Private personalized dynamic ride sharing

© 2016 Dr. Preeti GoelAlleviating metropolitan traffic congestion is one of the major issues faced throughout the world. On one hand, the falling car occupancy rates indicate that more than 80% of the congestion can be attributed to the empty car seats. A highly promising approach to combat traffic congestion is dynamic ride sharing, which aims to utilize the transport capacity of the existing vehicles on roads. Dynamic ride sharing is a service that enables shared vehicle rides (on a one time or recurrent basis) in real time and at short notice. The growing use and popularity of smart phones and GPS enabled devices provides us with tools required to efficiently implement a location-based service such as dynamic ride sharing and improve car occupancy rates. However, privacy and safety concerns are one of the main obstacles faced when encouraging people to use such a service. In this thesis, we present a personalized dynamic ride sharing model built ground up with the objective to ensure privacy, safety and trust to the users. In the first part of the thesis, we develop a model for dynamic ride sharing in which users submit trip intents (rather than exact location and time information) to the service provider to find potential matches. The proposed model highlights the privacy benefits of established pick up or drop off locations and selects these locations randomly from the set of arterial intersections, according to the population densities of suburbs. In the second work, we present models for optimal pick up or drop off location selection to enhance ride sharing such that passengers can be picked up collectively by drivers and passengers can have privacy guarantees. Finally, in the third part, we produce useful data to design the selection of pick up or drop off locations such that ride sharing can be designed to take care of special events and traffic flows which do not follow the population density of suburbs. Our main contribution in this research is that we have presented a privacy aware dynamic ride sharing system. We show that it is feasible to combine privacy with convenience while maintaining utility, and our system enhances opportunities for ride sharing. We present extensive experimental evaluations that validate the effectiveness of our privacy protection models and demonstrate the efficiency of our algorithms. We demonstrated through our dynamic ride sharing that huge benefits can be achieved in reducing congestion and overall travel km, for the city of Melbourne, with 11.6 million trips per weekday and an average trip length of 10.2 km, our proposed dynamic ride sharing model would save 35.95 million km per weekday