| 引用本文: | 温惠英,张东冉,陆思园.GA-LSTM模型在高速公路交通流预测中的应用[J].哈尔滨工业大学学报,2019,51(9):81.DOI:10.11918/j.issn.0367-6234.201806085 |
| WEN Huiying,ZHANG Dongran,LU Siyuan.Application of GA-LSTM model in highway traffic flow prediction[J].Journal of Harbin Institute of Technology,2019,51(9):81.DOI:10.11918/j.issn.0367-6234.201806085 |
|
| 摘要: |
| 为提高高速公路交通流预测精度,为高速公路管理部门动态控制诱导提供有效支撑,以实时交通流预测误差最小为目标,通过对高速公路数据的清洗和归一处理,分为4个不同时间间隔的数据集,按比例划分为训练数据集和测试数据集. 采用遗传算法（GA）对数据时间窗步长、长短期记忆（LSTM）神经网络的隐藏层数、训练次数、dropout进行优化调参,分析4种参数对模型寻优影响,GA-LSTM模型在keras中以Tensorflow为后台进行训练拟合. 结果表明:GA-LSTM模型寻优速度快,同传统预测算法中的SVM、KNN、BP和LSTM神经网络相比较,GA-LSTM对数据预测均方误差和均方根误差最小,模型表现出更好的预测性能. |
| 关键词: 交通流预测 长短期记忆 循环神经网络 深度学习 遗传算法 |
| DOI：10.11918/j.issn.0367-6234.201806085 |
| 分类号:U491 |
| 文献标识码:A |
| 基金项目:国家自然科学基金(2,7) |
|
| Application of GA-LSTM model in highway traffic flow prediction |
|
WEN Huiying,ZHANG Dongran,LU Siyuan
|
|
(School of Civil and Transportation, South China University of Technology, Guangzhou 510641, China)
|
| Abstract: |
| To improve the accuracy of highway traffic flow prediction and provide effective support for the dynamic control induction of highway management departments, this paper takes the minimum prediction error of real-time traffic flow as the goal and divides the highway data into four different time intervals by cleaning and normalizing. The data set was divided into training data sets and test data sets. Genetic algorithm (GA) was used to optimize the parameters of data time window step as well as long-term and short-term memory (LSTM) neural network of hidden layer, training times, and dropout, and analyze the influence of four parameters on model optimization. In keras, GA-LSTM model utilized Tensorflow as a background for training and fitting. Experiments show that the GA-LSTM model had a fast search speed. Compared with the SVM, KNN, BP, and LSTM neural networks in the traditional prediction algorithm, the GA-LSTM had the minimum mean square error and root mean square error for data prediction, and the model exhibited better predictive performance. |
| Key words: traffic flow prediction long-term and short-term memory recurrent neural network deep learning genetic algorithm |
