖
2
𝑛
𝑖=1 −(∑ 𝑥𝑖
𝑛
𝑖=1 )2 √𝑛 ∑ 𝑦𝑖
2
𝑛
𝑖=1 −(∑ 𝑦𝑖
𝑛
𝑖=1 )2
(1)
3.5.5. Long short-term memory
The LSTM method is a particular recurrent neural network (RNN) designed to solve the problem of
long-term and short-term dependencies in data sequences. LSTM overcomes this problem with gate
operations and memory cells that retain information longer. Three types of gates are used, namely, the forget
gate to determine how far information from the previous step must be maintained or forgotten, the input gate
to determine how far new data from the current input must be stored in the memory cell, the output gate to
determine how far the data from the cell memory must be used to calculate the output current [37], [38].
The application of the LSTM method in the IoT system in the incubator in this study begins with the
initialization step and data preparation to be analyzed based on the attribute dataset, as shown in Table 3.
Then, the LSTM model is built and trained using training data. This process involves determining parameters
such as the number of layers and neurons and selecting activation and optimization operations. Once the
model is trained, it can make predictions based on test data. This makes evaluating the model performance
possible by measuring the difference between the prediction and the actual value. Algorithm 4 represents the
basic steps of the LSTM.
Algorithm 4. LSTM application in IoT systems in incubators
Input: Dataset sensor
Output: Predictive value
DESCRIPTION:
initialize LSTM parameters
prepare training_data
prepare test_data
training (training_data):
for each sample in training_data do:
compute all gate outputs and states (w_f, w_i, w_o, cell state)
compute final output
end
end
testing (test_data):
for each sample in test_data do:
compute all gate outputs and states
record final output as prediction
end
for each prediction in actual value do:
compute difference between prediction and actual value
record differences
end
end
Then mathematically, the operations within the LSTM unit, which enable it to recognize patterns in
sequential data and retain and manipulate information over long periods, can be described by (2)-(9), and the
structure of the LSTM is shown in Figure 6 [39]–[41]. All stages in model building, from data training to
testing, were carried out by using the Python programming language. In addition, we also rely on several
additional libraries to support the modeling process.
11. Int J Elec & Comp Eng ISSN: 2088-8708
Developing a smart system for infant incubators using the internet of … (I Komang Agus Ady Aryanto)
2303
𝐹𝑡 = 𝑠𝑖𝑔𝑚𝑜𝑖𝑑([𝐻𝑡−1, 𝑋𝑡] . 𝑊𝑓 + 𝑏𝑓) (2)
𝐼𝑡 = 𝑠𝑖𝑔𝑚𝑜𝑖𝑑([𝐻𝑡−1, 𝑋𝑡] . 𝑊𝑖 + 𝑏𝑖) (3)
𝐶𝑡
̃ = tanh([𝐻𝑡−1, 𝑋𝑡] . 𝑊
𝑐 + 𝑏𝑐) (4)
𝐶𝑡 = (𝐹𝑡 . 𝐶𝑡−1) + (𝐼𝑡 . 𝐶𝑡
̃ ) (5)
𝑂𝑡 = 𝑠𝑖𝑔𝑚𝑜𝑖𝑑(𝑊
𝑜 . [𝐻𝑡−1, 𝑋𝑡] + 𝑏𝑜) (6)
𝐻𝑡 = 𝑂𝑡 . tanh( 𝐶𝑡) (7)
𝑠𝑖𝑔𝑚𝑜𝑖𝑑(𝑥) =
1
1+𝑒−𝑥 (8)
tanh(𝑥) =
𝑒𝑥−𝑒−𝑥
𝑒𝑥+𝑒−𝑥 (9)
Figure 6. LSTM design structure
3.6. Evaluation of predictive performance
The model obtained from training with the LSTM was evaluated using several techniques.
Evaluation techniques used in this study include root mean squared error (RMSE), mean absolute error
(MAE), mean absolute percentage error (MAPE), and coefficient of determination (R2
). RMSE measures the
difference between the predicted value generated by the model and the actual value, as shown in (10) [42],
[43]. Meanwhile, MAE is similar to RMSE, but the difference lies in its tolerance for outliers, which is stated
in (11) [42], [43]. In addition, MAPE is used to determine the scaling of the prediction error in percentage
terms, the calculation of which is described in (12) [42], [43].
On the other hand, R2
is used to measure the variation of the variables in the model. If the R2
value
is high, the model can be considered good, whereas if the value is low, then the model may not be effective.
The equation for R2
is shown in (13)-(15) [42], [43]. In this study, the symbols in the evaluation formula can
be explained as follows: n represents the amount of data, 𝑦𝑖 is the actual value, 𝑦𝑖
̃ is the predicted value, and
Σ represents the sum of all data.
𝑅𝑀𝑆𝐸 = √
∑ (𝑦𝑖−𝑦𝑖
̃)2
𝑛
𝑖=1
𝑛
(10)
𝑀𝐴𝐸 =
∑ |𝑦𝑖−𝑦𝑖
̃|
𝑛
𝑖=1
𝑛
(11)
𝑀𝐴𝑃𝐸 =
1
𝑛
∑
|𝑦𝑖−𝑦𝑖
̃|
𝑦𝑖
𝑛
𝑖=1 × 100% (12)
𝑆𝑆𝑟𝑒𝑠 = ∑ (𝑦𝑖 − 𝑦𝑖
̃)2
𝑛
𝑖=1 (13)
𝑆𝑆𝑡𝑜𝑡 = ∑ (𝑦𝑖 − 𝑦
̅)2
𝑛
𝑖=1 (14)
12. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2293-2312
2304
𝑅2
= 1 −
𝑆𝑆𝑟𝑒𝑠
𝑆𝑆𝑡𝑜𝑡
(15)
3.7. Design data output
Figure 7 shows the design for the output data generated by the incubator. This includes how data is
collected, processed, and presented to users. This design includes essential elements that ensure critical
information can be easily understood and applied to make informed decisions about baby care. The
components in this data output include data visualization and monitoring, notification, control system, data
logging, predictive analytics, and system integration.
In this study, the process of visualizing and monitoring data is carried out after the sensor data on
the incubator has been successfully sent to the database, where the data is then visualized and monitored
through a web dashboard that has been designed. This dashboard allows users to monitor real-time status
indicators and incubator condition trends through a responsive web interface with intuitive graphs and tables.
Then, the designed notification system can automatically warn users when abnormal or emergency conditions
occur. Apart from providing notifications, this system can also be controlled remotely via a web dashboard
by adjusting the operational parameters of the incubator. Furthermore, data collected and stored in a database
can be downloaded in various file formats to facilitate data access and analysis. For example, data can be
downloaded as XLSX, CSV, JSON, PDF, or XML files, allowing users to perform further analysis.
The analysis process uses the LSTM method to develop a model that can predict the temperature
value in the incubator based on previous data patterns stored in the database. The results of this prediction
can then be used to optimize incubator operations, predict changes in conditions, and make adjustments
before conditions change significantly. This system is based on an IoT application so that it can be integrated
with other systems such as electronic medical record systems through the API. Thus, the data generated by
this IoT incubator system can be used to create various applications to improve baby care.
Figure 7. Design of output data
4. RESULTS AND DISCUSSION
This section will present the system analysis and design results implemented previously. This
research aims to develop a baby incubator system by adopting the IoT concept, which is combined with the
LSTM method to make predictions about incubator temperature values in the future. In addition, sensor data
from the hardware installed on the incubator will be visualized using web technology and stored in a database
for easy access and further analysis.
The first process involves collecting data from measurements made by sensors attached to the
incubator. Data from this sensor is divided into four categories: baby body temperature sensors, incubator
environmental sensors, heart rate sensors, and saturation sensors. Each of these sensors has an essential role in
monitoring the infant's condition and the environment in the incubator. Visualization of these various sensors
produces patterns of information, as shown in Figure 8(a) shows body temperature data visualization,
Figure 8(b) shows heart rate data, Figure 8(c) shows incubator temperature data, and Figure 8(d) shows
saturation data. We then use these patterns to predict future temperature values in developing learning models.
Measurement results data from sensors in the incubator are stored directly in the database, and the
characteristics of the data are shown in Table 5. This data is then used as a dataset in making learning
models. This dataset is multivariate data, where each row includes various features such as time, body
temperature, incubator temperature, heart rate, and saturation. This dataset is also a time series data, meaning
that the data is collected sequentially over time, and each data point is related to the data point before and
after. In this dataset, the time intervals are five seconds apart, and the total amount of data is 2,880 taken over
four hours, as shown in Table 6.
13. Int J Elec & Comp Eng ISSN: 2088-8708
Developing a smart system for infant incubators using the internet of … (I Komang Agus Ady Aryanto)
2305
(a)
(b)
(c)
(d)
Figure 8. Pattern of data for each sensor measurement (a) body temperature, (b) heart rate, (c) incubator
temperature, and (d) saturation
14. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2293-2312
2306
Table 5. Statistical summary of the sensor data characteristics
Variable T_b T_i HR SPO
count 2,880 2,880 2,880 2,880
mean 35.36 27.01 66.43 84.21
std 0.54 0.32 5.04 3.54
min 34.2 26.2 58 78
max 36.2 27.5 92 98
Table 6. Dataset information in the database record table
Item Hour T_b T_i HR SPO
1 15:00:05 34.7 26.2 68 85
2 15:00:10 34.7 26.2 68 85
3 15:00:15 34.7 26.2 68 85
. . . . . .
. . . . . .
2878 18:59:50 35.8 27.5 61 89
2879 18:59:55 35.8 27.5 61 89
2880 19:00:00 35.8 27.5 61 89
The dataset is divided into two parts, namely 80% training data, or 2,304 data lines, and 20% test
data, or 576 data lines. The training data trains the model and sets parameters to make predictions. At the
same time, the test data is used to evaluate the extent to which the model can make correct predictions on
previously unknown data.
Based on Table 7, it can be seen that the incubator temperature attribute has a positive correlation
with all other attributes. The correlation value between incubator temperature and body temperature is 0.48,
with a heart rate of 0.29 and a saturation of 0.23. The correlation results show that the dataset used in this
study tends to have a positive correlation with incubator temperature. Therefore, we can identify the factors
that influence the incubator temperature for the analysis process and make decisions based on the correlation
between the attributes in the dataset.
Table 7. Correlation coefficients of attribute in the dataset
T_b T_i HR SPO
T_b 1.0 0.48 0.35 0.31
T_i 0.48 1.0 0.29 0.23
HR 0.35 0.29 1.0 0.022
SPO 0.31 0.23 0.022 1.0
The results of web application development are shown in Figure 9(a) for the dashboard and
control system pages, Figure 9(b) for sensor data pages, and Figure 9(c) for notification pages. The web
application includes a dashboard page that displays real-time data from various sensors, including the
baby's body temperature, incubator temperature, heart rate, and oxygen saturation sensors. This data is
presented in graphs and numbers so users can easily understand and analyze patterns in the data based on
specific time records. In addition, an essential feature of this application is to provide notifications or
warnings if the data from the sensor shows abnormal conditions. Through the web application, users can
also manually control the conditions in the incubator. This gives the user the flexibility to set and monitor
temperature conditions in real-time, thus ensuring an optimal environment for the baby being treated in the
incubator.
Furthermore, this application has a page to display data stored in database data. The data displayed
on this page can be printed in various formats such as CSV, Excel, JSON, or PDF. Through this page, users
can also sort and search data. This sorting feature can be done by determining the data parameters such as
time, sensor value, or sensor type. Meanwhile, the data search feature can be used by entering certain
keywords, helping users quickly find specific data in the system.
Figure 10 shows the results of implementing the electronic incubator designed in this study.
Figure 10(a) shows the hardware installation results on the incubator, Figure 10(b) depicts the
implementation of the PCB along with sockets for connecting sensors and microcontrollers, while
Figure 10(c) displays the sensor devices installed on the incubator. Each component, from sensors to
actuators, is structured in a PCB layout. After that, the program is uploaded to the microcontroller for
testing. During the test, all components are operational and active, and sensor data such as heart rate,
15. Int J Elec & Comp Eng ISSN: 2088-8708
Developing a smart system for infant incubators using the internet of … (I Komang Agus Ady Aryanto)
2307
incubator temperature, body temperature, and oxygen saturation can also be collected. In addition, testing
is also carried out to ensure all actuator devices function correctly.
(a)
(b)
(c)
Figure 9. Web application (a) dashboard page and control system, (b) data record page, and (c) notification
16. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2293-2312
2308
(a) (b)
(c)
Figure 10. The hardware results including (a) device installation, (b) PCB and microcontroller components,
and (c) sensors and actuators
Furthermore, testing was also carried out to test the integration process between electronic devices
and the IoT platform. The Wi-Fi module is used as a connecting network so that sensor data that has been
collected can be sent to an IoT Broker, where the data is then stored in a database and visualized via web
pages, as shown in Table 4, Table 5, and Figure 8. In addition, this sensor data is also used for the dataset for
making a model with the LSTM method, with results as shown in Table 7.
Based on the results of experiments carried out on the learning model, the results are shown in
Table 8. We evaluated this model using RMSE, MAE, MAPE, and R2
metrics. This model uses two layers of
LSTM, and we conducted experiments with several numbers of neurons in each layer. The results show that
as many as 60 neurons produce the highest predictive value or R2
, equal to 0.934. However, it is essential to
note that model performance does not always increase as the number of neurons increases.
Furthermore, we also conducted experiments on the model by adjusting the lookback value.
Lookback refers to the model ability to look at data at previous time intervals before making predictions
about future data. For example, in this dataset, with a time interval of 5 seconds, if lookback is set as 6, then
the model will predict 1 data forward based on 6 previous data. We conducted an experimental scenario by
setting the lookback value from 1 to 10, with 60 neurons for each layer. The experimental results show that
lookback 6 produces the best predictive value, which is 0.934, as shown in Table 9.
Next, we also experimented with inputting each attribute from the dataset into the model. From
Table 10, it can be seen that the predicted value for the input attribute T_b has the highest value of 0.845. As
for the HR input, a predictive value of 0.805 is obtained, and the SPO input produces a predictive value of
0.590. The results of the predicted value of each attribute show that all attributes positively impact model
performance because each attribute has a different contribution to the final prediction. This analysis reveals
that the attributes T_b, HR, and SPO each make important contributions to predictions, with T_b having the
most significant impact.
17. Int J Elec & Comp Eng ISSN: 2088-8708
Developing a smart system for infant incubators using the internet of … (I Komang Agus Ady Aryanto)
2309
Table 8. The result of selecting the number of neurons
Number of neurons LSTM - 1 Number of neurons LSTM - 2 RMSE (o
C) MAE (o
C) MAPE (%) R2
100 100 0.017 0.008 0 0.918
90 90 0.020 0.014 0.1 0.893
80 80 0.027 0.022 0.1 0.793
70 70 0.029 0.026 0.1 0.770
60 60 0.015 0.008 0 0.934
50 50 0.015 0.006 0 0.933
40 40 0.045 0.023 0.1 0.436
30 30 0.042 0.027 0.1 0.503
20 20 0.059 0.046 0.2 0.035
10 10 0.023 0.016 0.1 0.851
5 5 0.031 0.021 0.1 0.726
Table 9. The result of the selection is the number of lookbacks
Lookbacks RMSE (o
C) MAE (o
C) MAPE (%) R2
1 0.023 0.015 0.1 0.859
2 0.047 0.035 0.1 0.392
3 0.024 0.017 0.1 0.843
4 0.030 0.027 0.1 0.751
5 0.034 0.018 0.1 0.677
6 0.015 0.008 0 0.934
7 0.028 0.022 0.1 0.787
8 0.032 0.030 0.1 0.719
9 0.026 0.021 0.1 0.814
10 0.041 0.028 0.1 0.522
Table 10. The results of the selection of input types for the LSTM
Input type Correlation
coefficient (r)
RMSE
(o
C)
MAE
(o
C)
MAPE
(%)
R2
T_b 0.48 0.024 0.020 0.1 0.845
HR 0.29 0.026 0.019 0.1 0.805
SPO 0.23 0.038 0.035 0.1 0.590
The plotting results between the predicted results and the actual values in the test data are shown in
Figure 11 (in Appendix). The red line shows the predicted result, while the blue line shows the actual value.
In general, the plotting results show that the predicted value follows the pattern of the actual value. Even so,
the model does not follow the actual value pattern perfectly. Several differences or deviations between the
predicted results and the actual values need further attention to improve the accuracy and quality of model
predictions.
In Figure 11(a), the plot results are obtained with LSTM-1 100 neurons and LSTM-2 100 neurons
with a lookback of 6. Figure 11(b) shows the plot results with LSTM-1 90 neurons and LSTM-2 90 neurons,
also with a lookback of 6. Figure 11(c) displays the plot results with LSTM-1 60 neurons and LSTM-2 60
neurons, again with a lookback of 6. Lastly, in Figure 11(d), the plot results are achieved with LSTM-1 50
neurons and LSTM-2 50 neurons, maintaining a lookback of 6.
5. CONCLUSION
This research presents a new approach to incubator system development with the internet of things
and deep learning concept, designed by combining hardware, network, software, and database management.
Based on the research results, it was found that hardware such as sensors installed in incubators could
measure environmental conditions and send their values to the database via the Internet using the MQTT
protocol. The sensor device connected to the microcontroller performs measurements every five-second
interval. In the experiment, the incubator was turned on for 4 hours, and the data was successfully stored in a
database of 2,880 rows. In addition, through the web application, users can view real-time data with visual
graphs and tables. This web application also provides notifications if conditions change in the incubator. In
the web application, the user can also manually control the temperature conditions inside the incubator. This
system is also equipped with API features to facilitate integration with other systems related to patient health
data. The data stored in the database is also used as a dataset for model building using the LSTM deep
learning method. This dataset has four attributes, namely T_i, T_b, HR, and SPO. The attribute selected as the
target or label in the dataset is T_b. Furthermore, the value of the correlation coefficient (r) on the dataset for
each attribute with a target (T_b) is obtained, namely T_i of 0.48, HR of 0.29, and SPO of 0.23. Then, based
18. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2293-2312
2310
on this dataset, the model was developed using LSTM by dividing the dataset into two types, namely 80%
training data and 20% test data. The best prediction results are obtained using two LSTM layers from several
model experiments on test data. Each layer has 60 neurons and 6 lookback settings, producing an R2
prediction value of 0.934. In addition, the error value of the model for the test data for each matrix is RMSE
of 0.015 and MAE of 0.008. Furthermore, based on the results of input experiments with each attribute in the
dataset, it appears that the best R2
predictions are obtained for the T_b attribute with a value of 0.845, for the
HR attribute with a value of 0.805, and the SPO attribute with a value of 0.590. These results show the
variability of predictive performance for each input attribute.
APPENDIX
(a)
(b)
(c)
(d)
Figure 11. Results comparison of actual value and predicted value (a) LSTM 1 and 2: 100,
(b) LSTM 1 and 2: 90, (c) LSTM 1 and 2: 60, and (d) LSTM 1 and 2: 50
19. Int J Elec & Comp Eng ISSN: 2088-8708
Developing a smart system for infant incubators using the internet of … (I Komang Agus Ady Aryanto)
2311
REFERENCES
[1] A. Latif, H. A. Widodo, R. A. Atmoko, T. N. Phong, and E. T.Helmy, “Temperature and humidity controlling system for baby
incubator,” Journal of Robotics and Control (JRC), vol. 2, no. 3, pp. 190–193, 2021, doi: 10.18196/jrc.2376.
[2] M. A. Mahdi, A. H. Issa, and S. A. Gitaffa, “Machine learning techniques based data-driven fault detection of multiple
transducers,” in AIP Conference Proceedings, 2023, doi: 10.1063/5.0154268.
[3] F. Ahmed, A. Sufyan, S. Hussain, A. Rehman, S. Amin, and Y. Salam, “Smart baby incubator,” in 2021 International Conference on
Computing, Electronic and Electrical Engineering (ICE Cube), Oct. 2021, pp. 1–5, doi: 10.1109/ICECube53880.2021.9628245.
[4] L. Lamidi, A. Kholiq, and M. Ali, “A low cost baby incubator design equipped with vital sign parameters,” Indonesian Journal of
electronics, electromedical engineering, and medical informatics, vol. 3, no. 2, pp. 53–58, May 2021, doi:
10.35882/ijeeemi.v3i2.3.
[5] A. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari, and M. Ayyash, “Internet of things: a survey on enabling technologies,
protocols, and applications,” IEEE Communications Surveys & Tutorials, vol. 17, no. 4, pp. 2347–2376, 2015, doi:
10.1109/COMST.2015.2444095.
[6] M. A. Khan et al., “A deep learning-based intrusion detection system for MQTT enabled IoT,” Sensors, vol. 21, no. 21, pp. 1–25,
Oct. 2021, doi: 10.3390/s21217016.
[7] W. Widhiada, I. N. G. Antara, I. N. Budiarsa, and I. M. G. Karohika, “The robust PID control system of temperature stability and
humidity on infant incubator based on Arduino ATMega 2560,” IOP Conference Series: Earth and Environmental Science, vol.
248, no. 1, pp. 1–12, Apr. 2019, doi: 10.1088/1755-1315/248/1/012046.
[8] W. H. Organization, R. Health, P. Cooper, and M. McCormick, “Managing newborn problems: a guide for doctors, nurses, and
midwives,” World Health Organization, 2003.
[9] I. N. K. Wardana, J. W. Gardner, and S. A. Fahmy, “Optimising deep learning at the edge for accurate hourly air quality
prediction,” Sensors, vol. 21, no. 4, pp. 1–28, Feb. 2021, doi: 10.3390/s21041064.
[10] J. Krohkaew, P. Nilaphruek, N. Witthayawiroj, S. Uapipatanakul, Y. Thwe, and P. N. Crisnapati, “Thailand raw water quality
dataset analysis and evaluation,” Data, vol. 8, no. 9, pp. 1–17, Sep. 2023, doi: 10.3390/data8090141.
[11] I. Sukma et al., “Real-time wireless temperature measurement system of infant incubator,” International Journal of Electrical and
Computer Engineering (IJECE), vol. 13, no. 1, pp. 1152–1160, Feb. 2023, doi: 10.11591/ijece.v13i1.pp1152-1160.
[12] P. T. Kapen, Y. Mohamadou, F. Momo, D. K. Jauspin, N. Kanmagne, and D. D. Jordan, “Development of a neonatal incubator
with phototherapy, biometric fingerprint reader, remote monitoring, and heart rate control adapted for developing countries
hospitals,” Journal of Neonatal Nursing, vol. 25, no. 6, pp. 298–303, Dec. 2019, doi: 10.1016/j.jnn.2019.07.011.
[13] M. Irmansyah, “Design and application of portable heart rate and weight measuring tool for premature baby with microcontroller
base,” International Journal of GEOMATE, vol. 17, no. 61, pp. 195–201, Sep. 2019, doi: 10.21660/2019.61.ICEE12.
[14] A. Alimuddin, R. Arafiyah, I. Saraswati, R. Alfanz, P. Hasudungan, and T. Taufik, “Development and performance study of
temperature and humidity regulator in baby incubator using fuzzy-PID hybrid controller,” Energies, vol. 14, no. 20, pp. 1–21, Oct.
2021, doi: 10.3390/en14206505.
[15] P. A. Aya-Parra, A. J. Rodriguez-Orjuela, V. Rodriguez Torres, N. P. Cordoba Hernandez, N. Martinez Castellanos, and J.
Sarmiento-Rojas, “Monitoring monitoring system for operating variables in incubators in the neonatology service of a highly
complex hospital through the internet of things (IoT),” Sensors, vol. 23, no. 12, pp. 1–18, Jun. 2023, doi: 10.3390/s23125719.
[16] G. Cay et al., “NeoWear: an IoT-connected e-textile wearable for neonatal medical monitoring,” Pervasive and Mobile
Computing, vol. 86, pp. 1–17, Oct. 2022, doi: 10.1016/j.pmcj.2022.101679.
[17] M. A. Mahdi, S. A. Gittaffa, and A. H. Issa, “Multiple fault detection and smart monitoring system based on machine learning
classifiers for infant incubators using raspberry Pi 4,” Journal Européen des Systèmes Automatisés, vol. 55, no. 6, pp. 771–778,
Dec. 2022, doi: 10.18280/jesa.550609.
[18] P. N. Crisnapati and D. Maneetham, “RIFIS: a novel rice field sidewalk detection dataset for walk-behind hand tractor,” Data,
vol. 7, no. 10, pp. 1–16, Sep. 2022, doi: 10.3390/data7100135.
[19] H. Shi, L. Niu, and J. Sun, “Construction of industrial internet of things based on MQTT and OPC UA protocols,” in 2020 IEEE
International Conference on Artificial Intelligence and Computer Applications (ICAICA), Jun. 2020, pp. 1263–1267, doi:
10.1109/ICAICA50127.2020.9182598.
[20] Y. Yu, X. Si, C. Hu, and J. Zhang, “A review of recurrent neural networks: LSTM cells and network architectures,” Neural
Computation, vol. 31, no. 7, pp. 1235–1270, Jul. 2019, doi: 10.1162/neco_a_01199.
[21] A. Huiyao, S. Yang, Y. Tao, L. Hui, Z. Peng, and Z. Jun, “A new architecture of ajax web application security crawler with finite-
state machine,” in 2014 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, Oct.
2014, pp. 112–117, doi: 10.1109/CyberC.2014.27.
[22] H. K. Dhalla, “A performance analysis of native JSON parsers in java, python, MS.NET core, JavaScript, and PHP,” in 2020 16th
International Conference on Network and Service Management (CNSM), 2020, pp. 1–5, doi: 10.23919/CNSM50824.2020.9269101.
[23] H. Shamkhalichenar, C. J. Bueche, and J.-W. Choi, “Printed circuit board (PCB) technology for electrochemical sensors and
sensing platforms,” Biosensors, vol. 10, no. 11, pp. 1–16, Oct. 2020, doi: 10.3390/bios10110159.
[24] A. Bouraiou et al., “Display on web browser using ethernet shield and LM35 sensor based on Arduino board,” in 2022 19th
International Multi-Conference on Systems, Signals & Devices (SSD), 2022, pp. 421–424, doi: 10.1109/SSD54932.2022.9955956.
[25] K. Chaarmart, A. Vora-ud, and T. Seetawan, “Temperature controlling and monitoring system of Mao-wine aging tank for local
enterprises,” in 2021 Research, Invention, and Innovation Congress: Innovation Electricals and Electronics (RI2C), Sep. 2021,
pp. 243–246, doi: 10.1109/RI2C51727.2021.9559768.
[26] Y. A. Ahmad, T. Surya Gunawan, H. Mansor, B. A. Hamida, A. Fikri Hishamudin, and F. Arifin, “On the evaluation of DHT22
temperature sensor for IoT application,” in 2021 8th International Conference on Computer and Communication Engineering
(ICCCE), Jun. 2021, pp. 131–134, doi: 10.1109/ICCCE50029.2021.9467147.
[27] C. C. Paglinawan, G. A. R. Bordonada, and A. V. D. Roseus, “Infrared temperature detection using MLX90614 sensor for
wearable applications,” in 2023 15th International Conference on Computer and Automation Engineering (ICCAE), Mar. 2023,
pp. 385–388, doi: 10.1109/ICCAE56788.2023.10111139.
[28] A. C. Bento, “An experimental survey with NodeMCU12e+shield with Tft Nextion and MAX30102 sensor,” in 2020 11th IEEE
Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), Nov. 2020, pp. 82–86, doi:
10.1109/IEMCON51383.2020.9284870.
[29] C.-H. Lee, W.-H. Lee, and S.-M. Kim, “Development of IoT-based real-time fire detection system using raspberry pi and fisheye
camera,” Applied Sciences, vol. 13, no. 15, pp. 1–14, Jul. 2023, doi: 10.3390/app13158568.
[30] S. Avallone, P. Imputato, G. Redieteab, C. Ghosh, and S. Roy, “Will OFDMA improve the performance of 802.11 Wi-Fi
networks,” IEEE Wireless Communications, vol. 28, no. 3, pp. 100–107, Jun. 2021, doi: 10.1109/MWC.001.2000332.
20. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2293-2312
2312
[31] D. Dinculeană and X. Cheng, “Vulnerabilities and limitations of MQTT protocol used between IoT devices,” Applied Sciences,
vol. 9, no. 5, pp. 1–10, Feb. 2019, doi: 10.3390/app9050848.
[32] H. Siddharthan, T. Deepa, and P. Chandhar, “SENMQTT-SET: an intelligent intrusion detection in IoT-MQTT networks using
ensemble multi cascade features,” IEEE Access, vol. 10, pp. 33095–33110, 2022, doi: 10.1109/ACCESS.2022.3161566.
[33] R. A. Light, “Mosquitto: server and client implementation of the MQTT protocol,” The Journal of Open Source Software, vol. 2,
no. 13, p. 265, 2017, doi: 10.21105/joss.00265.
[34] T. N. Ford, E. Gamess, and C. Ogden, “Performance evaluation of different raspberry Pi models as MQTT servers and clients,”
International journal of Computer Networks & Communications, vol. 14, no. 2, pp. 1–18, Mar. 2022, doi: 10.5121/ijcnc.2022.14201.
[35] K. Manandhar, X. Cao, F. Hu, and Y. Liu, “Detection of faults and attacks including false data injection attack in smart grid using
kalman filter,” IEEE Transactions on Control of Network Systems, vol. 1, no. 4, pp. 370–379, Dec. 2014, doi:
10.1109/TCNS.2014.2357531.
[36] Q. Tao, F. Liu, Y. Li, and D. Sidorov, “Air pollution forecasting using a deep learning model based on 1D convnets and
bidirectional GRU,” IEEE Access, vol. 7, pp. 76690–76698, 2019, doi: 10.1109/ACCESS.2019.2921578.
[37] I. N. K. Wardana, J. W. Gardner, and S. A. Fahmy, “Estimation of missing air pollutant data using a spatiotemporal convolutional
autoencoder,” Neural Computing and Applications, vol. 34, no. 18, pp. 16129–16154, Sep. 2022, doi: 10.1007/s00521-022-
07224-2.
[38] Y.-C. Liang, I. Wijaya, M.-T. Yang, J. R. C. Juarez, and H.-T. Chang, “Deep learning for infant cry recognition,” International
Journal of Environmental Research and Public Health, vol. 19, no. 10, pp. 1–10, May 2022, doi: 10.3390/ijerph19106311.
[39] T. Li, M. Hua, and X. Wu, “A hybrid CNN-LSTM model for forecasting particulate matter (PM2.5),” IEEE Access, vol. 8,
pp. 26933–26940, 2020, doi: 10.1109/ACCESS.2020.2971348.
[40] Q. Wang, R.-Q. Peng, J.-Q. Wang, Z. Li, and H.-B. Qu, “NEWLSTM: an optimized long short-term memory language model for
sequence prediction,” IEEE Access, vol. 8, pp. 65395–65401, 2020, doi: 10.1109/ACCESS.2020.2985418.
[41] V. Gude and S. Corns, “Integrated deep learning and supervised machine learning model for predictive fetal monitoring,”
Diagnostics, vol. 12, no. 11, pp. 1–16, Nov. 2022, doi: 10.3390/diagnostics12112843.
[42] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE,
MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Computer Science, vol. 7, pp. 1–24, Jul. 2021, doi:
10.7717/peerj-cs.623.
[43] T. O. Hodson, “Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not,” Geoscientific Model
Development, vol. 15, no. 14, pp. 5481–5487, Jul. 2022, doi: 10.5194/gmd-15-5481-2022.
BIOGRAPHIES OF AUTHORS
I Komang Agus Ady Aryanto Completed a computer systems undergraduate
program at the ITB STIKOM Bali in 2015. After that, continued his master's degree in
computer systems at the Ganesha University of Education and finished his education in 2018.
He lecturer on the ITB STIKOM Bali since 2018 until now and teaching web programming,
internet of things, sensors and transducers, microcontroller programming, data structures, and
databases. The research topics occupied are the internet of things, information systems,
computer science, robotics, and programming. In addition, he also works as a software
developer to develop web-based and mobile applications that have been implemented in the
fields of government, transportation, industry, academics, hospitals, and others. He can be
contacted at email: i_komang@mail.rmutt.ac.th and komang.aryanto@gmail.com.
Dechrit Maneetham is a lecturer in the Faculty of Engineering Education at
Rajamangala University, Thailand for more than 15 years. Fields taught by lecturers are
mechatronics, robotics, and internet of things. Education in Computer Engineering with M.S
and B.Tech degrees at the Raja Mongkut University of Technology in Thailand. D.Eng
doctoral education in the field of mechatronics at the Asian Institute of Technology. Then the
second Ph.D. doctoral education at Mahasarakham University in the field of computer
engineering. Author of books on PLC, microcontroller, pneumatics, and robotics topics.
Research interest in the fields of mechatronics, automation, internet of things, and robotics and
has published more than 30 international papers. He can be contacted at email:
dechrit_m@rmutt.ac.th.
Evi Triandini as a lecturer at the ITB STIKOM Bali in the information systems
study program. Teach courses related to software engineering, object-oriented modeling, and
information systems design. Undergraduate education was taken by the University of
Brawijaya in Indonesia in the field of Agricultural Cultivation. Master's degree at Asia
Institute of Technology Thailand with M.Eng. Doctoral education at the Institute of
Technology Sepuluh November Surabaya Indonesia in the department of computer science
with the title Dr. Published research has topics that include information systems, software, and
electronic commerce. She can be contacted at email: evi@stikom-bali.ac.id.