Abstract
Utilizing large-scale GPS data to improve taxi services becomes a popular research problem in the areas of data mining, intelligent transportation, and the Internet of Things. In this paper, we utilize a large-scale GPS data set generated by over 7,000 taxis in a period of one month in Nanjing, China, and propose TaxiRec; a framework for discovering the passenger-finding potentials of road clusters, which is incorporated into a recommender system for taxi drivers to hunt passengers. In TaxiRec, we first construct the road network by defining the nodes and road segments. Then, the road network is divided into a number of road clusters through a clustering process on the mid points of the road segments. Afterwards, a set of features for each road cluster is extracted from real-life data sets, and a ranking-based extreme learning machine (ELM) model is proposed to evaluate the passenger-finding potential of each road cluster. Experimental results demonstrate the feasibility and effectiveness of the proposed framework.
Original language | English |
---|---|
Title of host publication | GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems |
DOIs | |
Publication status | Published - 3 Nov 2015 |
Externally published | Yes |
Keywords
- Extreme learning machine
- Passenger-finding potential
- Recommender system
- Taxi trajectory data