Real-Time Intelligent Recognition of Chaos in Traffic Flow Using Reduced Support Vector Machine

Abstract

The real-time recognition problem of chaos in traffic flow was studied using reduced support vector machine. Based on analyzing the demand of intelligent transportation system and the problems of the exiting recognition methods, the intelligent real-time recognition method of chaos in traffic flow was proposed. The principle and the structure of the system are briefly introduced. There are online recognition subsystem and offline recognition subsystem mainly. Normal methods are used in the offline recognition model. The online recognition model was established using reduced support vector machine, which the wavelet packet energy features vector of the anterior time series of traffic flow in every training samples were used as input variables. The reduced samples are treated as the final training sample. When the new samples are appended, the reduced set may be updated. The rules of models can be updated and the problem of large sample size could be solved. The simulation result shows that the method is correct and feasible. And it can satisfy the real-time requirement of chaos recognition.

Control priorities of signal on-ramps metering based on chaos state identification

“…The first is to identify the chaotic situation before putting the control measures in place. The real time situation of mainline freeway can be immediately determined by the traffic flow chaos intelligent recognition subsystem (which includes two modules of online recognition and offline recognition) [15] . Compared to earlier chaos recognition techniques, this recognition system is unique.…”

“…0,1 is the authority and weight of + and − . The control timing of multiple ramps based on chaotic state is determined by the size of [15] . Based on the traffic flow data under the chaotic state of the main highway, considering the proportion of ramp traffic flow weight, the difference ratio of sub-sections is calculated using equation (8) to determine the signal control order of the ramp.…”

“…Figure 2 Xi'an ring freeway. When the traffic flow on the mainline reaches 675 vehicles, it reaches the critical traffic flow in a chaotic state [15,20] . By using the improved QHM model, the critical states of the three sub-sections can be obtained.…”

“…The following two issues must be resolved in the multi-ramp coordinated control of an freeway based on chaotic state identification: ① identify the order of ramp control; ② determine the time of start and end of control. In order to quickly identify the chaotic state for the first issue, He [15] assembled a small sample of traffic flow observation samples and extracted their eigenvalues. It is possible to identify the ramp control opportunity when λ max is the threshold value.…”

The Integrated Application of Improved Methods on the Chaos Identification in Microcosmic Simulation Traffic Flow

“…Study on chaos in traffic flow has been developed and certain success has been achieved [1][2][3][4]. It is a basic and key problem for study on chaos in traffic flow to identify chaos.…”