Dynamic Optimization Long Short-Term Memory Model Based on Data Preprocessing for Short-Term Traffic Flow Prediction

被引:14
作者
Zhang, Yang [1 ]
Xin, Dongrong [2 ]
机构
[1] Fujian Univ Technol, Sch Transportat, Fuzhou 350118, Peoples R China
[2] Fujian Univ Technol, Sch Civil Engn, Fuzhou 350118, Peoples R China
关键词
Predictive models; Classification algorithms; Prediction algorithms; Support vector machines; Adaptation models; Heuristic algorithms; Machine learning; Traffic flow prediction; deep learning; long short-term memory; support vector regression; particle swarm optimization; SUPPORT VECTOR REGRESSION; DEEP BELIEF NETWORKS; NEURAL-NETWORK; GENETIC ALGORITHM; LSTM; FEATURES;
D O I
10.1109/ACCESS.2020.2994655
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In order to eliminate outliers in traffic flow data collection and promote the generalization performance of traffic flow prediction, this paper proposes a dynamic optimization long short-term memory (LSTM) model based on data preprocessing for short-term traffic flow prediction. A new classification algorithm named Asym-Gentle Adaboost with Cost-sensitive support vector machine (AGACS) is used for preprocessing traffic flow data. AGACS tries to employ Cost-sensitive SVM (CS-SVM) as weak component classifier in Asymmetric Gentle AdaBoost, and divide the data collection into outlier data and normal data. Only normal data is used for training LSTM to predict traffic flow and an improved chaotic Particle Swarm Optimization (CPSO) is used for dynamic optimizing hidden layer structure of LSTM to promote the generalization and robustness performance of model. The efficiency of the proposed method is proved with real traffic flow data, and the experimental results show that preprocess collecting data and dynamic optimize model structure are conducive to improve the performance of algorithm, and the proposed method achieved better performance than those of three other classical deep learning prediction methods.
引用
收藏
页码:91510 / 91520
页数:11
相关论文
共 40 条
[1]   A Novel Fuzzy-Based Convolutional Neural Network Method to Traffic Flow Prediction With Uncertain Traffic Accident Information [J].
An, Jiyao ;
Fu, Li ;
Hu, Meng ;
Chen, Weihong ;
Zhan, Jiawei .
IEEE ACCESS, 2019, 7 :20708-20722
[2]  
[Anonymous], [No title captured]
[3]   Segmentation of vehicle detector data for improved k-nearest neighbours-based traffic flow prediction [J].
Bernas, Marcin ;
Placzek, Bartlomiej ;
Porwik, Piotr ;
Pamula, Teresa .
IET INTELLIGENT TRANSPORT SYSTEMS, 2015, 9 (03) :264-274
[4]   Real-Time Freeway-Experienced Travel Time Prediction Using N-Curve and k Nearest Neighbor Methods [J].
Bustillos, Brenda I. ;
Chiu, Yi-Chang .
TRANSPORTATION RESEARCH RECORD, 2011, (2243) :127-137
[5]   A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting [J].
Cai, Pinlong ;
Wang, Yunpeng ;
Lu, Guangquan ;
Chen, Peng ;
Ding, Chuan ;
Sun, Jianping .
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2016, 62 :21-34
[6]   Multiple sources and multiple measures based traffic flow prediction using the chaos theory and support vector regression method [J].
Cheng, Anyu ;
Jiang, Xiao ;
Li, Yongfu ;
Zhang, Chao ;
Zhu, Hao .
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2017, 466 :422-434
[7]   Exploring spatial-temporal relations via deep convolutional neural networks for traffic flow prediction with incomplete data [J].
Deng, Shaojiang ;
Jia, Shuyuan ;
Chen, Jing .
APPLIED SOFT COMPUTING, 2019, 78 :712-721
[8]   Speech corpora subset selection based on time-continuous utterances features [J].
Dong, Luobing ;
Guo, Qiumin ;
Wu, Weili .
JOURNAL OF COMBINATORIAL OPTIMIZATION, 2019, 37 (04) :1237-1248
[9]   Short-term prediction of lane-level traffic speeds: A fusion deep learning model [J].
Gu, Yuanli ;
Lu, Wenqi ;
Qin, Lingqiao ;
Li, Meng ;
Shao, Zhuangzhuang .
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2019, 106 :1-16
[10]   Forecasting urban traffic flow by SVR with continuous ACO [J].
Hong, Wei-Chiang ;
Dong, Yucheng ;
Zheng, Feifeng ;
Lai, Chien-Yuan .
APPLIED MATHEMATICAL MODELLING, 2011, 35 (03) :1282-1291