Accounting for people is the first step of every manpower-based organization in today’s world. Hence, it takes up a signification amount of energy and value in the form of money from respective organizations for both
implementing a suitable system for manpower management as well as maintaining that same system. Although this amount of expenditure for big organizations is near to nothing, rather just a formality, it does not hold as much truth for small organizations such as schools, colleges, and even universities to a certain degree. This is the first point. The second point for discussion is that much work has been done to solve this issue. Various technologies like Biometrics, RFID, Bluetooth, GPS, QR Code, etc., have been used to tackle the issues of attendance collection. This study paves
the path for researchers by reviewing practical methods and technologies used for existing attendance systems.
Air quality forecasting using convolutional neural networksBIJIAM Journal
Air pollution is now one of the biggest environmental risks, which causes more than 6 million premature deathseach year from heart diseases, stroke, diabetes, respiratory disease, and so on. Protecting humans from thedamage which is caused by air pollution is one of the major issues for the global community. The prediction ofair pollution can be done by machine learning (ML) algorithms. ML combines statistics and computer science tomaximize the prediction power. ML can be also used to predict the air quality index (AQI). The aim of this researchis to develop a convolutional neural network (CNN) model to predict air quality from the unseen data set, whichincludes concentration of nitrogen dioxide (NO2), carbon monoxide (CO), and sulfur dioxide (SO2). The proposedsystem will be implemented in two steps; the first step will focus on data analysis and pre-processing, includingfiltering, feature extraction, constructing convolutional neural network layers, and optimizing the parameters ofeach layer, while the second step is used to evaluate its model accuracy. The output is predicted as AQI for thedeveloped CNN model. The developed CNN model achieves a root-mean-square error of 13.4150 and a highaccuracy of 86.585%. The overall model is implemented using MATLAB software.
Prevention of fire and hunting in forests using machine learning for sustaina...BIJIAM Journal
Deforestation, illegal hunting, and forest fires are a few current issues that have an impact on the diversity andecosystem of forests. To increase the biodiversity of species and ecosystems, it becomes imperative to preservethe forest. The conventional techniques employed to prevent these issues are costly, less effective, and insecure.The current systems are unreliable and use more energy. By utilizing an Internet of Things (IOT) system, thistechnology offers a more practical and economical method of continuously maintaining and monitoring the statusof the forest. To guarantee excellent security, this system combines a number of sensors, alarms, cameras, lights,and microphones. It aids in reducing forest loss, animal trafficking, and forest fires. In the suggested system,sensors are used for monitoring, and cloud storage is used for data storage. Through the use of machine learning,the raspberry pi camera module significantly aids in the prevention of unlawful wildlife hunting as well as thedetection and prevention of forest fires.
Object detection and ship classification using YOLO and Amazon RekognitionBIJIAM Journal
The need for reliable automated object detection and classification in the maritime sphere has increasedsignificantly over the last decade. The increased use of unmanned marine vehicles necessitates the developmentand use of an autonomous object detection and classification systems that utilize onboard cameras and operatereliably, efficiently, and accurately without the need for human intervention. As the autonomous vehicle realmmoves further away from active human supervision, the requirements for a detection and classification suite callfor a higher level of accuracy in the classification models. This paper presents a comparative study using differentclassification models on a large maritime vessel image dataset. For this study, additional images were annotatedusing Roboflow, focusing on the types of subclasses that had the lowest detection performance, a previous workby Brown et al. (1). The present study uses a dataset of over 5,000 images. Using the enhanced set of imageannotations, models were created in the cloud using Google Colab using YOLOv5, YOLOv7, and YOLOv8 as wellas in Amazon Web Services using Amazon Rekognition. The models were tuned and run for five runs of 150 epochseach to collect efficiency and performance metrics. Comparison of these metrics from the YOLO models yieldedinteresting improvements in classification accuracies for the subclasses that previously had lower scores, but atthe expense of the overall model accuracy. Furthermore, training time efficiency was improved drastically using thenewer YOLO APIs. In contrast, using Amazon Rekognition yielded superior accuracy results across the board, butat the expense of the lowest training efficiency.
Machine learning for autonomous online exam frauddetection: A concept designBIJIAM Journal
E-learning (EL) has emerged as one of the most valuable means for continuing education around the world,especially in the aftermath of the global pandemic that included a variety of obstacles. Real-time onlineassessments have become a significant concern for educational organizations. Instances of fraudulent behaviorduring online exams (OEs) have created considerable challenges for exam invigilators, who are unable to identifyand remove such dishonest behavior. In response to this significant issue, educational institutions have used avariety of manual procedures to alleviate the situation, but none of these measures have shown to be particularlyinnovative or effective. The current study presents a novel strategy for detecting fraudulent actions in real timeduring OEs that uses convolutional neural network (CNN) algorithms and image processing. The developmentmodel will be trained using the CK and CK++ datasets. The training procedure will use 80% of the selecteddataset, with the remaining 20% used for model testing to confirm the model’s efficacy and generalization capacity.This project intends to revolutionize the monitoring and prevention of fraudulent actions during online tests byintegrating CNN techniques and image processing. The use of CK and CK++ datasets, as well as an 80–20split for training and testing, contributes to the study’s thorough and rigorous approach. Educational institutionscan improve their assessment procedures and maintain the credibility of EL as a credible and equitable way ofcontinuing education by successfully using this unique technique.
Prognostication of the placement of students applying machine learning algori...BIJIAM Journal
Placement is the process of connecting the selected candidate with the employer. Every student might have adream of having a job offer when he or she is about to complete her course. All educational institutions aim athaving their students well placed in good organizations. The reputation of any institution depends on the placementof its students. Hence, many institutions try hard to have a good placement cell. Classification using machinelearning may be utilized to retrieve data from the student-databases. A prediction model that can foretell theeligibility of the students based on their academic and extracurricular achievements is proposed. Related data wascollected from many institutions for which the placement-prediction is made. This paradigm is being weighed upwith the existing algorithms, and findings have been made regarding the accuracy of predictions. It was found thatthe proposed algorithm performed significantly better and yielded good results.
Drug recommendation using recurrent neural networks augmented with cellular a...BIJIAM Journal
Drug recommendation systems are systems that have the capability to recommend drugs. On a daily basis, a huge amount of data is being generated by the patients. All this valuable data can be properly utilized to create a reliable drug recommendation system. In this paper, we recommend a system for drug recommendations. The main scope of our system is to predict the correct medication based on reviews and ratings. Our proposed system uses natural language processing techniques (NLP), recurrent neural networks (RNN), and cellular automata (CA). We also considered various metrics like precision, recall, accuracy, F1 score, and ROC curve as measures of our system’s performance. NLP techniques are being used for gathering useful information from patient data, and RNN is a machine learning methodology that works really well in analyzing textual data. The system considers various patient data attributes like age, gender, dosage, medical history, and symptoms in order to make appropriate predictions. The proposed system has the potential to help medical professionals make informed drug recommendations.
Discrete clusters formulation through the exploitation of optimized k-modes a...BIJIAM Journal
This article focuses on the results of self-funded quantitative research conducted by social workers working inthe “refugee” crisis and social services in Greece (1). The research, among other findings, argues that front-lineprofessionals possess specific characteristics regarding their working profile. Statistical methods in the researchperformed significance tests to validate the initial hypotheses concerning the correlation between dataset variables.On the contrary of this concept, in this work, we present an alternative approach for validating initial hypothesesthrough the exploitation of clustering algorithms. Toward that goal, we evaluated several frequently used clusteringalgorithms regarding their efficiency in feature selection processes, and we finally propose a modified k-Modesalgorithm for efficient feature subset selection.
Emotion Recognition Based on Speech Signals by Combining Empirical Mode Decom...BIJIAM Journal
This paper proposes a novel method for speech emotion recognition. Empirical mode decomposition (EMD) is applied in this paper for the extraction of emotional features from speeches, and a deep neural network (DNN) is used to classify speech emotions. This paper enhances the emotional components in speech signals by using EMD with acoustic feature Mel-Scale Frequency Cepstral Coefficients (MFCCs) to improve the recognition rates of emotions from speeches using the classifier DNN. In this paper, EMD is first used to decompose the speech signals, which contain emotional components into multiple intrinsic mode functions (IMFs), and then emotional features are derived from the IMFs and are calculated using MFCC. Then, the emotional features are used to train the DNN model. Finally, a trained model that could recognize the emotional signals is then used to identify emotions in speeches. Experimental results reveal that the proposed method is effective.
Air quality forecasting using convolutional neural networksBIJIAM Journal
Air pollution is now one of the biggest environmental risks, which causes more than 6 million premature deathseach year from heart diseases, stroke, diabetes, respiratory disease, and so on. Protecting humans from thedamage which is caused by air pollution is one of the major issues for the global community. The prediction ofair pollution can be done by machine learning (ML) algorithms. ML combines statistics and computer science tomaximize the prediction power. ML can be also used to predict the air quality index (AQI). The aim of this researchis to develop a convolutional neural network (CNN) model to predict air quality from the unseen data set, whichincludes concentration of nitrogen dioxide (NO2), carbon monoxide (CO), and sulfur dioxide (SO2). The proposedsystem will be implemented in two steps; the first step will focus on data analysis and pre-processing, includingfiltering, feature extraction, constructing convolutional neural network layers, and optimizing the parameters ofeach layer, while the second step is used to evaluate its model accuracy. The output is predicted as AQI for thedeveloped CNN model. The developed CNN model achieves a root-mean-square error of 13.4150 and a highaccuracy of 86.585%. The overall model is implemented using MATLAB software.
Prevention of fire and hunting in forests using machine learning for sustaina...BIJIAM Journal
Deforestation, illegal hunting, and forest fires are a few current issues that have an impact on the diversity andecosystem of forests. To increase the biodiversity of species and ecosystems, it becomes imperative to preservethe forest. The conventional techniques employed to prevent these issues are costly, less effective, and insecure.The current systems are unreliable and use more energy. By utilizing an Internet of Things (IOT) system, thistechnology offers a more practical and economical method of continuously maintaining and monitoring the statusof the forest. To guarantee excellent security, this system combines a number of sensors, alarms, cameras, lights,and microphones. It aids in reducing forest loss, animal trafficking, and forest fires. In the suggested system,sensors are used for monitoring, and cloud storage is used for data storage. Through the use of machine learning,the raspberry pi camera module significantly aids in the prevention of unlawful wildlife hunting as well as thedetection and prevention of forest fires.
Object detection and ship classification using YOLO and Amazon RekognitionBIJIAM Journal
The need for reliable automated object detection and classification in the maritime sphere has increasedsignificantly over the last decade. The increased use of unmanned marine vehicles necessitates the developmentand use of an autonomous object detection and classification systems that utilize onboard cameras and operatereliably, efficiently, and accurately without the need for human intervention. As the autonomous vehicle realmmoves further away from active human supervision, the requirements for a detection and classification suite callfor a higher level of accuracy in the classification models. This paper presents a comparative study using differentclassification models on a large maritime vessel image dataset. For this study, additional images were annotatedusing Roboflow, focusing on the types of subclasses that had the lowest detection performance, a previous workby Brown et al. (1). The present study uses a dataset of over 5,000 images. Using the enhanced set of imageannotations, models were created in the cloud using Google Colab using YOLOv5, YOLOv7, and YOLOv8 as wellas in Amazon Web Services using Amazon Rekognition. The models were tuned and run for five runs of 150 epochseach to collect efficiency and performance metrics. Comparison of these metrics from the YOLO models yieldedinteresting improvements in classification accuracies for the subclasses that previously had lower scores, but atthe expense of the overall model accuracy. Furthermore, training time efficiency was improved drastically using thenewer YOLO APIs. In contrast, using Amazon Rekognition yielded superior accuracy results across the board, butat the expense of the lowest training efficiency.
Machine learning for autonomous online exam frauddetection: A concept designBIJIAM Journal
E-learning (EL) has emerged as one of the most valuable means for continuing education around the world,especially in the aftermath of the global pandemic that included a variety of obstacles. Real-time onlineassessments have become a significant concern for educational organizations. Instances of fraudulent behaviorduring online exams (OEs) have created considerable challenges for exam invigilators, who are unable to identifyand remove such dishonest behavior. In response to this significant issue, educational institutions have used avariety of manual procedures to alleviate the situation, but none of these measures have shown to be particularlyinnovative or effective. The current study presents a novel strategy for detecting fraudulent actions in real timeduring OEs that uses convolutional neural network (CNN) algorithms and image processing. The developmentmodel will be trained using the CK and CK++ datasets. The training procedure will use 80% of the selecteddataset, with the remaining 20% used for model testing to confirm the model’s efficacy and generalization capacity.This project intends to revolutionize the monitoring and prevention of fraudulent actions during online tests byintegrating CNN techniques and image processing. The use of CK and CK++ datasets, as well as an 80–20split for training and testing, contributes to the study’s thorough and rigorous approach. Educational institutionscan improve their assessment procedures and maintain the credibility of EL as a credible and equitable way ofcontinuing education by successfully using this unique technique.
Prognostication of the placement of students applying machine learning algori...BIJIAM Journal
Placement is the process of connecting the selected candidate with the employer. Every student might have adream of having a job offer when he or she is about to complete her course. All educational institutions aim athaving their students well placed in good organizations. The reputation of any institution depends on the placementof its students. Hence, many institutions try hard to have a good placement cell. Classification using machinelearning may be utilized to retrieve data from the student-databases. A prediction model that can foretell theeligibility of the students based on their academic and extracurricular achievements is proposed. Related data wascollected from many institutions for which the placement-prediction is made. This paradigm is being weighed upwith the existing algorithms, and findings have been made regarding the accuracy of predictions. It was found thatthe proposed algorithm performed significantly better and yielded good results.
Drug recommendation using recurrent neural networks augmented with cellular a...BIJIAM Journal
Drug recommendation systems are systems that have the capability to recommend drugs. On a daily basis, a huge amount of data is being generated by the patients. All this valuable data can be properly utilized to create a reliable drug recommendation system. In this paper, we recommend a system for drug recommendations. The main scope of our system is to predict the correct medication based on reviews and ratings. Our proposed system uses natural language processing techniques (NLP), recurrent neural networks (RNN), and cellular automata (CA). We also considered various metrics like precision, recall, accuracy, F1 score, and ROC curve as measures of our system’s performance. NLP techniques are being used for gathering useful information from patient data, and RNN is a machine learning methodology that works really well in analyzing textual data. The system considers various patient data attributes like age, gender, dosage, medical history, and symptoms in order to make appropriate predictions. The proposed system has the potential to help medical professionals make informed drug recommendations.
Discrete clusters formulation through the exploitation of optimized k-modes a...BIJIAM Journal
This article focuses on the results of self-funded quantitative research conducted by social workers working inthe “refugee” crisis and social services in Greece (1). The research, among other findings, argues that front-lineprofessionals possess specific characteristics regarding their working profile. Statistical methods in the researchperformed significance tests to validate the initial hypotheses concerning the correlation between dataset variables.On the contrary of this concept, in this work, we present an alternative approach for validating initial hypothesesthrough the exploitation of clustering algorithms. Toward that goal, we evaluated several frequently used clusteringalgorithms regarding their efficiency in feature selection processes, and we finally propose a modified k-Modesalgorithm for efficient feature subset selection.
Emotion Recognition Based on Speech Signals by Combining Empirical Mode Decom...BIJIAM Journal
This paper proposes a novel method for speech emotion recognition. Empirical mode decomposition (EMD) is applied in this paper for the extraction of emotional features from speeches, and a deep neural network (DNN) is used to classify speech emotions. This paper enhances the emotional components in speech signals by using EMD with acoustic feature Mel-Scale Frequency Cepstral Coefficients (MFCCs) to improve the recognition rates of emotions from speeches using the classifier DNN. In this paper, EMD is first used to decompose the speech signals, which contain emotional components into multiple intrinsic mode functions (IMFs), and then emotional features are derived from the IMFs and are calculated using MFCC. Then, the emotional features are used to train the DNN model. Finally, a trained model that could recognize the emotional signals is then used to identify emotions in speeches. Experimental results reveal that the proposed method is effective.
Enhanced 3D Brain Tumor Segmentation Using Assorted Precision TrainingBIJIAM Journal
A brain tumor is a medical disorder faced by individuals of all demographics. Medically, it is described as the spread of nonessential cells close to or throughout the brain. Symptoms of this ailment include headaches, seizures, and sensory changes. This research explores two main categories of brain tumors: benign and malignant. Benign spreads steadily, and malignant express growth makes it dangerous. Early identification of brain tumors is a crucial factor for the survival of patients. This research provides a state-of-the-art approach to the early identification of tumors within the brain. We implemented the SegResNet architecture, a widely adopted architecture for threedimensional segmentation, and trained it using the automatic multi-precision method. We incorporated the dice loss function and dice metric for evaluating the model. We got a dice score of 0.84. For the tumor core, we got a dice score of 0.84; for the whole tumor, 0.90; and for the enhanced tumor, we got a score of 0.79.
Hybrid Facial Expression Recognition (FER2013) Model for Real-Time Emotion Cl...BIJIAM Journal
Facial expression recognition is a vital research topic in most fields ranging from artificial intelligence and gaming to human–computer interaction (HCI) and psychology. This paper proposes a hybrid model for facial expression recognition, which comprises a deep convolutional neural network (DCNN) and a Haar Cascade deep learning architecture. The objective is to classify real-time and digital facial images into one of the seven facial emotion categories considered. The DCNN employed in this research has more convolutional layers, ReLU activation functions, and multiple kernels to enhance filtering depth and facial feature extraction. In addition, a Haar Cascade model was also mutually used to detect facial features in real-time images and video frames. Grayscale images from the Kaggle repository (FER-2013) and then exploited graphics processing unit (GPU) computation to expedite the training and validation process. Pre-processing and data augmentation techniques are applied to improve training efficiency and classification performance. The experimental results show a significantly improved classification performance compared to state-of-the-art (SoTA) experiments and research. Also, compared to other conventional models, this paper validates that the proposed architecture is superior in classification performance with an improvement of up to 6%, totaling up to 70% accuracy, and with less execution time of 2,098.8 s.
Role of Artificial Intelligence in Supply Chain ManagementBIJIAM Journal
The term “supply chain” refers to a network of facilities that includes a variety of companies. To minimise the entire cost of the supply chain, these entities must collaborate. This research focuses on the use of Artificial Intelligence techniques in supply chain management. It includes supply chain management examples like as
demand forecasting, supply forecasting, text analytics, pricing panning, and more to help companies improve their processes, lower costs and risk, and boost revenue. It gives us a quick rundown of all the key principles of economics and how to comprehend and use them effectively.
An Internet – of – Things Enabled Smart Fire Fighting SystemBIJIAM Journal
Fire accident is a mishap that could be either man made or natural. Fire accident occurs frequently and can be controlled but may at time result in severe loss of life and property. Many a times fire fighters struggle to sort out the exact source of fire as it is continuously flammable and it spreads all over the area. On this concern, we have designed an Internet – of – Things (IoT) based device which sorts out the exact source of fire through a software and
hardware devices and also the complete detail of an area can be visualized by fire fighters which are preinstalled in the software itself. Because of our system’s intelligence in decision making during fire fighting, the proposed system is claimed as ‘Smart Fire Fighting System’. The implementation of the smart fire fighting system can make
the fire fighters to analyze the current situation immediately and make the decision quicker in an effective manner. Because of this system, fire losses in a building can be greatly reduced and many lives can be rescued immediately and moreover fire spread can also be restricted.
Evaluate Sustainability of Using Autonomous Vehicles for the Last-mile Delive...BIJIAM Journal
This study aims to determine if autonomous vehicles (AV) for last-mile deliveries are sustainable from three perspectives: social, environmental, and economic. Because of the relevance of AV application for last-mile delivery, safety was only addressed for the sake of societal sustainability. According to this study, it is rather safe to deploy AVs for delivery since current society’s speed restriction and decent road conditions give the foundation for AVs to run safely for last-mile delivery in metropolitan areas. Furthermore, AV has a distinct advantage in the event of a pandemic. The biggest worry for environmental sustainability is the emission problem. In terms of a series of emissions, it is established that AV has a substantial benefit in terms of emission reduction. This is mostly due to the differences in driving behaviour between autonomous cars and human vehicles. Because of AV’s commercial character, this research used a quantitative approach to highlight the economic sustainability of AV. The
study demonstrates the economic benefit of AV for various carrying capacities.
Transforming African Education Systems through the Application of IOTBIJIAM Journal
The project sought to provide a paradigm for improving African education systems through the use of the IOT. The created IOT model for Africa will enable African countries, notably Namibia, to exchange educational content and resources with other African countries. The objective behind the IOT paradigm in Africa’s education sectors is to provide open access to knowledge and information. The study revealed that there are no recognised platforms in African education systems that are utilised by African governments to interact, communicate, and share educational material directly with African institutions. As a result, the current research developed a model for
transforming African education systems using the IOT in the Namibian context, which will serve as a centralised online platform for self-study, new skill acquisition, and self-improvement using materials provided by African institutions of higher learning. Everyone is welcome to use the platform, including students, instructors, and
members of the general public.
Deep Learning Analysis for Estimating Sleep Syndrome Detection Utilizing the ...BIJIAM Journal
Manual sleep stage scoring is frequently performed by sleep specialists by visually evaluating the patient’s neurophysiological signals acquired in sleep laboratories. This is a difficult, time-consuming, & laborious process. Because of the limits of human sleep stage scoring, there is a greater need for creating Automatic Sleep Stage Classification (ASSC) systems. Sleep stage categorization is the process of distinguishing the distinct stages of sleep & is an important step in assisting physicians in the diagnosis & treatment of associated sleep disorders. In this research, we offer a unique method & a practical strategy to predicting early onsets of sleep disorders, such as restless leg syndrome & insomnia, using the Twin Convolutional Model FTC2, based on an algorithm composed of two modules. To provide localised time-frequency information, 30 second long epochs of EEG recordings are subjected to a Fast Fourier Transform, & a deep convolutional LSTM neural network is trained for sleep stage categorization. Automating sleep stages detection from EEG data offers a great potential to tackling sleep irregularities on a
daily basis. Thereby, a novel approach for sleep stage classification is proposed which combines the best of signal
processing & statistics. In this study, we used the PhysioNet Sleep European Data Format (EDF) Database. The code
evaluation showed impressive results, reaching accuracy of 90.43, precision of 77.76, recall of 93,32, F1-score of 89.12 with the final mean false error loss 0.09. All the source code is availlable at https://github.com/timothy102/eeg.
Robotic Mushroom Harvesting by Employing Probabilistic Road Map and Inverse K...BIJIAM Journal
A collision-free path to a destination position in a random farm is determined using a probabilistic roadmap (PRM) that can manage static and dynamic obstacles. The position of ripening mushrooms is a result of picture processing. A mushroom harvesting robot is explored that uses inverse kinematics (IK) at the target
position to compute the state of a robotic hand for grasping a ripening mushroom and plucking it. The DenavitHartenberg approach was used to create a kinematic model of a two-finger dexterous hand with three degrees of freedom for mushroom picking. Unlike prior experiments in mushroom harvesting, mushrooms are not planted in a grid or design, but are randomly scattered. At any point throughout the harvesting process, no human interaction is necessary
Enhanced 3D Brain Tumor Segmentation Using Assorted Precision TrainingBIJIAM Journal
A brain tumor is a medical disorder faced by individuals of all demographics. Medically, it is described as the spread of nonessential cells close to or throughout the brain. Symptoms of this ailment include headaches, seizures, and sensory changes. This research explores two main categories of brain tumors: benign and malignant. Benign spreads steadily, and malignant express growth makes it dangerous. Early identification of brain tumors is a crucial factor for the survival of patients. This research provides a state-of-the-art approach to the early identification of tumors within the brain. We implemented the SegResNet architecture, a widely adopted architecture for threedimensional segmentation, and trained it using the automatic multi-precision method. We incorporated the dice loss function and dice metric for evaluating the model. We got a dice score of 0.84. For the tumor core, we got a dice score of 0.84; for the whole tumor, 0.90; and for the enhanced tumor, we got a score of 0.79.
Hybrid Facial Expression Recognition (FER2013) Model for Real-Time Emotion Cl...BIJIAM Journal
Facial expression recognition is a vital research topic in most fields ranging from artificial intelligence and gaming to human–computer interaction (HCI) and psychology. This paper proposes a hybrid model for facial expression recognition, which comprises a deep convolutional neural network (DCNN) and a Haar Cascade deep learning architecture. The objective is to classify real-time and digital facial images into one of the seven facial emotion categories considered. The DCNN employed in this research has more convolutional layers, ReLU activation functions, and multiple kernels to enhance filtering depth and facial feature extraction. In addition, a Haar Cascade model was also mutually used to detect facial features in real-time images and video frames. Grayscale images from the Kaggle repository (FER-2013) and then exploited graphics processing unit (GPU) computation to expedite the training and validation process. Pre-processing and data augmentation techniques are applied to improve training efficiency and classification performance. The experimental results show a significantly improved classification performance compared to state-of-the-art (SoTA) experiments and research. Also, compared to other conventional models, this paper validates that the proposed architecture is superior in classification performance with an improvement of up to 6%, totaling up to 70% accuracy, and with less execution time of 2,098.8 s.
Role of Artificial Intelligence in Supply Chain ManagementBIJIAM Journal
The term “supply chain” refers to a network of facilities that includes a variety of companies. To minimise the entire cost of the supply chain, these entities must collaborate. This research focuses on the use of Artificial Intelligence techniques in supply chain management. It includes supply chain management examples like as
demand forecasting, supply forecasting, text analytics, pricing panning, and more to help companies improve their processes, lower costs and risk, and boost revenue. It gives us a quick rundown of all the key principles of economics and how to comprehend and use them effectively.
An Internet – of – Things Enabled Smart Fire Fighting SystemBIJIAM Journal
Fire accident is a mishap that could be either man made or natural. Fire accident occurs frequently and can be controlled but may at time result in severe loss of life and property. Many a times fire fighters struggle to sort out the exact source of fire as it is continuously flammable and it spreads all over the area. On this concern, we have designed an Internet – of – Things (IoT) based device which sorts out the exact source of fire through a software and
hardware devices and also the complete detail of an area can be visualized by fire fighters which are preinstalled in the software itself. Because of our system’s intelligence in decision making during fire fighting, the proposed system is claimed as ‘Smart Fire Fighting System’. The implementation of the smart fire fighting system can make
the fire fighters to analyze the current situation immediately and make the decision quicker in an effective manner. Because of this system, fire losses in a building can be greatly reduced and many lives can be rescued immediately and moreover fire spread can also be restricted.
Evaluate Sustainability of Using Autonomous Vehicles for the Last-mile Delive...BIJIAM Journal
This study aims to determine if autonomous vehicles (AV) for last-mile deliveries are sustainable from three perspectives: social, environmental, and economic. Because of the relevance of AV application for last-mile delivery, safety was only addressed for the sake of societal sustainability. According to this study, it is rather safe to deploy AVs for delivery since current society’s speed restriction and decent road conditions give the foundation for AVs to run safely for last-mile delivery in metropolitan areas. Furthermore, AV has a distinct advantage in the event of a pandemic. The biggest worry for environmental sustainability is the emission problem. In terms of a series of emissions, it is established that AV has a substantial benefit in terms of emission reduction. This is mostly due to the differences in driving behaviour between autonomous cars and human vehicles. Because of AV’s commercial character, this research used a quantitative approach to highlight the economic sustainability of AV. The
study demonstrates the economic benefit of AV for various carrying capacities.
Transforming African Education Systems through the Application of IOTBIJIAM Journal
The project sought to provide a paradigm for improving African education systems through the use of the IOT. The created IOT model for Africa will enable African countries, notably Namibia, to exchange educational content and resources with other African countries. The objective behind the IOT paradigm in Africa’s education sectors is to provide open access to knowledge and information. The study revealed that there are no recognised platforms in African education systems that are utilised by African governments to interact, communicate, and share educational material directly with African institutions. As a result, the current research developed a model for
transforming African education systems using the IOT in the Namibian context, which will serve as a centralised online platform for self-study, new skill acquisition, and self-improvement using materials provided by African institutions of higher learning. Everyone is welcome to use the platform, including students, instructors, and
members of the general public.
Deep Learning Analysis for Estimating Sleep Syndrome Detection Utilizing the ...BIJIAM Journal
Manual sleep stage scoring is frequently performed by sleep specialists by visually evaluating the patient’s neurophysiological signals acquired in sleep laboratories. This is a difficult, time-consuming, & laborious process. Because of the limits of human sleep stage scoring, there is a greater need for creating Automatic Sleep Stage Classification (ASSC) systems. Sleep stage categorization is the process of distinguishing the distinct stages of sleep & is an important step in assisting physicians in the diagnosis & treatment of associated sleep disorders. In this research, we offer a unique method & a practical strategy to predicting early onsets of sleep disorders, such as restless leg syndrome & insomnia, using the Twin Convolutional Model FTC2, based on an algorithm composed of two modules. To provide localised time-frequency information, 30 second long epochs of EEG recordings are subjected to a Fast Fourier Transform, & a deep convolutional LSTM neural network is trained for sleep stage categorization. Automating sleep stages detection from EEG data offers a great potential to tackling sleep irregularities on a
daily basis. Thereby, a novel approach for sleep stage classification is proposed which combines the best of signal
processing & statistics. In this study, we used the PhysioNet Sleep European Data Format (EDF) Database. The code
evaluation showed impressive results, reaching accuracy of 90.43, precision of 77.76, recall of 93,32, F1-score of 89.12 with the final mean false error loss 0.09. All the source code is availlable at https://github.com/timothy102/eeg.
Robotic Mushroom Harvesting by Employing Probabilistic Road Map and Inverse K...BIJIAM Journal
A collision-free path to a destination position in a random farm is determined using a probabilistic roadmap (PRM) that can manage static and dynamic obstacles. The position of ripening mushrooms is a result of picture processing. A mushroom harvesting robot is explored that uses inverse kinematics (IK) at the target
position to compute the state of a robotic hand for grasping a ripening mushroom and plucking it. The DenavitHartenberg approach was used to create a kinematic model of a two-finger dexterous hand with three degrees of freedom for mushroom picking. Unlike prior experiments in mushroom harvesting, mushrooms are not planted in a grid or design, but are randomly scattered. At any point throughout the harvesting process, no human interaction is necessary
Robotic Mushroom Harvesting by Employing Probabilistic Road Map and Inverse K...
Automation Attendance Systems Approaches: A Practical Review
1. BOHR International Journal of Internet of Things, Artificial Intelligence and Machine Learning
2022, Vol. 1, No. 1, pp. 23–31
https://doi.org/10.54646/bijiam.005
www.bohrpub.com
Automation Attendance Systems Approaches: A Practical Review
Ata Jahangir Moshayedi1, Atanu Shuvam Roy1, Liefa liao1, Hong Lan1, Mehdi Gheisari2,4,∗,
Aaqif Afzaal Abbasi3 and Seyed Mojtaba Hosseini Bamakan5
1School of Information Engineering, Jiangxi University of Science And Technology, No 86, Hongqi Avenue,
Ganzhou City, Jiangxi Province, P.R. China 341000
2Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
3Department of Software Engineering, Foundation University Islamabad 44000, Pakistan
4Department of Computer Science and Technology, Islamic Azad University, Iran
5Department of Industrial Management, Yazd University, Yazd, 89195-741, Iran
∗Corresponding author: mehdi.gheisari61@gmail.com
Abstract. Accounting for people is the first step of every manpower-based organization in today’s world. Hence, it
takes up a signification amount of energy and value in the form of money from respective organizations for both
implementing a suitable system for manpower management as well as maintaining that same system. Although this
amount of expenditure for big organizations is near to nothing, rather just a formality, it does not hold as much truth
for small organizations such as schools, colleges, and even universities to a certain degree. This is the first point. The
second point for discussion is that much work has been done to solve this issue. Various technologies like Biometrics,
RFID, Bluetooth, GPS, QR Code, etc., have been used to tackle the issues of attendance collection. This study paves
the path for researchers by reviewing practical methods and technologies used for existing attendance systems.
Keywords: Biometric, attendance systems, QR Code, RFID, Face Recognition, Software System.
INTRODUCTION
Student attendance collection and management is one of
the most time-consuming works in any school, university,
and education system. In fact, gathering attendance is a
time- consuming job that takes lecture time and takes
the teacher’s energy. But if the teacher does not do so,
the school and family will not know if the students are
pursuing the light of education. This issue has been tried to
solve with the help of various approaches by using various
technologies available to date. The previous record on the
research paper and product shows the Biometrics, includ-
ing palm, iris, facial recognition, RFID, NFC, Bluetooth,
barcode, and QR, which are more demanding to make
the system as automated as possible. In the next section,
various types of these technologies used are described.
This paper divides them into five subsections – Biometric
Attendance System, Facial Recognition Based Attendance
System, RFID Based Attendance System, QR Code based
Attendance System and finally Embedded System based
Attendance System. Following this review of existing
attendance systems, the paper concludes with a summary
of the types and a short excerpt about the importance of
attendance management systems and integrating existing
technologies to solve modern problems.
ATTENDANCE SYSTEMS VARIETY
Biometric Attendance System
The word Biometric comes from the word biometry, which
means the process by which a person’s unique biological
or physical traits are accounted for identification. The most
common Biometrics used today are palmprint, fingerprint,
face, and iris. And the biometric attendance system uses
one or more of these traits in conjunction to confirm the
identity of the personnel attending lectures. A few existing
research works are surveyed to showcase existing work in
the sector. In their review paper, Tsai-Cheng Li et al. [1]
studied biometrics technology applied in the attendance
23
2. 24 Ata Jahangir Moshayedi et al.
Figure 1. System Design of O. Shoewu et al. [2].
management system. Their aim was based on some per-
tinent literature reviews through which they concluded
that attendance management is an important measure and
means for discipline as it dictates the productivity of an
organization and its sustainability. Biometric data is a mea-
surable biological trait that is unique to every person on the
planet and can be automatically verified to confirm a per-
son’s identity. Most of the studies have shown that either
hand geometry or fingerprint recognition is a very suitable
means for the attendance management system.Even on the
topic of improving efficiency and service quality, most of
the respondents gave a reply of “agree” or “no comment”.
The paper also states that the biometric recognition system
has the least controversies as it is exceedingly difficult to
crack, and employees and respondents feel safe and fair
that it should be the way to manage public attendance. In
their paper, O. Shoewu et al. [2] have talked about develop-
ing a biometric- based attendance management system and
compared it with a traditional manual attendance system
(Figure 1).
According to Figure 1, their system uses two steps to
both enrol and authenticate the users. First, all biometric
data is scanned securely through biometric devices; then,
their software executes a program for feature extraction
from the scanned data and stores it with the biometric
owner ID. Although the authentication only performs the
same steps once, it matches the data stored in the SQL
database. The system also produces an attendance sum-
mary report and flags mismatch attempts. The researchers
concluded that the system was particularly useful because
of its short implementation time and high success rate. On
the other side, one of the most secure forms of biometric
recognition is iris recognition. In fact, it is more secure than
traditional fingerprint recognition or palm recognition.
Seifedine Kadry et al. [3], in their paper, have described
a wireless attendance management system based on this
very technology (Figure 2).
Figure 2(A) shows the Iris Scan procedure of the system.
And Figure 2(B) shows how the iris recognition module
connects to the workstation and completes the system.
The system follows three basic modules: image acquisi-
tion and preprocessing texture extraction and signature
encoding, and iris signature matching for authentication.
The researchers have established a cheaper way to commit
the task by taking in offline iris recognition and pairing
it with a management computer via a PTR2000+ wireless
communication module [22–30]. Their test resulted with a
98.3% success rate. Hence, they concluded that implement-
ing such a technique with iris recognition can prove ease of
access in attendance management systems.
Facial Recognition Based Attendance System
Facial Recognition is a part of Biometrics but again, not
quite so. Because facial recognition can be fooled, whereas
Biometrics defines uniqueness, meaning that identifying
traits must be unique. Facial recognition is common in
every face because no face is the same in most cases. And it
is easy to implement because any camera with appropriate
software can do the task. In their research, Naveed Khan
Balcoh et al. [4] introduce face detection as an accurate and
efficient replacement for the old school manual attendance
system (Figure 3). Their system from Figure 3 used the
EigenFace method to verify faces one by one and match
them with their face database and commit the attendance
task. Their face database was populated with face data
through a series of image processing techniques, including
Figure 2. (A): Iris Scan Procedure of the system [3]. (B): System Design of Kadry et al. [3].
3. Automation Attendance Systems Approaches 25
Figure 3. System Design of Balcoh et al. [4].
Figure 4. System Design of Mehta et al. [5].
image histogram normalization, noise gratification, skin
classification, and finally, face detection by selecting the
region of interest.
The same process goes for attendance by face recog-
nition. In their research, Preeti Mahita et al. [5] show a
facial recognition-based attendance management system
on the raspberry pi 2 with the included raspberry pi camera
(Figure 4).
They used the voila-jones algorithm and local binary
pattern in conjunction to identify the faces of the people in
a photo. The faces will be stored in the database again the
personal identification, which will then be used to identify
the personnel present. They conclude a 92% accuracy with
their system. This accuracy is unacceptable when it comes
to class attendance as they are very much vital. Priya Pasur-
mati et al. [6] shows a much more advanced version of
the facial recognition-based attendance management sys-
tem. Their research uses an open-source facial recognition
framework called OpenCV and uses python as their main
environment of work (Figure 5).
Figure 5. System design of Pasurmarti et al. [6].
In the above Figure, their system design shows the
components used. They used a physical webcam to accom-
plish the task. But the paper concludes with no real-world
application proof of the system but only the results of an
efficient facial recognition system using python.
RFID/NFC Attendance System
RFID is an abbreviation for “radio-frequency identifica-
tion”, which basically means that the communication is
done through radio frequencies. In this system, informa-
tion is digitally stored inside a tag or card, which can be
read through radio frequencies. Near Field Communica-
tion(NFC) is an RFID-based technology that can act as a
tag and reader. This technology is cheap to manufacture
now and hence can be readily used in the work sector.
Here a handful of research works on RFID based atten-
dance systems have been surveyed, some of which work in
conjunction with other technologies like Bluetooth. In their
paper, Vishal Bhalla et al. [7] described a system based on
Bluetooth technology and RFID reader application. Their
proposed system is very novel because they have used
RFID matrix cards to gather students’ attendance and then
used Bluetooth for the teacher or professor to confirm the
attendance before the data gets permanently sent to the
main database (Figure 6).
As explained in the system design in Figure 6, once the
data is sent to the central database, it can be edited later,
and reports can be generated via emails. By approach-
ing this double layer model, the error in their system
is extremely low, and almost only human error remains.
Their system significantly reduces time consumption in
the whole system too. In their paper, the researchers also
mention that this project model can be further secured by
introducing a fingerprint when authenticating the use of
a terminal. They have used Bluetooth rather than Wi-Fi
4. 26 Ata Jahangir Moshayedi et al.
Figure 6. System Design of Bhallah et al. [7].
Figure 7. System Design of Arulogun et al. [8].
and other long-range solutions because of range, power
consumption, and ease of availability as they are using the
Bluetooth devices embedded in cell phones of the teachers
taking the attendance where the teachers will use their very
cell phones to confirm the RFID attendances. Arulogun
O. T. et al. [8], in their paper, presents an intelligent RFID
based students’ attendance control and management sys-
tem. Their simple system is illustrated in Figure 7.
In their project, they used passive tags due to the cost
and implementation flexibility. Upon bringing those tags
close to the designated reader, the reader captures
the card’s data and sends it to the system, recording the
time of arrival and departure. Their software for handling
the data is made with Visual C# with Visual Basic GUI
incorporated with Microsoft’s SQL server to store the data.
The researchers conclude that incorporating a facial recog-
nition application would further enhance security.
Nikhil P. Shegokar et al. [9], in their study, compare exist-
ing technologies in the scope of automated attendance
system based on raspberry pi and prefers NFC to be
the better path. They compared the various biometrics
technologies, facial recognition, iris recognition, and NFC.
Their paper does not quite show any active system to be
implemented, though.
QR Code Attendance System
The word QR stands for Quick Response in the term QR
Code. It belongs to the two-dimensional code family whose
predecessor is actually barcodes. But barcodes have many
limitations hence QR codes have superseded them. One of
the main reasons why QR code is better is that QR code
can store huge amount of information in any orientation
with much more damage tolerance than all other 2D code
technology out there. At the same time, it is industrially
cheap to implement. To make the reasons for why QR code
is much more efficient a bit clearer, a small survey on the
existing applications of the QR code technology proves
useful.
Tin Jin Soon [10] surveyed and explained the fundamen-
tals of QR code in his journal and also showed various
widespread implementation of the QR code technology. He
reviewed the technologies used in the fields of industry
and transport, from the identification of different prod-
ucts to banknotes. Online and local ordering system, food
freshness control system, bet ticket management system,
patient management system, livestock tracking, jewelry
certification system, agriculture, telecommunications, pay-
ments and other fields – all use QR codes widely. And for
the merits of using QR codes in all these sectors are the
same i.e. efficiency and profitability. Masahiro Hara [11] in
his research shows a similar picture as Tin Jin Soon with
a more historic approach. He in his paper have stated that
before QR code was there, barcode was widely used. But
it came with some limitations like reading directions and
information capacity. So QR code or quick response code
was developed which removed these limitations; and even
allowed alphanumeric characters in different languages
to be encoded and represented through it. Compared to
previous generation of 2D codes like barcodes, QR codes
have error correction capability up to 30% whereas the
other technology has zero. A QR code which is five times a
barcode can be read in around 30 ms with a bare minimum
RISC processor (MIPS: 18) in any orientation. And because
of its versatility, high speed reading, miniaturization capa-
bility, it is widely used in industrial sectors. Two layered
QR codes are used in order to expand security avoiding
copying confidential QR codes.For these above reasons
and the added facility of cheap implementation QR code
technology was chosen for this project.
Here some existing works related to QR code-based
attendance system are surveyed below.
Hsin-Chih Lai et al. [12] in their research shows a broad
implementation of the QR code technology. They show the
implementation of mobile learning in outdoor education
through the implication of QR codes. In their study they
developed an outdoor education information system that
combines natural and cultural environment GMs or Green
Maps using QR codes. The implementation had QR codes
printed on a GM and then students on site for explo-
ration of the outdoor environment were asked to scan the
QR codes to find relevant information from the internet.
The idea being that having static QR codes on GMs can
easily be scanned by a cell phone to retrieve information
about the place and the place’s elements. A rough sketch
5. Automation Attendance Systems Approaches 27
Figure 8. Implementation of QR Codes on GMs [12].
Figure 9. System Design of Hendry et al. [13].
about their implementation of QR codes on Green Maps is
Figure 8.
MRM Hendry et al. [13] in their paper have proposed
a smart attendance system by applying QR code. Their
system was built with PhP, MySQL and Apache based on
WAMP Server. The application would prompt registration
for first time and then can be logged in to take atten-
dance by generating qr codes. The codes can be scanned
with a mobile device and hence attendance can be taken
and then reports are generated via checklists and can be
printed. Their system provides very minimal functionality
yet gives one of the first ideas about implementing QR
codes in attendance management system which is shown
in Figure 9.
An enhanced version of MRM Hendry et al. [13]’s
research is the research by the next group of researchers.
Xiong Wei et al. [14] in their research paper made a system
Figure 10. System Sequence of Wei et al. [14].
Figure 11. System Design of Fauzi et al. [15].
for smart attendance system with QR codes with function-
alities such as student details, subject details, and report
export as csv. They have used SQLite Database as their
primary data storage technology. And their whole system
is based on android application. Both the teacher and
student interact with the system through app. This system
is very suitable for small classrooms but not good for big
ones because of this very reason. The researchers conclude
that integration with facial recognition would prove the
system more secure. Their system’s idea of sequence is as
Figure 10.
Ahmad Fahmi Mohd Fauzi et al. [15] showcased a quite
different kind of system which functions both as a web
based smart door lock system as well as attendance man-
agement system although the main focus is on the smart
door itself. In fact, their system is one of the few projects
out there which uses both a facial recognition system and
a QR code system in conjunction. Their proposed system
has the raspberry pi working with a camera that scans the
static QR code on the student or staff’s ID card and matches
it with the QR code stored on the database. The researchers
conclude that the efficiency of this method needs to be fur-
ther evaluated in the future as this is a preliminary work.
Their research’s system design is portrayed in Figure 11.
Their proposed system according to Figure 11 has the
raspberry pi working with a camera that scans the static
QR code on the student or staff’s ID card and matches it
with the QR code stored on the database. The researchers
conclude that the efficiency of this method needs to be
further evaluated in the future as this is a preliminary
work.
6. 28 Ata Jahangir Moshayedi et al.
Figure 12. System Architecture of Shailendra et al. [16].
Figure 13. Overall design of Asabere et al. [21].
Embedded Systems-based Attendance Systems
A combination of hardware and software designed and
deployed for a specific function is called an embed system.
Such a system is also able to run inside larger systems. Usu-
ally, this system has a finite set of functions. And in terms of
attendance management systems or attendance methods
using technology, embedded systems along with various
sensors are used. A design and framework for taking
attendance in schools and colleges using AVR ATMEGA16
of ATMEL a low power CMOS 8-bit microcontroller as the
handheld client and the Raspberry Pi as the server was
presented by Shailendra et al. [16]. The system architec-
ture uses the raspberry pi as the main server while the
ATMEGA powered handheld device with Xbee in every
class like a zonal model [17] (Figure 12).
The above system design in Figure 12 shows an example
of single board computer-based attendance system where
the raspberry pi connected by the ATMEGA powered
handheld device – both are the backbones of the two-part
system. Swarnendu Ghosh et al. [18] in their paper used
biometric sensor with Arduino uno. This is an example
of technologies being used in conjunction. The Arduino
attendance module consisted of the Arduino UNO, fin-
gerprint sensor, Bluetooth sensor and an LCD was named
SAS module or Smart Attendance System Module. An
android application was also made and could connect to
Figure 14. Various technologies used for attendance management
system.
the module using Bluetooth for management. This kind
of combination and application through the connection
of Arduino with application using Bluetooth or another
medium is novel and very practical. Other applications
such as virtual reality and exergames [19] uses this kind
of communication. Arduino and RFID is also used in
combination in many projects such as Arbain et al. [20]’s
(2014) LAS which is a web-based laboratory attendance
system. They used RFID tags inside ID cards as medium
of attendance for staffs controlled by Arduino which can
connect to the system using USB connection. Asabere
et al. [21] (2020) in their paper constructed an attendance
system with a fingerprint module and Arduino Wemos D1
ESP8266 (Figure 13).
From their overall system design in Figure 14, three tech-
nologies – namely, biometric, microcontroller and Wi-Fi
is used in conjunction. The figure also shows an exam-
ple of microcontroller-based attendance system where the
Arduino board is the main backbone of the system. The fol-
lowing Table 1 compares the different types of attendance
systems based on the advantages and disadvantages of the
technologies used in them.
According to Table 1, biometric attendance, RFID, Facial
Recognition, QR code – all three require devices, and main-
tenance. All the available techs require server software and
DBMS as a common requirement to operate. Embedded
system & QR code-based attendance system is the cheapest
and easiest to deploy due to its size. QR code systems are
the one that’s sub-automatic as it requires clients to scan
the QR code themselves.
7. Automation Attendance Systems Approaches 29
Table 1. Advantages & disadvantages of existing attendance management system technologies.
No. Method Hardware Software Advantage Disadvantage
1 Biometric Attendance Fingerprint Reader, Retina Scan
Machine
Custom Software, Server
Software, DBMS
Automatic Cost of Machine
& Maintenance
2 RFID RFID Reader,
RFID Tags
Custom Software, DBMS Automatic
4 Facial Recognition Infrared Camera, Server Facial Recognition
software, Server Software,
DBMS
Automatic
4 QR Code Camera, QR or Barcode Scanner,
Server
DBMS, Server Software Sub- Automatic,
Cheap
5 Embedded Systems Microcontroller (Arduino
/ATMEGA), Single Board
Computer (SBC) e.g., Raspberry
Pi + Other Detection Technology
Server Software, DBMS Automatic, Easily
Deployable
Needs Expert to
Operate
CONCLUSION
Finally, based on the survey and discussion above, the
attendance management system uses four different tech-
niques, at least one subclass of this technique, such as
fingerprint reading under biometrics or NFC under RFID.
These are shown in detail in the illustration 13.
As shown in the Figure 14, Attendance Management
Systems can be classified into four basic types based on
the technologies used. The first type – Biometrics can be
divided into two types: Fingerprint and Iris. The second
type – RFID can be divided into two types as well: NFC
and RFID Tag. The third type – Facial recognition can
utilize two methods. They are Normal camera which are
cameras we used typically to take photos and the second
is IR based cameras. Example for IR based cameras can be
Night-vision cameras, CCTV Cameras etc. These are more
accurate than normal cameras. The last and final category
is QR. Usually QR is application based. On that basis of
methodology, it can be divided into two more categories:
Web-Based and App-Based. Each of these technologies can
be used in combination with another to make the system
more secure. The last type – Embedded Systems can be an
example of this statement. The main division of this type
is microcontroller based and single board computer (SBC)
based. In conclusion, there are different ways a problem
can be solved. And for attendance management system
the most feasible design seems to be when cloud technolo-
gies [31–39] and service robots, deep learning etc. [40–53]
are used in conjunction. Attendance management systems
are not just required for schools, colleges, or educational
institutions. They are vastly used for any place where labor
is main workforce. Software companies, movie studios,
industries etc. require a lot of manpower to function. And
there may be classified work going on even. Keeping track
of them is vital for the development of the said organi-
zation. In this paper, we list the various prominent types
of technologies to do exactly that as the world grows and
more and more people go towards work better solutions
are needed integrating the most prominent technologies.
CONFLICT OF INTEREST
The authors declare that this article does not contain any
conflict of interest.
AUTHOR CONTRIBUTIONS
Conceptualization: Ata Jahangir Moshayedi, Atanu
Shuvam Roy, Liefa liao, Mehdi Gheisari
Methodology: Mehdi Gheisari, AAqif Afzal Abbasi,
Investigation: Ata Jahangir Moshayedi, Atanu Shuvam
Roy, Liefa liao, Hong Lan, Mehdi Gheisari, AAqif Afzal
Abbasi, SM Hosseini Bamakan
Resources: Hong Lan, Mehdi Gheisari, AAqif Afzal
Abbasi,
Writing-original draft preparation: Ata Jahangir
Moshayedi, Atanu Shuvam Roy, Hong Lan
Writing-review and editing: Ata Jahangir Moshayedi,
Atanu Shuvam Roy, Mehdi Gheisari
All authors have read and agreed to the published version
of the manuscript.
FUNDING
This work is supported by Islamic Azad University and
Amir Kabir University of Science and Technology Iran.
ACKNOWLEDGMENTS
Special thanks to Islamic Azad University and AmirKabir
University. Moreover, we are also thankful to Shenzhen
BKD for its support.
REFERENCES
[1] Li, Tsai-Cheng, Huan-Wen Wu, and Tiz-Shiang Wu. “The study of
biometrics technology applied in attendance management system.”
2012 Third International Conference on Digital Manufacturing &
Automation. IEEE, 2012.
8. 30 Ata Jahangir Moshayedi et al.
[2] Shoewu, O., and O. A. Idowu. “Development of attendance manage-
ment system using biometrics.” The Pacific Journal of Science and
Technology 13.1 (2012): 300–307.
[3] Kadry, Seifedine, and Mohamad Smaili. “Wireless attendance man-
agement system based on iris recognition.” Scientific Research and
essays 5.12 (2013): 1428–1435.
[4] Balcoh, Naveed Khan, M. Haroon Yousaf, Waqar Ahmad, and
M. Iram Baig. “Algorithm for efficient attendance management: Face
recognition based approach.” International Journal of Computer
Science Issues (IJCSI) 9, no. 4 (2012): 146.
[5] Mehta, Preeti, and Pankaj Tomar. “An efficient attendance manage-
ment sytem based on face recognition using Matlab and Raspberry
Pi 2.” International Journal of Engineering Technology Science and
Research IJETSR 3.5 (2016): 71–78.
[6] Pasumarti, Priya, and P. Purna Sekhar. “Classroom attendance
using face detection and Raspberry-Pi.” International Research
Journal of Engineering and Technology (IRJET) 5.03 (2018):
167–171.
[7] Bhalla, Vishal, Tapodhan Singla, Ankit Gahlot, and Vijay Gupta.
“Bluetooth based attendance management system.” International
Journal of Innovations in Engineering and Technology (IJIET) 3, no. 1
(2013): 227–233.
[8] Arulogun, Oladiran Tayo, Adeboye Olatunbosun, O. A. Fakolujo,
and Olayemi Mikail Olaniyi. “RFID-based students attendance man-
agement system.” (2013).
[9] Shegokar, Nikhil P., S. Kaustubh, and Manekar Amitkumar.
“Review automated students attendance Management System using
Raspberry-Pi and NFC.” Technology (IJRCIT) 1.1 (2015).
[10] Soon, Tan Jin. “QR code.” Synthesis Journal 2008 (2008): 59–78.
[11] HARA, Masahiro. “Development and popularization of QR code.”
Synthesiology English edition 12.1 (2019): 19–28.
[12] Lai, Hsin-Chih, Chun-Yen Chang, Li Wen-Shiane, Yu-Lin Fan, and
Ying-Tien Wu. “The implementation of mobile learning in outdoor
education: Application of QR codes.” British Journal of Educational
Technology 44, no. 2 (2013): E57–E62.
[13] Hendry, Md Rizal Md, Mohd Noah A. Rahman, and Afzaal H.
Seyal. “Smart attendance system applying QR code.” 12th Interna-
tional Conference on Latest Trends in Engineering and Technology
(ICLTET’2017) May. 2017.
[14] Wei, Xiong, Anupam Manori, Nandgopal Devnath, Nitin Pasi, and
Vivek Kumar. “QR Code Based Smart Attendance System.” Interna-
tional Journal of Smart Business and Technology 5, no. 1 (2017): 1–10.
[15] Fauzi, Ahmad Fahmi Mohd, Nur Nabila Mohamed, Habibah
Hashim, and Mohammed A. Saleh. “Development of web-based
smart security door using qr code system.” In 2020 IEEE Interna-
tional Conference on Automatic Control and Intelligent Systems
(I2CACIS), pp. 13–17. IEEE, 2020.
[16] Shailendra, M. Singh, M. A. Khan, V. Singh, A. Patil and S. Wadar,
“Attendance management system,” 2015 2nd International Confer-
ence on Electronics and Communication Systems (ICECS), 2015,
pp. 418–422, doi: 10.1109/ECS.2015.7124938.
[17] Moshayedi, Ata Jahangir, Atanu Shuvam Roy, Liefa Liao, and Shuai
Li. “Raspberry Pi SCADA Zonal based System for Agricultural Plant
Monitoring.” In 2019 6th International Conference on Information
Science and Control Engineering (ICISCE), pp. 427–433. IEEE, 2019.
[18] S. Ghosh, S. K. Mohammed, N. Mogal, P. K. Nayak and B. Champaty,
“Smart Attendance System,” 2018 International Conference on Smart
City and Emerging Technology (ICSCET), 2018, pp. 1–5, doi: 10.110
9/ICSCET.2018.8537298.
[19] A. J. Moshayedi, S. K. Sambo and A. Kolahdooz, “Design And Devel-
opment of Cost-Effective Exergames For Activity Incrementation,”
2022 2nd International Conference on Consumer Electronics and
Computer Engineering (ICCECE), 2022, pp. 133–137, doi: 10.1109/
ICCECE54139.2022.9712844.
[20] N. Arbain, N. F. Nordin, N. M. Isa and S. Saaidin, “LAS: Web-based
laboratory attendance system by integrating RFID-ARDUINO tech-
nology,” 2014 2nd International Conference on Electrical, Electronics
and System Engineering (ICEESE), 2014, pp. 89–94, doi: 10.1109/IC
EESE.2014.7154601.
[21] Asabere, Prince, Francois Sekyere, and Willie K. Ofosu. “Wireless
biometric fingerprint attendance system using Arduino and MySQL
database.” International Journal of Computer Science, Engineering
and Applications (IJCSEA) Vol. 9 (2020).
[22] Gheisari, Mehdi, Guojun Wang, Md Zakirul Alam Bhuiyan, and
Wei Zhang. “Mapp: A modular arithmetic algorithm for privacy
preserving in iot.” In 2017 IEEE International Symposium on Parallel
and Distributed Processing with Applications and 2017 IEEE Interna-
tional Conference on Ubiquitous Computing and Communications
(ISPA/IUCC), pp. 897–903. IEEE, 2017.
[23] Ashourian, Mohsen, Mehdi Gheisari, and Ali Hashemi. “An
Improved Node Scheduling Scheme for Resilient Packet Ring Net-
work.” Majlesi Journal of Electrical Engineering 9.2 (2015): 43.
[24] Sharifzadeh, Manaf, Kaveh Bashash, Shahram Bashokian, and mehdi
gheisari. “A Comparison with two semantic sensor data storages in
total data transmission.” arXiv preprint arXiv:1401.7499 (2014)
[25] Porkar, P., Mojtaba Fazli, and M. Gheisari. “Sensor networks chal-
lenges.” 11th international conference on data networks, DNCOCO
‘12. 2012.
[26] Khajehyousefi, Mehdi, “A Comparison with Three Proposed Sensors
Data’s Storages.” International Conference on Advanced Computer
Theory and Engineering, 4th (ICACTE 2011). ASME Press, 2011.
[27] Gheisari, M., Esnaashari, M. (2017). A survey to face recognition
algorithms: advantageous and disadvantageous. Journal Modern
Technology & Engineering, V. 2(1), pp. 57–65.
[28] Alzubi J.A., Yaghoubi A., Gheisari M., Qin Y. (2018) Improve
Heteroscedastic Discriminant Analysis by Using CBP Algorithm.
In: Vaidya J., Li J. (eds) Algorithms and Architectures for Paral-
lel Processing. ICA3PP 2018. Lecture Notes in Computer Science,
vol. 11335. Springer, Cham
[29] Noor, F, Sajid, A, Shah, SBH, Zaman, M, Gheisari, M, Mariappan, V.
Bayesian estimation and prediction for Burr-Rayleigh mixture model
using censored data. Int J Commun Syst. 2019;e4094. https://doi.or
g/10.1002/dac.4094
[30] Gheisari, Mehdi, Aaqif Afzaal Abbasi, Zahra Sayari, Qasim Rizvi,
Alia Asheralieva, Sabitha Banu, Feras M. Awaysheh, Syed Bilal
Hussain Shah, and Khuhawar Arif Raza. “A survey on cluster-
ing algorithms in wireless sensor networks: Challenges, research,
and trends.” In 2020 International Computer Symposium (ICS),
pp. 294–299. IEEE, 2020.
[31] Shao, Yongfu, Jue Wu, Hongping Ou, Min Pei, Li Liu, Ali Akbar
Movassagh, Ashutosh Sharma, Gaurav Dhiman, Mehdi Gheis-
ari, and Alia Asheralieva. “Optimization of ultrasound informa-
tion imaging algorithm in cardiovascular disease based on image
enhancement.” Mathematical Problems in Engineering 2021 (2021).
[32] Mangla, Monika, Sanjivani Deokar, Rakhi Akhare, and Mehdi Gheis-
ari. “A Proposed Framework for Autonomic Resource Management
in Cloud Computing Environment.” In Autonomic Computing in
Cloud Resource Management in Industry 4.0, pp. 177–193. Springer,
Cham, 2021.
[33] Li, Lintao, Parv Sharma, Mehdi Gheisari, and Amit Sharma.
“Research on TCP Performance Model and Transport Agent Archi-
tecture in Broadband Wireless Network.” Scalable Computing: Prac-
tice and Experience 22, no. 2 (2021): 193–201.
[34] K. A. Raza, A. Asheralieva, M. M. Karim, K. Sharif, M. Gheisari and
S. Khan, “A Novel Forwarding and Caching Scheme for Information-
Centric Software-Defined Networks,” 2021 International Sympo-
sium on Networks, Computers and Communications (ISNCC), 2021,
pp. 1–8, doi: 10.1109/ISNCC52172.2021.9615667.
9. Automation Attendance Systems Approaches 31
[35] Gheisari, Mehdi, Zohreh Safari, Mohammad Almasi, Abel Sridharan,
Ragesh GK, Yang Liu, and Aaqif Afzaal Abbasi. “A novel enhanced
algorithm for efficient human tracking.” Int J Inf & Commun Technol
11, no. 1 (2022): 1–7.
[36] Abdullah Ajmal, Hamza Aldabbas, Rashid Amin, Sundas Ibrar,
Bader Alouffi, Mehdi Gheisari, “Stress-Relieving Video Game and
Its Effects: A POMS Case Study”, Computational Intelligence and
Neuroscience, vol. 2022, Article ID 4239536, 11 pages, 2022. https:
//doi.org/10.1155/2022/4239536
[37] Alzubi, Jafar A., AliAkbar Movassagh, Mehdi Gheisari, Hamid
Esmaeili Najafabadi, Aaqif Afzaal Abbasi, Yang Liu, Zhou Ping-
mei, Mahdieh Izadpanahkakhk, and AmirHossein Pourishaban
Najafabadi. “A Dynamic SDN-based Privacy-Preserving Approach
for Smart City Using Trust Technique.” In 2022 9th Iranian Joint
Congress on Fuzzy and Intelligent Systems (CFIS), pp. 1–5. IEEE,
2022.
[38] Yongsheng Rao, Saeed Kosari, Mehdi Gheisari, “New Results in
Vague Incidence Graphs with Application”, Journal of Function
Spaces, vol. 2022, Article ID 3475536, 7 pages, 2022. https://doi.
org/10.1155/2022/3475536
[39] GhadakSaz, Ehsan, et al. “Design, Implement and Compare two
proposed sensor data’s storages Named SemHD and SSW.” From
Editor in Chief (2012): 78.
[40] Ata Jahangir Moshayedi, Atanu Shuvam Roy, and Liefa Liao, “PID
Tuning Method on AGV (Automated Guided Vehicle) Industrial
Robot,” vol. 12, no. 4, pp. 53–66, 2020.
[41] Ata jahangir Moshayedi and D. C. Gharpure, “Path and Position
Monitoring Tool for Indoor Robot Application,” Int. J. Appl. Electron.
Phys. Robot., vol. 1, no. 1, pp. 10–13, Jul. 2013, doi: 10.7575/aiac.ija
epr.v.1n.1p.10.
[42] Ata jahangir Moshayedi and D. Gharpure, “Implementing Breath
to Improve Response of Gas Sensors for Leak Detection in Plume
Tracker Robots,” in Proceedings of the Third International Confer-
ence on Soft Computing for Problem Solving, 2014, pp. 337–348.
[43] A. abbasi Ata Jahangir Moshayedi Liefa Liao, Shuai Li, “Path plan-
ning and trajectroy tracking of a mobile robot using bio-inspired
optimization algorithms and PID control,” in 2019 IEEE Interna-
tional Conference on Computational Intelligence and Virtual Envi-
ronments for Measurement Systems and Applications (CIVEMSA),
2019, vol. 2, no. 2, p. 60.
[44] Ata Jahangir Moshayedi and D. C. Gharpure, “Development of Posi-
tion Monitoring system for studying performance of wind tracking
algorithms,” in Robotics; Proceedings of ROBOTIK 2012; 7th German
Conference on, 2012, pp. 1–4.
[45] A. J. Moshayedi, J. Li, and L. Liao, “Simulation study and PID
Tune of Automated Guided Vehicles (AGV),” in 2021 IEEE Interna-
tional Conference on Computational Intelligence and Virtual Envi-
ronments for Measurement Systems and Applications (CIVEMSA),
2021, pp. 1–7.
[46] A. Jahangir Moshayedi, G. Xu, L. Liao, and A. Kolahdooz, “Gentle
Survey on MIR Industrial Service Robots: Review & Design,” J. Mod.
Process. Manuf. Prod., vol. 10, no. 1, pp. 31–50, 2021.
[47] Abbasi, A., Mahmoud, Zadeh, S., Yazdani, A. et al. Feasibility assess-
ment of Kian-I mobile robot for autonomous navigation. Neural
Comput & Applic 34, 1199–1218 (2022). https://doi.org/10.1007/
s00521-021-06428-2
[48] Ata jahangir Moshayedi, M. Gheibollahi, and L. Liao, “The quadro-
tor dynamic modeling and study of meta-heuristic algorithms per-
formance on optimization of PID controller index to control angles
and tracking the route,” IAES Int. J. Robot. Autom., vol. 9, no. 4,
p. 256, 2020, doi: 10.11591/ijra.v9i4.pp256-270.
[49] Ata jahangir Moshayedi, E. Kazemi, M. Tabatabaei, and L. Liao,
“Brief modeling equation for metal-oxide; tgs type gas sensors,”
Filomat, vol. 34, no. 15, pp. 4997–5008, 2020, doi: 10.2298/FIL201
5997M.
[50] Zhang, X., Song, Z., Moshayedi, A.J. et al. Security scheduling
and transaction mechanism of virtual power plants based on dual
blockchains. J Cloud Comp 11, 4 (2022). https://doi.org/10.1186/s1
3677-021-00273-3
[51] Moshayedi, Ata Jahangir, Atanu Shuvam Roy, Amin Kolahdooz,
and Yang Shuxin. 2022. “Deep Learning Application Pros And Cons
Over Algorithm”. EAI Endorsed Transactions on AI and Robotics 1
(February):1–13. https://doi.org/10.4108/airo.v1i.19.
[52] Moshayedi, Ata Jahangir, Atanu Shuvam Roy, Sithembiso Khaya
Sambo, Yangwan Zhong, and Liefa Liao. 2022. “Review On: The
Service Robot Mathematical Model”. EAI Endorsed Transactions on
AI and Robotics 1 (February):1–19. https://doi.org/10.4108/airo.v
1i.20.
[53] A. J. Moshayedi, M. S. Hosseini, and F. Rezaee, “WiFi Based Mas-
sager Device with NodeMCU Through Arduino Interpreter,” J.
Simul. Anal. Nov. Technol. Mech. Eng., vol. 11, no. 1, pp. 73–79,
2019.