基于DACO-Bi-LSTM的交通流量预测  

Traffic flow prediction based on DACO - Bi - LSTM

作　　者：郭金城 潘伟民[1] GUO Jin-cheng;PAN Wei-min(College of Computer Science and Technology,Xinjiang Normal University,Urumqi 830054,China)

机构地区：[1]新疆师范大学计算机科学技术学院,乌鲁木齐830054

出　　处：《信息技术》2024年第5期8-14,21,共8页Information Technology

基　　金：国家自然科学基金项目(62162061)。

摘　　要：针对交通流量预测任务存在预测精度低、泛化性不足且对深度学习模型调参不全面等问题,提出了一种基于改进蚁群优化算法的双向LSTM交通流量预测模型,利用改进蚁群算法的全局寻优能力对Bi-LSTM网络的层数、神经元个数、批次大小、训练次数进行优化调参。在英国高速公路和深圳政府开放平台发布的宝安区日车流量两个公开数据集上进行实验,以RMSE、MAE为评估指标,结果表明:DACO-Bi-LSTM模型具有较强的寻优能力,同时表现出更好的预测性能。To solve the problems of low prediction accuracy,insufficient generalization and incomplete hyperparameters tuning of deep learning model existed in traffic flow forecasting task,an improved ant colony algorithm based Bi-LSTM traffic flow prediction model is put forward,which uses global optimization capability of the improved ant colony algorithm to optimize hyperparameters tuning towards layers of Bi-LSTM network,number of neurons,batch size,and the number of training.Experiments are carried out on two public data sets of daily traffic flow in British Motorway and Bao’an District published by Shenzhen Government Open Platform,with RMSE and MAE being as evaluation indexes.The results show that DACO-Bi-LSTM model has strong optimization ability and better prediction performance,and shows better prediction performance.

关 键 词：交通流量预测 蚁群算法优化 双向长短时记忆网络 模型调参 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]