Affiliations: [a] Advanced Innovation Center for Future Education, Beijing Normal University, Beijing, China | [b] Institute for Infocomm Research (I2R), A*STAR, Singapore | [c] Nanyang Technological University, Singapore | [d] Big Data Centre for Technology-Mediated Education, Beijing Normal University, Beijing, China
Abstract: The fast advancements in sensor data acquisition and vehicle telematics facilitate data collection from taxis and thus, enable building a system to monitor and analyze the citywide taxi service. In this paper, we present a novel and practical system for taxi service analytics and visualization. By utilizing both real time and historical taxi data, the system conducts the estimation on region based passenger wait time for taxi, where recurrent neural network (RNN) and deep learning algorithms are used to build a predictive model. The built RNN-based predictive model achieves 73.3% overall accuracy, which is significantly higher than other classic models. Meanwhile, the system conducts the analytics on the taxi pickup hotspots and trip distributions. The experimental results show that around 97% trips are accurately identified and more than 200 hotspots in the city are successfully detected. Moreover, a novel three dimensional (3D) visualization together with the informative user interface is designed and implemented to ease the information access, and to help system users to understand the characteristics and gain insights of the taxi service.
Keywords: Recurrent neural network, deep learning, passenger wait time, intelligent transportation system, urban computing
