Cell phone big data to compute mobility scenarios for future smart cities

Efficient mobility is a key aspect for the future smart cities. The real added value for smart cities is the real-time optimization of vehicular and public transportation flows to reduce traffic congestions, costs, and emissions. Observing constantly the behaviour of people moving around the city can help policy makers to act promptly and to fix congested flows dynamically. In this paper, we describe from a technical point-of-view an original use of big data (coming from the cellular network of the Vodafone Italy Telco operator) to compute mobility patterns for smart cities. The paper also discusses five innovative mobility patterns that describe different mobility scenarios of the city, starting from how people move around point-of-interests of the city in real time. The mobility patterns have been experimentally validated in a real industrial setting and for the Milan metropolitan city. The study conducted confirmed the quality of the patterns and their importance in smart cities, by showing how cell phone big data can complete other sources of people information. These mobility patterns can be exploited by policy makers to improve the mobility in a city, or by Navigation Systems and Journey Planners to provide final users with accurate travel plans.

[1]  Davide Tosi,et al.  Big Data from Cellular Networks: Real Mobility Scenarios for Future Smart Cities , 2016, 2016 IEEE Second International Conference on Big Data Computing Service and Applications (BigDataService).

[2]  J.-G. Remy.  Computing travel time estimates from GSM signalling messages: the STRIP project , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[3]  Richard L. Smith,et al.  PREDICTIVE INFERENCE , 2004 .

[4]  Fabio Ricciato,et al.  Exploiting Cellular Networks for Road Traffic Estimation: A Survey and a Research Roadmap , 2009, VTC Spring 2009 - IEEE 69th Vehicular Technology Conference.

[5]  Luo Dayong,et al.  Apply Cellular Wireless Location Technologies to Traffic Information Gathering , 2009, 2009 Second International Conference on Intelligent Computation Technology and Automation.

[6]  R. Fisher.  019: On the Interpretation of x2 from Contingency Tables, and the Calculation of P. , 1922 .

[7]  Liang Liu,et al.  Estimating Origin-Destination Flows Using Mobile Phone Location Data , 2011, IEEE Pervasive Computing.

[8]  Alexandre M. Bayen,et al.  Evaluation of traffic data obtained via GPS-enabled mobile phones: The Mobile Century field experiment , 2009 .

[9]  Davide Tosi,et al.  Correlation of Weather and Moods of the Italy Residents through an Analysis of Their Tweets , 2016, 2016 IEEE 4th International Conference on Future Internet of Things and Cloud Workshops (FiCloudW).

[10]  Noel A Cressie.  Spatial Data Analysis by Example—Volume I: Point Pattern and Quantitative Data , 1987 .

[11]  Jiawei Han,et al.  Adaptive Fastest Path Computation on a Road Network: A Traffic Mining Approach , 2007, VLDB.

[12]  Roberta Terruggia,et al.  Big data from cellular networks: How to estimate energy demand at real-time , 2015, 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[13]  Carlo Ratti,et al.  Real-Time Urban Monitoring Using Cell Phones: A Case Study in Rome , 2011, IEEE Transactions on Intelligent Transportation Systems.

[14]  Fabio Ricciato,et al.  Steps towards the Extraction of Vehicular Mobility Patterns from 3G Signaling Data , 2012, TMA.

[15]  Fabio Ricciato,et al.  Road traffic estimation from cellular network monitoring: A hands-on investigation , 2009, 2009 IEEE 20th International Symposium on Personal, Indoor and Mobile Radio Communications.

[16]  Davide Tosi,et al.  Vehicular traffic predictions from cellular network data — A real world case study , 2014, 2014 International Conference on Connected Vehicles and Expo (ICCVE).

[17]  Albert-László Barabási,et al.  Understanding individual human mobility patterns , 2008, Nature.

[18]  William G. Griswold,et al.  Mobility Detection Using Everyday GSM Traces , 2006, UbiComp.

[19]  R. Fisher.  On the Interpretation of χ2 from Contingency Tables, and the Calculation of P , 2010 .

[20]  Marco Luca Sbodio,et al.  AllAboard: Visual Exploration of Cellphone Mobility Data to Optimise Public Transport , 2016, IEEE Trans. Vis. Comput. Graph..

[21]  V. Venkateswaran,et al.  Dynamic road traffic management based on krushkal's algorithm , 2011, 2011 International Conference on Recent Trends in Information Technology (ICRTIT).