Bus Arrival Time Research Articles

Bus Arrival Time Modeling Based on Auckland Data

Inaccurate bus arrival time predictions are counterproductive to changing transport habits and promoting public transport use. This research sought to improve the bus passenger experience in terms of bus arrival time prediction by investigating various time series and regression-based techniques suitable for bus arrival time modeling. The models developed in the current study included: random walk with drift, multivariate linear regression, decision tree, artificial neural networks, and gene expression programming models. Historic automatic vehicle location and passenger flow data obtained for four bus routes spanning Auckland city, in both travel directions, were used as model inputs. Specifically, 10 independent variables were incorporated in the regression models, with distance between bus stops being the most significant predictor for bus travel time. Research results indicated that time series models outperformed regression techniques, with the time series artificial neural network being the most successful of the seven models developed. Moreover, the alternative models all performed significantly better than the prediction engine currently utilized by an Auckland bus company for arrival time prediction. However, these results require corroboration with manually collected field data, on account of the quality concerns afflicting the raw data reported by the transport company.

Coordinated Transit Signal Priority Model Considering Stochastic Bus Arrival Time

This paper presents an advanced transit signal priority (ATSP) control model that considers bus progression at downstream intersections when giving priority at upstream intersections and stochastic bus arrival times. The ATSP control model is applicable to arterials with bus lanes. At the center of the ATSP control model is a stochastic programming model formulated to find the optimum priority strategies at each intersection of interest, which minimize bus delays while having the least negative impact on general traffic. The uncertainty in bus arrivals is taken into account by considering stochastic bus dwell times. The ATSP control is implemented in a traffic micro-simulation environment and compared with conventional transit signal priority (CTSP) control. Extensive simulation experiments are conducted with different traffic congestion levels, bus headway levels, and dwell-time distributions. Results show that the ATSP control generates an additional reduction in bus delay of around 10% when compared to the CTSP control.

STUDY OF IMPROVING PERFORMANCE OF RAPID TRANSIT (BRT) BUS IN YOGYAKARTA

The implementation of the Rapit Transit Bus (BRT) requires evaluation of performance, by exploring service quality. Because service quality is important for the success of Trans Jogja. The purpose of this study was to determine the existing conditions of bus rapid transit (BRT) service and performance in the city of Yogyakarta, and to find out the priority strategies for implementing bus rapid transit (BRT) management at the study site. The method used in this study was the Science and QFD methods. The results of the research on the existing level of BRT performance in Yogyakarta, the arrival and departure times of Trans Jogja buses are good and can satisfy passengers, but the waiting time and operating time still need handling. The research results of the priority strategies for implementing BRT management management that need to be addressed are ease of location from the community living environment to the Trans Jogja bus stop, ease of change of mode, and management of cost compliance.

Knotted-line: A Visual explorer for uncertainty in transportation system

Abstract Public transport system(PTS) is a complex system, and there are various uncertainties caused by traffic congestion, varying departure interval of buses, etc. In this paper, taking bus as an example, a novel visualization model knotted-line for transportation system uncertainties is proposed. The knotted-line visualization model consists of three parts, the violin plot, multi-layer ring and risk indicator. The violin plot shows the uncertainty of passengers’ waiting time. The multi-layer ring describes the uncertainty of bus arrival time. The risk indicator expresses the possibility of passenger spending time on the trip. A user study is conducted to evaluate the proposed visualization method. The results show that the proposed knotted-line visualization model is helpful for passengers to understand the uncertainty in transportation system and help users to make decisions.

A Novel Bus-Dispatching Model Based on Passenger Flow and Arrival Time Prediction

Public transport is vital to people's daily travel, and bus dispatching plays a significant role in the public transport system. With deep learning having been widely applied and achieved great success in many fields, bus dispatching methods based on deep learning are proposed in succession. Currently, many bus dispatching models assume that the bus departure timetable is fixed and optimize the bus departure timetable interval according to passenger flow. However, the bus departure timetable is variable in general, only considering that the bus arrival time is insufficient. Targeting the above challenges, we propose a novel dynamic bus dispatching model based on arrival time and passenger flow prediction (D-ATPF). First, the historical origin-destination (OD) data and the transfer data are obtained by processing the bus trajectory data and the passenger card-swiping records, and the bus arrival time is extracted by analyzing the GPS trajectory. Second, the components of bus arrival time and passenger flow prediction based on long short-term memory (P-LSTM) are adopted to predict the future passenger flow and bus arrival time. Finally, the genetic algorithm-based bus dispatching model (GABD model) searches the minimum waiting time for passengers by using stay strategy. By using data of five lines with 124 bus stations and a total of 902509 records in Guangzhou city, China, our experimental results show that: 1) the average mean absolute percentage error (MAPE) and root mean square error (RMSE) of passenger prediction are 14% and 7.5, respectively; 2) the average MAPE and RMSE of bus arrival time are 7.5% and 13.5, respectively; 3) regarding the passenger flow and arrival time prediction, the proposed D-ATPF model reduced waiting time by 829.68 min, accounting for 25.19% of the total waiting time; and 4) compared with the real-time stay strategy, the reduced waiting time of this method increased by 5.94%. Therefore, the D-ATPF model provided a more practical model for buses dispatching.

Multi-output Deep Learning for Bus Arrival Time Predictions

Abstract Accurate and reliable predictions for bus arrival in public transport networks are essential for delivering an attractive service. This paper presents a multi-model approach for bus arrival prediction. The approach uses three distinct sub-models in an ensemble model. A multi-output, multi-time-step, deep neural network using Convolutional and Long short-term memory (LSTM) layers is used for travel time, and more simplistic models are used for dwell time and seasonal components. The method is empirically evaluated and compared to other popular approaches. We find that the proposed model saturations outperforms the other methods, while in other saturations performs similar.

Performance Analysis of Bus Arrival Time Prediction Using Machine Learning Based Ensemble Technique

Bus transport is an important means of communication in a modern world of smart cities. These smart cities require intelligent transportation systems. Such systems need effective techniques to be developed to meet customer requirements. Machine learning is one of those techniques for developing mathematical models to predict based on given data. Such techniques can be used to detect the arrival time of a bus at a given bus stop based on the historical data of the bus. In this paper Random Forest, Lasso and Ridge regression are used to train and analyze the performance over standard dataset in comparison with ensemble of Random Forest, Lasso and Ridge regression. Performance of ensemble techniques is better as compared used to Lasso, Ridge Regression, XGBoosting, and Gradiant Boosting.

Assessing the reliability of fog computing for smart mobility applications in VANETs

As a recent computing paradigm, Fog Computing is opening new sets of opportunities by bringing the computational resources, applications and services closer to their consumers, making it a good foundation for the Internet of Things (IoT). As part of the IoT umbrella, Vehicular ad-hoc Networks (VANETs) offer new communication and computing opportunities that traditional paradigms, such as Cloud Computing, are unable to solve, e.g. location-awareness, latency and capacity of detecting and acting in real time to unforeseen events. As a natural computing extension, Fog Computing can be the next requirement of VANETs, enabling the deployment of mobility-related applications and services.In this work we propose a generic architecture for the deployment of Fog Computing applications and services in a VANET environment. Moreover, we provide a proof-of-concept system to perform data analytics in a hybrid VANET/Fog environment. Our system is used by two Fog applications, one for city traffic anomaly detection, and another to estimate the bus time of arrival to feed traveller information. The reliability of such applications are validated through real mobility information from a large vehicular testbed currently deployed. The results show that using Fog Computing with a small set of recent regional data is very suitable for this type of applications, since the estimations of traffic anomalies and bus arrival times are very similar to those provided by the Cloud. Additionally, network performance results show that Fog applications can provide reliable information in a considerable shorter period of time, while at the same time they reduce the amount of traffic over the VANET backhaul infrastructure.

Combining Local Search into Genetic Algorithm for Bus Schedule Coordination through Small Timetable Modifications

Synchronizing bus arrival and departure times at transfer stations could reduce excess transfer times. This paper addresses the planning level of bus schedule coordination problem through small timetable modifications to given an initial timetable. Timetable modifications consist of shifts in initial departure times of vehicles from the depot. Headway-sensitive passenger demand is also considered in this problem. A nonlinear mixed integer-programming model is proposed for the problem to maximize the number of total transferring passengers with smalll excess transfer times. Based on the analysis of the proposed model, a genetic algorithm combining local search (GACLS) is designed to solve this model. Several numerical experiments are performed to show the utility and performance of GACLS. For small case, the proposed GACLS is highly effective, and can obtain the optimal solution with less time than enumeration method. For large real case, the GACLS also has good performances.

A Robust Optimization Approach to Public Transit Mobile Real-time Information

In the past few years, numerous mobile applications have made it possible for public transit passengers to find routes and learn about the expected arrival times of their transit vehicles. Previous studies show that provision of accurate real-time bus information is vital to passengers for reducing their anxieties and wait times at bus stops. Inadequate and/or inaccurate real-time information not only confuses passengers but also reinforces the bad image of public transit. However, almost all methods of real-time information optimization are aimed at predicting bus arrival or travel times. In order to make up for the lack of information accuracy, this paper proposes a new approach to optimize mobile real-time information for each transit route based on robust linear optimization. An error estimation is added to current bus arrival time information as a new element of mobile bus applications. The proof process of the robust optimization model is also presented in this paper. In the end, the model is tested on two comparable bus routes in Shanghai. The real-time information for these two routes was obtained from Shanghai Bus, a mobile application used in Shanghai City. The test results reflect the validity, disadvantages, and risk costs of the model.

WiFi Sensing-Based Real-Time Bus Tracking and Arrival Time Prediction in Urban Environments

Offering the services of real-time tracking and arrival time prediction is a common welfare for bus riders and transit agencies, especially in urban environments. On the down side, the traditional GPS-based solutions work poorly in urban areas due to urban canyons, while the location systems based on cellular signal also suffer from inherent limitations. In this paper, we present a powerful tool named signal Voronoi diagram (SVD) to partition the radio-frequency signal space of WiFi access points (APs), distributed, where a bus travels, into signal cells, and then into fine-grained signal tiles, tackling the problem of noisy received signal strength readings and possible AP dynamics. On top of SVD, we present a novel framework so-called WiLocator, to track an urban bus based on the surrounding WiFi information collected by the commodity off-the-shelf smartphones of bus riders and the mobility constraint of a bus. To predict the bus arrival time, we incorporate the computed location information and the temporal consistency of travel time of buses on the overlapped road segments. We then present WiLocator(p) which utilizes the historical data of bus locations to compute dominated road sub-segments of WiFi APs, such that we do not necessarily locate a bus from scratch, and show that the proposed framework can be applied for locating unknown WiFi APs surrounding the bus roads, and indoor localization as well. We implement the prototype of WiLocator and WiLocator(p), and conduct the in-situ experiments to show their efficiency in bus tracking.

Bus-arrival time prediction using bus network data model and time periods

Real-time information system about bus arrival and departure times at bus stops is one of the key elements of high-quality public transport. To provide accurate prediction of bus arrival at the bus stop the information of current position of the bus and bus travel time to the target stop are required. This paper investigates the bus velocity during different time periods and the impact of the bus network data model on the real-time prediction of arrival times at bus stops. The proposed model classifies bus travel times into time periods with respect to the historical data and the data model of the bus network. Discussion of four types of data model is presented, such as: a data model defined by bus stops and junctions of the roads, a data model defined only by bus stops, a data model which addresses the individual parts of the network in relation to the potential barriers that affect the travel speed of buses, and a data model with fixed-length links of the bus network. The analysis is performed in two different environments, the city of Ljubljana and the city of Maribor. The travel times are classified according to the average travel speed into four time periods: morning, afternoon, weekend and off-peak periods. Simulations showed that both the data model of the bus network and classifying runs into time periods affect the accuracy of predictions of bus arrival times at bus stops.

Private Shuttles and Public Transportation: Effects of Shared Transit Stops on Travel Time and Reliability in Seattle

An Employer Shared Transit Stop (ESTS) pilot was introduced in April, 2017 by the Seattle Department of Transportation (SDOT) and King County Metro (KCM). Eleven bus stops within the City of Seattle were identified for stop-sharing with private shuttles that serve employees of and are operated by Microsoft and Seattle Children’s Hospital, respectively. This study utilizes real-time transit performance data that was generated by KCM, then collected and aggregated by the company Swiftly to assess the impacts of the ESTS program on bus transit reliability. Data analyses based on visualization tools on the Swiftly Insights platform of route-level schedule adherence as well as fixed panel regressions at the mean and at the 0.90 and 0.95 quantile of stop-level schedule adherence are considered. On average, bus transit reliability has not been affected by the ESTS pilot program. Statistically significant results indicating a potential delay in bus arrival times as a result of ESTS stop-sharing were found at only one of the nine stops considered in the study. An increase in participating companies and stops is recommended.

Improving the quality of service in public road transportation using real time travel information system

The impact of road public transport in urban transportation cannot be ignored, however, the quality of services provided is not high enough. This has made it unattractive to prospective passengers and less competitive to private transport. One of the ways of resolving these challenges with a view to increasing the quality of service is by the provision of platforms that provides travel information in real time to prospective users. This was achieved in this paper using web, mobile, and short messaging service platforms. The developed platforms employed an artificial neural network-based bus arrival time prediction model for predicting bus arrival time. The accuracy of the prediction model was evaluated using mean absolute error and mean absolute percentage error while the performance and impact of the developed platforms were assessed from users' perspective through a survey based on the unified theory of acceptance and use of technology (UTAUT) model.

Алгоритм прогнозирования моментов времени прибытия городских пассажирских автобусов на основе Марковских цепей

Developing public transport is an effective way to solve traffic congestion and improve travel efficiency. Improving bus service quality can attract passengers to travel by public transport. In the past, as the bus arrival time is unknown, and the buses often arrive inaccurate, passengers feel anxious and the quality of public transport service declined. Even though some bus stations equipped with electronic bus stop boards, the predicted bus arrival time is often inaccurate. Therefore, in order to convenient for people travel by public transit, this paper puts forward the method of bus travel time prediction based on the Markov chain which considers the spatial-temporal characteristics of the bus travel time. The prediction method can improve the quality of the bus service, help the travelers to make travel planning and reduce the waiting time. The algorithm is verified by the actual operation data of No.114 bus line in Harbin. The results show that the prediction error is small, and the algorithm is easy to implement.

Improving Reliability of Bus Arrival Time Predictions Considering delay Time at Signalized Intersection

Improving Reliability of Bus Arrival Time Predictions Considering delay Time at Signalized Intersection

Analysis of bus travel time distributions for varying horizons and real-time applications

Given the increasing interest in real-time bus arrival information, producing reliable estimation is essential to maximize the benefits of real-time systems. The primary objectives of this paper are to analyze the changes of bus travel time characteristics as pseudo horizon varies and how such characteristics can be applied to real-time bus arrival estimation. In this study, “horizon” refers to the distance between a real-time bus location and a bus stop, whereas “pseudo horizon” refers to the distance from a GPS point to an upstream GPS point. In contrast to existing methods that provide point estimates of bus arrival times, this study provides interval estimates that take into account the uncertainty of future bus arrival times given that early and late buses have their own respective ramifications. A methodology is developed to analyze the bus travel time distribution systematically based on different pseudo horizons since such distributions are critical to producing reliable bus arrival information. The analysis of real transit GPS data shows a significant change in bus travel time characteristics around a pseudo horizon range of 8 km. The analysis of changes in probability densities with pseudo horizons shows that bus travel time distribution converges from a rightly skewed distribution to a more symmetrical distribution from a shorter to a longer pseudo horizon. Lognormal and normal distributions are found to be the best models for before and after a cut-off horizon of 7–8 km, respectively. Instead of a single distribution, the outcomes of this study suggest a combination of probability distributions based on the estimation horizon to be used to provide better bus arrival time estimations.

A hybrid model based method for bus travel time estimation

ABSTRACTProviding accurate information about bus arrival time to passengers can make the public transport system more attractive. Such information helps the passengers by reducing the uncertainty on waiting time and the associated frustrations. However, accurate estimation of bus travel time is still a challenging problem, especially under heterogeneous and lane-less traffic conditions. The accuracy of such information provided to passengers depends mainly on the estimation method used, which in turns depends on the input data used. Hence, developing suitable estimation methods and identifying the most significant/appropriate input data are important. The present study focused on these aspects of development of estimation methods that can accurately estimate travel time by using significant inputs. In order to identify significant inputs, a data mining technique, namely the k-NN classifying algorithm, was used. It is based on the similarity in pattern between the input and historic data. These identified inputs were then used in a hybrid model that combined exponential smoothing technique with recursive estimation scheme based on the Kalman Filtering (KF) technique. The optimal values of the smoothing parameter were dynamically estimated and were updated using the latest measurements available from the field. The performance of the proposed algorithm showed a clear improvement in estimation accuracy when compared with existing methods.

Prediction of Bus Travel Time Using Random Forests Based on Near Neighbors

AbstractThe prediction of bus arrival time is important for passengers who want to determine their departure time and reduce anxiety at bus stops that lack timetables. The random forests based on the near neighbor (RFNN) method is proposed in this article to predict bus travel time, which has been calibrated and validated with real‐world data. A case study with two bus routes is conducted, and the proposed RFNN is compared with four methods: linear regression (LR), k‐nearest neighbors (KNN), support vector machine (SVM), and classic random forest (RF). The results indicate that the proposed model achieves high accuracy. That is, one bus route has the results of 13.65 mean absolute error (MAE), 6.90% mean absolute percentage error (MAPE), 26.37 root mean squared error (RMSE) and 13.77 (MAE), 7.58% (MAPE), 29.01 (RMSE), respectively. RFNN has a longer computation time of 44,301 seconds for a data set with 14,182 data. The proposed method can be optimized by the technology of parallel computing and can be applied to real‐time prediction.

I-UMDPC: The Improved-Unusual Message Delivery Path Construction for Wireless Sensor Networks With Mobile Sinks

This paper considers the data delivery delay problem in wireless sensor networks. The delivery delay is a significant measure when the data freshness is the first concern of users. The goal of this paper is to route delay-sensitive data to mobile nodes (M nodes) within an allowed latency. The data collection system is composed of a set of M nodes amounted on buses, a set of sensor nodes to detect the interested phenomenon and a set of special nodes deployed at bus stops to assist data routing. An optimization-based approach called improved-unusual message delivery path construction (I-UMDPC) is proposed. Considering the actual features of bus operation, two aspects of uncertainties are accounted in our approach: 1) the bus arrival time and 2) the stop duration. Extensive simulations as well as practical experiments on our testbed demonstrate that I-UMDPC is able to route delay-sensitive data reliably and efficiently and performs better than existing work.