论文部分内容阅读
道路交通流预测是现代智能交通系统的关键技术之一,短时预测是实现先进的交通控制和车辆导航的技术基础。为了提高短时交通流预测的精准度,提出了一种基于小波去噪和自适应遗传算法优化BP神经网络的预测模型。利用小波分解和重构将交通流转换成具有不同频率的多个平滑子序列,然后分别对各个子序列进行预测,此种方式能有效降低被预测交通流数据的时变性、复杂性以及非线性,同时自适应遗传算法具有全局搜索能力,能有效地避免神经网络易陷入局部极小值的缺陷,提高了预测模型的精准度。
Road traffic flow prediction is one of the key technologies of modern intelligent transportation system. Short-term prediction is the technical basis for realizing advanced traffic control and vehicle navigation. In order to improve the accuracy of short-term traffic flow prediction, a prediction model based on wavelet denoising and adaptive genetic algorithm to optimize BP neural network is proposed. Using wavelet decomposition and reconstruction, the traffic flow is transformed into multiple smooth subsequences with different frequencies, and then each subsequence is predicted separately. This method can effectively reduce the time-varying, complexity and nonlinearity of the predicted traffic flow data At the same time, adaptive genetic algorithm has the ability of global search, which can effectively avoid the defect that neural network is easy to fall into local minimum and improve the accuracy of prediction model.