论文部分内容阅读
交通流量预测是交通控制与交通诱导的关键技术,然而对于实现准确流量预测的可靠知识隐藏在大量的交通数据之中,需要对海量数据进行挖掘以发现潜在流量变化规律.传统的交通流量预测主要依靠专家经验对数据进行类别标记,其预测结果受到专家知识限制的影响较大.为了减轻人为因素的影响,提出一种混合智能数据挖掘的交通流量预测模型.首先利用自组织神经网络(SOM)的无监督学习方式实现海量数据类型特性的自动标识,降低对专家经验的依赖度;其次采用改进遗传算法(GA)优化模糊神经网络(FNN),对标识数据进行学习,建立交通流量预测模型.通过对智能交通系统(ITS)的实际数据进行分析,结果表明本文所提出的数据挖掘方法准确有效,预测精度达到95%,比不使用遗传算法优化提高了近8%.
Traffic flow forecasting is the key technology of traffic control and traffic guidance.However, the reliable knowledge of accurate traffic forecasting is hidden in a large amount of traffic data, and the massive data needs to be tapped to discover the potential traffic variation.Traditional traffic flow forecasting mainly Relying on the expert experience to classify the data, the prediction result is greatly influenced by the expert knowledge limitation.In order to reduce the influence of human factors, a traffic flow prediction model based on hybrid intelligent data mining is proposed.Firstly, using SOM (Self Organizing Neural Network) The unsupervised learning method can realize the automatic identification of massive data type characteristics and reduce the dependence on the expert experience. Secondly, the improved genetic algorithm (GA) is used to optimize the fuzzy neural network (FNN) to learn the identification data and establish the traffic flow forecasting model. By analyzing the actual data of ITS, the results show that the data mining method proposed in this paper is accurate and effective, the prediction accuracy reaches 95%, which is nearly 8% higher than that without genetic algorithm optimization.