Comparative Assessment of Dynamic Travel Time Prediction Models in the Developing Countries Cities (original) (raw)
Related papers
Travel Time Prediction Modelling in Mixed Traffic Conditions
INTERNATIONAL JOURNAL FOR TRAFFIC AND TRANSPORT ENGINEERING, 2018
Over the past few decades, exponential increase in vehicle ownership resulted in issues of traffic control and management. Intelligent Transportation System (ITS) is one of the solutions for the intelligent management of traffic. ITS applications like Advanced Traveler Information Systems and Advanced Traffic Management Systems need travel time as a major input. The estimation of travel time in urban network became more complicated because of the rapid change in the system and traffic. This study is done in order to assess the impact of different travel modes on travel time. Data has been collected on a stretch of 14 km length in Warangal city, India using GPS probe vehicle along with video camera. Different private modes of transportation such as 2 wheeler, passenger car and 3 wheeler have been used as test vehicles for the collection of data in different traffic flow scenarios. Artificial Neural Network and a multi linear regression model have been developed to compare the estimated travel times with the field data. Two combinations of ANN model using single hidden layer, different numbers of neurons and epochs have been compared. The travel time of different modes has been compared and the effect of vehicle composition on travel time has been analyzed. The ANN model perform better than the regression model.
A Suitable Approach for Evaluating Bus Arrival Time Prediction Techniques in Egypt
Accurate Bus arrival time prediction depending on a real-time basis has become an essential and important element in management transportation systems. This paper demonstrates the results of field tests for evaluating bus arrival time prediction in Egypt. One of the most difficult aspects of evaluating an operational field test is obtaining consumer response to products or services that are not market ready or even completely functional. Field tests were performed under real traffic situations in order to test the system in terms of prediction of bus arrival time to stations depending on two techniques consisting of Kalman filter and Neural Network. Findings from the field test at the real-world sites indicated that the system would be capable estimate the prediction time.
Dynamic Bus Travel Time Prediction Models on Road with Multiple Bus Routes
Accurate and real-time travel time information for buses can help passengers better plan their trips and minimize waiting times. A dynamic travel time prediction model for buses addressing the cases on road with multiple bus routes is proposed in this paper, based on support vector machines (SVMs) and Kalman filtering-based algorithm. In the proposed model, the well-trained SVM model predicts the baseline bus travel times from the historical bus trip data; the Kalman filtering-based dynamic algorithm can adjust bus travel times with the latest bus operation information and the estimated baseline travel times. The performance of the proposed dynamic model is validated with the real-world data on road with multiple bus routes in Shenzhen, China. The results show that the proposed dynamic model is feasible and applicable for bus travel time prediction and has the best prediction performance among all the five models proposed in the study in terms of prediction accuracy on road with multiple bus routes.
A New Travel Time Prediction Method for Intelligent Transportation System
including advanced traveler information systems. The main purpose of this research is to develop a dynamic travel time prediction model for road networks. In this study we proposed a new method to predict travel times using Artificial Neural Network model because artificial neural network has exhibited high accuracy and speed when applied to large databases. In addition, we compare the proposed method with such prediction methods as link-based prediction model and time varying coefficient linear regression model. It is shown from our experiment that ANN predictor can reduce mean absolute relative error significantly rather than the other predictors. We illustrate that ANN is suitable and performs well for traffic data analysis.
Bus travel time prediction: a log-normal auto-regressive (AR) modelling approach
Transportmetrica A: Transport Science, 2020
Providing real-time arrival time information of the transit buses has become inevitable in urban areas to improve the efficiency of the public transportation system. However, accurate prediction of arrival time of buses is still a challenging problem in dynamically varying traffic conditions especially under heterogeneous traffic condition without lane discipline. One broad approach researchers have adopted over the years is to divide the entire bus route into sections and model the correlations of section travel times either spatially or temporally. The proposed study adopts this approach of working with section travel times and developed two predictive modelling methodologies namely (a) classical time-series approach employing a seasonal AR model with possible integrating non-stationary effects and (b) linear non-stationary AR approach, a novel technique to exploit the notion of partial correlation for learning from data to exploit the temporal correlations in the bus travel time data. Many of the reported studies did not explore the distribution of travel time data and incorporated their effects into the modelling process while implementing time series approach. The present study conducted a detailed analysis of the marginal distributions of the data from Indian conditions (that we use for testing in this paper). This revealed a predominantly log-normal behaviour which was incorporated into the above proposed predictive models. Towards a complete solution, the study also proposes a multi-section ahead travel time prediction algorithm based on the above proposed classes of temporal models learnt at each section to facilitate real time implementation. Finally, the predicted travel time values were corroborated with the actual travel time values. From the results, it was found that the proposed method was able to perform better than historical average, exponential smoothing, ARIMA, and ANN methods and the methods that considered either temporal or spatial variations alone.
Keywords: Makurdi town bus services Bus travel time multiple linear regression model ANN model ABSTRACT The lack of information on bus travel time in Makurdi town to enable trip makers plan for journeys is seen as a challenge in recent times. This study developed a multiple linear regression model for predicting bus travel time along bus routes in Makurdi town. Specifically, the study assessed bus travel time on routes without designated bus stops, examined geometric features of bus routes, assessed bus dwell time and travel speeds in a heterogeneous traffic stream on routes in Makurdi town. It developed and validated a model for the bus travel time. Field survey focused on the major bus routes in Makurdi town which included; High Level roundabout to School of Remedial Studies junction (HL-SRS), High Level roundabout to Federal Medical Centre junction (HL-FMC), Wurukum roundabout to Coca Cola Complex (W-CCC) and Wurukum roundabout to Welfare Quarters junction (W-WQ). Independent parameters examined on the sites for model development included; bus route length, bus travel speed, average dwell time at random stops for pickup and alighting of passengers, bus headway, the total number of cross and Tee intersections along the bus route, volume of motorcycles, private cars and trucks in the traffic stream, while the dependent variable was bus travel time. Based on the built model, 15 minutes approximately was established as the average bus travel time for all bus routes in Makurdi town assuming all other variables have zero magnitude. Goodness of fit test of the model yielded significant value for coefficient of determination (R 2 = 0.952) and the use of Artificial Neural Network (ANN) method for validating the model also confirmed it accuracy at 93% approximately. It was therefore concluded that, bus travel time on major routes in Makurdi town could be accurately estimated using the built multiple linear regression model provided all essential input parameters of the model are used. The establishment of designated bus stops along bus routes within Makurdi town to minimise bus dwell frequency and for accurate estimation of bus travel time, as well as erection of travel information bill boards along bus routes stating average bus travel time to inform commuters that have high value of travel time were recommended.
Travel time prediction for urban networks is an important issue in Advanced Traveler Information Systems (ATIS) since drivers can make individual decisions, choose the shortest route, avoid congestions and improve network efficiency based on the predicted travel time information. In this research, two algorithms are proposed to estimate and predict travel time for urban networks, the simulation-based and time-series models. The simulation-based model, DynaTAIWAN, designed and developed for mixed traffic flows, is adopted to simulate the traffic flow patterns. The Autoregressive Integrated Moving Average (ARIMA) model, calibrated with vehicle detector (VD) data, is integrated with signal delay to predict travel time for arterial streets. In the numerical analysis, an arterial street in Kaohsiung city in Taiwan is conducted to illustrate these two models. The empirical and historical data are used to predict and analyze travel time, including: travel time data from survey and historic...
Neural Networks Model for Travel Time Prediction Based on ODTravel Time Matrix
ArXiv, 2020
Public transportation system commuters are often interested in getting accurate travel time information to plan their daily activities. However, this information is often difficult to predict accurately due to the irregularities of road traffic, caused by factors such as weather conditions, road accidents, and traffic jams. In this study, two neural network models namely multi-layer(MLP) perceptron and long short-term model(LSTM) are developed for predicting link travel time of a busy route with input generated using Origin-Destination travel time matrix derived from a historical GPS dataset. The experiment result showed that both models can make near-accurate predictions however, LSTM is more susceptible to noise as time step increases.
Cairo is experiencing traffic congestion that places it among the worst in the world. Obviously, it is difficult if not impossible to solve the transportation problem because it is multi-dimensional problem but it's good to reduce this waste of money and the associated waste of time resulting from congestion. One way to accomplish this is to provide driver or passenger with current traffic information throughout their trip. Travel time prediction is becoming increasingly important and it is one of the most important traffic information for both drivers and passengers. It is difficult to measure the travel time directly so the present study estimates the travel time using the speed. In this paper we present a model based approach for travelling time prediction. It will provide both passenger or driver with the fastest routes depending on the travel time. The proposed method uses DSmT (Dezert-Smarandache Theory) as a fusion technique and Artificial Neural Network as mining tool. The estimates are corroborated using actual values and the results show the model performing well and gave us acceptable prediction.
Online Bus Arrival Time Prediction Using Hybrid Neural Network and Kalman filter Techniques
The ability to obtain accurate predictions of bus arrival time on a real time basis is vital to both bus operations control and passenger information systems. Several studies have been devoted to this arrival time prediction problem in many countries; however, few resulted in completely satisfactory algorithms. This paper presents an effective method that can be used to predict the expected bus arrival time at individual bus stops along a service route. This method is a hybrid scheme that combines a neural network (NN) that infers decision rules from historical data with Kalman filter (KF) that fuses prediction calculations with current GPS measurements. The proposed algorithm relies on real-time location data and takes into account historical travel times as well as temporal and spatial variations of traffic conditions. A case study on a real bus route is conducted to evaluate the performance of the proposed algorithm in terms of prediction accuracy. The results indicate that the system is capable of achieving satisfactory performance and accuracy in predicting bus arrival times for Egyptian environments.