A Crowdsensing Campaign and Data Analytics for Assisting Urban Mobility Pattern Determination

The ever-progressing advancements in urban growth and technological development in recent decades have caused a noticeable increase of the phenomenon of socialenvironmental deterioration, leading to a decline in quality of life, reduction of social welfare and difficult urban mobility for people living in cities. The concept of Smart City can be used to mitigate several of the challenges arising from the aforementioned issues, relying on multiple tools and techniques (such as crowdsensing) to gather essential context data about how actual citizens consume resources and commute throughout their everyday lives. In this paper, we show how an urban mobility data analytics tool may help to determine the most visited regions and interconnections in an urban area. This information has been obtained using data gathered from a pool of users participating in a crowdsensing campaign, using the ParticipAct Brazil platform. The obtained results confirm the reliability of the information produced, highlighting the regions with the highest concentration of people during the geolocation monitoring process and their connections; therefore, this data may be used to plan possible future changes to how the city allocates its resources, to better suit the mobility needs of its citizens.

[1]  Károly Farkas,et al.  Crowdsending based public transport information service in smart cities , 2015, IEEE Communications Magazine.

[2]  Jian Tang,et al.  Sensing as a Service: Challenges, Solutions and Future Directions , 2013, IEEE Sensors Journal.

[3]  Vikas Agarwal,et al.  USense -- A Smartphone Middleware for Community Sensing , 2013, 2013 IEEE 14th International Conference on Mobile Data Management.

[4]  Annalisa Cocchia.  Smart and Digital City: A Systematic Literature Review , 2014 .

[5]  G Ambrosino,et al.  Enabling intermodal urban transport through complementary services : from Flexible Mobility Services to the Shared Use Mobility Agency: Workshop 4. Developing inter-modal transport systems , 2016 .

[6]  Fan Ye,et al.  Mobile crowdsensing: current state and future challenges , 2011, IEEE Communications Magazine.

[7]  Antonio Corradi,et al.  Crowdsensing and proximity services for impaired mobility , 2016, 2016 IEEE Symposium on Computers and Communication (ISCC).

[8]  Antonio Corradi,et al.  Automatic extraction of POIs in smart cities: Big data processing in ParticipAct , 2015, 2015 IFIP/IEEE International Symposium on Integrated Network Management (IM).

[9]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[10]  Sudha Ram,et al.  A big data approach for smart transportation management on bus network , 2016, 2016 IEEE International Smart Cities Conference (ISC2).

[11]  J. Jokinen,et al.  Crowdsensing-based transportation services - An analysis from business model and sustainability viewpoints , 2016 .

[12]  Károly Farkas,et al.  Participatory sensing based real-time public transport information service , 2014, 2014 IEEE International Conference on Pervasive Computing and Communication Workshops (PERCOM WORKSHOPS).

[13]  R. Suganya,et al.  Data Mining Concepts and Techniques , 2010 .

[14]  Antonio Corradi,et al.  Smartphones as smart cities sensors: MCS scheduling in the ParticipAct project , 2015, 2015 IEEE Symposium on Computers and Communication (ISCC).

[15]  Dan Grigoras,et al.  Scheduling crowdsensing data to smart city applications in the cloud , 2016, 2016 IEEE 12th International Conference on Intelligent Computer Communication and Processing (ICCP).