¹College of computer science, Chongqing University, Chongqing, 400044, China
²Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education, Chongqing University, China

---

Abstract—Existing time-series models that are used for short-term traffic condition forecasting are mostly monophyletic detector in nature. Generally, informationfusion online from multi-source sensors to more accurately and completely obtains traffic condition than using either of them alone. In this paper, a prediction method for real-time traffic condition prediction is presented, in which the multisource detection data are collected by different components of a time-series data sets, such as Global Position System (GPS), Radio Frequency Identification (RFID), video camera. Finally, a case study at the Chongqing, China, city center with serious traffic congestion is performed to illustrate the forecasting strategy. The results indicate that the presented forecasting strategy is one of the effective approaches to predict the real-time traffic condition in a road network, especially at the locations where no continuous data collection takes place.

Index Terms—Traffic condition, forecasting, GPS, RFID, video camera.

[PDF]

Cite: Qinglu Ma, Weining Liu, Dihua Sun, "Hybrid Multi-Sensor Data for Traffic Condition Forecasting," Journal of Computers vol. 7, no. 8, pp. 1870-1879, 2012.