Botany krishna series 2nd semester Only Mcq type questions
Collective awareness for human ict collaboration in smart cities
1. Collective awareness for Human-ICT
collaboration in Smart Cities
Nicola Bicocchi, Alket Cecaj, Damiano Fontana, Marco Mamei,
Andrea Sassi,and Franco Zambonelli
University of Studies of Modena and Reggio Emilia, Italy
WETICE 2013
2. The future of cities and urban environment.
A very dense digital ecosystem
of interconnected individuals:
sensors, actuators and citizens.
A socio-technical ecosystem
3. SAC Capabilities of humans and ICT devices.
Complementary
sensing,computing
and actuating
capabilities.
Cooperation in a
Goal directed way
ICT Humans
Sensing
Sensor and camera
networks, RFID tags,
smart phone sensors
5 human senses, fact
posted on social
networks
Computing
Data analysis, data
aggregation, basic
situation recognition
Pattern analysis,
advanced situation
recognition, emotion
recognition
Actuating
Traffic lights, public
displays, personal
displays, actuating
devices on
infrastructures
Human Body
4. • An urban Superorganism
• Loop of the SAC capabilities
for coherent collective behavior based on collective sensing and
collective awareness
6. • Case study: Intelligent Transportation System.
• Collective sensing
• Humans sharing
• traffic-related events
• ICT devices monitoring
• traffic in real-time
• Collective awareness
• Traffic congestion infered by
• road charateristics context
• ITS endowed with situation aware modules
•
• Collective actions
• Modelling current traffic conditions dynamically
• Recomending re-routings, intermodal routes or viability changes
7. • Challenges for Superorganism
architecture
• Support for heterogeneity and interoperability
• Support for dynamic reconfigurability
• High degree of awareness
• Strategies for dynamic selection
• Bottom-up and top-down design approaches
8. An architectural proposal
Two tier middleware
architecture
Middleware on individuals
Centralized control
engines in a cloud
environment
9. • Middleware on individuals
• Low layer API to abstarct
SAC capabilities
Awareness module.
Self optimizing and
reconfiguring module
10. • Middleware on control engine
• Autonomic architecture
Sensing specific aspects through superorganisms
Reacting to specific situations
Actuating urban superorganisms to optimize, steer or sense again
12. • Conclusions and future work
• Conclusions
• Innovative collaborative and collective behaviors resulting in urban
intelligence
• Many research challenges and suitable middleware infrastructures have
to be developed
• Future work
• Investigating in detail the challenges
• Implementing prototypes
Our vision of how urban environments are evolving.
Citizens will have the possibility of being continuously connected in a situation and socialy aware way between them and also with other entities or sensors called individuals. This leads to a very dense digital ecosystem and to a superorganism that will contribute towards a Smart City vison
Each individual of the digital ecosystem has complementary sensing, computing and actuating capabilities. From the human side : using the five senses, pattern and emotion recognition, human body (moving towards a direction, making actions) … from the ICT side: sensor networks, RFID tags, smartphone sensors. Data analysis and aggregation. Traffic light, public displayes, actuating devices on infrastructures.
This very large number of interconnected individuals (similarly to an ant colony) can be exploited to define what is defined as a Superorganism In particular closing the previously illustrated capabilities in a loop and making such activities collabarative ones, is possible to realize coherent collective behavior. These collective behaviors will be based on the collective sensing and collective awareness of urban facts and issues- Furthermore il will be possible to plan for collective actions aimed at fixing problems or adaplively steering urban dynamics.
Recent studies in the field of self-organized and self-adaptive systems have focused in defining a catalogue of bioinspired mecanisms with the intent to overcome the limit of ah-hoc implementations. The basic idea is that of providing the bio-inspired self-organizing pattern modules with a set of reusable patterns that could be used to ease engineering.
Following the Superorganism’s paradigm, citizens can cooperate with each other to steer the behavior of the city in terms of mobility dynamics.
1- the sw architecture has to realize an abstraction layer in order to achive the same goal on different individuals (wether humans or ICT devices)
2- depending on the execution context dynamic service compostion and configuration in needed
3- opportunisticaly sense and recognise many heterogeneous kind of situations
4- individuals have to be connected to support collective behaviors
5-evaluate which individuals are more suitable to be involved based on knowledge of their status
6- in top-down design approach the requiremnts of sw architecture are known but systems deisgned this way are not able to cope with dynamic context. On the other hand systems designed with a bottom-up approach are more robust and suitable for pervasive environment but controllin them by design is not easy. So there must be a combination of the to approaches and the optimal trade-off must be found.
Middleware on top of individuals enabling urban superorganism features.
It is worth noticing that the proposed infrastructure is also important to support privacy of data. Therfore more can be done and kept within the person hanset and th greater the preservation of privacy.
The awareness module uses three conseptual layers to reach its goal: the sensor, the classifier and the awareness layer. The awareness layer in particular by enabling a control layer interact with the sensor layer and with the classifier one in a feedback loop. That means the sensor layer can use the data computed by the awareness layer to favor and obtain desired user behavior and or participation and in this direction collaborative filtering tecniques could be used to recommend possible solutions or alternatives. The classifier and awareness layer itself will use clustering algorithms and machine learning tecniques to classify and learn from data.