Search Results (55)

Accurate bus passenger flow prediction is a critical prerequisite for optimizing resource allocation in intelligent bus systems and improving public transport service quality. However, due to dynamic fluctuations in passenger travel demand and the complex topological structure of bus networks, effectively capturing the inherent spatiotemporal dependencies of passenger flow remains a significant challenge. To address this issue, this paper proposes GAT-Informer, a hybrid deep learning model for short-term bus passenger flow prediction. Unlike conventional methods that mainly rely on fixed physical adjacency or single-view spatial correlations, the proposed model incorporates domain knowledge into graph construction through a four-dimensional associated-node mechanism. Specifically, four types of features, namely line connectivity, spatial proximity, OD correlation, and station functional similarity, are used to identify relevant associated nodes and construct a passenger flow interaction spatiotemporal graph that better reflects inter-station dependencies. Based on this graph, a Graph Attention Network (GAT) is introduced to adaptively learn spatial interaction features and differentiated influence weights among associated stations. The spatially enhanced features extracted by GAT are then fed into the Informer network, where probabilistic sparse self-attention and hierarchical timestamp encoding are employed to efficiently capture long-term temporal dependencies and periodic fluctuation patterns of passenger flow. Experimental results based on bus passenger flow data from Foshan City show that the proposed GAT-Informer model significantly outperforms benchmark models, including LSTM-Transformer, CNN-GRU, and STGCN, across different prediction horizons, validating its effectiveness and improved predictive performance in bus passenger flow prediction. Full article

Accurate short-term metro passenger flow forecasting plays a key role in urban transit management, supporting train scheduling, crowd control, and operational planning. Jointly modeling station-level inflow/outflow (IO) and inter-station origin–destination flows (OD/DO) has proven effective for improving prediction accuracy, as it allows the model to leverage dependencies across different flow granularities. However, effectively exploiting such dependencies remains nontrivial. Station-level intensity (IO) and inter-station migration patterns (OD/DO) differ substantially in both representation and dynamics, and the dependencies between them are inherently directional and uneven. As a result, commonly used parameter-sharing mechanisms in multi-task learning are often insufficient to capture informative cross-task interactions. To address this issue, we propose CATI (Cross-Attention-based Task Interaction), a unified framework for joint multi-granular metro flow forecasting. CATI first learns task-specific spatiotemporal representations for IO, OD, and DO flows, and then introduces directed cross-attention with Gated Residual Fusion to model selective and asymmetric interactions across tasks. In addition, an aggregation-consistency regularization is employed to maintain structural coherence between station-level and inter-station predictions. Experiments on real-world metro datasets from Hangzhou and Shanghai show that CATI consistently outperforms strong baselines across multiple prediction horizons and tasks. Further analysis indicates that the model learns adaptive attention patterns, task-dependent gating behaviors, and controlled interaction strengths, which together explain its improved performance. These results suggest that explicitly modeling asymmetric cross-task interactions is important for multi-granular spatiotemporal forecasting in metro systems. Full article

As a vital part of urban public transportation system, subway passenger flow prediction plays a crucial role in alleviating traffic congestion, improving transportation infrastructure, and optimizing travel experience. Existing subway passenger flow prediction mainly focuses on short-term predictions of inbound/outbound passenger flow and origin-destination (O-D) demand. Subway section passenger flow prediction can provide a more direct reflection of passenger fluctuations across different line segments, and offer robust support for management and resource allocation. We propose a subway section passenger flow generation model and a prediction method based on LTiT (LSTM-TSSA-iTransformer). This model is based on the overall architecture of the iTransformer encoder, and an LSTM (Long Short-Term Memory) network is employed to capture the temporal characteristics of subway section passenger flow. This is combined with the TSSA (Token Statistics Self-Attention) to adaptively weight the information at key time points. Efficient performance of the model was evaluated by comparing its predictions with other models, including SARIMA (Seasonal Auto-Regressive integrated moving average), BP neural networks, LightGBM (Light Gradient Boosting Machine) and LSTM (Long Short-Term Memory). Experimental results show that the proposed model outperforms traditional baseline models in evaluation metrics such as R², MAE, MSE, and MAPE. Finally, we further investigate the selection of input window length and prediction step size, and perform robustness analysis under different noise conditions. Full article

Against the backdrop of smart cities and digital cultural tourism, the accurate prediction of urban passenger flow is of great significance for public security management and resource allocation. However, existing studies mostly rely on single data sources or only perform a simple concatenation of multi-source features, lacking systematic indicator system design. Meanwhile, weekly or monthly data are commonly used with coarse temporal granularity, making it difficult to capture short-term fluctuations and lag effects. To overcome these limitations, this paper collects the daily passenger flow data of Hangzhou from 15 March 2024 to 15 March 2025; integrates multi-dimensional factors such as keyword search trends across platforms, holidays and major events, and online public opinion; and constructs three daily characteristic indicators: online search index, humanistic–meteorological index, and textual sentiment index. The data denoising, dimensionality reduction, and sentiment quantification are realized through methods including SSA, PCA, and SnowNLP. On this basis, a hybrid CNN-GRU model integrated with the attention mechanism is proposed. An improved artificial bee colony (ABC) algorithm is adopted for global hyperparameter optimization, and a weighted hybrid loss function (JQHL) is introduced to enhance the model’s adaptability to extreme values. The results show that the ABC-CNN-GRU-Attention model, incorporating multi-dimensional indicators, outperforms traditional methods on evaluation metrics, including MAE, RMSE, MAPE, R², and RPD, demonstrating a higher prediction accuracy and robustness. Full article

With the acceleration of urbanization, public transit systems face prominent challenges, including insufficient passenger flow prediction accuracy and low scheduling efficiency. This study analyzes passenger flow variation patterns from both spatial and temporal dimensions, constructs spatiotemporal matrices, and employs matrix dimensionality reduction methods to extract key features. We propose a passenger flow prediction model based on GCN-AM-LSTM and a dynamic real-time intelligent scheduling strategy. For passenger flow prediction, the model first utilizes Graph Convolutional Networks (GCNs) to extract spatial features of the transit network, then employs Attention Mechanism-enhanced Long Short-Term Memory networks (AM-LSTM) to perform weighted extraction of temporal features, and finally integrates external factors such as weather conditions to generate prediction outputs. For scheduling optimization, a dynamic real-time scheduling mode is adopted: the foundational framework optimizes dynamic departure timetables using a multi-objective particle swarm optimization algorithm, which is then combined with real-time passenger flow data to adjust departure intervals at the route level and implement stop-skipping strategies at the station level. Validation was conducted using Xiamen BRT Line 1 as a case study. Experimental results demonstrate that the proposed GCN-AM-LSTM prediction model reduces Mean Absolute Error (MAE) by 14% and 22% compared to CNN and LSTM models, respectively, achieving significantly improved prediction accuracy. Regarding scheduling optimization, the number of departures decreased by 15.24%, passenger waiting time costs were reduced by 3.7%, and transit operating costs decreased by 3.19%, effectively balancing service quality and operational efficiency. Full article

Against the backdrop of China’s “dual-carbon” goals, accurate analysis and prediction of subway passenger flows are crucial for optimizing operational efficiency and advancing low-carbon urban transportation. Beijing’s subway network exhibits pronounced spatiotemporal heterogeneity across workdays, weekends, and holidays, yet existing studies often rely on static networks or single-scale temporal analyses, failing to capture dynamic flow evolution. To address this gap, this study develops a dynamic time-varying network framework with a 15 min temporal granularity, integrating sliding time-window analysis, node strength evaluation, and betweenness centrality for bottleneck identification. A Temporal–Spatial Fusion Gated Recurrent Unit (TSF-GRU) model is proposed to fuse temporal dependencies, spatial correlations, and network topology for short-term passenger flow forecasting. Results show distinct flow patterns: workdays feature a “concentrated commuting” dual peak, holidays a “steady continuous” leisure pattern, and weekends an “extended flexible” hybrid pattern. Station functions and bottleneck evolution vary dynamically across date types, with transportation hubs central on holidays/weekends and business nodes dominating workday peaks. The TSF-GRU model achieves a test-set MAPE of 7.62% and bottleneck prediction accuracy of 92.3%, outperforming traditional methods. This study provides a feasible pathway for refined, low-carbon subway operations in megacities and methodological support for achieving dual-carbon goals. Full article

Urban rail transit networks in developing countries are rapidly expanding, entering a networked operational phase where accurate passenger flow forecasting is crucial for optimizing vehicle scheduling, resource allocation, and transportation efficiency. In the short term, accurate real-time forecasting enables the dynamic adjustment of train headways and crew deployment, reducing average passenger waiting times during peak hours and alleviating platform overcrowding; in the long term, reliable trend predictions support strategic planning, including capacity expansion, station retrofitting, and energy management. This paper proposes a novel hybrid forecasting model, EEMD-TiDE, that combines improved Ensemble Empirical Mode Decomposition (EEMD) with a Time Series Dense Encoder (TiDE) to enhance prediction accuracy. The EEMD algorithm effectively overcomes mode mixing issues in traditional EMD by incorporating white noise perturbations, decomposing raw passenger flow data into physically meaningful Intrinsic Mode Functions (IMFs). At the same time, the TiDE model, a linear encoder–decoder architecture, efficiently handles multi-scale features and covariates without the computational overhead of self-attention mechanisms. Experimental results using Xi’an Metro passenger flow data (2017–2019) demonstrate that EEMD-TiDE significantly outperforms baseline models. This study provides a robust solution for urban rail transit passenger flow forecasting, supporting sustainable urban development. Full article

Short-term passenger flow prediction provides critical data-driven support for optimizing resource allocation, guiding passenger mobility, and enhancing risk response capabilities in urban rail transit systems. To further improve prediction accuracy, this study proposes a hybrid SMA-VMD-Informer-BiLSTM prediction model. Addressing the challenge of error propagation caused by non-stationary components (e.g., noise and abrupt fluctuations) in conventional passenger flow signals, the Variational Mode Decomposition (VMD) method is introduced to decompose raw flow data into multiple intrinsic mode functions (IMFs). A Slime Mould Algorithm (SMA)-based optimization mechanism is designed to adaptively tune VMD parameters, effectively mitigating mode redundancy and information loss. Furthermore, to circumvent error accumulation inherent in serial modeling frameworks, a parallel prediction architecture is developed: the Informer branch captures long-term dependencies through its ProbSparse self-attention mechanism, while the Bidirectional Long Short-Term Memory (BiLSTM) network extracts localized short-term temporal patterns. The outputs of both branches are fused via a fully connected layer, balancing global trend adherence and local fluctuation characterization. Experimental validation using historical entry flow data from Weihouzhuang Station on Xi’an Metro demonstrated the superior performance of the SMA-VMD-Informer-BiLSTM model. Compared to benchmark models (CNN-BiLSTM, CNN-BiGRU, Transformer-LSTM, ARIMA-LSTM), the proposed model achieved reductions of 7.14–53.33% in $f_{mse}$, 3.81–31.14% in $f_{rmse}$, and 8.87–38.08% in $f_{mae}$, alongside a 4.11–5.48% improvement in $R^2$. Cross-station validation across multiple Xi’an Metro hubs further confirmed robust spatial generalizability, with prediction errors bounded within $f_{mse}$: 0.0009–0.01, $f_{rmse}$: 0.0303–0.1, $f_{mae}$: 0.0196–0.0697, and $R^2$: 0.9011–0.9971. Furthermore, the model demonstrated favorable predictive performance when applied to forecasting passenger inflows at multiple stations in Nanjing and Zhengzhou, showcasing its excellent spatial transferability. By integrating multi-level, multi-scale data processing and adaptive feature extraction mechanisms, the proposed model significantly mitigates error accumulation observed in traditional approaches. These findings collectively indicate its potential as a scientific foundation for refined operational decision-making in urban rail transit management, thereby significantly promoting the sustainable development and long-term stable operation of urban rail transit systems. Full article

In this study, a Long Short-Term Memory (LSTM) model with extra variables such as weather conditions and school days was developed within a multi-scale framework in order to forecast passenger flow in both bus and rail systems, covering both regional and route-level analyses. In addition, the performance of the LSTM model was compared against three separate deep learning models. Among these, the Nonlinear Autoregressive Network with Exogenous Inputs (NARX) time series model produced the lowest error values, achieving a high level of accuracy. While no considerable changes were observed in regional rail passenger flow as a result of the inclusion of weather-related variables, a 2.2% drop in the RMSE value was achieved in bus passenger flow at the regional level; however, this improvement remains relatively modest. In contrast, at the route level, RMSE values declined by 2.4% for rail and 3.69% for bus routes. These findings reveal that the inclusion of weather-related variables significantly improves the prediction of bus passenger flow, underlining the benefits of integrating such data into forecasting models. Furthermore, the findings of this study analytically support transportation planners in making more informed, data-driven decisions regarding scheduling and capacity management. Full article

Aiming at the robustness problem of the extreme learning machine (ELM) in noisy and nonuniform data scenarios, this paper proposes an improved algorithm (BFGS-URWELM) that integrates uniform residual weighting and Broyden–Fletcher–Goldfarb–Shanno (BFGS) quasi-Newton optimization. This method introduces a sample weighting mechanism based on the target residual variance, dynamically adjusts the importance of training samples, and iteratively corrects the input weights and biases of the ELM in combination with the BFGS optimization strategy, effectively improving the prediction accuracy and stability of the model. The experiment is based on the passenger flow data of 80 subway stations and compares traditional machine learning algorithms, ensemble learning methods, and ELM variant models. The results show that BFGS-URWELM achieves 28.34, 0.3071, and 19.76 in the RMSE, MAPE, and MAE indicators, respectively, which are 19.9–33.5% higher than the baseline ELM. In addition, the residual distribution is more concentrated near the zero value, and the goodness of fit $R^2$ is improved to 0.96. The algorithm significantly reduces the prediction error under high-noise data and provides a highly robust solution for traffic flow prediction tasks. Full article

This study proposes a methodology that integrates real-time data and predictive modeling to identify the passenger flow and occupancy levels within a multimodal transport hub. This tool enables the implementation of control and planning strategies to ensure a high Level of Service (LOS). The tool is based on a Long Short-Term Memory (LSTM) model and heterogeneous data sources, including an Automatic Passenger Counting (APC) system, which are utilized to estimate the real-time passenger flow and area occupancy. The Module A of the Moncloa Interchange in Madrid is the case study, and the results reveal that transport-dedicated zones have higher occupancy levels. Methodologically, time series data were standardized to a uniform frequency to ensure consistency, and the training set consisted of seven months of available data. The model performs better in high-occupancy zones. Despite maintaining a LOS A, some periods experience temporary congestion. These findings indicate that the variations in occupancy levels influence the service quality and highlight the essential role of dynamic interchange management. Tailored operational strategies can optimize the service levels and improve the user experience by anticipating congestion through predictive modeling. This can help enhance public transport’s attractiveness, minimize the perceived transfer penalties, make transfers more efficient, and reinforce transport hubs’ role in sustainable urban mobility. Full article

Traditional station passenger flow prediction can no longer meet the application needs of urban rail transit vehicle scheduling. Station passenger flow can only predict station distribution, and the passenger flow distribution in general sections is unknown. Accurate short-term travel origin and destination (OD) passenger flow prediction is the main basis for formulating urban rail transit operation organization plans. To simultaneously consider the spatiotemporal characteristics of passenger flow distribution and achieve high precision estimation of origin and destination (OD) passenger flow quickly, a predictive model based on a temporal convolutional network and a long short-term memory network (TCN–LSTM) combined with an attention mechanism was established to process passenger flow data in urban rail transit. Firstly, according to the passenger flow data of the urban rail transit section, the existing data characteristics were summarized, and the impact of external factors on section passenger flow was studied. Then, a temporal convolutional network and long short-term memory (TCN–LSTM) deep learning model based on an attention mechanism was constructed to predict interval passenger flow. The model combines some external factors such as time, date attributes, weather conditions, and air quality that affect passenger flow in the interval to improve the shortcomings of the original model in predicting origin and destination (OD) passenger flow. Taking Chongqing Rail Transit as an example, the model was validated, and the results showed that the deep learning model had significantly better prediction results than other baseline models. The applicability analysis in scenarios such as high/medium/low passenger flow could achieve stable prediction results. Full article

Accurate prediction of station passenger flow is crucial for optimizing rail transit efficiency, but peak passenger flow in urban rail transit (URT) is often disrupted by random events, making predictions challenging. In this paper, in order to solve this challenge, the Bi-graph Graph Convolutional Spatio-Temporal Feature Fusion Network (BGCSTFFN)-based model is introduced to capture complex spatio-temporal correlations. A combination of a graph convolutional neural network and a Transformer is used. The model separately inputs land use (point of interest, POI) and station adjacency information as features into the BGCSTFFN model, using the Pearson correlation coefficient matrix, which is evaluated on real passenger flow dataset from 1 to 25 January 2019 in Hangzhou. The results showed that the model consistently provided the best prediction results across different datasets and prediction tasks compared to other baseline models. In addition, in tasks involving predictions with different combinations of inputs and prediction steps, the model showed superior performance at multiple prediction steps. Its practical application is validated by comparing the results of passenger flow prediction for different types of stations. In addition, the impact of these features on the prediction accuracy and the generalization ability of the model were verified by designing ablation experiments and testing on different datasets. Full article

The purpose of this paper is to optimize the accuracy of airport express passenger flow prediction so as to meet the need for the optimal allocation of traffic resources against the background of accelerated urbanization and the rapid development of airport express services. A fusion intelligence network model (FINM) is proposed, which integrates the advantages of convolutional neural networks, bidirectional long short-term memory networks, and gated recurrent units. Firstly, by using the powerful feature extraction ability of convolutional neural networks, local features and detail information are captured from the input data to improve the data representation ability. Secondly, bidirectional long short-term memory networks are used to process the sequence data, capture the global information and its context relationship, and enhance the model’s understanding of the dependence of time series data. Finally, gated recurrent units are introduced to simplify the computational complexity while maintaining high prediction accuracy and training efficiency. Based on the actual passenger flow data for Tianjin Metro Line 2 on a 30 min time scale, the proposed FINM is verified. The experimental results show that the model achieves an excellent performance, with 0.0160, 0.0947, 0.0160, 0.1255, 18.40, and 0.7788 in key indicators such as loss value (Loss Value), mean absolute error (MAE), mean squared error (MSE), root mean square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination (R-Squared). Compared with the comparison algorithm, this model shows significant advantages in all indicators, which proves its effectiveness in dealing with complex time series data. Full article

In high-speed railway systems, the management of security resources at high-speed train stations is crucial for ensuring passenger safety and improving service efficiency. Effective security resource management enables the quick and efficient handling of large volumes of passengers, reduces queuing times, and ensures that safety measures are strictly enforced. However, current management practices often rely on a fixed-shift system, which lacks a dynamic correlation between the number of open security lanes and real-time passenger flow. This mismatch leads to resource shortages during peak times and resource wastage during off-peak periods. To address these challenges, this study introduces the Multi-Head Attention Long Short-Term Memory Network and Model Predictive Control (MHALSTM-MPC) model to improve security resource management at high-speed railway stations. The MHALSTM component predicts passenger flow by capturing trends and patterns, while the MPC component formulates an optimization problem that minimizes waiting times and operational costs by repeatedly solving it within a finite time horizon based on predicted passenger flow. This approach ensures real-time adjustments to security checkpoint configurations and staff allocation, achieving optimal resource utilization in response to forecasted demand. Experimental results based on real passenger flow data from Z City East Station demonstrate that the MHALSTM-MPC model reduces the average waiting time per passenger by 18.79% compared to the fixed-shift model and by 13.59% compared to the static scheduling model. Additionally, it achieves a 4.82% reduction in total human-hours compared to the fixed-shift model and a 2.65% reduction compared to the static scheduling model, highlighting its effectiveness in optimizing resource allocation and improving operational efficiency. Full article