A “semi-lazy” approach to probabilistic path prediction in dynamic environments
Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining
coRide: carpool service with a win-win fare model for large-scale taxicab networks
Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems
| Hi-index | 0.00 |
We demonstrate a system that monitors the taxi availability at taxi stands by mining real-time taxi trajectory data streams. The system includes a server-side trajectory data stream processing and mining program and a client-side mobile application for Android smart phones. The server program continuously monitors for each taxi stand the numbers of taxis queueing at the taxi stand, the numbers of taxis that will pass the taxi stand, as well as the traffic conditions in the area around the stand. It delivers real time taxi and traffic information to mobile users via Restful web services. The client-side location-based mobile application consumes these services to help mobile users make informed transportation choices. For example the availability of taxis might yet be a deterrent when traffic is congested. Real world taxi trajectory data from more than 14000 taxis are used in the demo.