Related references
Note: Only part of the references are listed.
Article
Engineering, Civil
Fang Yang et al.
Summary: This paper investigates the prediction of short-term passengers' origin and destination demands. By analyzing the temporal and spatial correlations and complexity, the predictive performances of different models at different time intervals are discussed. The study finds that the spatial correlations of the OD matrix are more important than the temporal correlations and complexity, and the number of principal components of the OD flow can measure the forecasting performance of a model.
Article
Transportation
Jiangbo Wang et al.
Summary: This study empirically explores the impact of the built environment on demand-responsive transit (DRT) use through a case study of a successful DRT system in Dalian, China. The results suggest that factors such as residential population, employment density, land use composition, connectivity, and accessibility contribute to DRT use. The findings highlight the potential marketing direction for DRT systems in serving niche markets poorly served by regular transit services.
TRAVEL BEHAVIOUR AND SOCIETY
(2023)
Article
Computer Science, Artificial Intelligence
Jie Zeng et al.
Summary: This study proposes a SARGCN model for metro passenger flow prediction, which constructs a knowledge graph of the metro system and integrates travel behaviors and spatiotemporal dependencies. The model outperforms advanced baselines and is validated on metro systems in Shenzhen and Hangzhou.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Xin Wang et al.
Summary: This study proposes an end-to-end forecast hybrid architecture for metro outbound passenger flow based on deep learning and ensemble learning technology. The architecture integrates multiple passenger flow features and combines bagging ensemble learning strategy and transfer learning, achieving high forecast accuracy, timeliness, and practicality.
IET INTELLIGENT TRANSPORT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jiexia Ye et al.
Summary: This paper proposes a deep learning approach for accurate prediction of metro OD matrix by considering recent destination distribution, enhancing station representation, and exploring global spatial dependency and multiple temporal scale correlations. Results on Shenzhen and Hangzhou metro systems demonstrate the superiority of the proposed model over other competitors.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Wenhua Jiang et al.
Summary: Short-term OD flow prediction is crucial for urban railway system operations, but has received less attention compared to other passenger demand prediction problems. The paper presents a novel deep learning architecture that incorporates multiple LSTM networks with attention mechanism, temporally shifted graph matrix, and a reconstruction mechanism to handle partial OD flow observations. The model is validated using smart card data from Hong Kong's MTR system and outperforms state-of-the-art prediction models, highlighting the importance of partial observation in improving prediction accuracy and robustness.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Economics
Benjamin J. Tomhave et al.
Summary: This study proposes a new method for estimating transit route choice, which generates high-quality transit path choice sets and produces detailed temporal information. By estimating a multinomial logit model, the most likely transit path can be calculated, and it is found that express bus routes have a negative impact on low-income groups while transitways have a positive impact on high-income groups.
TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE
(2022)
Article
Transportation Science & Technology
Jacqueline Arriagada et al.
Summary: We contribute to the understanding of public transport passenger route choice behavior by developing and applying methods that capture behavioral strategies by making use of smart card data. We propose the classification of possible route choice behavioral strategies into disaggregated strategies and aggregated strategies. Through empirical analysis using indicator functions and latent class methods, we confirm the hypothesis of heterogeneity in route choice strategies among public transport passengers. Our findings indicate that heterogeneity exists between users and across contexts, with different preferences for common lines or specific itineraries. This study highlights the importance of considering individual differences in understanding and modeling route choice behavior.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2022)
Article
Operations Research & Management Science
Zhanhong Cheng et al.
Summary: This paper proposes a method for short-term OD matrix forecasting based on DMD and low-rank high-order VAR model. By reconstructing the problem as a data-driven regression model and using a tailored online update algorithm for updating model coefficients, the method shows robustness in handling noisy and sparse data and outperforms baseline models in predicting OD matrices and boarding flow.
TRANSPORTATION SCIENCE
(2022)
Article
Economics
Yang Liu et al.
Summary: Understanding the determinants of route choice behavior in a multi-modal transit network of metro and shared bike is important for improving personalized multimodal travel services. This study analyzed the route choice behavior of metro-bikeshare users, considering their socio-economic attributes and perceived congestion. The results showed that the models with load status attributes had better performance, and the sensitivity of exit-lease users to train crowding was significantly higher than that of return-enter users. Additionally, factors such as shared bike inventory, departure time, and user type also had a significant impact on route choice behavior.
TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE
(2022)
Article
Green & Sustainable Science & Technology
Yi Cao et al.
Summary: This study constructs a short-term metro passenger-flow prediction model by integrating ensemble empirical mode decomposition and long short-term memory neural network to improve the prediction accuracy. The results show that the proposed EEMD-LSTM model outperforms the traditional EMD-LSTM model in predicting metro passenger flow, demonstrating its effectiveness in sustainable urban development.
Article
Engineering, Multidisciplinary
Jun Yang et al.
Summary: Short-term Origin-Destination (OD) flow prediction is crucial for Smart Metro, improving operational safety and passenger experience. To address the challenges of high dimensionality and sparse data, a threshold-based method and spatiotemporal virtual graph convolutional network (ST-VGCN) are proposed, achieving accurate predictions.
MATHEMATICAL PROBLEMS IN ENGINEERING
(2022)
Article
Engineering, Industrial
Xin Yang et al.
Summary: Short-term prediction of passenger volume is crucial for urban rail companies, and this paper introduces an improved Spatiotemporal Long Short-Term Memory model (Sp-LSTM) based on deep learning and big data techniques. A case study on the Beijing Metro Airport Line shows that the proposed method outperforms other prediction methods.
INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS
(2021)
Article
Engineering, Civil
Loutao Shen et al.
Summary: The paper introduces a hybrid short-term forecasting approach that combines the modified gravity model and deep learning models, striking a balance between model interpretability and forecasting accuracy. Applied to short-term passenger flow forecasting in the Beijing metro system, the experimental results demonstrate that the hybrid approach outperforms benchmark models.
TRANSPORTATION RESEARCH RECORD
(2021)
Article
Engineering, Civil
Enjian Yao et al.
Summary: This study explores the differences in passenger destination choice between holidays and normal days, proposing a forecasting model for holiday passenger flow distribution using data from Guangzhou Metro. The model, calibrated using the improved WESML method, outperforms comparable models in terms of forecasting accuracy by introducing explanatory variables and considering the particularities of holiday passenger behavior.
JOURNAL OF ADVANCED TRANSPORTATION
(2021)
Article
Transportation Science & Technology
Jinlei Zhang et al.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2021)
Article
Transportation Science & Technology
Yiwen Zhu et al.
Summary: The paper presents a data-driven model, PIIM, for inferring passenger itineraries in urban heavy rail systems, which can assess the impact of near capacity operations on customers, evaluate system performance, and understand passenger behavior when choosing alternative routes. Through multiple modules, the model accurately predicts passenger itineraries, left behind probabilities, route choice fractions, and other performance metrics.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2021)
Article
Engineering, Civil
Wei Chen et al.
Summary: This paper proposes a new method based on deep learning technology to evaluate congestion delays in subway stations of urban rail transit. By using AFC data and Conv-LSTM network to extract spatial and temporal characteristics, it solves the short-term prediction problem of subway congestion delays.
JOURNAL OF ADVANCED TRANSPORTATION
(2021)
Article
Engineering, Civil
Chao Yu et al.
Summary: This paper proposes a data-driven method to identify metro passenger mobility patterns using AFC and geo-based data, including the use of POI data and stacked auto-encoder to embed trip data into low-dimensional vectors, and using density-based clustering algorithm to identify passenger mobility patterns.
JOURNAL OF ADVANCED TRANSPORTATION
(2021)
Article
Engineering, Civil
Jia Lu et al.
JOURNAL OF TRANSPORTATION ENGINEERING PART A-SYSTEMS
(2020)
Article
Engineering, Multidisciplinary
Wusheng Liu et al.
MATHEMATICAL PROBLEMS IN ENGINEERING
(2020)
Article
Engineering, Civil
Yuedi Yang et al.
JOURNAL OF ADVANCED TRANSPORTATION
(2020)
Article
Engineering, Electrical & Electronic
Zhiqiang Guo et al.
IET INTELLIGENT TRANSPORT SYSTEMS
(2019)
Article
Green & Sustainable Science & Technology
Muhammad Aqib et al.
Article
Physics, Multidisciplinary
Jianjun Wu et al.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2019)
Article
Engineering, Electrical & Electronic
Dawei Li et al.
IET INTELLIGENT TRANSPORT SYSTEMS
(2019)
Article
Computer Science, Artificial Intelligence
Bowen Du et al.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2018)
Article
Mathematics, Interdisciplinary Applications
Yong-Sheng Zhang et al.
DISCRETE DYNAMICS IN NATURE AND SOCIETY
(2015)
Article
Metallurgy & Metallurgical Engineering
Yao Xiang-ming et al.
JOURNAL OF CENTRAL SOUTH UNIVERSITY
(2015)
