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(en-semble 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ermse分别降低了8.7%、48.3%、53.1%、57.6%,误差emape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ermse降低了60.2%,emape降低了12.4%,判定系数r2提高了0.616 5;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ermse减小了53.1%,emape降低了50.6%,判定系数r2提高了0.807 8.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 prob-lem 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 optimiza-tion(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 re-sults 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 ermse of EEMD-PSO-LSTM is reduced by 8.7%,48.3%,53.1%,and 57.6%,respectively.Meanwhile,the emape is reduced by 12.4%,36.9%,50.6%,and 61.2%,respectively.Compared with the PSO-LSTM,the ermse of the EEMD-PSO-LSTM is reduced by 60.2%,the emape is reduced by 12.4%,and the r2 is increased by 0.616 5.The PSO Introduced to optimize neural networks can help improve prediction performance.Compared with the EEMD-LSTM,the ermse of the EEMD-PSO-LSTM is reduced by 53.1%,the emape is diminished by 50.6%,and the r2 is climbed to 0.807 8.The re-sults can improve the prediction accuracy of traffic accidents and help relevant departments effectively improve road traffic safety.