[1]陈 雄,王海晨.基于 ISSA-LSTM 模型的短时交通流预测[J].计算机技术与发展,2023,33(04):198-204.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 029]
　CHEN Xiong,WANG Hai-chen.Research on Traffic Flow Prediction Based on ISSA-LSTM Model[J].,2023,33(04):198-204.[doi:10. 3969 / j. issn. 1673-629X. 2023. 04. 029]

点击复制

基于 ISSA-LSTM 模型的短时交通流预测()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

33

期数:

2023年04期

页码:

198-204

栏目:

新型计算应用系统

出版日期:

2023-04-10

文章信息/Info

Title:

Research on Traffic Flow Prediction Based on ISSA-LSTM Model

文章编号:

1673-629X(2023)04-0198-07

作者:

陈 雄; 王海晨

长安大学 信息工程学院,陕西 西安 710064

Author(s):

CHEN Xiong; WANG Hai-chen

School of Information Engineering,Chang’an University,Xi’an 710064,China

关键词:

智能交通; 交通流预测; 长短时记忆网络; 麻雀搜索算法; 参数寻优

Keywords:

intelligent transportation; traffic flow prediction; long short-term memory; sparrow search algorithm; parameter optimization

分类号:

TP391

DOI:

10. 3969 / j. issn. 1673-629X. 2023. 04. 029

摘要:

针对现有模型对短时交通流预测精确度不高、模型参数难以确定的问题,提出一种基于改进的麻雀搜索算法(ISSA) 和 LSTM 的短时交通流预测模型( ISSA-LSTM) 。 使用改进的 ISSA 算法优化 LSTM 的关键参数,减少参数的不确定性,从而构建预测精度高的交通流预测模型。 该模型具备 LSTM 提取时序数据深层特征的能力,融合了 SSA 算法快速收敛和全局搜索的特点,并且改进了 SSA 算法麻雀最初位置分布完全随机的特点,使其能均匀地分布在各个区间,避免出现局部最优的可能。 在真实的交通流数据集上进行验证,将模型的预测结果与 BP、GRU、LSTM、PSO-LSTM 和 SSA-LSTM 网络的预测结果进行对比。 实验结果表明,ISSA-LSTM 模型的 RMSE 相较于 LSTM 模型下降了 3. 263,MAE 下降了 1. 87,MAPE下降了 0. 949 百分点, R2 上升了 0. 276 百分点,相较于其他对比模型,组合模型的 RMSE、MAE、MAPE、 R2 的评价指标效果均为最好。 因此,ISSA-LSTM 模型在短时交通流预测上有较高的预测精度和预测稳定性,对预测交通流有借鉴意义。

Abstract:

Aiming at the problems that the existing models have low accuracy in predicting traffic flow and the model parameters aredifficult to determine,a traffic flow prediction model ( ISSA - LSTM) based on an improved Sparrow Search Algorithm ( ISSA) andLSTM is proposed. The ISSA is used to optimize the key parameters?

of LSTM and reduce the uncertainty of the parameters,so as to builda traffic flow prediction model with high prediction accuracy. The model has the ability of LSTM to extract deep features of time seriesdata,combines?

the characteristics of fast convergence and global search of SSA algorithm and improves the characteristics?

of SSAalgorithm that the initial position distribution of sparrows is completely random,so that it can be evenly distributed in each interval toavoid occurrence of possible local optima. Validated on a real traffic flow dataset, and compared the prediction results of the model withthe prediction results of BP,GRU,LSTM,PSO-LSTM and SSA-LSTM networks. The experimental results show that compared with theLSTM model,the RMSE of the ISSA-LSTM model decreases by 3. 263,the MAE decreases by 1. 87,the MAPE decreases by 0. 949 percentage points and the R2 increases by 0. 276 percentage points. The evaluation indicators of RMSE、MAE、MAPE and R2 of ISSA-LSTMmodel are both the best compared with other comparison models. Therefore,the ISSA-LSTM model has higher prediction accuracy andprediction stability in short-term traffic flow prediction,which has reference significance for predicting traffic flow.

常用功能