Short-Term Prediction of Bus Passenger Flow Based on a Hybrid Optimized LSTM Network

doi:10.3390/ijgi8090366

IOCAS-IR > 海洋环流与波动重点实验室

	Short-Term Prediction of Bus Passenger Flow Based on a Hybrid Optimized LSTM Network
	Han, Yong 1,2; Wang, Cheng 1,2; Ren, Yibin 3,4; Wang, Shukang 5; Zheng, Huangcheng 6; Chen, Ge 1,2
	2019-09-01
发表期刊	ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
卷号	8 期号:9 页码:24
通讯作者	Ren, Yibin(yibinren@qdio.ac.cn)
摘要	The accurate prediction of bus passenger flow is the key to public transport management and the smart city. A long short-term memory network, a deep learning method for modeling sequences, is an efficient way to capture the time dependency of passenger flow. In recent years, an increasing number of researchers have sought to apply the LSTM model to passenger flow prediction. However, few of them pay attention to the optimization procedure during model training. In this article, we propose a hybrid, optimized LSTM network based on Nesterov accelerated adaptive moment estimation (Nadam) and the stochastic gradient descent algorithm (SGD). This method trains the model with high efficiency and accuracy, solving the problems of inefficient training and misconvergence that exist in complex models. We employ a hybrid optimized LSTM network to predict the actual passenger flow in Qingdao, China and compare the prediction results with those obtained by non-hybrid LSTM models and conventional methods. In particular, the proposed model brings about a 4%-20% extra performance improvements compared with those of non-hybrid LSTM models. We have also tried combinations of other optimization algorithms and applications in different models, finding that optimizing LSTM by switching Nadam to SGD is the best choice. The sensitivity of the model to its parameters is also explored, which provides guidance for applying this model to bus passenger flow data modelling. The good performance of the proposed model in different temporal and spatial scales shows that it is more robust and effective, which can provide insightful support and guidance for dynamic bus scheduling and regional coordination scheduling.
关键词	passenger flow short-term prediction long short-term memory network hybrid optimization algorithm
DOI	10.3390/ijgi8090366
收录类别	SCI
语种	英语
资助项目	Science and Technology Project of Qingdao[16-6-2-61-NSH] ; Science and Technology Project of Qingdao[16-6-2-61-NSH]
WOS研究方向	Physical Geography ; Remote Sensing
WOS类目	Geography, Physical ; Remote Sensing
WOS记录号	WOS:000488826400023
出版者	MDPI
引用统计	被引频次：28[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.qdio.ac.cn/handle/337002/163441
专题	海洋环流与波动重点实验室
通讯作者	Ren, Yibin
作者单位	1.Ocean Univ China, Coll Informat Sci & Engn, 238 Songling Rd, Qingdao 266100, Shandong, Peoples R China 2.Qingdao Natl Lab Marine Sci & Technol, Lab Reg Oceanog & Numer Modeling, Qingdao 266237, Shandong, Peoples R China 3.Chinese Acad Sci, Ctr Ocean Mega Sci, Inst Oceanol, CAS Key Lab Ocean Circulat & Waves, 7 Nanhai Rd, Qingdao 266071, Shandong, Peoples R China 4.Qingdao Natl Lab Marine, Pilot Natl Lab Marine Sci & Technol, 1 Wenhai Rd, Qingdao 266237, Shandong, Peoples R China 5.Qingdao Surveying & Mapping Inst, 189 Shandong Rd, Qingdao 266000, Shandong, Peoples R China 6.Ant Financial Serv Grp, Z Space 556 Xixi Rd, Hangzhou 310000, Zhejiang, Peoples R China
通讯作者单位	中国科学院海洋研究所
推荐引用方式 GB/T 7714	Han, Yong,Wang, Cheng,Ren, Yibin,et al. Short-Term Prediction of Bus Passenger Flow Based on a Hybrid Optimized LSTM Network[J]. ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION,2019,8(9):24.
APA	Han, Yong,Wang, Cheng,Ren, Yibin,Wang, Shukang,Zheng, Huangcheng,&Chen, Ge.(2019).Short-Term Prediction of Bus Passenger Flow Based on a Hybrid Optimized LSTM Network.ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION,8(9),24.
MLA	Han, Yong,et al."Short-Term Prediction of Bus Passenger Flow Based on a Hybrid Optimized LSTM Network".ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION 8.9(2019):24.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Han-2019-Short-term-（9994KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	浏览
Short-Term Predictio（9994KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	浏览