On the privacy of crowd-sourced data collection for distance-to-empty prediction and eco-routing

The paradigm of crowd-sourced data collection (also known as participatory sensing) has been bolstered by the extensive availability of on-board sensors and electronic devices in nowadays vehicles, which can be applied in a wide range of transportation applications. Distance-to-empty (DTE) is the distance an electric vehicle (EV) or internal-combustion engine (ICE) vehicle can reach before its battery/fuel is exhausted, which is determined by a variety of uncertain factors, such as driving behavior, terrain, types of road, traffic, and vehicle specification. Eco-routing aims to optimize the route selection with lower energy consumption. The accuracy of DTE prediction and eco-routing can be enhanced substantially by the crowd-sourced data collected from diverse drivers and vehicles. However, a critical concomitant issue for crowd-sourced data collection is privacy, because the personal travel history may be misused without consents from the contributing users. To encourage large-scale adoption and contributions of crowd-sourced data collection from end users, this paper addresses the issue of privacy and proposes possible solutions to tackle the challenges. In particular, we discuss a solution of matrix factorization from collaborative filtering to enhance the privacy of crowd-sourced data collection in the context of transportation applications, such as DTE prediction and eco-routing.

[1]  Sid Chi-Kin Chau,et al.  A social approach for predicting distance-to-empty in vehicles , 2014, e-Energy.

[2]  Chi-Kin Chau,et al.  Personalized Prediction of Vehicle Energy Consumption Based on Participatory Sensing , 2016, IEEE Transactions on Intelligent Transportation Systems.

[3]  Erik Wilhelm,et al.  A Participatory Sensing Approach for Personalized Distance-to-Empty Prediction and Green Telematics , 2015, e-Energy.

[4]  M. Abou Zeid,et al.  A statistical model of vehicle emissions and fuel consumption , 2002, Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems.

[5]  Eva Ericsson,et al.  Independent driving pattern factors and their influence on fuel-use and exhaust emission factors , 2001 .

[6]  Jingyu Hua,et al.  Differentially Private Matrix Factorization , 2015, IJCAI.

[7]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[8]  Mirco Musolesi,et al.  The Rise of People-Centric Sensing , 2008, IEEE Internet Comput..

[9]  Matthew J. Barth,et al.  Arterial roadway energy/emissions estimation using modal-based trajectory reconstruction , 2011, 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[10]  Chi-Kin Chau,et al.  Personalized Prediction of Driving Energy Consumption based on Participatory Sensing , 2016, ArXiv.

[11]  Peter J. Haas,et al.  Large-scale matrix factorization with distributed stochastic gradient descent , 2011, KDD.

[12]  Markus Lienkamp,et al.  A modular and dynamic approach to predict the energy consumption of electric vehicles , 2013 .

[13]  Stratis Ioannidis,et al.  Privacy-preserving matrix factorization , 2013, CCS.

[14]  Anupam Joshi,et al.  StreetSmart Traffic: Discovering and Disseminating Automobile Congestion Using VANET's , 2007, 2007 IEEE 65th Vehicular Technology Conference - VTC2007-Spring.

[15]  Simon Mayer,et al.  CLOUDTHINK: A SCALABLE SECURE PLATFORM FOR MIRRORING TRANSPORTATION SYSTEMS IN THE CLOUD , 2015 .

[16]  Dominik Karbowski,et al.  Energy Consumption Prediction of a Vehicle along a User-Specified Real-World Trip , 2012 .

[17]  Roksana Boreli,et al.  Applying Differential Privacy to Matrix Factorization , 2015, RecSys.

[18]  Kanok Boriboonsomsin,et al.  Impacts of Road Grade on Fuel Consumption and Carbon Dioxide Emissions Evidenced by Use of Advanced Navigation Systems , 2009 .