FOA-SVR在交通流预测中的研究 SVR Based on FOA and Its Application in Traffic Flow Predication

交通流量预测是实现智能交通系统的重要工作。为了更准确地对交通流量进行预测，结合支持向量回归机(SVR)与果蝇算法(FOA)，提出了FOA-SVR的交通流量预测模型。利用果蝇算法优化支持向量回归机的训练参数，以得到预测性能更好的支持向量回归预测模型。仿真结果表明，FOA-SVR模型比传统的支持向量机模型预测精度更高，可以更好的对交通流进行预测。 The accurate predication of traffic flow is an essential job in ITS. In order to predict traffic flow exactly, the FOA-SVR prediction model combining Support Vector Regression (SVR) and fruit fly optimization algorithm (FOA) is presented to forecast railway traffic flow. Using fruit fly optimization algorithm to optimize training parameters of Support Vector Regression, which can obtain superior SVR prediction model. The experiment results show that the FOA-SVR model has more accuracy, which provides a new approach for traffic flow prediction.