摘要
道路交通事故精准预测是有效提升交通安全的重要手段,由于事故数据经常呈现非线性、波动性、无周期性等特征,现有的算法存在预测效果不佳的问题。为此本文提出基于集合经验模态分解降噪算法(ensemble empirical mode decomposition,EEMD)和优化长短时记忆神经网络(long short-term memory,LSTM)的交通事故数量预测模型。在单一模型的基础上,引入降噪算法EEMD对噪声大的交通事故时间序列进行降噪处理,利用EEMD对事故时间序列进行分解得到多个子序列和1个残差项;基于粒子群优化算法(particle swarm optimization,PSO)优化LSTM网络结构参数,并在LSTM的最优网络结构下提取数据中的时间特征信息进行预测,对各子序列及残差的预测结果求和得到最终预测结果。研究结果表明:相对于EMD-PSO-LSTM,PSO-LSTM,EEMD-LSTM,LSTM这4个模型,EEMD-PSO-LSTM的预测效果最好,其对应的预测误差e_(rmse)分别降低了8.7%、48.3%、53.1%、57.6%,误差e_(mape)分别降低了12.4%、36.9%、50.6%、61.2%。进一步研究表明,运用EEMD对数据进行降噪预处理能提高预测精度,与PSO-LSTM模型相比,EEMD-PSO-LSTM模型的误差e_(rmse)降低了60.2%,e_(mape)降低了12.4%,判定系数r^(2)提高了0.6165;引入PSO模型优化神经网络结构同样也能有效提升预测效果,与EEMD-LSTM模型相比,EEMD-PSO-LSTM模型的误差e_(rmse)减小了53.1%,e_(mape)降低了50.6%,判定系数r^(2)提高了0.8078。该研究结果能够提高交通事故预测精度,帮助相关部门有效提高道路交通安全水平。
Accurate prediction of road traffic accidents is essential to improve traffic safety effectively.Due to the frequent non-linear,fluctuating,and nonperiodic characteristics of accident data,existing algorithms have the problem of poor prediction performance.Therefore,a method for traffic prediction that uses a long short-term memory network(LSTM)combined with ensemble empirical mode decomposition(EEMD)and particle swarm optimization(PSO)is proposed.Based on a single model,the EEMD is first used to break down the noise of accident data and obtain multiple subsequences and a residual.Based on LSTM optimized by PSO,the temporal feature infor mation extracted from the data is predicted under the optimal network structure of LSTM.Then,the prediction results of each subsequence and residual are summed to obtain the final prediction result.The results show that,compared with the EMD-PSO-LSTM,PSO-LSTM,EEMD-LSTM,and LSTM,the e_(rmse)of EEMD-PSO-LSTM is reduced by 8.7%,48.3%,53.1%,and 57.6%,respectively.Meanwhile,the e_(mape)is reduced by 12.4%,36.9%,50.6%,and 61.2%,respectively.Compared with the PSO-LSTM,the e_(rmse)of the EEMD-PSO-LSTM is reduced by 60.2%,the e_(mape)is reduced by 12.4%,and the r 2 is increased by 0.6165.The PSO Introduced to optimize neural networks can help improve prediction performance.Compared with the EEMD-LSTM,the e_(rmse)of the EEMD-PSO-LSTM is reduced by 53.1%,the e_(mape)is diminished by 50.6%,and the r 2 is climbed to 0.8078.The results can improve the prediction accuracy of traffic accidents and help relevant departments effectively improve road traffic safety.
作者
刘清梅
万明
严利鑫
郭军华
LIU Qingmei;WAN Ming;YAN Lixin;GUO Junhua(School of Transportation Engineering,East China Jiaotong University,Nanchang 330013,China;School of Traffic and Transportation,Nanchang Jiaotong Institute,Nanchang 330013,China)
出处
《交通信息与安全》
CSCD
北大核心
2023年第5期12-23,共12页
Journal of Transport Information and Safety
基金
国家自然科学基金项目(52162049)
赣鄱俊才支持计划-主要学科学术和技术带头人培养项目——青年人才(20232BCJ23012)
江西省研究生创新专项(YC2021-S457)资助。
关键词
交通安全
事故预测
长短时记忆神经网络
粒子群算法
集合经验模态分解
traffic safety
accident prediction
long short-term memory neural network
particle swarm algorithm
ensemble empirical mode decomposition
