Traffic flow prediction using orthogonal arrays and Takagi-Sugeno neural fuzzy models

Abstract

Takagi-Sugeno neural fuzzy models (TS-models) have commonly been applied in the development of traffic flow predictors based on traffic flow data captured by the on-road sensors installed along a freeway. However, using all captured traffic flow data is ineffective for the TS-models for traffic flow predictions. Therefore, an appropriate on-road sensor configuration consisting of significant sensors is essential to develop an accurate TS-model for traffic flow forecasting. Although the trial and error method is usually used to determine the appropriate on-road sensor configuration, it is time-consuming and ineffective in trialing all individual configurations. In this paper, a systematic and effective experimental design method involving orthogonal arrays is used to determine appropriate on-road sensor configurations for TS-models. A case study was conducted based on the development of TS-models using traffic flow data captured by on-road sensors installed on a Western Australia freeway. Results show that an appropriate on-road sensor configuration for the TS-model can be developed in a reasonable amount of time when an orthogonal array is used. Also, the developed TS-model can generate accurate traffic flow forecasting.