关键词: 交通流预测, 检测器优化, 遗传算法, 小波神经网络

Abstract: According to the shortcoming that traffic detector configuration is not considered in traffic flow prediction, this paper proposes an algorithm for short-term traffic flow prediction based on detector optimal selection. The paper takes the minimum?mean square?prediction error?as the objective function, selects suitable detectors with genetic algorithm, and predicts the?short term traffic flow with wavelet neural network. The test results with America I-84 highway measured data show that the proposed algorithm has higher accuracy compared with the traditional method, and it is an efficient method to the short-term traffic flow prediction.

Key words: traffic flow forecasting, sensor optimization, Genetic Algorithm（GA）, wavelet neural network