ST-former for short-term passenger flow prediction during COVID-19 in urban rail transit system

Accurate passenger flow prediction of urban rail transit is essential for improving the performance of intelligent transportation systems, especially during the epidemic. How to dynamically model the complex spatiotemporal dependencies of passenger flow is the main issue in achieving accurate passenger flow prediction during the epidemic. To solve this issue, this paper proposes a brand-new transformer-based architecture called STformer under the encoder-decoder framework specifically for COVID-19. Concretely, we develop a modified self-attention mechanism named Causal-Convolution ProbSparse Self-Attention (CPSA) to model the multiple temporal dependencies of passenger flow with low computational costs. To capture the complex and dynamic spatial dependencies, we introduce a novel Adaptive Multi-Graph Convolution Network (AMGCN) by leveraging multiple graphs in a self-adaptive manner. Additionally, the Multi-source Data Fusion block fuses the passenger flow data, COVID-19 confirmed case data, and the relevant social media data to study the impact of COVID-19 to passenger flow. Experiments on real-world passenger flow datasets demonstrate the superiority of ST-former over the other eleven state-of-the-art methods. Several ablation studies are carried out to verify the effectiveness and reliability of our model structure. Results can provide critical insights for the operation of URT systems.

Meta-learning Based Short-Term Passenger Flow Prediction for Newly-Operated Urban Rail Transit Stations

Accurate short-term passenger flow prediction in urban rail transit stations has great benefits for reasonably allocating resources, easing congestion, and reducing operational risks. However, compared with data-rich stations, the passenger flow prediction in newly-operated stations is limited by passenger flow data volume, which would reduce the prediction accuracy and increase the difficulty for station management and operation. Hence, how accurately predicting passenger flow in newly-operated stations with limited data is an urgent problem to be solved. Existing passenger flow prediction approaches generally depend on sufficient data, which might be unsuitable for newly-operated stations. Therefore, we propose a meta-learning method named Meta Long Short-Term Memory Network (Meta-LSTM) to predict the passenger flow in newly-operated stations. The Meta-LSTM is to construct a framework that increases the generalization ability of long short-term memory network (LSTM) to various passenger flow characteristics by learning passenger flow characteristics from multiple data-rich stations and then applying the learned parameter to data-scarce stations by parameter initialization. The Meta-LSTM is applied to the subway network of Nanning, Hangzhou, and Beijing, China. The experiments on three real-world subway networks demonstrate the effectiveness of our proposed Meta-LSTM over several competitive baseline models. Results also show that our proposed Meta-LSTM has a good generalization ability to various passenger flow characteristics, which can provide a reference for passenger flow prediction in the stations with limited data.

Short-term passenger flow prediction for multi-traffic modes: A residual network and Transformer based multi-task learning method

With the prevailing of mobility as a service (MaaS), it becomes increasingly important to manage multi-traffic modes simultaneously and cooperatively. As an important component of MaaS, short-term passenger flow prediction for multi-traffic modes has thus been brought into focus. It is a challenging problem because the spatiotemporal features of multi-traffic modes are critically complex. To solve the problem, this paper proposes a multi-task learning-based model, called Res-Transformer, for short-term passenger flow prediction of multi-traffic modes (subway, taxi, and bus). Each traffic mode is treated as a single task in the model. The Res-Transformer consists of three parts: (1) several modified transformer layers comprising 2D convolutional neural networks (CNN) and multi-head attention mechanism, which helps to extract the spatial and temporal features of multi-traffic modes, (2) a residual network architecture used to extract the inner pattern of different traffic modes and enhance the passenger flow features of multi-traffic modes. The Res-Transformer model is evaluated on two large-scale real-world datasets from Beijing, China. One is the region of a traffic hub and the other is the region of a residential area. Experiments are conducted to compare the performance of the proposed model with several state-of-the-art models to prove the effectiveness and robustness of the proposed method. This paper can give critical insights into the short-tern passenger flow prediction for multi-traffic modes.

GCN-Transformer for short-term passenger flow prediction on holidays in urban rail transit systems

The short-term passenger flow prediction of the urban rail transit system is of great significance for traffic operation and management. The emerging deep learning-based models provide effective methods to improve prediction accuracy. However, most of the existing models mainly predict the passenger flow on general weekdays, while few studies focus on predicting the holiday passenger flow, which can provide more significant information for operators because congestions or accidents generally occur on holidays. To this end, we propose a deep learning-based model named GCN-Transformer comprising graph conventional neural network (GCN) and Transformer for short-term passenger flow prediction on holidays. The GCN is applied to extract the spatial features of passenger flows and the Transformer is applied to extract the temporal features of passenger flows. Moreover, in addition to the historical passenger flow data, social media data are also incorporated into the prediction model, which has been proven to have a potential correlation with the fluctuation of passenger flow. The GCN-Transformer is tested on two large-scale real-world datasets from Nanning, China during the New Year holiday and is compared with several conventional prediction models. Results demonstrate its better robustness and advantages among baseline methods, which provides overwhelming support for practical applications of short-term passenger flow prediction on holidays

An end-to-end predict-then-optimize clustering method for intelligent assignment problems in express systems

Express systems play important roles in modern major cities. Couriers serving for the express system pick up packages in certain areas of interest (AOI) during a specific time. However, future pick-up requests vary significantly with time. While the assignment results are generally static without changing with time. Using the historical pick-up request number to conduct AOI assignment (or pick-up request assignment) for couriers is thus unreasonable. Moreover, even we can first predict future pick-up requests and then use the prediction results to conduct the assignments, this kind of two-stage method is also impractical and trivial, and exists some drawbacks, such as the best prediction results might not ensure the best clustering results. To solve these problems, we put forward an intelligent end-to-end predict-then-optimize clustering method to simultaneously predict the future pick-up requests of AOIs and assign AOIs to couriers by clustering. At first, we propose a deep learning-based prediction model to predict order numbers on AOIs. Then a differential constrained K-means clustering method is introduced to cluster AOIs based on the prediction results. We finally propose a one-stage end-to-end predict-then-optimize clustering method to assign AOIs to couriers reasonably, dynamically, and intelligently. Results show that this kind of one-stage predict-then-optimize method is beneficial to improve the performance of optimization results, namely the clustering results. This study can provide critical experiences for predict-and-optimize related tasks and intelligent assignment problems in express systems.

Graph-GAN: A spatial-temporal neural network for short-term passenger flow prediction in urban rail transit systems

Short-term passenger flow prediction plays an important role in better managing the urban rail transit (URT) systems. Emerging deep learning models provide good insights to improve short-term prediction accuracy. However, a large number of existing prediction models combine diverse neural network layers to improve accuracy, making their model structures extremely complex and difficult to be applied to the real world. Therefore, it is necessary to trade off between the model complexity and prediction performance from the perspective of real-world applications. To this end, we propose a deep learning-based Graph-GAN model with a simple structure and high prediction accuracy to predict short-term passenger flows of the URT network. The Graph-GAN consists of two major parts: (1) a simplified and static version of the graph convolution network (GCN) used to extract network topological information; (2) a generative adversarial network (GAN) used to predict passenger flows, with generators and discriminators in GAN just composed of simple fully connected neural networks. The Graph-GAN is tested on two large-scale real-world datasets from Beijing Subway. A comparison of the prediction performance of Graph-GAN with those of several state-of-the-art models illustrates its superiority and robustness. This study can provide critical experience in conducting short-term passenger flow predictions, especially from the perspective of real-world applications.

Network-wide link travel time and station waiting time estimation using automatic fare collection data: A computational graph approach

Urban rail transit (URT) system plays a dominating role in many megacities like Beijing and Hong Kong. Due to its important role and complex nature, it is always in great need for public agencies to better understand the performance of the URT system. This paper focuses on an essential and hard problem to estimate the network-wide link travel time and station waiting time using the automatic fare collection (AFC) data in the URT system, which is beneficial to better understand the system-wide real-time operation state. The emerging data-driven techniques, such as computational graph (CG) models in the machine learning field, provide a new solution for solving this problem. In this study, we first formulate a data-driven estimation optimization framework to estimate the link travel time and station waiting time. Then, we cast the estimation optimization model into a CG framework to solve the optimization problem and obtain the estimation results. The methodology is verified on a synthetic URT network and applied to a real-world URT network using the synthetic and real-world AFC data, respectively. Results show the robustness and effectiveness of the CG-based framework. To the best of our knowledge, this is the first time that the CG is applied to the URT. This study can provide critical insights to better understand the operational state in URT.