Dwell Time Estimation Research Articles

Impact of Station Design and Passengers Flow on Urban Rail Dwell Time: A Systemwide Analysis Using APC and AVL Data

In this paper, we investigated the impact on dwell time of station design, train load, and passenger flow, considering boarding fraction. We employed system-wide automated data sources including automatic passenger counting and automatic vehicle location data in the rail transit system in Calgary, Canada. Regression analyses were conducted to achieve accurate dwell time estimation by calculating passenger load per car, boarding, and alighting passengers per door, and also identifying the critical door with the highest demand. Observations for each critical door were divided based on the fraction of boarding passengers with respect to the sum of boarding and alighting. Six stations with distinct geometric designs were selected for comparison to assess their impact on dwell time. The results indicate that, for dominant boarding or alighting, a longer time is needed per passenger to alight or board, respectively. Our findings indicate that a station with a middle platform and two entrances positioned in the middle performed better in terms of dwell time in the case of alighting-dominant and mixed passenger flow. For stations experiencing boarding-dominant passenger flows, side platforms with multiple entrances at the ends and middle outperformed. Narrower platforms experienced significantly longer dwell times than other selected stations under similar demand. While the conclusion about the station design may not be generic, the proposed model provides a consistent and adaptable approach to study the impact of station design and passenger flows on urban rail dwell times, facilitating better-informed decision-making for station design or modification and enhancement of the overall rail system performance.

A Comparative Study of Machine Learning Models for Predicting Vessel Dwell Time Estimation at a Terminal in the Busan New Port

Container shipping plays a pivotal role in global trade, and understanding the duration that vessels spend in ports is crucial for efficient voyage planning by shipping companies. However, these companies often rely solely on one-way communication for required arrival times provided by terminals. This reliance on fixed schedules can lead to vessels arriving punctually, only to face berths that are still occupied, resulting in unnecessary waiting times. Regrettably, limited attention has been given to these issues from the perspective of shipping companies. This study addresses this gap by focusing on the estimation of dwell times for container vessels at a terminal in the Port of Busan using various machine learning techniques. The estimations were compared against the terminal’s operational reference. To compile the dataset, a 41-month history of terminal berth schedules and vessel particulars data were utilized and preprocessed for effective training. Outliers were removed, and dimensions were reduced. Six regression machine learning algorithms, namely adaptive learning, gradient boosting, light gradient boosting, extreme gradient boosting, categorical boosting and random forest, were employed, and their parameters were fine-tuned for optimal performance on the validation dataset. The results indicated that all models exhibited superior performance compared to the terminal’s operating reference model.

Examining Bus Lost Time Dynamics for a Bus Rapid Transit Station

Bus Rapid Transit (BRT) systems are considered to be the most effective alternative for solving urban transportation problems for both developed and developing countries. The conventional approach to estimate dwell time (DT) is based on traditional DT models derived for normal bus stops, but not for modern BRT stations. BRT stations are different from bus stops in terms of length of platform, multiple loading areas, and number of passengers handled. Therefore, understanding dwell time dynamics, including the recently-introduced component of Bus Lost Time (BLT), is important to improve the operations of BRT systems. This research introduces various possible scenarios of alighting and boarding using video data collected at the Shivranjini BRT station in Ahmedabad, India.In total, 877 observations of BLT and DT were extracted from 17 hours of video data recorded for one full-service time of the day. The possibility of BLT occurrence was examined and explained with the help of conceptual line diagrams, and the probability distribution of BLT was fitted for two loading area platforms by considering 401 observations from the BRT platform video data of the entire service period. A comparative evaluation was made between observed and estimated BLT values. This study estimated station capacities before and after, including BLT as a DT component to observe the effect of BLT on BRT stop capacity. It was observed from the results that including BLT in dwell time reduced BRT capacity by 11%. This study provides ready-to-use BLT values for correct estimation of dwell time, thus improving accurate estimation of BRT station capacity.

Recognition of Vehicles Entering Expressway Service Areas and Estimation of Dwell Time Using ETC Data.

To scientifically and effectively evaluate the service capacity of expressway service areas (ESAs) and improve the management level of ESAs, we propose a method for the recognition of vehicles entering ESAs (VeESAs) and estimation of vehicle dwell times using electronic toll collection (ETC) data. First, the ETC data and their advantages are described in detail, and then the cleaning rules are designed according to the characteristics of the ETC data. Second, we established feature engineering according to the characteristics of VeESA and proposed the XGBoost-based VeESA recognition (VR-XGBoost) model. Studied the driving rules in depth, we constructed a kinematics-based vehicle dwell time estimation (K-VDTE) model. The field validation in Part A/B of Yangli ESA using real ETC transaction data demonstrates that the effectiveness of our proposal outperforms the current state-of-the-art. Specifically, in Part A and Part B, the recognition accuracies of VR-XGBoost are 95.9% and 97.4%, respectively, the mean absolute errors (MAEs) of dwell time are 52 and 14 s, respectively, and the root mean square errors (RMSEs) are 69 and 22 s, respectively. In addition, the confidence level of controlling the MAE of dwell time within 2 min is more than 97%. This work can effectively recognize the VeESA and accurately estimate the dwell time, which can provide a reference idea and theoretical basis for the service capacity evaluation and layout optimization of the ESA.

Estimating bus dwell time: A review of the literature

ABSTRACT An accurate estimation of bus dwell time (BDT) is important as it directly influences the prediction of vehicles’ arrival times at bus stops and hence, the reliability of their services. Developing an efficient method to estimate BDT has received significant attention in the literature as numerous studies have been conducted on this topic. This paper provides an overview of research works conducted in the past on bus dwell time. It covers three aspects: first methods used in the literature to estimate BDT, second factors influencing BDT and third methods used in the literature to collect data. The methods used in the literature to estimate BDT are broadly classified and discussed under three categories namely, regression-based models, probabilistic and time series models and artificial intelligence-based models along with their strengths and weaknesses. The influence of different policy measures related to characteristics of bus, passengers, time-of-day, transit, and route are discussed. The research trends reveal an increasing tendency to employ more advanced methods for data collection (using GPS, APC and AVL) and modelling (e.g. using machine learning-based methods).

Dwell Time Estimation of Import Containers as an Ordinal Regression Problem

The optimal stacking of import containers in a terminal reduces the reshuffles during the unloading operations. Knowing the departure date of each container is critical for optimal stacking. However, such a date is rarely known because it depends on various attributes. Therefore, some authors have proposed estimation algorithms using supervised classification. Although supervised classifiers can estimate this dwell time, the variable “dwell time” takes ordered values for this problem, suggesting using ordinal regression algorithms. Thus, we have compared an ordinal regression algorithm (selected from 15) against two supervised classifiers (selected from 30). We have set up two datasets with data collected in a container terminal. We have extracted and evaluated 35 attributes related to the dwell time. Additionally, we have run 21 experiments to evaluate both approaches regarding the mean absolute error modified and the reshuffles. As a result, we have found that the ordinal regression algorithm outperforms the supervised classifiers, reaching the lowest mean absolute error modified in 15 (71%) and the lowest reshuffles in 14 (67%) experiments.

Dwell time estimation at intersections for improved vehicular micro cloud operations

Edge computing is becoming a major building block of next generation 5G/6G networks. However, infrastructure might not always be available because of slow deployment. At the same time, vehicular networks are becoming a reality now and cars are being equipped with a variety of short-range communication devices. The idea of vehicular micro clouds is to turn cars into (virtual) edge computing infrastructure. One of the challenging questions in this domain is to maintain data within and among such micro clouds. In this paper, we focus on this task and present a novel solution for such data exchange between vehicular micro clouds. For efficient operation, the dwell times of cars in such a micro cloud need to be known or accurately predicted. In an extensive study based on trace data, we investigate the distribution of dwell times of cars at intersections. We make use of this distribution as an input for designing an improved data exchange algorithm. As not all intersections are the same, adding additional variance further benefits the solution. We evaluated our algorithm in different vehicular densities, and we observed that we could maintain data 22–208% longer within the micro clouds using our new algorithm. Overall, our results show that our algorithm clearly outperforms previous solutions.

High resolution small-scale inorganic scintillator detector: HDR brachytherapy application.

Brachytherapy (BT) deals with high gradient internal dose irradiation made up of a complex system where the source is placed nearby the tumor to destroy cancerous cells. A primary concern of clinical safety in BT is quality assurance to ensure the best matches between the delivered and prescribed doses targeting small volume tumors and sparing surrounding healthy tissues. Hence, the purpose of this study is to evaluate the performance of a point size inorganic scintillator detector (ISD) in terms of high dose rate brachytherapy (HDR-BT) treatment. A prototype of the dose verification system has been developed based on scintillating dosimetry to measure a high dose rate while using an 192 Ir BT source. The associated dose rate is measured in photons/s employing a highly sensitive photon counter (design data: 20 photons/s). Dose measurement was performed as a function of source-to-detector distance according to TG43U1 recommendations. Overall measurements were carried out inside water phantoms keeping the ISD along the BT needle; a minimum of 0.1cm distance was maintained between each measurement point. The planned dwell times were measured accurately from the difference of two adjacent times of transit. The ISD system performances were also evaluated in terms of dose linearity, energy dependency, scintillation stability, signal-to-noise ratio (SNR), and signal-to-background ratio (SBR). Finally, a comparison was presented between the ISD measurements and results obtained from TG43 reference dataset. The detection efficiency of the ISD was verified by measuring the planned dwell times at different dwell positions. Measurements demonstrated that the ISD has a perfectly linear behavior with dose rate (R2 =1) and shows high SNR (>35) and SBR (>36) values even at the lowest dose rate investigated at around 10cm from the source. Standard deviation (1σ) remains within 0.03% of signal magnitude, and less than 0.01% STEM signal was monitored at 0.1cm source-to-detector distance. Stability of 0.54% is achieved, and afterglow stays less than 1% of the total signal in all the irradiations. Excellent symmetrical behavior of the dose rate regarding source position was observed at different radiation planes. Finally, a comparison with TG-43 reference dataset shows that corrected measurements agreed with simulation data within 1.2% and 1.3%, and valid for the source-to-detector distance greater than 0.25cm. The proposed ISD in this study anticipated that the system could be promoted to validate with further clinical investigations. It allows an appropriate dose verification with dwell time estimation during source tracking and suitable dose measurement with a high spatial resolution both nearby (high dose gradient) and far (low dose gradient) from the source position.

Applying a Dwell Time-Based 5G V2X Cell Selection Strategy in the City of Los Angeles, California

The fifth generation of wireless networks is expected to provide high capacity, low latency, high reliability, and massive connectivity services. Ultra-dense network (UDN) is a clear trend for enhancing capacity, coverage, and load balancing. In UDNs, the cell selection issue for moving vehicles should be addressed. In this paper, a cell selection strategy known as a dwell time estimation (DTE) scheme is proposed, which is based on Vehicle-to-Everything (V2X) communications. It selects small cells that have the longest dwell time in a vehicle’s direction to decrease handover (HO) rate. The proposed DTE scheme is evaluated using two datasets, which are 5G small cells and vehicles datasets, that were collected in the city of Los Angeles in California. The simulation result shows that our DTE algorithm outperforms other recent related schemes in terms of the mean number of HOs by up to 36.26% because it prolongs the dwell time of the vehicle within the serving small cell. Consequently, it reduces the average number of HO failures and unnecessary HOs. In addition, it gives improvements in terms of the average achievable downlink throughput and network energy efficiency. Furthermore, it has superiority over the other schemes in terms of the mean packet delay by up to 16.49%.

Impact of Carriage Crowding Level on Bus Dwell Time: Modelling and Analysis

This paper develops two types of estimation models to quantify the impacts of carriage crowding level on bus dwell time. The first model (model I) takes the crowding level and the number of alighting and boarding passengers into consideration and estimates the alighting time and boarding time, respectively. The second model (model II) adopts almost the same regression method, except that the impact of crowding on dwell time is neglected. The analysis was conducted along two major bus routes in Harbin, China, by collecting 640 groups of dwell times under crowded condition manually. Compared with model II, the mean absolute error (MAE) of model I is reduced by 137.51%, which indicates that the accuracy of bus dwell time estimation could be highly improved by introducing carriage crowding level into the model. Meanwhile, the MAE of model I is about 3.9 seconds, which is acceptable in travel time estimation and bus schedule.

Dwell Time Estimation Using Real-Time Train Operation and Smart Card-Based Passenger Data: A Case Study in Seoul, South Korea

Dwell time is a critical factor in constructing and adjusting railway timetables for efficient and accurate operation of railways. This paper develops dwell time estimation models for a Shinbundang line (S line) in Seoul, South Korea using support vector regression (SVR), multiple linear regression (MLR), and random forest (RF) techniques utilizing archived real-time metro operation data along with smart card-based passenger information. In the first phase of this research, the collected data are processed to extract boarding and alighting passenger counts and observed dwell times of each train at all stations of the S line under the current operational environment. In the second phase, we develop SVR, MLR, and RF-based dwell time estimation models. It is found that the SVR-based model successfully estimates the dwell times within 10 s of differences for 84.4% of observed data. The results of this paper are especially beneficial for autonomous railway operations that need constructing and maintaining dynamic railway timetables that require reliable dwell time predictions in real-time.

Target Network Selection Algorithm based on Required Dwell Time Estimation

In wireless communication of fourth generation the expectation to integrate a diverse heterogeneous wireless network leads to a worldwide seamless mobility. For seamless mobility in heterogenous wireless networks, selection of best target network from available network is primary goal for handovers. To achieve this goal, we devise a target network selection algorithm to enhance the user satisfaction level.The method relies on a dwell time and prediction of received signal strength. By observing the Predicted received signal strength for a specified dwell time duration, a mobile node is able to decide whether to tigger the handoff process or not. Once the handoff process is triggered. Target network is selected depending upon a cost function. The Simulated results shows that, the proposed algorithm improves the handover performance by measuring the received signal strength accurately. It also selects the optimum target network quantitatively. Therefore, results obtained through our proposed algorithm are more accurate as compared to existing handover algorithms.

Target Network Selection Algorithm based on Required Dwell Time Estimation

In wireless communication of fourth generation the expectation to integrate a diverse heterogeneous wireless network leads to a worldwide seamless mobility. For seamless mobility in heterogenous wireless networks, selection of best target network from available network is primary goal for handovers. To achieve this goal, we devise a target network selection algorithm to enhance the user satisfaction level.The method relies on a dwell time and prediction of received signal strength. By observing the Predicted received signal strength for a specified dwell time duration, a mobile node is able to decide whether to tigger the handoff process or not. Once the handoff process is triggered. Target network is selected depending upon a cost function. The Simulated results shows that, the proposed algorithm improves the handover performance by measuring the received signal strength accurately. It also selects the optimum target network quantitatively. Therefore, results obtained through our proposed algorithm are more accurate as compared to existing handover algorithms.

Implementing transit signal priority in a connected vehicle environment with and without bus stops

ABSTRACTConnected vehicles give more precise and detailed information on vehicle movements, thus can be beneficial to provide priority to public transportation. This paper proposes a transit signal priority algorithm using connected vehicle information for multimodal traffic control. The algorithm can also be adapted to scenarios with near-side or far-side bus stops. Moreover, it can minimize either signal delay or schedule delay for buses while minimizing additional car delays. Simulation is conducted for different volume to capacity ratios, bus arrivals, bus occupancies, and penetration rates. Results show that this algorithm successfully reduces the total passenger delay. It is also shown that this algorithm is not sensitive to the assumed bus passenger occupancy, nor the estimation of bus dwell time, hence does not require accurate information on these parameters. Overall, this algorithm seems rather promising as it significantly reduces the delay of buses with minimal increase to the delay of cars in the conflicting approach.

Testing the Generality of a Passenger Disregarded Train Dwell Time Estimation Model at Short Stops: Both Comparison and Theoretical Approaches

Train dwell time estimation is a critical issue in both scheduling and rescheduling phases. In a previous paper, the authors proposed a novel dwell time estimation model at short stops which did not require the passenger data. This model shows promising results when applied to Dutch railway stations. This paper focuses on testing and improving the generality of the model by two steps: first, the model is tested by applying more independent datasets from another city and comparing the estimation accuracy with the previous Dutch case; second, the model’s generality is tested by a theoretical approach through the analysis of individual model parameters, variables, model scenarios, and model structure as well as work conditions. The validation results during peak hours show that the MAPE of the model is 11.4%, which is slightly better than the results for the Dutch railway stations. A more generalized predictor called “dwell time at the associated station” is used to replace the square root term in the original model. The improved model can estimate train dwell time in all the investigated stations during both peak and off-peak periods. We conclude that the proposed train dwell time estimation model is generic in the given condition.

Estimation of train dwell time at short stops based on track occupation event data: A study at a Dutch railway station

SummaryTrain dwell time is one of the most unpredictable components of railway operations, mainly because of the varying volumes of alighting and boarding passengers. However, for reliable estimations of train running times and route conflicts on main lines, it is necessary to obtain accurate estimations of dwell times at the intermediate stops on the main line, the so‐called short stops. This is a great challenge for a more reliable, efficient and robust train operation. Previous research has shown that the dwell time is highly dependent on the number of boarding and alighting passengers. However, these numbers are usually not available in real time. This paper discusses the possibility of a dwell time estimation model at short stops without passenger demand information by means of a statistical analysis of track occupation data from the Netherlands. The analysis showed that the dwell times are best estimated for peak and off‐peak hours separately. The peak‐hour dwell times are estimated using a linear regression model of train length, dwell times at previous stops and dwell times of the preceding trains. The off‐peak‐hour dwell times are estimated using a non‐parametric regression model, in particular, the k‐nearest neighbor model. There are two major advantages of the proposed estimation models. First, the models do not need passenger flow data, which is usually impossible to obtain in real time in practice. Second, detailed parameters of rolling stock configuration and platform layout are not required, which makes the model more generic and eases implementation. A case study at Dutch railway stations shows that the estimation accuracy is 85.8%–88.5% during peak hours and 80.1% during off‐peak hours, which is relatively high. We conclude that the estimation of dwell times at short stop stations without passenger data is possible. Copyright © 2016 John Wiley & Sons, Ltd.

Graph‐Based Dwell Time Computation Methods for Discrete‐Time Switched Linear Systems

AbstractAnalytical computation methods are proposed for evaluating the minimum dwell time and the average dwell time guaranteeing the asymptotic stability of a discrete‐time switched linear system whose switchings are assumed to respect a given directed graph. The minimum and average dwell time can be found using the graph that governs the switchings, and the associated weights. This approach, which is used in a previous work for continuous‐time systems having non‐defective subsystems, has been adapted to discrete‐time switched systems and generalized to allow defective subsystems. Moreover, we present a novel method to improve the dwell time estimation in the case of bimodal switched systems. In this method, scaling algorithms to minimize the condition number have been used to give better minimum dwell time and average dwell time estimates.

An ELM-Based Approach for Estimating Train Dwell Time in Urban Rail Traffic

Dwell time estimation plays an important role in the operation of urban rail system. On this specific problem, a range of models based on either polynomial regression or microsimulation have been proposed. However, the generalization performance of polynomial regression models is limited and the accuracy of existing microsimulation models is unstable. In this paper, a new dwell time estimation model based on extreme learning machine (ELM) is proposed. The underlying factors that may affect urban rail dwell time are analyzed first. Then, the relationships among different factors are extracted and modeled by ELM neural networks, on basis of which an overall estimation model is proposed. At last, a set of observed data from Beijing subway is used to illustrate the proposed method and verify its overall performance.

Estimation of bus dwell time using univariate time series models

SummaryA significant proportion of bus travel time is contributed by dwell time for passenger boarding and alighting. More accurate estimation of bus dwell time (BDT) can enhance efficiency and reliability of public transportation system. Regression and probabilistic models are commonly used in literatures where a set of independent variables are used to define the statistical relationship between BDT and its contributing factors. However, due to technical and monetary constraints, it is not always feasible to collect all the data required for the models to work. More importantly, the contributing factors may vary from one bus route to another. Time series based methods can be of great interest as they require only historical time series data, which can be collected using a facility known as automatic vehicle location (AVL) system. This paper assesses four different time series based methods namely random walk, exponential smoothing, moving average (MA), and autoregressive integrated moving average to model and estimate BDT based on AVL data collected from Auckland. The performances of the proposed methods are ranked based on three important factors namely prediction accuracy, simplicity, and robustness. The models showed promising results and performed differently for central business district (CBD) and non‐CBD bus stops. For CBD bus stops, MA model performed the best, whereas for non‐CBD bus stops, ARIMA model performed the best compared with other time series based models. Copyright © 2014 John Wiley & Sons, Ltd.

Modeling Bus Dwell Time with Decision Tree-Based Methods

A large proportion of transit travel time is made up by dwell time for passengers boarding and alighting. More accurate modeling and estimation of bus dwell time (BDT) can enhance the efficiency and reliability of the public transportation system. Multiple linear regression (MLR) has been the most commonly used method in the literature for modeling and estimating BDT. However, the underlying assumptions of the MLR method, such as multicollinearity and normality of random error, cannot always be satisfied for real applications. This study developed and implemented two methods based on decision trees (DTs), namely, classification and regression tree and chi-squared automatic interaction detector, for the first time for BDT modeling and estimation. The models were compared with the traditional MLR model after calibrating and validating the new models against the data collected from four bus stops in Auckland, New Zealand. Various error measurements were used to evaluate the accuracy of the models. The DT-based methods eliminated the limitations of the MLR method and provided reliable and accurate estimation of BDT.