On-Road Sensor Configuration Design for Traffic Flow Prediction Using Fuzzy Neural Networks and Taguchi Method

Abstract

On-road sensors provide proactive traffic control centers with current traffic flow conditions in order to forecast the future conditions. However, the number of on-road sensors is usually huge, and not all traffic flow conditions captured by these sensors are useful for predicting future traffic flow conditions. The inclusion of all captured traffic flow conditions is an ineffective means of predicting future traffic flow. Therefore, the selection of appropriate on-road sensors, which are significantly correlated to future traffic flow, is essential, although the trial and error method is generally used for the selection. In this paper, the Taguchi method, which is a robust and systematic optimization approach for designing reliable and high-quality models, is proposed for determinations of appropriate on-road sensors, in order to capture useful traffic flow conditions for forecasting. The effectiveness of the Taguchi method is demonstrated by developing a traffic flow predictor based on the architecture of fuzzy neural networks which can perform well on traffic flow forecasting. The case study was conducted based on traffic flow data captured by on-road sensors located on a Western Australia freeway. The advantages of using the Taguchi method can be indicated: 1) Traffic flow predictors with high accuracy can be designed, and 2) development time of traffic flow predictors is reasonable.Index Terms-Fuzzy neural networks (FNNs), fuzzy systems, on-road sensor, orthogonal array, sensor configuration, Taguchi method, traffic flow control, traffic flow prediction.

A Fault Tolerance Mechanism for On-Road Sensor Networks

“…The management center, which is usually deployed in a city or town, is a management entity to manage sensors and analyze the collected traffic information by neural network techniques [8]. Therefor all the on-road sensors need to communicate with the management center to transfer information or obtain some signals.…”

“…Therefore, a typical On-Road Sensor Network (ORSN) is formed by a majority of wireless sensors communicating through radio links and certain sensors serving as data collectors and relaying collected data to a remote data center through radio or cable/fiber [7]. It boasts properties like flexible and easy deployment, two-way communication, and is distinguished from regular wireless sensor networks by its linear-like topology [8]. As illustrated in Figure 1, a typical ORSN scenario consists of a large number and variety of sensors for different ITS functions; however, as they are serving a common ITS system, they can cooperate and perform multi-hop data transmission to reduce energy consumption at individual sensor nodes [9].…”

Urban Traffic Flow Prediction System Using a Multifactor Pattern Recognition Model

“…This system was shown to have better functionality than traditional feed forward neural networks using back propagation learning. Further, Chan et al [21] combined a fuzzy neural network and the Taguchi method to create a traffic flow prediction model. They used the Taguchi method to set a reasonable number of on-road sensors and demonstrated that the collected information was useful.…”

Evolution modeling of collective vehicles in vehicle ad hoc networks

“…Reference [13] proposed an approach to integrating SUMO and OMNet and [11] try to integrate the simulation of communication and traffic flow. However, most of them face problems on scalability and cannot support interactions between moving of vehicles and road information that is coming from the traffic administrator or traffic control centers [14], or from neighbourhood vehicles. This paper proposes a dynamic evolution model for urban VANETs, which is based on the similarity between the intelligent transportation and biological collective behaviors and can describe the dynamic interactive process between the collective moving behaviors of vehicles and road information.…”