计算机应用与软件2026，Vol.43Issue(3)：178-182,196,6.DOI:10.3969/j.issn.1000-386x.2026.03.026
基于SSA-CNN-BILSTM组合优化的时空序列预测模型
SPATIOTEMPORAL SEQUENCE PREDICTION MODEL BASED ON COMBINED SSA-CNN-BILSTM OPTIMIZATION
赵立新 1金辉 1刘潇2
作者信息
- 1. 辽宁工业大学汽车与交通工程学院 辽宁 锦州 121000
- 2. 北方工业大学电气与控制工程学院 北京 100000
- 折叠
摘要
Abstract
In order to extract the latent features and hidden information of spatiotemporal series data more effectively and improve the prediction accuracy of the model,a spatiotemporal series prediction method based on SSA-CNN-BILSTM combination optimization is proposed.Using convolution and pooling of convolutional neural network(CNN)to extract features from input data,and using BILSTM to predict,the sparrow search algorithm(SSA)was used to optimize the parameters of the model.The simulation experiment was carried out with the passenger flow data of Chengdu Rail Transit,and two evaluation indexes were selected and compared with LSTM,BILSTM,CNN-BILSTM and PSO-CNN-BILSTM respectively.The results show that the combined model has the best prediction precision,the SSA-CNN-BILSTM combined optimization model presented in this paper is proved to be an effective time-space series prediction method.关键词
时空序列预测/长短时记忆网络/卷积神经网络/组合优化Key words
Time-space series prediction/Long short-term memory network/Convolution neural network/Combinatorial optimization分类
信息技术与安全科学引用本文复制引用
赵立新,金辉,刘潇..基于SSA-CNN-BILSTM组合优化的时空序列预测模型[J].计算机应用与软件,2026,43(3):178-182,196,6.
