Urban rail transit passenger flow forecast based on LSTM with enhanced long‐term features

Yang, Dan; Chen, Kairun; Yang, Mengning; Zhao, Xiaochao

doi:10.1049/iet-its.2018.5511

Cited by 81 publications

(47 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, some achievements have been made in the prediction of passenger flow and traffic congestion by using the deep learning method. Yang et al [11] proposed an improved long-term feature model based on long-term short-term memory (ELF-LSTM) neural network. It makes full use of the advantages of the long short-term memory (LSTM) neural network model in processing time series and overcomes the limitation that it cannot fully learn long-term time dependence due to time lag.…”

Section: Related Workmentioning

confidence: 99%

A Deep Learning Model with Conv-LSTM Networks for Subway Passenger Congestion Delay Prediction

Chen

Liu

et al. 2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

When urban rail transit is faced with a large number of commuter passengers during peak periods, passengers are often waiting for the next train because the subway is running at full load, which causes delays to the overall travel time of passengers. The calculation and prediction of the congestion delay in subway stations can guide the operation department and passengers to make better planning and selection. In this paper, we use a new method based on deep learning technology to evaluate the congestion delay of subway stations. Firstly, we use automatic fare collection (AFC) system data to evaluate the congestion delays of stations. Then, we use a convolutional long short-term memory (Conv-LSTM) network to extract spatial and temporal characteristics to solve the short-term prediction problem of the subway congestion delay in the network structure. The spatiotemporal variables include inbound passenger flow, outbound passenger flow, number of passengers delayed, and average delay time. As a spatiotemporal sequence, the input and prediction targets are both spatiotemporal three-dimensional tensors in the end-to-end training model. The effectiveness of the method is verified by a case study of the Chongqing Rail Transit. Experimental results show that Conv-LSTM is better than the benchmark models in capturing spatial and temporal correlation.

show abstract

Section: Related Workmentioning

confidence: 99%

A Deep Learning Model with Conv-LSTM Networks for Subway Passenger Congestion Delay Prediction

Chen

Liu

et al. 2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…Different hidden units can affect prediction accuracy, and in order to choose the best value, it was necessary to search and compare the different units. Firstly, we tested the hidden units from [5,10,15,30,50,100] with LSTM and GRU. The findings indicate that the best results occur for a unit of 5, no matter whether LSTM or GRU is used.…”

Section: ⅳ Datamentioning

confidence: 99%

Truck Traffic Flow Prediction Based on LSTM and GRU Methods With Sampled GPS Data

et al. 2020

View full text Add to dashboard Cite

“…Specifically, the long short-term memory (LSTM) neural network (NN), a popular variant of RNN [ 12 ], will be used. The LSTM-based prediction model has been successfully employed in several cases of time series prediction when considering historical information, such as short wind speed [ 13 ], sea surface temperature [ 14 ], soil moisture [ 15 ], animal behavior pattern [ 16 ], traffic speed [ 17 , 18 ], travel time [ 19 ], and rail transit passenger flow [ 20 ], showing outstanding results. Recently, Yang et al [ 21 ] presented the LSTM network to predict the periodic landslide displacement, which was found to properly model the dynamic characteristics of landslides than static models and make full use of the historical information.…”

Section: Introductionmentioning

confidence: 99%

Predicting Slurry Pressure Balance with a Long Short‐Term Memory Recurrent Neural Network in Difficult Ground Condition

Wang

Xie

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The safety of tunneling with shield tunnel boring machines largely depends on the tunnel face pressure, which is currently decided by human operators empirically. Face pressure control is vulnerable to human misjudgment and human errors can cause severe consequences, especially in difficult ground conditions. From a practical perspective, it is therefore beneficial to have a model capable of predicting the tunnel face pressure given operation and the changing geology. In this paper, we propose such a model based on deep learning. More specifically, a long short-term memory (LSTM) recurrent neural network is employed for tunnel face pressure prediction. To correlate with PLC data, linear interpolation is employed to transform the borehole geological data into sequential geological data according to the shield machine position. The slurry pressure in the excavation chamber (SPE) is taken as the output in the case study of Nanning Metro, which is confronted with the clogging problem due to the mixed ground of mudstone and round gravel. The LSTM-based SPE prediction model achieved an overall MAPE and RMSE of 3.83% and 10.3 kPa, respectively, in mudstone rich ground conditions. Factors that influence the model, including different kinds and length of input data and comparison with the traditional machine learning-based model, are also discussed.

show abstract

Urban rail transit passenger flow forecast based on LSTM with enhanced long‐term features

Cited by 81 publications

References 37 publications

A Deep Learning Model with Conv-LSTM Networks for Subway Passenger Congestion Delay Prediction

A Deep Learning Model with Conv-LSTM Networks for Subway Passenger Congestion Delay Prediction

Truck Traffic Flow Prediction Based on LSTM and GRU Methods With Sampled GPS Data

Predicting Slurry Pressure Balance with a Long Short‐Term Memory Recurrent Neural Network in Difficult Ground Condition

Contact Info

Product

Resources

About