Transit Passenger Research Articles

Short-term inbound rail transit passenger flow prediction based on BILSTM model and influence factor analysis

Short-term inbound rail transit passenger flow prediction based on BILSTM model and influence factor analysis

COVID-19: Perceptions of public transit passengers on its management and influence on sustainable transport in Ibadan

COVID-19: Perceptions of public transit passengers on its management and influence on sustainable transport in Ibadan

THE RELATIONSHIP BETWEEN SERVICE QUALITY, PERCEIVED VALUE, SATISFACTION AND BEHAVIOURAL INTENTIONS IN RAIL TRANSIT INDUSTRY

Much has been written about service quality, perceived value and its impacts on satisfaction and behavioural intentions. However, little research on this perspective has been carried out in public rail transit settings in Malaysia. The aim of this study is to investigate the relationship between service quality, perceived value, satisfaction, and behavioural intentions of Mass Rapid Transit (MRT) passengers in Klang Valley, Malaysia. A survey method via structured questionnaire was employed and analysis was performed using Statistical Package of Social Science (SPSS). Perceived value for money and service quality are found to be important predictors of satisfaction and behavioural intentions among MRT passengers. Thus, the findings lend support to the means end chain theory. This study also includes a discussion, conclusions, implications, and limitations of the study.

Planning of integrated mobility-on-demand and urban transit networks

We envision a multimodal transportation system where Mobility-on-Demand (MoD) service is used to serve the first mile and last mile of transit trips. For this purpose, the current research formulates an optimization model for designing an integrated MoD and urban transit system. The proposed model is a mixed-integer non-linear programming model that captures the strategic behavior of passengers in a multimodal network through a passenger assignment model. It determines which transit routes to operate, the frequency of the operating routes, the fleet size of vehicles required in each transportation analysis zone to serve the demand, and the passenger flow on both road and transit networks. A Benders decomposition approach with several enhancements is proposed to solve the given optimization program. Computational experiments are presented for the Sioux Falls multimodal network. The results show a significant improvement in the congestion in the city center with the introduction and optimization of an integrated transportation system. The proposed design allocates more vehicles to the outskirt zones in the network (to serve the first mile and last mile of transit trips) and more frequency to the transit routes in the city center. The integrated system significantly improves the share of transit passengers and their level of service in comparison to the base optimized transit system. The sensitivity analysis of the bus and vehicle fleet shows that increasing the number of buses has more impact on improving the level of service of passengers compared to increasing the number of MoD vehicles. Finally, we provide managerial insights for deploying such multimodal service.

Forecasting Daily and Weekly Passenger Demand for Urban Rail Transit Stations Based on a Time Series Model Approach

Forecasting daily and weekly passenger demand is a key fundamental process used by existing urban rail transit (URT) station authorities to diagnose operational problems and make decisions about train schedule patterns to improve operational efficiency, increase revenue management, and improve driving safety. The accuracy of the forecast results will directly affect the operation planning of urban rail transit (URT). Therefore, based on the collected inbound historical passenger data, this study used the Box–Jenkins time series with the Facebook Prophet algorithm to analyze the characteristics of urban rail transit passenger demand and achieved better computational forecasting performance accuracy. After analyzing the periodicity, correlation, and stationarity, different time series models were constructed. The Akaike information criteria (AIC), Bayesian information criteria (BIC), mean squared error (MSE), and root mean squared error (RMSE) were used to evaluate the adequacy of the best forecast model from among several tested candidates’ models for the Box–Jenkins. The parameters of the daily and weekly models were estimated using statistical software. The experimental results of this study are of both theoretical and practical significance to the urban rail transit (URT) station authorities for an effective station planning system. The forecasting results signify that the SARIMA (5, 1, 3) (1, 0, 0)24 model performs better and is more stable in forecasting the daily passenger demand, and the ARMA (2, 1) model performs better in forecasting the weekly passenger demand. When comparing the SARIMA and ARMA models with the Facebook Prophet, results show that the Facebook Prophet model is superior to the SARIMA model for the daily time series, and the ARMA model is superior to the Facebook Prophet model for the weekly time series.

A Model of a Limited-Stop and Local Mixed Bus Service with Increased Fares for the Limited-Stop Service

This study designs a limited-stop and local mixed bus service from the perspectives of both transit agencies and passengers based on a proposed optimization model. Close attention was paid to the increase in fares for the limited-stop service in the proposed model to offset the loss in bus fare. The objective function was to minimize the passenger travel time and bus agency costs; the decision variables were the stops for the limited-stop service and the headways of the limited-stop and local services; the constraints included the range of fare increases for the limited-stop service and other factors. The Lingo software and the genetic algorithm were compared in solving the proposed model from the aspects of solving time and results. Because the solutions for the model within the planning time and the influence of the global optimal solution upon parametric analysis were stable, the Lingo software was more suitable for the proposed model. Evaluations of the total costs for the mixed service and local-only service were carried out for different bus corridor lengths. The ratio of the fares for the limited-stop service to the fares for the local service must be within the appropriate range in order to take advantage of the limited-stop service. When the stop spacing and the bus corridor distance were longer, the mixed service was more competitive and noticeable.

Research of Passenger Flow Forecast of Urban Rail Transit Based on Data Mining

With the development of China's economy and society, urban construction is constantly improving, urban rail transit is becoming more mature, and people's demand for travel quality is getting higher and higher. However, the imperfect operation and management leads to the contradiction between supply and demand of urban rail transit. Passenger flow data of rail transit is the basis of operation scheduling, and accurate prediction can effectively improve the utilization rate of operating energy. In this paper, through data mining of passenger flow data, the law of passenger flow in time dimension is analyzed, and three different forecasting models are established for rail transit passenger flow data. Finally, the forecasting effects of each model are compared. The characteristics of passenger flow are analyzed in the time dimension, which shows the different changing rules of passenger flow on working days and rest days. In the discussion of the three forecasting methods, firstly, the time series forecasting method is realized by SPSS software, and the final model parameters are determined by unit root test, autocorrelation analysis, partial autocorrelation analysis and Bayesian information criterion. After that, the regression prediction model of support vector machine and BP neural network model are established by MATLAB. The former maps nonlinear passenger flow data into high-dimensional space to find linear relationship for prediction, while the latter realizes passenger flow prediction by establishing neural network model. Finally, by comparing the three prediction models, the results show that the average absolute error of BP neural network prediction method is 13%, which is 44% and 10% lower than that of time series method and support vector machine method, respectively, with high accuracy.

Tribological Properties of Laser Cladded Alloys for Repair of Rail Components.

Tram or light rail systems are heavily relied upon for passenger transit; however, low-carbon steel grades commonly used in special trackwork, such as in switches, are prone to wear, rolling contact fatigue (RCF), and deformation under cyclic wheel-rail contact. To address this, laser cladding can be used to apply a metal coating to protect the underlying substrate and rebuild the worn rail profiles. Laser cladding may also be applied to remove cracking by rebuilding the rail head. The tribological characteristics of light rail components after laser cladding with Stellite 6 and a newly developed martensitic stainless steel were investigated, using roller-on-disc wear testing. Analysis of the microstructure, mechanical properties, and wear performance was undertaken to develop a comprehensive understanding of the influence of the laser cladding type on the wear and surface fatigue performance. Both cladding alloys significantly improved the tribological performance. These findings were compared to those for a laser cladded hypereutectoid rail type (reported in our previous study). It was found that laser cladding with a suitable alloy was an effective technique for improving the tribological properties, increasing the wear resistance, and increasing the retardation of cracking on both substrates. These findings suggest laser cladding may be used to repair light rail components, and this technique can be optimized to suit different rail grades. This makes laser cladding a flexible and versatile maintenance strategy, in both coating and repair applications, to prolong the operational lifetime of critical components for the railway industry.

Key Factors, Planning Strategy and Policy for Low-Carbon Transport Development in Developing Cities of China.

Exploring key impact factors and their effects on urban residents' transport carbon dioxide (CO2) emissions is significant for effective low-carbon transport planning. Researchers face the model uncertainty problem to seek a rational and better explanatory model and the key variables in the model set containing various factors after they are arranged and combined. This paper uses the Bayesian Model Averaging method to solve the above problem, explore the key variables, and determine their relative significance and averaging effects. Beijing, Xi'an, and Wuhan are selected as three case cities for their representation of developing Chinese cities. We found that the initial key factor increasing transport emissions is the high dependence on cars, and the second is the geographical location factor that much more suburban residents suffer longer commuting. Developing satellite city rank first for reducing transport emissions due to more local trips with an average short distance, the second is the metro accessibility, and the third is polycentric form. Key planning strategies and policies are proposed: (i) combining policies of car restriction based on vehicle plate number, encouraging clean fuel cars, a carbon tax on oil uses, and rewarding public transit passengers; (ii) fostering subcenters' strong industries to develop self-contained polycentric structures and satellite cities, and forming employment and life circle within 5 km radius; and (iii) integrating bus and rail transit services in the peripheral areas and suburbs and increasing the integration level of muti-modes transferring in transport hubs. The findings will offer empirical evidence and reference value in developing cities globally.

The Modern Streetcar in the U.S.: An Examination of Its Ridership, Performance, and Function as a Public Transportation Mode

Seven U.S. cities reported operating streetcar service to the National Transit Database in 2012, and many other cities are building or planning streetcar investments. Yet despite the increased popularity of streetcar investments, there is a lack of information about how these investments function as transportation modes, as opposed to urban development tools. This paper examines the streetcar as a public transit mode by examining ridership, service, service productivity, cost effectiveness, and other indicators of the streetcar’s performance and function in the carriage of transit passengers. There is considerable variation in all of these measures, with the variability a function of the different environments in which streetcars operate, the different roles they play in the local transit system, and differences in the operating characteristics of the streetcars themselves. Among the cases, Portland’s streetcar emerges as a strong performer, Little Rock’s and Tampa’s streetcars as relatively poor performers, and the other streetcars have mixed performance results.

Evaluation of Horizontal Equity under a Distance-Based Transit Fare Structure

Horizontal equity requires equal distribution of investment/benefit/costs among equal members of society. In other words, a transit passenger should pay as much as he/she uses. This study evaluated the measure of fulfillment of this rule in a case study, developed a distance-based fare structure, and shows that justice is better served by switching to the proposed structure. Fare elasticity of demand and probability distribution of transit passenger trip lengths were investigated through a field survey. Although mainly used in the measurement of inequality in income or wealth, the Gini index and the recovery ratio (revenue to cost for each transit passenger) in evaluating equity were used in this study. Results show that the Gini index would decrease from 0.38 to 0.17 after switching from a flat to a distance-based structure. Assessment of the ratio of revenue per mile over cost per mile (RPM/CPM) shows that switching to a distance-based fare structure makes the RPM/CPM curve significantly flatter, which indicates more similarity among passengers. As a byproduct, the amount of change in demand and revenue of the transit system also were formulated.

Using GIS for Measuring Transit Stop Accessibility Considering Actual Pedestrian Road Network

Bus stops attain their importance to the transit service from being the main points of contact between the passenger and the bus. Considering spatial attributes, both the location and the spacing of bus stops significantly affect transit service performance and passenger satisfaction, as they influence travel time in addition to their role in ensuring reasonable accessibility. Knowing that every transit trip begins and ends with pedestrian travel, access to a bus stop is considered a critical factor for assessing the accessibility of the stop location. In this research, transit stop access coverage is estimated based on the actual pedestrian road network surrounding the stop. Accordingly, new indices are developed to assess a bus stop location on a more spatial basis. These indices measure the accessibility of a bus stop through the surrounding road network in addition to the ratio of actual access coverage to the ideal access coverage of a stop.

Impacts of Express Bus Service on Passenger Demand

The Region of Waterloo, Ontario, is a rapidly-growing metropolitan area approximately 100 km west of Toronto. In 2005, the Region’s transit operator, Grand River Transit, introduced an express bus service, known as iXpress, along the central north-south corridor of the Region. This paper explores the impact of the iXpress service on transit user costs and passenger attraction. We employ a methodology to quantify the generalized cost (including waiting time, in-vehicle and transfer times) of transit trips between key destinations in the Region before and after the implementation of iXpress. We also develop a methodology to identify those customers who benefit from the reduced cost of the iXpress. Finally, we present the change in ridership (boardings) in the corridor pre- and post-implementation. From these demand and cost data, we compute transit elasticity of demand with respect to generalized cost.

Structure Optimization and Governance of Multilevel Rail Transit Integration under the Background of a Metropolitan Area Based on the Industrial Internet of Things Security Data Fusion Method

In recent years, the urban rail transit network architecture has gradually grown, the contradiction between rail transit passenger flow and transport load has been deepening, and its carrying capacity has also been tested. Passenger flow risk has become the most important source of risk in rail transit. The key to restricting rail transit service quality is how to effectively monitor and manage rail transit passenger flow and provide accurate and convenient early warning to staff. In order to effectively manage the complex passenger flow scene, the premise is to distinguish the real-time state of its moving target. The time series data feature extraction and LSTM data fusion were used to analyze the traffic data sequence in the multilevel rail transit network model. The multilevel rail transit integration of the Internet of things is modeled by the method of data fusion. It can be seen from the experimental data that in the data fusion mode, the network comprehensive evaluation prediction value fitting effect can quickly converge, and the error rate is less than 4%. By comparing the mean square error (MSE) and mean absolute error (MAE) data of the traditional method and the experimental method used in this paper through two different datasets, it was understood that the MAE under the data fusion method was reduced by 8 compared with the traditional method, and the MSE was decreased by 33, indicating that this method can bring better simulation effect to the model. The improvement of the synergistic and complementary functional network and the acceleration of the efficient and convenient flow of elements are the inevitable results of the integration of multilayer rail transit in the metropolitan area.

Analysis of Passenger Flow Characteristics of Urban Rail Transit Based on Spatial Data Dynamic Analysis Technology

Based on spatial data dynamic analysis technology, the characteristics of urban rail transit passenger flow are analyzed. This study analyzes the passenger flow characteristics of urban rail transit from the perspective of operation and planning by using the dynamic analysis technology of spatial data, combined with social and economic development. Based on the analysis of research data from the study of passenger traffic and passenger traffic data measurement, the characteristics of passenger traffic from urban railways are derived from the time distribution, spatial distribution, and transfer of passengers waiting on the platform. The final length of line 3 is 39.7 m, the passenger volume is 102, with 11 people/day, the passenger flow density is 1.8/2.3, and the high section in peak hours is 2.4/3.2. By considering the various influencing factors, efforts should be made to develop urban rail transit projects to promote the growth of social and economic benefits.

New Deep Learning-Based Passenger Flow Prediction Model

The ability to predict passenger flow in transport networks is an important aspect of public transport management. It helps improve transport services, aids those responsible for management to obtain early warning signals of emergencies and unusual circumstances and, in general, makes cities smarter and safer. This paper develops a long short-term memory-based (LTSM-based) deep learning model to predict short-term transit passenger volume on transport routes in Istanbul. This prediction model has been created using a dataset that included the number of people who used different transit routes in Istanbul at one-hour intervals between January and December 2020. The proposed multilayer LSTM-based deep learning model has been compared with popular models such as random forest (RF), support vector machines, autoregressive integrated moving average, multilayer perceptron, and convolutional neural network. The experimental findings showed that the proposed multilayer LSTM-based deep learning model outperformed the other models with regard to prediction for each transfer route. Furthermore, RF, one of the machine learning models used, produced remarkably successful results.

Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) for Short-Term Forecasting of Transit Passenger Flow

Short-term forecasting of passenger flow is critical for transit management and crowd regulation. Spatial dependencies, temporal dependencies, inter-station correlations driven by other latent factors, and exogenous factors bring challenges to the short-term forecasts of passenger flow of urban rail transit networks. An innovative deep learning approach, Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) is proposed to forecast passenger flow in urban rail transit systems to incorporate these complex factors. We propose to use multiple graphs to encode the spatial and other heterogenous inter-station correlations. The temporal dynamics of the inter-station correlations are also modeled via the proposed multi-graph convolutional-recurrent neural network structure. Inflow and outflow of all stations can be collectively predicted with multiple time steps ahead via a sequence to sequence(seq2seq) architecture. The proposed method is applied to the short-term forecasts of passenger flow in Shenzhen Metro, China. The experimental results show that MGC-RNN outperforms the benchmark algorithms in terms of forecasting accuracy. Besides, it is found that the inter-station driven by network distance, network structure, and recent flow patterns are significant factors for passenger flow forecasting. Moreover, the architecture of LSTM-encoder-decoder can capture the temporal dependencies well. In general, the proposed framework could provide multiple views of passenger flow dynamics for fine prediction and exhibit a possibility for multi-source heterogeneous data fusion in the spatiotemporal forecast tasks.

Exploring the Potential Impact of Crowdshipping Using Public Transport in Singapore

Because of increased urbanization and a rise in e-commerce activities, the demand for freight transport in cities is growing. E-retailers and logistics companies face the challenge of making timely, cost-effective, and reliable deliveries. To address this problem, the concept of crowdshipping has gained interest. Crowdshipping enlists members of the public to pick up and drop off parcels, ideally en route to their pre-committed destination. Individuals, such as commuters using public transport, can be engaged to fulfill deliveries as “crowdshippers.” This research explores the potential impact of crowdshipping using public transport in a congested city, focusing on Singapore as a case study. First, an online survey was conducted to investigate the willingness of transit passengers to act as crowdshippers. Then, a parcel allocation model was developed to match parcels with public bus journeys. In the case of there not being enough crowdshippers available, the remaining parcels will be delivered using the carrier’s delivery vans, which are subject to a vehicle routing problem. Using real-world data, we compared the performance of an e-commerce carrier with and without crowdshipping. The results show that crowdshipping can reduce vehicle kilometers traveled and associated air emissions by up to 17%. The carrier’s delivery cost can be reduced by up to 29% per parcel. These savings can be realized even if crowdshipping is limited to off-peak travel hours only. In a congested city with an extensive transit system, crowdshipping using public transport has the potential to be a sustainable means of moving goods in urban areas.

Mobile Public Transportation Application: Factors Influencing Urban Rail Transit Passengers' Use

This paper thoroughly explored and discussed the factors that affect Mobile Public Transportation Applications usage among urban rail transit passengers. To do so, a model known as the Unified Theory of Acceptance and Use of Technology (UTAUT) was chosen to determine the significant factors influencing mobile application usage among passengers in Klang Valley, Malaysia. During its primary data collection, an online survey was deployed to 109 passengers using an online survey platform. According to the modal split analysis, most female students and private-sector employees aged 18-29 years use the Mobile Public Transportation Application with route projection during an emergency, depending on the mobile application facilitating conditions. Moreover, based on the factors analysis' result, facilitating conditions are an essential factor compared to the other constructs. However, the study's findings might be biased towards a certain age and gender group due to its respondent reach. Therefore, an equal number of respondents in various age and gender groups is highly recommended for future research to fully grasp the factors that may affect passengers using the Mobile Public Transportation Application in urban mobility.

Short-Term Passenger Flow Prediction of Urban Rail Transit Based on SDS-SSA-LSTM

Predicting rail transit passenger flow is crucial for modifying the metro schedule. To increase prediction accuracy, a model is proposed that combines long short-term memory (LSTM) with single spectrum analysis (SSA). Firstly, a stepwise decomposition sampling (SDS) strategy based on SSA progressive decomposition is proposed as a solution to the data leaking issue in traditional sequence decomposition. Then, based on this strategy, the passenger flow time series with complex features is decomposed into a relatively single trend and fluctuation component. Finally, the LSTM network is employed to perform short-term predictions on each component separately. The predicted value of each component is accumulated to obtain the original passenger flow’ predicted result. The example shows that, compared with the single LSTM and other hybrid models, the proposed method offers a greater overall prediction accuracy in the experimental days, and the method has specific applicability.