A Trajectory Recommendation System for Efficient Finding of Passengers

Please enable javascript in your browser.

Aledavood, Ebrahim | 2019

435 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 53071 (01)
University: Sharif University of Technology
Department: Industrial Engineering
Advisor(s): Khedmati, Majid; Rafiee, Majid
Abstract:
Recommending routes to city taxis in order to improve their performance in finding passengers can reduce traffic, pollution and waiting time for passengers, as well as this, increasing the efficiency of taxis can increase their income. In this study, by analyzing trajectory data obtained from 536 taxis in San Francisco over a period of one month, we generated networks of cells, each of which has time-dependent characteristics such as the probability of finding a passenger, the capacity of each cell, or the amount of demand exists is in the cell and the average speed of passing through that cell. also, the connections between these cells in order to make more use of the experiences of taxi drivers, have been determined by analyzing the behavior of taxis. In this research, the MECR (Minimum Expected Cost Route) recommendation algorithm is also introduced to use the information stored on the created networks to find a route for a set of taxis to reduce time and distance of finding a passenger. The results of the evaluation show that the proposed algorithm performs better than the LCP method in order to improve the performance of the taxis
Keywords:
Cellular Network ; Recommender System ; Routing Recommendation System ; Trajectory Data ; Spatio-Temporal Recommender System