Short‐term passenger flow forecasting using CEEMDAN meshed CNN‐LSTM‐attention model under wireless sensor network

Abstract

For a long time, the accurate prediction of passenger flow can provide early warning information for various industries such as the public service industry, tourism industry, and industrial business, thus opportunely arranging passengers and providing homologous services to relieve the overloading of places and the accidents caused by overcrowding of people. In recent years, by using the wireless sensor network to sense the passenger data in advance, the technique of machine learning and neural networks has been utilized to assist the short‐term passenger flow prediction. In this study, building on convolutional neural network (CNN) and long short‐term memory network (LSTM), a complete ensemble empirical mode decomposition with adaptive noise algorithm (CEEMDAN) and attention‐based CNN‐LSTM network to extract both temporal and spatial characteristics of passenger flow data, is proposed. Moreover, the problem of the inaccuracy of the noise part is properly solved by adding the CEEMDAN algorithm to the input layer. With the proposed network structure, the CNN‐LSTM network is replaced with the Conv‐LSTM network to reduce the information loss and get a further performance improvement. The result shows that 39% performance improvement can be achieved than the case with a single LSTM network, and 28% performance improvement can be achieved than the CNN‐LSTM network.

Optimal demand response programs selection using CNN‐LSTM algorithm with big data analysis of load curves

“…The CNN-LSTM Algorithm consists of the combination of two algorithms named CNN and LSTM. The CNN algorithm is a type of DL algorithm, and the LSTM algorithm is a Recurrent Neural Network (RNN) algorithm [36].…”

Short-time prediction model for cross-section passenger flow of trains in urban transit using GCN-AM-BiLSTM

“…To characterize spatial characteristics, many scholars have introduced convolutional neural networks(CNN) into the field. Wang et al [41] proposed a CNN-LSTM model based on the attention mechanism; Wang et al [42] constructed a prediction model based on convolutional LSTM with K-mean clustering algorithm; Zhao et al [43] established a hybrid model based on CNN and residual network(ResNet). However, it was found that the urban rail network presents obvious non-Euclidean properties, and CNN is mostly applicable to Euclidean data with regular spatial structure, leading to the limitation of its spatial characteristics extraction capability.…”

Prediction model of short-term passenger flow of urban rail transit trains integrating temporal and spatial features

“…Zhao 14 optimized the LSTM based on Nadam and SGD algorithm, which improved the training efficiency and convergence rate of the model. In order to fully extract the spatial-temporal features of passenger flow distribution, Wang 15 proposed a CNN-LSTM model based on attention mechanism; Wang 16 combined the convolution LSTM with the K-means clustering algorithm; and Zhao 17 constructed a hybrid model based on convolutional neural network(CNN) and Residual network(ResNet). Ma 18 constructed a two-column model based on CNN and LSTM to finely extract the spatial and temporal features of the passenger flow sequence, but the input and output of the two-column structure are relatively independent, ignoring the interaction between different features, and the prediction accuracy decreased when applied to more complex scenarios.…”