Passenger Behavior Research Articles

Virtual Dynamic Marshalling of Trains under Severe Epidemic Situation

In the context of the global epidemic, urban rail transit has the risk of spreading the virus. Taking Beijing Metro Line 1 as an example, this project establishes a dynamic model of train variable marshalling by studying passenger behavior and virus transmission, aiming to explore more intelligent marshalling mode, optimize transportation organization, and improve the flexibility of train marshalling and dispatching of urban rail transit, so as to improve its transportation efficiency and reduce the station personnel density, Then reduce the risk of disease infection of passengers in the process of taking urban rail transit under the background of the outbreak. The results show that: Dynamic marshalling technology can significantly improve the transport efficiency of urban rail transit trains and effectively control the risk of infection of passengers.

Risk Assessment of Passenger Behaviors That Influence Accident Type and Severity in Metro Operation.

The unsafe behavior of passengers frequently causes metro operation accidents. This research aims to establish a model for evaluating the risk of unsafe behavior among subway passengers and for assessing the severity of different types of accidents caused by passenger unsafe behavior. A risk assessment model that combines the Interaction Matrix (IM) model with a Monte Carlo algorithm was established to quantitatively test the risk of unsafe behavior among passengers. Based on the initial data of 234 cases, the behavioral risks in accidents were simulated, and the resulting risks follow a normal distribution. After analyzing the differences in behavioral risk distribution characteristics, the targeted risk mitigation countermeasures were obtained. Results showed that there are 12 kinds of unsafe behaviors related to 4 metro operation accident types. Among them, crowded stampede caused by four kinds of passengers' unsafe behavior has the highest risk mean (μ) of 5.14, followed by escalator injury (4.72), pinched by a shielding barrier (4.42) and fall injury (4.14). The severity of different types of accidents caused by different unsafe behaviors of passengers was obtained, which can provide a basis for targeted risk mitigation strategies and measures.

Research on Choice Preference of Parallel Trains for High-Speed Rail Heterogeneous Passengers

The passenger capacity utilization of parallel trains on China’s high-speed railway (HSR) varies greatly, which seriously affects the revenue and passenger service quality of railroad companies. One of the key factors contributing to this issue is the uniformity of fares. To address this, China’s railway enterprises are implementing differential pricing reforms for parallel trains. This paper presents a two-step method that combines latent class analysis (LCA) and random parameter logit (RPL) models to estimate the preferences of diverse passengers for parallel trains and quantify them using willingness to pay. To illustrate this, we conducted revealed preference and stated preference questionnaire surveys at Nanning East Railway Station, China, focusing on the Nanning-Guangzhou HSR route. These surveys gathered data on passengers’ personal and travel attributes. LCA was carried out according to passenger attributes, and passengers were divided into three categories according to the goodness-of-fit measures. Through the questionnaire data, the travel time and departure time period of each category of the passenger were converted into costs, and the absolute value of each influencing factor of passengers for parallel trains was obtained. Considering the limited rational choice behavior of passengers, the perceived value of each influencing factor of passengers on parallel trains was calculated through prospect theory. Finally, an RPL model for parallel train choice of heterogeneous passengers was constructed, and the parameters of each category of the passenger were estimated based on the absolute value and perceived value of the influencing factors.

Large-scale Passenger Behavior Learning and Prediction in Airport Terminals based on Multi-Agent Reinforcement Learning

For the problem of predicting passenger flow in airport terminals, multi-agent reinforcement learning is applied to airport terminals simulation. Multi-Agent Reinforcement Learning based on Group Shared Policy with Mean-field and Intrinsic Rewards (GQ-MFI) is proposed to predict passenger behavior in order to simulate the distribution of flow in different areas of the terminal at different time periods. Independent learning of multi-agent may lead to environmental instability and long convergence time. To improve the adaptability of agents in non-stationary environments and accelerate learning time, a multi-agent grouping learning strategy is proposed. Clustering is used to group multi-agent, and a shared Q-table is set within each group to improve the learning efficiency of multi-agent. Meanwhile, in order to simplify the interaction information among the agent after grouping, the idea of average field is used to transmit partial global information among the agent within the group. Intrinsic rewards are added to make the agent closer to human cognition and behavioral patterns. By conducting the airport terminal simulations using Anylogic, the experimental results show that the training speed of this algorithm is 17% higher than that of Q-learning algorithm, and it achieves good prediction accuracy in predicting the number of security check passengers with a time scale of 10 minutes.

Profiling Public Transit Passenger Mobility Using Adversarial Learning

It is important to capture passengers’ public transit behavior and their mobility to create profiles, which are critical for analyzing human activities, understanding the social and economic structure of cities, improving public transportation, assisting urban planning, and promoting smart cities. In this paper, we develop a generative adversarial machine learning network to characterize the temporal and spatial mobility behavior of public transit passengers, based on massive smart card data and road network data. The Apriori algorithm is extended with spatio-temporal constraints to extract frequent transit mobility patterns of individual passengers based on a reconstructed personal trip dataset. This individual-level pattern information is used to construct personalized feature vectors. For regular and frequent public transit passengers, we identify similar transit mobility groups using spatio-temporal constraints to construct a group feature vector. We develop a generative adversarial network to embed public transit mobility of passengers. The proposed model’s generator consists of an auto-encoder, which extracts a low-dimensional and compact representation of passenger behavior, and a pre-trained sub-generator containing generalization features of public transit passengers. Shenzhen City is taken as the study area in this paper, and experiments were carried out based on smart card data, road network data, and bus GPS data. Clustering analysis of embedding vector representation and estimation of the top K transit destinations were conducted, verifying that the proposed method can profile passenger transit mobility in a comprehensive and compact manner.

Alighting and boarding time prediction in different types of waiting areas at subway stations

The alighting and boarding behavior of passengers at the subway station can directly affect the dwell time of trains, and then affect the service level of stations. The HPO-BP prediction model for the alighting and boarding time in scenarios with different types of waiting areas is proposed in this paper. The number of passengers, gender, whether to carry luggage or children, and the degree of passenger civilization are selected as the main influence factors after analyzing the data of field investigations, which are defined as the input variables of the prediction model. The alighting and boarding time is defined as the output variable. The HPO-BP prediction model is trained, tested and validated by using the data collected in the field investigations. The comparison results indicate that the prediction accuracies of the proposed model in a single waiting area and double waiting areas are 35.8% and 62.8% higher than that of the BP neural network, and are also significantly improved compared with other advanced algorithms. It can be concluded that the gender of passengers is the most important factor affecting passengers’ alighting and boarding time after the interpretation and analysis of the SHAP model. Moreover, the degree of passenger civilization also has a certain impact on the alighting and boarding efficiency.

Mobility challenges for senior passengers during the Covid-19 pandemic

This paper aims to clarify the differences in the factors influencing subway traffic behaviour of senior passengers (SP) and non-senior passengers (NSP) during the coronavirus disease-2019 (Covid-19) pandemic based on big data in Seoul, South Korea. A one-way analysis of variance is carried out to analyse the influencing factors of subway use of SP and NSP during the Covid-19 pandemic. Furthermore, a multiple linear regression is conducted to identify the factors affecting SP and NSP. Finally, the traffic patterns of SP and NSP were analysed with respect to districts by way of geographically weighted regression. The spatial scope of this study includes Seoul, which consists of 25 districts (gu). The temporal range is from 1 January 2017 to 31 December 2020, and the number of people using subway in Seoul is used as the main dataset. The results suggest that SP are more affected by subway than NSP, and the most influential factors are cultural gathering facilities and the number of subway stations. The regression model showed high explanatory power for southern Seoul, which has a high concentration of facilities related to the influencing factors.

A probabilistic bottom-up modelling approach for synthetic load profiles within the energy efficiency management of cruise ship cabins

A reliable estimate of the electrical demand is a decisive factor in the design of electric board systems on cruise ships. This applies to all areas of the ship, including the hotel area with its up to several thousand cabins, which account for a non-negligible share of the total energy demand. In this paper, a simplified bottom-up model that can depict the electrical demand cabins with high temporal resolution and thus support marine and electrical engineers in developing future on-board power grids is presented. Key-card data will be used as a basis to easily access the behaviour of passengers on board. Another benefit is that the key data of the electrical consumers can be easily adapted to different types of ships and cabins. By including the ships route it is possible to precisely calculate the heat input through the glazing at any time of day and to determine its effect on the air-conditioning requirement. The model presented here is therefore not limited to certain regions but can be used globally. The functionality of the model is demonstrated on the example of a Caribbean cruise where the average electrical demand of a cabin is determined to 1.6 kWh per day.

Deep reinforcement learning of passenger behavior in multimodal journey planning with proportional fairness

Multimodal transportation systems require an effective journey planner to allocate multiple passengers to transport operators. One example is mobility-as-a-service, a new mobility service that integrates various transport modes through a single platform. In such a multimodal and diverse journey planning problem, accommodating heterogeneous passengers with different and dynamic preferences can be challenging. Furthermore, passengers may behave based on experiences and expectations, in the sense that the transport experience affects their state and decision of the next transport service. Current methods of treating each journey planning optimization as a non-time varying single experience problem cannot adequately model passenger experience and memories over many journeys over time. In this paper, we model passenger experience as a Markov model where prior experiences have a transient effect on future long-term satisfaction and retention rate. As such, we formulate a multi-objective journey planning problem that considers individual passenger preferences, experiences, and memories. The proposed approach dynamically determines utility weights to obtain an optimal journey plan for individual passengers based on their status. To balance the profit received by each transport operator, we present a variant-based proportional fairness. Our experiments using real-world and synthetic datasets show that our approach enhances passenger satisfaction, compared to baseline methods. We demonstrate that the overall profit is increased by 2.3 times, resulting in a higher retention rate caused by higher satisfaction levels. Our proposed approach can facilitate the participation of transport operators and promote passenger acceptance of MaaS.

Passenger flow anomaly detection in urban rail transit networks with graph convolution network-informer and Gaussian Bayes models.

Passenger flow anomaly detection in urban rail transit networks (URTNs) is critical in managing surging demand and informing effective operations planning and controls in the network. Existing studies have primarilyfocused on identifying the source of anomalies at a single station byanalysing the time-series characteristics of passenger flow. However, they ignoredthe high-dimensional and complex spatial features of passenger flow and thedynamic behaviours of passengers in URTNs during anomaly detection. This article proposes a novel anomaly detection methodology based on a deeplearning framework consisting of a graph convolution network (GCN)-informer model and a Gaussian naive Bayes model. The GCN-informer model is used to capture the spatial and temporal features of inbound and outbound passenger flows, and it is trained on normal datasets. The Gaussian naive Bayes model is used to construct a binary classifier for anomaly detection, and its parameters are estimated by feeding the normal and abnormal test data into the trained GCN-informer model. Experiments are conducted on a real-world URTN passenger flow dataset from Beijing. The results show that the proposed framework has superior performancecompared to existing anomaly detection algorithms in detecting network-level passenger flow anomalies. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

Data-Driven Real-Time Denied Boarding Prediction in Urban Railway Systems

Providing real-time crowding information in urban railways would enable informed travel decisions and encourage cooperative behavior of passengers, as well as improve operating efficiency and safety. However, the problem of real-time crowding prediction is not trivial because of the unavailability of ground-truth crowding data, particularly for the direct impact of crowding on passengers (e.g., denied boarding on platforms). This paper proposes a data-driven method for real-time denied boarding prediction in urban railway systems using automated fare collection (AFC) and automated vehicle location (AVL) data. It predicts the denied boarding probability distribution or its derived metrics as a function of explanatory variables, including demand, operations, and incident-related factors. The method is validated through a case study covering 18 months on Hong Kong Mass Transit Railways. The results highlight the model’s accurate and robust performance in predicting denied boarding on platforms using purely AFC and AVL data (e.g., an average of 6%–7% error) under both recurrent and non-recurrent situations, in which transfer demand-related factors contribute most to the prediction. The prediction model outputs can support proactive operations control and management, as well as provision of customer information without relying on expensive and time-consuming data collection efforts. Customer information, for example, can include the average number of trains to wait before boarding or the average waiting time on the platform.

Maximizing non-aeronautical revenues in airport terminals using gate assignment and passenger behaviour modelling

Airports must ensure that their operations can efficiently adapt to the emerging needs considering both the passenger experience and their economic viability. One way to achieve this is by optimizing the airport operations, aiming to maximize revenue levels considering operational objectives and passenger requirements inside the airport. This study presents an original mixed-integer linear programming model (MILP), which combines the gate assignment problem with passenger behaviour modelling. First, a survey was conducted to collect relevant information to model passenger behaviour and the purchases conducted in a terminal, leading to the estimation of discrete choice models that quantify the probability that a passenger makes purchases of certain levels at the terminal according to their flight type (departure, arrival or transfer). Then, the proposed MILP model assigns gates which would expectedly increase the airport non-aeronautical revenues at the terminal airport by matching flights and passenger gate categories to the most profitable gates, considering the proximity to the retail area, the walking distance needed to get to a gate in a specified time-horizon and the operational constraints of the airport. The application to the Lisbon Airport case study showed a potential increase of 8%–12.2% in revenues corresponding to 1732.7€ and 2967.3€ in half-an-hour time slots.

Understanding passenger travel choice behaviours under train delays in urban rail transits: a data-driven approach

The analysis of passenger travel choice behaviours under train delays has become a crucial topic in research on urban rail transit operation management. In this paper, we focus on analysing travel choices of affected regular passengers under train delays by utilizing the data collected through an automatic fare collection (AFC) system along with train delay log records. Along this line, we propose a data-driven four-stage framework for studying regular passengers’ responses under delays, consisting of data profiling, regular passenger screening and travel patterns extraction, affected regular passenger identification, and affected passenger behaviour prediction modelling. Using a real-world case of the Shenzhen Metro in China, we conduct extensive experiments for method validation and feature insights analysis. The proposed framework could provide a microscopic view of passenger travel behaviours under train delays for fine prediction and exhibit a possibility for multi-source heterogeneous data mining in passenger behaviour analysis and train delay-related tasks.

Public transport development and changing transport behavior

The purpose of the article is to identify the tasks of developing urban transport infrastructure and changing the transport behavior of passengers. Urban transport should allow solving the following tasks: the possibility of planning the travel time, ensuring the reliability and safety of the trip, creating conditions for the availability of transport services at their cost, safety and comfort, as well as providing transport services at minimal economic costs. In the process of applying analytical research methods, actual problems of urban infrastructure have been identified and directions for solving these problems have been proposed. Human transport behavior in the conditions of rapid development of information and communication technologies has been analyzed. The growing digitalization leads to the creation of a wide variety of proposals for the implementation of mobility and its use. In addition to multimodality, this also applies to suggestions for information support and organization of systems.

Sustainable urban mobility: Flexible bus service network design in the post-pandemic era

The excessive traffic congestion in vehicles lowers the service quality of urban bus system, reduces the social distance of bus passengers, and thus, increases the spread speed of epidemics, such as coronavirus disease. In the post-pandemic era, it is one of the main concerns for the transportation agency to provide a sustainable urban bus service to balance the travel convenience in accessibility and the travel safety in social distance for bus passengers, which essentially reduces the in-vehicle passenger congestion or smooths the boarding–alighting unbalance of passengers. Incorporating the route choice behavior of passengers, this paper proposes a sustainable service network design strategy by selecting one subset of the stops to maximize the total passenger-distance (person × kilometers) with exogenously given loading factor and stop-spacing level, which can be captured by constrained non-linear programming model. The loading factor directly determines the in-vehicle social distance, and the stop-spacing level can efficiently reduce the ridership with short journey distance. Therefore, the sustainable service network design can be used to help the government minimize the spread of the virus while guaranteeing the service quality of transport patterns in the post-pandemic era. A real-world case study is adopted to illustrate the validity of the proposed scheme and model.

Multi-scale risk assessment and mitigations comparison for COVID-19 in urban public transport: A combined field measurement and modeling approach

The outbreak of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic has caused an unparalleled disruption to daily life. Given that COVID-19 primarily spreads in densely populated indoor areas, urban public transport (UPT) systems pose significant risks. This study presents an analysis of the air change rate in buses, subways, and high speed trains based on measured CO2 concentrations and passenger behaviors. The resulting values were used as inputs for an infection risk assessment model, which was used to quantitatively evaluate the effects of various factors, including ventilation rates, respiratory activities, and viral variants, on the infection risk. The findings demonstrate that ventilation has a negligible impact on reducing average risks (less than 10.0%) for short-range scales, but can result in a reduction of average risks by 32.1%–57.4% for room scales. When all passengers wear masks, the average risk reduction ranges from 4.5-folds to 7.5-folds. Based on our analysis, the average total reproduction numbers (R) of subways are 1.4-folds higher than buses, and 2-folds higher than high speed trains. Additionally, it is important to note that the Omicron variant may result in a much higher R value, estimated to be approximately 4.9-folds higher than the Delta variant. To reduce disease transmission, it is important to keep the R value below 1. Thus, two indices have been proposed: time-scale based exposure thresholds and spatial-scale based upper limit warnings. Mask wearing provides the greatest protection against infection in the face of long exposure duration to the omicron epidemic.

A choice model of security check channel for airline passengers considering heterogeneity in airport terminal

Having a better understanding of passenger behavior during security check is crucial to improve the efficiency of security check in airport terminal. The main aim of this study is to further the knowledge on how security channel choices are made and how different factors affects these choices. Decision making during security check implies different choices, of which one of the most important selections is the security channel. This paper investigates the effects of environmental (distance and queue length of channels) and passengers’ own factors (age, gender and luggage) on security channel choice. A sample of 530 passengers from the surveillance video is obtained and a mixed logit model (ML) is calibrated using these data. The model indicates that only distance, queue length, age and luggage can significantly affect the selection of security channel and the parameters of these factors are no longer fixed but obey normal distribution. Moreover, the results show that the parameters of distance and queue length have significant random distributions, which proves that decision making is influenced by a high degree of passenger heterogeneity. The findings of this study can be used to improve the queuing simulation models and the accuracy of their results in future research, which can assist in designing and managing the security check in the terminal system.

Two-Phase Model for Demand-Responsive Transit Considering the Cancellation Behavior of Boundedly Rational Passengers

The resurgence of demand-responsive transit (DRT) has been pushed toward a more sharable and user-friendly mobility service to reshape the urban mobility ecosystem. Nevertheless, to fulfill the swiftly growing diversified and personalized demand, how to depict the cancellation behavior of passengers remains an often overlooked but extremely significant challenge. This paper attempts to discuss the cancellation behavior in the two-phase optimization process. With regard to the unconfirmed reservation cancellation, bounded rationality is incorporated to portray the decision-making process of passengers. Bernoulli random variable is utilized to discuss the stochastic possibility of order cancellation. Simultaneously, a two-phase biobjective model considering the cancellation behavior is constructed to balance the inherent trade-off between passengers and operators. In addition, the algorithm based on multidirectional local search is constructed to achieve the Pareto front for the proposed model. Small-scale experiments in the Nguyen-Dupuis network are illustrated to validate the effectiveness of the algorithm. Subsequently, the Beijing case is further exemplified to evaluate the performance of DRT service considering the cancellation behavior. A reasonable penalty mechanism contributes to ensuring operating profit while substantially diminishing the penalty cost. Therefore, this paper facilitates not only capturing the cancellation behavior of passengers but also developing a more flexible and cost-effective DRT service.

A Comprehensive Analysis of Clustering Public Utility Bus Passenger’s Behavior during the COVID-19 Pandemic: Utilization of Machine Learning with Metaheuristic Algorithm

Public utility bus (PUB) systems and passenger behaviors drastically changed during the COVID-19 pandemic. This study assessed the clustered behavior of 505 PUB passengers using feature selection, K-means clustering, and particle swarm optimization (PSO). The wrapper method was seen to be the best among the six feature selection techniques through recursive feature selection with a 90% training set and a 10% testing set. It was revealed that this technique produced 26 optimal feature subsets. These features were then fed into K-means clustering and PSO to find PUB passengers’ clusters. The algorithm was tested using 12 different parameter settings to find the best outcome. As a result, the optimal parameter combination produced 23 clusters. Utilizing the Pareto analysis, the study only considered the vital clusters. Specifically, five vital clusters were found to have comprehensive similarities in demographics and feature responses. The PUB stakeholders could use the cluster findings as a benchmark to improve the current system.

Effect of time stress and store visibility on the dynamics of passenger activity choices at airport terminals based on indoor trajectory data

As mobile devices become more sophisticated and ubiquitous, airports have greater access to information on the activities of passengers and their reasons for engaging in such activities. This study proposes a novel trajectory-based dynamic choice model that can capture the effects of time stress, store visibility, and trajectory histories on activity choices in airport terminals. To evaluate the proposed model, two surveys on passenger trajectories and activities at Songshan Airport in Taipei, Taiwan, were conducted. The results reveal that although passengers under less time stress are more likely to perform discretionary activities, the dynamics of store-visiting choices suggest that airport shoppers can be distinguished into two types: shoppers whose store-visiting probability is negatively associated with time stress, and shoppers whose store-visiting probability has a concave relationship with time stress. The effect of visual attractiveness is especially strong for process activities (e.g., passing through security screening and passport control), and the variance in the visual-attractiveness effect for discretionary activities (e.g., shopping) is strongly influenced by the airport environment. The results also indicate novelty-seeking behavior: passengers are less likely to do something that they have already done. Our findings suggest that passengers behave heterogeneously in response to various levels of time stress but homogeneously in response to visual cues. Despite the variation in passenger characteristics, this study demonstrates that trajectory data alone are sufficient for the construction of passenger behavior models with satisfactory temporal transferability.