Predicting Station-Level Short-Term Passenger Flow in a Citywide Metro Network Using Spatiotemporal Graph Convolutional Neural Networks

Han, Yong; Wang, Shukang; Ren, Yibin; Wang, Cheng; Gao, Peng; Chen, Ge

doi:10.3390/ijgi8060243

Cited by 86 publications

(42 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intelligent and scientific analysis together with vivid visual expression are regarded as an important way to enhance respondents' perception of tourism flow information and knowledge. At present, the research on visualizing tourism big data is mainly based on existing GIS analysis methods [44][45][46], and few new methods that fully consider the characteristics of tourism flow have been proposed.…”

Section: Introductionmentioning

confidence: 99%

Regionalization Analysis and Mapping for the Source and Sink of Tourist Flows

Zhang

Chen

et al. 2019

IJGI

View full text Add to dashboard Cite

At present, population mobility for the purpose of tourism has become a popular phenomenon. As it becomes easier to capture big data on the tourist digital footprint, it is possible to analyze the respective regional features and driving forces for both tourism sources and destination regions at a macro level. Based on the data of tourist flows to Nanjing on five short-period national holidays in China, this study first calculated the travel rate of tourist source regions (315 cities) and the geographical concentration index of the visited attractions (51 scenic spots). Then, the spatial autocorrelation metrics index was used to analyze the global autocorrelation of the travel rates of tourist source regions and the geographical concentration index of the tourist destinations on five short-term national holidays. Finally, a heuristic unsupervised machine-learning method was used to analyze and map tourist sources and visited attractions by adopting the travel rate and the geographical concentration index accordingly as regionalized variables. The results indicate that both source and sink regions expressed distinctive regional differentiation patterns in the corresponding regional variables. This study method provides a practical tool for analyzing regionalization of big data in tourist flows, and it can also be applied to other origin-destination (OD) studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Regionalization Analysis and Mapping for the Source and Sink of Tourist Flows

Zhang

Chen

et al. 2019

IJGI

View full text Add to dashboard Cite

show abstract

“…To find the best learning rate scheduler for the model, another two experiments are conducted. We experiment with step decay and exponential decay, whose roles are defined as in Equations (15) and 16 (15) where lrstep_decay represents the learning rate of step decay, intial_lr represents the initial learning rate, drop is the parameter we need to adjust, epoch represents the number of epochs in the training process, and epoch_drop represents how many epochs we update lrstep_decay (here we use epochs_drop = 10).…”

Section: Choice Of Learning Rate Schedulermentioning

confidence: 99%

Section: Choice Of Learning Rate Schedulermentioning

confidence: 99%

“…A typical DL model can accept input data in raw format and automatically discover the required features level by level, which greatly simplifies feature engineering. With the DL-based model, there was a clear improvement of traffic prediction [12][13][14][15]. The LSTM [16] is a special kind of deep recurrent neuron network (RNN), which dynamically feeds the output of the previous step back into the input layer of the current step in sequence.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Han

Wang

Ren

et al. 2019

IJGI

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…Moreover, they have faster training speed and fewer parameters than RNN and CNN-based models. Some models considered recent, daily, and weekly patterns during the graph convolutional process [6,16,17]. Recent studies constructed multi-graph networks to capture several kinds of adjacent information, such as proximity, connectivity, and functionality, to improve precision [18,19].…”

Section: Introductionmentioning

confidence: 99%

Cluster-Based LSTM Network for Short-Term Passenger Flow Forecasting in Urban Rail Transit

2019

View full text Add to dashboard Cite

Short-term passenger flow forecasting is a crucial task in the operation of urban rail transit. Emerging deeplearning technologies have become effective methods to overcome this problem. In this study, we propose a deep-learning architecture called Conv-GCN combining graph convolutional network (GCN) and 3D convolutional neural network (3D CNN). First, we introduce a multi-graph GCN to deal with three patterns (recent, daily, and weekly patterns) of inflow and outflow separately. Multi-graph GCN network can capture spatiotemporal correlations and topological information in a whole network. Then, a 3D CNN is applied to deeply integrate the inflow and outflow information. High-level spatiotemporal features between different patterns of inflow and outflow, and between stations nearby and far away can be extracted by 3D CNN. Finally, a fully connected layer is used to output results. The Conv-GCN model is evaluated on smart card data of Beijing subway under the time interval of 10 min, 15 min, and 30 min. Results show that this model performs the best among seven other relative models. In terms of the RMSE, the performances under three time intervals have been improved by 9.402%, 7.756%, and 9.256%, respectively. This study can provide critical insights for subway operators to optimize the operation.

show abstract

Predicting Station-Level Short-Term Passenger Flow in a Citywide Metro Network Using Spatiotemporal Graph Convolutional Neural Networks

Cited by 86 publications

References 30 publications

Regionalization Analysis and Mapping for the Source and Sink of Tourist Flows

Regionalization Analysis and Mapping for the Source and Sink of Tourist Flows

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

Cluster-Based LSTM Network for Short-Term Passenger Flow Forecasting in Urban Rail Transit

Contact Info

Product

Resources

About