新疆大学电气工程学院
纸质出版:2022
移动端阅览
[1]曾蓉,黄德启,魏霞,等.改进WOA优化LSTM神经网络的短时交通流预测[J].新疆大学学报(自然科学版)(中英文),2022,39(02):242-248.
[1]曾蓉,黄德启,魏霞,等.改进WOA优化LSTM神经网络的短时交通流预测[J].新疆大学学报(自然科学版)(中英文),2022,39(02):242-248. DOI: 10.13568/j.cnki.651094.651316.2021.03.05.0001.
DOI:10.13568/j.cnki.651094.651316.2021.03.05.0001.
针对城市交通中交叉路口短时交通流预测问题,本文提出了一种IWOA-LSTM模型,该模型是在传统的WOA算法基础上,对初始种群进行tent混沌初始化,同时将线性递减的收敛因子改进为非线性的方式,再将改进后的IWOA算法与LSTM神经网络模型结合,所得到的IWOA-LSTM模型提高了对交通流预测的精度.本文选取了8个基准测试函数对IWOA算法进行性能测试和仿真实验,验证了改进的IWOA算法在收敛速度以及精度上的优势.最后将IWOALSTM模型的预测结果和PSO-LSTM模型的预测结果分别与实际交通流量进行对比,得出IWOA-LSTM算法误差更小的结论.
Aiming at the problem of short-term traffic flow prediction at intersections in urban traffic
this paper proposes an IWOA-LSTM model
which is based on the traditional WOA algorithm and initializes the initial population with tent chaos. At the same time
the linearly decreasing convergence factor is improved into a nonlinear way
and the improved IWOA algorithm is combined with the LSTM neural network model. The resulting IWOA-LSTM model improves the accuracy of traffic flow prediction. This paper selects 8 benchmark test functions to perform performance testing and simulation experiments on the IWOA algorithm
which verifies the advantages of the improved IWOA algorithm in convergence speed and accuracy. The prediction results of the IWOA-LSTM model and the PSO-LSTM model are compared with the actual traffic flow respectively
and the conclusion that the IWOA-LSTM algorithm has a smaller error is obtained.
LYU Y S, DUAN Y J, KANG W W, et al. Traffific flow prediction with big data:a deep learning approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2):865-873.
杨文忠,张志豪,柴亚闯,等.基于GBRT模型的交通事故预测[J].新疆大学学报(自然科学版)(中英文), 2020, 37(1):36-43.
张阳,杨书敏,辛东嵘,等.改进小波包与长短时记忆组合模型的短时交通流预测[J].交通运输系统工程与信息, 2020, 20(2):204-210.
王祥雪,许伦辉.基于深度学习的短时交通流预测研究[J].交通运输系统工程与信息, 2018, 18(1):81-88.
罗向龙,李丹阳,杨彧,等.基于KNN-LSTM的短时交通流预测[J].北京工业大学学报, 2018, 44(12):1521-1527.
满春涛,康丹青.考虑上下游的LSTM短时交通流量预测[J].哈尔滨理工大学学报, 2019, 24(5):101-107.
尹邵龙,赵亚楠.深度学习在城市交通流预测中的实践研究[J].现代电子技术, 2015, 38(15):158-162.
宋刚,张云峰,包芳勋,等.基于粒子群优化LSTM的股票预测模型[J].北京航空航天大学学报, 2019, 45(12):2533-2542.
张永,陈锋.一种改进的鲸鱼优化算法[J].计算机工程, 2018, 44(3):208-219.
何庆,魏康园,徐钦帅.求解函数优化问题的改进鲸鱼优化算法[J].微电子学与计算机, 2019, 36(4):72-77.
宋健,王聪,张宏立.基于云模型的混合粒子群算法的统一混沌系统时变参数辨识[J].新疆大学学报(自然科学版)(中英文),2020, 37(3):407-414.
JIN F, ZHAO B C. Short-term traffic flow prediction based on road network topology[J]. Journal of Beijing Institute of Technology,2019, 28(3):383-388.
李高盛,彭玲,李祥,等.基于LSTM的城市公交车站短时客流量预测研究[J].公路交通科技, 2019, 36(2):128-135.
LI R M, HUANG Y F, WANG J. Long-term traffic volume prediction based on K-means gaussian interval type-2 fuzzy sets[J].IEEE/CAA Journal of Automatica Sinica, 2019, 6(6):1344-1351.
0
浏览量
1079
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
