Passenger Data Research Articles

Evaluating hybrid model performance in predicting the impact of lockdown on controlling covid-19 cases progression in middle income settings

The rapidly spreading COVID-19 pandemic in 2020-2021 affected more than 190 countries, including Nigeria. Following this scenario, countries around the world were monitoring confirmed cases, recovering and dying. In order to reduce the impact of the pandemic, most countries implemented several measures to control the spread of the virus. These include closing schools and borders, shutting down public transport and workplaces, and restricting public gatherings until herd immunity is achieved through vaccination. The breakdown of the health system and the unpredictable nature of human behaviour makes it difficult to predict and evaluate the impact of lockdown on the COVID-19 pandemic in the long term. In light of the above, this study developed Hybrid ANN-CNN and four other models, namely LASSO, ANN, CNN and LSTM, to predict and evaluate the effect of human mobility on COVID-19 confirmed cases. To evaluate the effectiveness of non-pharmaceutical interventions (NPIs) and to predict the spread of COVID-19 confirmed cases, publicly availabledata on human mobility collected by Google and air passenger data were used. In this study, our motivation was to evaluate effect of lockdown on COVID-19 and models that predict the impact of human mobility on COVID-19 confirmed cases based on MSLE, Huber loss, and Log Cosh performance measures. At the end of the experiment, the developed hybrid ANN-CNN outperformed the other four models with MSLE of (0.0022), Huber Loss (0.0014) and Log Cosh (0.0013) respectively. This study serves as an alarm system to provide policy makers with the human mobility factors that can trigger large numbers of cases during a pandemic. This will allow for urgent public action.

A Novel Approach to Reduce Breaches of Aircraft Communication Data

Aircraft are complex systems that rely heavily on monitoring and real-time communications with the base station. During aviation and flight operations, diverse data are gathered from different sources, including the Cockpit Voice Recorder (CVR), Flight Data Recorder (FDR), logbook, passenger data, passenger manifest etc. Given the high sensitivity of flight data, it is an attractive target for adversaries which could result in operational, financial and safety related incidents. Communications between aircraft pilots and air traffic controllers are all unencrypted. The data, mainly audio communication files, are placed openly within data centers on the ground stations which could lead to a serious compromise in security and privacy. One may rely on the cloud owing to its on-demand features but to thwart possible attacks, the data need to be encrypted first, giving rise to the issue of conducting search over encrypted data. This research presents a novel approach for data security in aviation industry by introducing a semantic-based searchable encryption scheme over the cloud. The designed system has proven to be extraordinarily effective for semantic-based searchable encryption at the word and the text level. The rigorous security and complexity analysis shows that the proposed solution provides a high level of security and efficiency and can be effectively deployed in the aviation sector. The designed scheme is tested through a real-world aviation dataset collected to demonstrate the significance of this research. The proof of concept proves to be secure, privacy-preserving and lightweight while resisting distinguishability attacks.

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.

Time-dependent customized bus routing problem of large transport terminals considering the impact of late passengers

Customized bus (CB) provides convenient door-to-door transportation services to passengers through a subscription-based model. To ease the problem of insufficient taxis and private hire services at large transport terminals, we propose and evaluate a customized CB service for railway stations and airports in China. The proposed CB problem considers a routing problem with time-dependent travel time and late-customers. A periodic optimization approach is adopted to periodically collect passenger demands, optimize customized bus routes for the period, and re-optimize the routes to cater to late-coming customers. The static problem for each period is modeled as a time-dependent customized bus routing problem with time windows and release date (TDCBRPTW-R), which is solved with a hybrid meta-heuristic algorithm combining adaptive large neighborhood search (ALNS) with variable neighborhood descent (VND). An acceleration method is developed for insertion feasibility check for the TDCBRPTW-R. The stability and accuracy of the proposed algorithm is evaluated in the numerical experiments derived from Solomon’s data set. For the periodic re-optimization procedure, four methods are proposed to handle late customers according to different application scenarios. The re-optimization procedure is tested on the road network in Chengdu with passenger data provided by Didi Chuxing. The experiments demonstrate that a loose time window allows the service to serve more passengers and reduces operational costs. Lastly, the experiments also show the effectiveness of the proposed methods in handling late customers.

Scheduling of Coupled Train Platoons for Metro Networks: A Passenger Demand-Oriented Approach

In recent years the concept of virtual coupling, where multiple train units are virtually coupled into a platoon with very short following distances, has received considerable attention in the railway transportation field. This study introduces this concept into the train scheduling problem to improve line capacity and reduce congestion in urban metro networks. With consideration of the time-dependent passenger demand, train (platoon) loading capacity, and limited rolling stock resources, specifically, a mixed integer linear programming model is developed to simultaneously generate the platoon (de)coupling strategies, orders of trains, and their arrival/departure times at each station in the metro network. Several model improvement strategies, for example, model linearization and determination of big-[Formula: see text] values, are proposed to enhance the computational efficiency of the model. Finally, numerical experiments based on historical passenger data from the Beijing metro network are implemented to verify the effectiveness of the approach. The results demonstrate that the introduction of train platoons of different sizes can evidently reduce station congestion, while the percentage improvement greatly depends on the distribution of passenger demand.

A year-round analysis of railway station overruns due to low adhesion conditions

Key Performance Indicators, such as station overruns and delay minutes, are used to assess the performance and punctuality of the GB railway. They can be used to quantify the effects of low adhesion, but the majority of previous analysis has been constrained to the autumn season. A Python script has been created in this work to extract 11 years of detailed passenger and freight station overrun data, throughout the entire year. The information gathered includes time and date, location, direction, vehicle type, railhead conditions and subsequent delay minutes caused by the incident. Although the majority of low adhesion related overruns occur in the autumn season due to leaf fall, this work has highlighted the number of low adhesion related issues that occur throughout the year where there are no visible signs of contamination. This work gives an overview of this new dataset and looks at some key trends in the data but the granular detail available means that future case studies could be carried out in specific locations, linked to geographic and meteorological data, to assess when and why low adhesion is occurring. From an operational perspective, the dataset could then be used as a daily updated assessment of the effectiveness of low adhesion mitigation methods.

Modelling essential habitat for common scoter (Melanitta nigra) in a disturbed environment

The realised distribution of species in disturbed environments depends upon the degree to which their optimum habitat has been altered by impacts arising from human pressures. We investigated how pressures such as fishing activity, changes in prey availability and habitat quality affect the distribution of Common Scoter (CS) in the north Irish Sea. CS distribution data were obtained from aerial surveys in the winter of 2018–2019. We developed two generalised additive models using covariate information on depth, seabed shear stress, VMS activity of fishing vessels, AIS data of passenger and cargo vessels, portion of fine sand in the benthos, abundance of deep-burrowing bivalves and abundance of surficial bivalves. There was no clear evidence that the fishery, through either disturbance effects nor direct prey competition caused by extraction of razor clams, affected the distribution of CS in the area. However, indirect effects of the fishery, mediated through impacts on abundance and perhaps recruitment of bivalves on CS, could not be ruled out. The absence of a disturbance effect may be due to the small size of vessels in this fleet and their slow fishing speeds. The abundance of surficial bivalves, depth, the portion of fine sand and shear stress at the seabed in the sediments influenced CS distribution. This indicates that the distribution of CS in the area is driven by foraging conditions rather than the presence of fishing vessels.

Trip Destination Prediction Based on Hidden Markov Model for Multi-Day Global Positioning System Travel Surveys

Different individuals may move to different regions over time, but every individual has several fixed travel positions or unique travel patterns. Predicting destinations of each individual facilitates traffic demand management, which has great research value. Based on the data of multi-day GPS and passengers’ travel survey, a hidden Markov model (HMM) is employed in this paper to predict trip destination for weekdays and weekends. Firstly, the habit of destination choice among consecutive days and weeks can be discovered by identifying frequently visited destinations. Then, on the basis of Viterbi algorithm, this paper takes frequently visited destinations as one of the factors of the predicting process and constructs a travel destination prediction model based on HMM. Then, the HMM is calibrated with Baum-Welch algorithm and passengers’ travel destination characteristics are effectively analyzed. Finally, the HMM was compared with several classical algorithms. The results show that the place of residence and work are the most probable activities to occur and workplace dominates the activities when duration is longer than 8 h. Moreover, the results of frequently visited destinations identification indicate that the patterns of destination choice on weekdays and weekends are different from each other. In addition, the results show that the prediction accuracy on weekdays is higher than that on weekends and HMM outperforms other prevailing algorithms. The method proposed in this paper can be applied to real-time travel navigation applications, as well as supporting health and safety fields, such as epidemic prevention and control.

Prediction of Bus Passenger Traffic using Gaussian Process Regression.

The paper summarizes the design and implementation of a passenger traffic prediction model, based on Gaussian Process Regression (GPR). Passenger traffic analysis is the present day requirement for proper bus scheduling and traffic management to improve the efficiency and passenger comfort. Bayesian analysis uses statistical modelling to recursively estimate new data from existing data. GPR is a fully Bayesian process model, which is developed using PyMC3 with Theano as backend. The passenger data is modelled as a Poisson process so that the prior for designing the GP regression model is a Gamma distributed function. It is observed that the proposed GP based regression method outperforms the existing methods like Student-t process model and Kernel Ridge Regression (KRR) process.

Research on temporal and spatial distribution characteristics of passenger flow of Daxing airport line based on automatic fare collection data

AbstractThe airport line plays an important role in the airport landside traffic connection, which greatly relieves the urban road pressure. Studying the characteristics and laws of the time and space distribution of the airport line passenger flow will provide basic support for the airport line's capacity configuration, passenger flow control, and air‐track coordinated operation, and will also provide quantitative basis for the layout of urban terminal buildings. This paper proposes a method to analyse the temporal and spatial distribution characteristics of airport line passenger flow based on AFC card swiping data. By mining and extracting the travel behaviour data of subway airport line air passengers, the distribution characteristics of airport line passenger flow are analysed and visualized from two aspects of passenger travel time and space. Finally, a case study is carried out based on the actual data of Daxing airport express. The results show that: (1) the travel time of departure and return passengers is concentrated in 60–90 min; (2) The departure and arrival points of passengers are concentrated within the Fourth Ring Road, and a large number of air passenger flows are gathered and evacuated at hubs such as Beijing South Railway Station and Beijing West Railway Station.

Train timetabling with passenger data and heterogeneous rolling stocks circulation on urban rail transit line

AbstractThe planning process in urban rail transportation can be split into several stages, including line planning, timetabling, rolling stock scheduling and so on. The outcome of a stage provides inputs or constraints to the subsequent ones. However, while the output can be good or optimal at each stage, it rarely considers the global quality for the overall planning process. Furthermore, problems tackled at planning phase often use a more aggregate representation of reality, to achieve a more general overview. An integrated approach, while more complex to solve, may mitigate the gap between solution of different stages and a validation of a plan would still be required before its implementation in practice. In this paper, we focus on integrated optimization of train timetabling and rolling stock circulation for urban rail transit line with time-based origin-destination-dependent passenger travel demand and heterogeneous rolling stocks. The aim is to generate a comfortable timetable for passengers and an efficient timetable for operators. The objective is to minimize the total waiting time for passengers and the costs for operators, while constraints regarding train movements, passenger boarding and alighting, available rolling stocks and their capacity are considered. A mixed integer linear programming model is formulated and solved by an iterative programming approach. Computational experiments are performed on the Chongqing Rail Transit Line 2 to verify the efficiency and effectiveness of the proposed model and solving method. With respect to CPLEX, results show the proposed iterative programming approach has advantages both on computation time and solution quality.

Stroke in Airplane Passengers: A Study from a Large International Hub

IntroductionStroke in air travelers is being increasingly recognized. We report on stroke among passengers arriving at or transiting through a busy air travel hub. MethodsThe stroke database of the sole tertiary care center for stroke in a large busy international hub was interrogated. Demographic data of transit passengers, their stroke risk factors, stroke severity, National Institutes of Health Stroke Scale (NIHSS), acute stroke interventions, discharge status and outcome utilizing the Modified Raking scale (mRS) were retrieved and compared between passengers and non-passenger controls. ResultsForty-three flight-related stroke patients were compared to 2564 non-passenger stroke patients. The mean age in the flight-related stroke group was 59.53±10.83 years, 30/43 (69.8%) were males. The stroke subtypes were ischemic in 30 (69.8%) patients, hemorrhagic in 9 (20.9%), and transient ischemic attack in 3 (7.0%), with one cerebral sinus venous thrombosis (2.3%). The mean NIHSS score was 7.79±6.44 in passengers, demonstrating moderate severity. Ten patients (23.3%) received thrombolysis, one (2.3%) received thrombectomy, and one (2.3%) received both thrombolysis and thrombectomy. Outcomes, 54.8% had a good outcome (mRS 0-2), and 45.2% had dependence/death (mRS 3-6). ConclusionAir passengers with stroke were found to be older with more severe strokes and a higher probability of receiving acute stroke treatment compared to non-passengers. Increased awareness with appropriate and timely recognition and triaging of transit passengers with stroke is warranted.

Effect of uniform time on the transmission of signals in rail open systems

Railroads and the Rail Traffic Control Systems installed on them in Poland have recently been undergoing rapid technological development (Brodzik, 2019). Modern transportation solutions are susceptible to electromagnetic interference (Paś and Rosiński, 2017). Development of modern railroad infrastructure means not only stations and modern rolling stock, but also safe and reliable train traffic control systems based on the latest telecommunication and IT technologies (Ciszewski et al., 2017). In the last century these technologies were still considered dangerous and were introduced with great fear. Today, computerized systems for controlling railway traffic on the track are becoming the norm. Systems are created as "overlays" for existing relay systems or autonomous systems are built based on microprocessor systems (Burdzik et al., 2017). Today it is hard to imagine a modern control room without computer equipment. The introduction of microprocessor technology to railroad traffic control devices took place at the turn of the century. However, the use of modern radio systems in rail transport is the moment when technology based on the appeared in the world LTE (Long-Term evolution) standard. The development of modern data transmission technologies is integrally connected with the mobility of its users. In the presented article the author has tried to determine the impact of transmission synchronization on the basic transmission parameters of LTE signal (Chrzan, 2021). The convenience of using rail communications for its users is the possibility of uninterrupted access to data transmission services along the entire route of the train. Therefore, the research presented in this article was focused on the use of the public radio communication network for passenger data transmission and data transmission for railroad needs. The article presents the influence of synchronisation of data transmission in open railway systems using GPS (Global Positioning System) technology. It presents a description of the physical phenomena associated with synchronisation, and presents the author's method for carrying out measurements on railway line No. 4. For this purpose, a diagnostic station was built and special software for data transmission encryption was prepared. The process of synchronisation of clocks with the use of uniform time was adopted as the basis. General measurement results and conclusions resulting from the use of open transmission in railway radiocommunication systems synchronised by the GPS system signal are presented.

A column generation algorithm for the demand‐responsive feeder service with mandatory and optional, clustered bus‐stops

AbstractWith the rise of smart cities, relevant passenger data can be collected to improve the quality of transport services. In this article, a demand‐responsive feeder service is presented. A feeder service transports passengers from a low‐demand area, like a suburban area, to a transportation hub, like a city center. The feeder service modeled in this article considers two sets of bus stops: mandatory stops and optional stops. Mandatory stops are always visited by a bus, while optional stops are only visited when a client nearby makes a request for transportation. This gives the service both flexibility and some predictability. To optimize the performance of the service, mathematical modeling techniques to improve the model's runtime are developed. It is concluded that a combination of column generation and the separation of sub‐tour elimination constraints decreases the computing time of small and midsize instances significantly.

THE SOLUTION OF MATHEMATICAL MODEL OF OTOBUS TICKET SALES WITH REFERRAL MARKETING STRATEGY

One of the ways to involve customers in marketing strategies is known as the referral strategy. This strategy has been applied in various fields for marketing, one of which is in the field of transportation. This study aims to determine the solution to the mathematical model of bus ticket sales using a referral strategy. The data in this study is bus passenger data throughout 2020 which was obtained from one of the Otobus companies in Jakarta. Mathematical model that is compiled using the analogy of the model of the spread of disease. The results of this study are a mathematical model of bus ticket sales using a referral strategy consisting of 4 compartments. The model solution is determined by iterating over the system of differential equations that has been formed. Based on the solution obtained, the simulation results show that the referral strategy in bus ticket sales is able to increase bus passengers up to 39.92%.

Bayesian Analysis for Metro Passenger Flows Using Automated Data

With the fast development of metro systems in many big cities, it is important to study the characteristics of passenger flows based on metro data for the management to guarantee service quality and safety. In this article, we build statistical models for the data of passengers’ tap-in and tap-out times in both no-transfer and one-transfer cases, and propose a Bayesian approach to estimate parameters in the models. These estimators can be used to evaluate a number of measures, which describe degrees of congestion and comfort, and to quantify their uncertainties. Application of our approach to Beijing metro shows different passengers follow different patterns between different routes and between off-peak and peak hours.

Screenline-Based Two-Step Calibration and its Application to an Agent-Based Urban Freight Simulator

Calibration is an essential process in making an agent-based simulator operational. In particular, the calibration for freight demand is challenging because of the model complexity and the shortage of available freight demand data compared with passenger data. This paper proposes a novel calibration method that relies solely on screenline counts, named screenline-based two-step calibration (SLTC). SLTC consists of two parts: (1) tour-based demand adjustment; and (2) model parameter updates. The former generates screenline-based tours by cloning/removing instances of the simulated goods vehicle tours, aiming to minimize the gaps between the observed and the simulated screenline counts. The latter updates the parameters of the commodity flow model which generates inputs to simulate goods vehicle tours. To demonstrate the practicality of the proposed method, we apply it to an agent-based urban freight simulator, SimMobility Freight. The result shows that SLTC allows the simulator to replicate the observed screenline counts with reasonable computational cost for calibration.

International Passenger Traffic at the Hellenic Airports: Impact of the COVID-19 Pandemic and Mid-Term Forecasting

The aviation industry in the COVID-19 pandemic era (caused by the SARS-CoV-2 pathogen) is practically starting from scratch as significant losses have been recorded since the outbreak in December 2019. This paper focuses on the study of the available historical operational data (provisional and final) of international passenger traffic to and from the Hellenic airports. The data originated from the official state statistics agency (Hellenic Civil Aviation Authority, HCAA). A forecasting model was developed to provide an estimation of the international passenger traffic at the Hellenic airports from August to December 2021. Through this analysis, the severe impact of two lockdown events and how they will affect the expected recovery rate of air travel is demonstrated. From this perspective, some first conclusions can be drawn about the expected recovery of international air travel to the growth rates of the 2019 pre-pandemic levels.

Estimating the potential for global dissemination of pandemic pathogens using the global airline network and healthcare development indices

Pandemics have the potential to incur significant health and economic impacts, and can reach a large number of countries from their origin within weeks. Early identification and containment of a newly emerged pandemic within the source country is key for minimising global impact. To identify a country’s potential to control and contain a pathogen with pandemic potential, we compared the quality of a country’s healthcare system against its global airline connectivity. Healthcare development was determined using three multi-factorial indices, while detailed airline passenger data was used to identify the global connectivity of all countries. Proximities of countries to a putative ‘Worst Case Scenario’ (extreme high-connectivity and low-healthcare development) were calculated. We found a positive relationship between a country’s connectivity and healthcare metrics. We also identified countries that potentially pose the greatest risk for pandemic dissemination, notably Dominican Republic, India and Pakistan. China and Mexico, both sources of recent influenza and coronavirus pandemics were also identified as among the highest risk countries. Collectively, lower-middle and upper-middle income countries represented the greatest risk, while high income countries represented the lowest risk. Our analysis represents an alternative approach to identify countries where increased within-country disease surveillance and pandemic preparedness may benefit global health.

The public transport navigation system

Public transport maps are typically designed in a way to support route finding tasks for passengers, while they also provide an overview about stations, metro lines, and city-specific attractions. Most of those maps are designed as a static representation, maybe placed in a metro station or printed in a travel guide. In this paper, we describe a dynamic, interactive public transport map visualization enhanced by additional views for the dynamic passenger data on different levels of temporal granularity. Moreover, we also allow extra statistical information in form of density plots, calendar-based visualizations, and line graphs. All this information is linked to the contextual metro map to give a viewer insights into the relations between time points and typical routes taken by the passengers. We also integrated a graph-based view on user-selected routes, a way to interactively compare those routes, an attribute- and property-driven automatic computation of specific routes for one map as well as for all available maps in our repertoire, and finally, also the most important sights in each city are included as extra information to include in a user-selected route. We illustrate the usefulness of our interactive visualization and map navigation system by applying it to the railway system of Hamburg in Germany while also taking into account the extra passenger data. As another indication for the usefulness of the interactively enhanced metro maps we conducted a controlled user experiment with 20 participants.Graphical abstract