Actual Passenger Flow Research Articles

Airport Express Passenger Flow Prediction Based on “Time-Feature” Cooperative Attention

Accurate prediction of airport express passenger flow is the basis for realizing intelligent, refined and efficient management and control of the airport rail transit system, and is of great significance to improving airport service levels and operational efficiency. Due to the numerous influencing factors that overlap with each other, and the complex mechanism of factors affecting passenger flow timing, accurate prediction of airport express passenger flow is extremely challenging. This paper proposes an airport express rail passenger flow prediction model based on the "time-feature" collaborative attention mechanism, which achieves accurate capture of the impact of multi-dimensional factors on airport express rail passenger flow in different time series. Experiments were conducted based on actual passenger flow data of the Beijing Capital International Airport Express Rail Link, and the results showed the effectiveness of the proposed method.

Forecasting Smart Tourism Visitor Flows Leveraging Big Data Technology Assistance

This study aims to explore the forecasting effect of smart tourism passenger flow supported by big data technology and improve the intelligence of smart tourism. In view of the differences in tourist traffic due to different times, the tourist traffic data in Xi'an from May 1, 2020, to April 1, 2021 are used as the sample period. Autoregressive Integrated Moving Average (ARIMA) is used to build a smart model of the tourism passenger flow prediction. The predictive performance of the constructed model is evaluated and analyzed. The results show that the prediction errors of the model algorithm Root Mean Squared Error (RMSE) and Mean Squared Error (MSE) are 2.22×10^1 and 4.95×10^2, respectively, which are smaller than other algorithms. The error is compared with the actual passenger flow with the highest accuracy. Therefore, the constructed model has high prediction accuracy in predicting and analyzing smart tourism passenger flow, which can provide a reference for the later tourist management and intelligent development of scenic spots.

Evaluating rail transit assignment models in the temporal dimension: The problem and its solution

Passenger flow is the foundation for urban rail transit (URT) operations. However, its calculated results from assignment models may deviate from the actual situation in both spatial and temporal dimensions, which arouses more attention and needs to be evaluated in particular. On the other hand, onboard video data from URT trains provides a potential way for model evaluation. This study defines the evaluation problem and proposes a methodological solution for evaluating rail transit assignment models in the temporal dimension, including qualitative validation and difference quantification. A suitable time granularity is determined for the best effectiveness and onboard video data is used for actual passenger flow extraction. The gap between the actual and the calculated by the model is identified with nonparametric statistical techniques (NPSTs) and quantified with time series similarity measurement (TSSM) methods. A case study on the Shanghai metro demonstrates the performance of the proposed approach, and several practice implications for URT operation agencies are also discussed.

Front-end speech processing system with SVM algorithm in rail passenger flow management

In order to achieve the goal of dynamically adjusting daily passenger flow to effectively control the overall efficiency of the transportation system, this study constructs a real-time monitoring and prediction system for subway passenger flow based on front-end voice processing technology and support vector machine models. The study first conducted a railway passenger flow analysis, and then used a support vector machine model to construct a preliminary prediction system. In order to achieve global optimization, the study also introduced particle swarm optimization algorithm to construct an optimization prediction model based on PSO-SVM. The results show that the proposed PSO-SVM method has undergone 48 iterations of training, and the predicted values closely match the actual passenger flow curve. The maximum RE error is 2%, and the overall prediction error is 98%. The decision coefficient of PSO-SVM is 0.998932. Therefore, this indicates that it has high performance and feasibility in predicting and controlling passenger flow during peak hours of urban rail transit.

Optimizing the Three-Dimensional Multi-Objective of Feeder Bus Routes Considering the Timetable

To optimize the evacuation process of rail transit passenger flows, the influence of the feeder bus network on bus demand is pivotal. This study first examines the transportation mode preferences of rail transit station passengers and addresses the feeder bus network’s optimization challenge within a three-dimensional framework, incorporating an elastic mechanism. Consequently, a strategic planning model is developed. Subsequently, a multi-objective optimization model is constructed to simultaneously increase passenger numbers and decrease both travel time costs and bus operational expenses. Due to the NP-hard nature of this optimization problem, we introduce an enhanced non-dominated sorting genetic algorithm, INSGA-II. This algorithm integrates innovative encoding and decoding rules, adaptive parameter adjustment strategies, and a combination of crowding distance and distribution entropy mechanisms alongside an external elite archive strategy to enhance population convergence and local search capabilities. The efficacy of the proposed model and algorithm is corroborated through simulations employing standard test functions and instances. The results demonstrate that the INSGA-II algorithm closely approximates the true Pareto front, attaining Pareto optimal solutions that are uniformly distributed. Additionally, an increase in the fleet size correlates with greater passenger volumes and higher operational costs, yet it substantially lowers the average travel cost per customer. An optimal fleet size of 11 vehicles is identified. Moreover, expanding feeder bus routes enhances passenger counts by 18.03%, raises operational costs by 32.33%, and cuts passenger travel time expenses by 21.23%. These findings necessitate revisions to the bus timetable. Therefore, for a bus network with elastic demand, it is essential to holistically optimize the actual passenger flow demand, fleet size, bus schedules, and departure frequencies.

Study on Dynamic Load of Air-Conditioning System in Subway Station Based on Hourly Passenger Flow

The research focuses on the air-conditioning system in a public area of a subway station. To address this, an optimization model based on the grid time segmentation method was constructed, specifically a GM (1,1) model. We explored the influence of the hourly passenger flow fluctuation on the load of the subway air-conditioning system, obtained the dynamic change law of the air conditioning system load in the subway station, and then dynamically adjusted the air conditioning system according to the dynamic change law to reduce the operation energy consumption of the system. Through the analysis of the simulation results, the model predicted that compared with the actual passenger flow data, the average maximum relative error was 14.97%. On this basis, the change law of the dynamic load of the subway air-conditioning system which caused by the change in passenger flow from time to time could be calculated and analyzed. Compared with the calculated load of the air conditioning system, the working day load was decreased by 1469.77 kW, or 22.00%. The findings indicate that in response to the dynamic load of fluctuations, timely adjustment of the air supply parameter of the air-conditioning system offers a significant reference point for optimizing energy efficiency in subway stations.

Optimization of smart bus scheduling based on dynamic speed limit of load rate

Aiming at the problem that fixed speed limit and static regular scheduling of single-type bus cannot meet the actual passenger flow demand with uneven distribution of time and space. By designing a dynamic speed limit rule of full load rate, based on the integrated scheduling of multiple types of bus models, taking the total passenger cost and bus scheduling cost as the overall optimization objective, and considering various constraints comprehensively, OBLESGA (Opposition-based learning elite strategy genetic algorithm) was designed to solve the problem, and the data of Beijing 563 route downlink was taken as an example for simulation experiment. The results show that OBLESGA can improve the convergence rate and solution accuracy of GA. At the same time, the optimized scheduling can reduce the cost of passenger congestion by 86.61 percent and the cost of passenger waiting times by 40.65 percent compared to traditional scheduling, while only increasing operating costs by 26.57 percent.

Ex Post Path Choice Estimation for Urban Rail Systems Using Smart Card Data: An Aggregated Time-Space Hypernetwork Approach

This paper proposes an ex post path choice estimation framework for urban rail systems using an aggregated time-space hypernetwork approach. We aim to infer the actual passenger flow distribution in an urban rail system for any historical day using the observed automated fare collection (AFC) data. By incorporating a schedule-based dynamic transit network loading (SDTNL) model, the framework captures the crowding correlation among stations and the interaction between the path choice and passenger left behind, which is important for the path choice estimation in a “near-capacity” operated urban rail system. The path choice estimation is formulated as an optimization problem, which aims to minimize the difference between the model-derived and observed information with path choice parameters as decision variables. The original problem is intractable because of nonlinear (logit model) and nonanalytical (SDTNL) constraints. A solution procedure is proposed to decompose the original problem into three tractable subproblems, which can be solved efficiently. Solving the decomposed problem is equivalent to finding a fixed point. We prove that the solution to the original problem is the same as the decomposed problem (i.e., the fixed point) when passenger path choices follow the predefined behavior model. If this condition does not hold, the solution of the original problem is proved to be an “almost fixed point” for the decomposed problem. The model is validated using both synthetic and real-world AFC data from a major urban railway system. The analysis with synthetic data validates the model’s effectiveness in estimating path choice parameters and left behind probabilities, which outperforms state-of-art simulation-based optimization methods and probabilistic models in both accuracy and efficiency. The analysis using actual data shows that the estimated path shares are more reasonable than the baseline uniform path shares and survey-derived path shares. The model estimation is robust to different initial parameter values and AFC data from various dates. Funding: The project is partially funded by the TRENoP Strategic Research funding at KTH. Supplemental Material: The online appendices are available at https://doi.org/10.1287/trsc.2022.1177 .

A robustness assessment with passenger flow data of high-speed rail network in China

Many existing studies on the robustness assessment of high-speed rail (HSR) networks use HSR services derived from timetable data as an alternative indicator of actual passenger flow. This alternative method has inherent limitations because of the various capacities and seat allocations among different HSR services operated between the same station pairs, leading to a biased evaluation of network robustness. Using an actual ticket sales dataset and HSR timetable data, this study integrates passenger volume into the robustness evaluation of China's HSR network. Moreover, this study proposes systematic methods to assess the robustness of HSR networks at the station and large-scale network levels, with procedure indicators. We design random failure and target attack simulation scenarios in un-weighted, travel-time-weighted, and flow-weighted networks. Simulation is conducted from 2014 to 2016, and with a medium-and long-term HSR network plan in China. Using the methodological advances and empirical studies, we find that China's HSR network became less robust first, and then enhanced robustness strength during network expansion. The significance of integrating passenger flow data in the robustness assessment is confirmed, as the same attack strategy may affect the total travel time and the number of passengers delivered differently. In addition, the proposed indicators are useful for capturing the procedure failure of HSR networks and critical stations.

Research on The Combined Operation Mode of Express-local Train in Urban Railways

The applicability of the combined operation mode of express-local train trains is analyzed. The express-local train without overrun scheme and the express train overrun scheme are studied. The influence of different express-local train schemes on the line capacity is analyzed. The setting method of express train non-stop and express train overrun station is determined. Finally, taking the Wenzhou Rail Transit Line S1 as an example, combined with the actual passenger flow data and travel plan data, the express-local train operation plans under different express and local train ratios are determined. It provides a reference for enterprises to operate express-local train trains.

The Use of Artificial Intelligence in the Construction of Operation Safety Early Warning Management System of Urban Rail Transit

In order to reduce the risk of safety management of urban rail transit (URRT) and improve the safety early warning of URRT, artificial intelligence (AI) is used to construct the early warning management system of URRT. Firstly, the four factors that affect the safety of URRT are discussed, the URRT system is divided into several modules, and the functions of each module are introduced. Secondly, the safety early warning analysis module is designed based on neural network technology to make it have the ability of safety early warning. Finally, the security prediction system is tested. The results show that the overall prediction error of probabilistic neural network algorithm used is less than 5%, and the classification accuracy of PNN is about 50%, which can achieve excellent prediction of data. The safety early warning system is used to predict the passenger flow of a station, and compared with the actual passenger flow, the prediction model has good prediction accuracy and credibility. Therefore, the safety early warning management system of URRT designed can meet the needs of practical application. This paper provides a reference for the safety management of URRT.

Layout Optimization of Guidance Signs in Subway Station Based on Passenger Flow Line

With the continuous acceleration of urbanization, urban public traffic congestion is becoming more and more serious. In order to alleviate traffic congestion, people’s demand for public transportation is increasing. Due to the increasing passenger flow in the subway station, the original guidance signs in the station often fail to play the expected role, and passengers cannot get effective guidance in the crowded passenger flow. This paper takes the maximum amount of information obtained by passengers as the objective function to establish the guidance sign layout model, and chooses a 0-1 integer programming model to solve it. Based on the distribution coefficient ρij; , the passenger flow wij; , the weight coefficient d and the inverse of the number of intersections qij , these four variables are used to comprehensively analyze the amount of guidance information of the guidance signs, and set constraints based on the number of passenger flow lines and guidance signs. Xiyuan Subway station, for example, through the site of the actual passenger flow survey, to obtain the required parameters, and finally using MATLAB programming solution, to get an effective guidance sign layout position, improve the guidance sign guide efficiency.

Urban Rail Transit System Network Reliability Analysis Based on a Coupled Map Lattice Model

During the last twenty years, the complex network modeling approach has been introduced to assess the reliability of rail transit networks, in which the dynamic performance involving passenger flows have attracted more attentions during operation stages recently. This paper proposes the passenger-flow-weighted network reliability evaluation indexes, to assess the impact of passenger flows on network reliability. The reliability performances of the rail transit network and passenger-flow-weighted one are analyzed from the perspective of a complex network. The actual passenger flow weight of urban transit network nodes was obtained from the Shanghai Metro public transportation card data, which were used to assess the reliability of the passenger-flow-weighted network. Furthermore, the dynamic model of the Shanghai urban rail transit network was constructed based on the coupled map lattice (CML) model. Then, the processes of cascading failure caused by network nodes under different destructive situations were simulated, to measure the changes of passenger-flow-weighted network reliability during the processes. The results indicate that when the scale of network damage attains 50%, the reliability of the passenger-flow-weighted network approaches zero. Consequently, taking countermeasures during the initial stage of network cascading may effectively prevent the disturbances from spreading in the network. The results of the paper could provide guidelines for operation management, as well as identify the unreliable stations within passenger-flow-weighted networks.

Cascading failure with preferential redistribution on bus–subway coupled network

Robustness studies on integrated urban public transport networks have attracted growing attention in recent years due to the significant influence on the overall performance of urban transport system. In this paper, topological properties and robustness of a bus–subway coupled network in Beijing, composed of both bus and subway networks as well as their interactions, are analyzed. Three new models depicting cascading failure processes on the coupled network are proposed based on an existing binary influence modeling approach. Simulation results show that the proposed models are more accurate than the existing method in reflecting actual passenger flow redistribution in the cascading failure process. Moreover, the traffic load influence between nodes also plays a vital role in the robustness of the network. The proposed models and derived results can be utilized to improve the robustness of integrated urban public transport systems in traffic planning.

Invulnerability Simulation of Urban Agglomeration Passenger Transport Network under Incomplete Information Attack Strategy

This paper explores the invulnerability of urban agglomeration transportation network under the incomplete information attack strategy. This approach employed the site mapping method to construct the urban agglomeration composite transportation network model, and the network is weighted based on the actual passenger flow. Then the nodes are defined according to the overload conditions. In addition, based on the capacity-load model, the cascading failure model of the urban agglomeration passenger transport network is constructed, and the incomplete information attack strategy and network invulnerability measure index are determined. Finally, the case of Hu-Bao-E-Yu urban agglomeration is simulated to quantify the effects of attack strategies with varied information level, node load factors, and capacity weight and distance weight of the residual connected edge. The results reveal that the network crash speed is positively related to the information span of the attacker unless the information span exceeds 0.9 or accuracy exceeds 0.6. When the information span is low, the information accuracy δ has a critical impact on the network crash speed. Moreover, in the presence of attack, high or low values of node load factor are conducive to the improvement of network invulnerability. As a scale-free network, urban agglomeration transportation network shows strong robustness to random attacks and exhibits vulnerability to deliberate attacks. The capacity weight value α and distance weight value β of residual connected edge have different effects on the network invulnerability under different information span strategies.

Multistation coordinated and dynamic passenger inflow control for a metro line

Passenger inflow control is an efficient way to relieve peak passenger flow and reduce security risks in metro networks. However, station operators develop passenger inflow control strategies independently, thus ignore the interactions among stations and lines in the actual operation. Subsequently, the single-fixed control intensity usually fails to satisfy dynamic temporal passenger demand, resulting in great stranded passengers. To address this problem, a coordinated and dynamic inflow control method is proposed to generate an optimal demand-driven control pattern in metro systems. First, a mixed integer programming model with the concept of the equivalent time interval is formulated to minimise the total number of stranded passengers on one line. Second, special consideration is paid to the transfer passengers with the aim of ensuring the safety of transfer stations. Finally, an actual passenger flow and train operation data in Beijing Batong line is conducted to test the performance of the approach. Compared with the non-coordinated and dynamic inflow control method, results show that the proposed model can balance the utilisation of transportation capacity and reduce the total number of stranded passengers by 20.6%. Sensitivity analysis results indicate that both transportation capacity and transfer capability are the main factors affecting the inflow control.

Analysis of Complex Transportation Network and Its Tourism Utilization Potential: A Case Study of Guizhou Expressways

Transportation is an example of a typical, open, fluid complex network system. Expressways are one form of complex transportation networks, and expressway service areas serve as infrastructure nodes in the expressway transportation network; hence, their construction has a significant impact on tourism development and utilization. Domestic and foreign studies on complex transportation networks have mostly been conducted from the perspective of railways, air transport, and urban transportation but seldom on expressway transportation networks. This study employed complex network theory, social network analysis, kernel density analysis, and bivariate autocorrelation to characterize the spatial structure of expressway transport networks in terms of geographical centrality. By innovating the coupling of geographical centrality and passenger flow centrality in clustering, the study also quantitatively analyzed the differences between the geographical advantage and actual passenger flow advantage of China’s Guizhou expressway transportation network to analyze the tourism utilization potential of expressway service areas. We found that (1) the geographical centrality of the Guizhou expressway transportation network ranged from −1.28 to 3.33, and its distribution shows a single-core, polyconcentric dispersed spatial structure; (2) the passenger-car flow rate ranged from 15,000 to 3.66 million, and its distribution showed a dual-core, polycentric dispersed structure that is weakly concentric; and (3) there was a positive correlation of 0.22 between the geographical centrality and passenger flow of the Guizhou expressway transportation network, which showed seven cluster types—“high-high,” “moderately high-high,” “low-high,” “moderately low-high,” “high-low,” “moderately high-low,” and “low-low”—for which seven corresponding models of tourism development were proposed. This study broadens the practical application of traffic network complexity research and provides a scientific basis for upgrading and transforming the Guizhou expressway transportation network as well as for developing composite tourism uses for expressway service areas.

A data-driven estimation method for potential passenger demand of last trains in metro based on external traffic data

The last train problem for metro is especially important because the last trains are the last chances for many passengers to travel by metro; otherwise, they have to choose other traffic modes like taxis or buses. Among the problems, the passenger demand is a vital input condition for the optimization of last train transfers. This study proposes a data-driven estimation method for the potential passenger demand of last trains. Through the geographic information, external traffic data including taxi and bus are first analyzed separately to match the origin–destination passenger flow during the last train period. A solving solution for taxi and bus is then developed to estimate the potential passenger flow for all the transfer directions of the target stations. Combining the estimated potential passenger flow and the actual passenger flow obtained by metro smart card data, the total potential passenger demand of last trains is obtained. The effectiveness of the proposed method is evaluated using a real-world metro network. This research can provide important guidance and act as a technical reference for the metro operations on when to optimize the last train transfers.

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

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.

A Hybrid Temporal-Spatio Forecasting Approach for Passenger Flow Status in Chinese High-Speed Railway Transport Hub

With the rapid development of high-speed railway in China, high-speed railway transport hub (HRTH) has become the high-density distribution center of passenger flow. In order to accurately detect potential safety hazard hidden in passenger flow, it is necessary to forecast the status of passenger flow. In this paper, we proposed a hybrid temporal-spatio forecasting approach to obtain the passenger flow status in HRTH. The approach combined temporal forecasting based on radial basis function neural network (RBF NN) and spatio forecasting based on spatial correlation degree. Computational experiments on actual passenger flow status from a specific bottleneck position and its correlation points in HRTH showed that the proposed approach is effective to forecast the passenger flow status with high precision.