Performance Comparison of Bus Travel Time Prediction Models across Indian Cities
08 May 2018-Transportation Research Record (SAGE PublicationsSage CA: Los Angeles, CA)-Vol. 2672, Iss: 31, pp 87-98
TL;DR: This work aims at developing a reliable structure for predicting arrival/travel time of various public transport systems under heterogeneous traffic conditions existing in India.
Abstract: Road traffic congestion has become a global worry in recent years. In many countries congestion is a major factor, causing noticeable loss to both economy and time. The rapid increase in vehicle ow...
Citations
More filters
TL;DR: The proposed model has been tested with two real cases of intercity public transport routes and from the results obtained, it may be concluded that the average error of the predictions is around 13% compared to the observed travel time values.
Abstract: In road-based mass transit systems, travel time is a key factor in providing quality of service. This article proposes a method of predicting travel time for this type of transport system. This method estimates travel time by taking into account its historical behaviour, represented by historical profiles, and the current behaviour recorded on the public transport vehicle for which the prediction is to be made. The model uses the k-medoids clustering algorithm to obtain historical travel time profiles. A relevant feature of the model is that it does not require recent travel time data from other vehicles. For this reason, the proposed model may be used in intercity transport contexts in which service planning is carried out according to timetables. The proposed model has been tested with two real cases of intercity public transport routes and from the results obtained we may conclude that, in general, the average error of the predictions is around 13% compared to the observed travel time values.
20 citations
TL;DR: The model is examined experimentally using traffic data on bus routes in the city of Samara, Russia and the obtained results confirm that the predictions provided by the model are of a high quality and it can be used for real-time arrival time prediction of public transport in the case of a large-scale transportation network.
Abstract: Arrival time of public vehicles to transport stops is a key point of information systems for passengers. Accurate information on the arrival time is important for travel arrangements since it helps to decrease the wait time at a stop and to choose an optimal alternate route. Recently, such information has been included to mobile navigation applications too. In the present paper, we analyze the abilities of the LSTM neural network to predict the arrival time of public vehicles. This model accounts for heterogeneous information about transport situation that directly or indirectly has an impact on the travel time prediction and includes statistical and real-time data of traffic flow. We examined the model experimentally using traffic data on bus routes in the city of Samara, Russia. The obtained results confirm that the predictions provided by our model are of a high quality and it can be used for real-time arrival time prediction of public transport in the case of a large-scale transportation network.
17 citations
Posted Content•
TL;DR: In this article, the authors proposed two approaches: (a) classical time-series approach employing a seasonal AR model and (b) unconventional linear, non-stationary AR approach.
Abstract: Providing real time information about the arrival time of the transit buses has become inevitable in urban areas to make the system more user-friendly and advantageous over various other transportation modes. 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 segment the entire bus route into segments and work with these segment travel times as the data input (from GPS traces) for prediction. This paper adopts this approach and proposes predictive modelling approaches which fully exploit the temporal correlations in the bus GPS data. Specifically, we propose two approaches: (a) classical time-series approach employing a seasonal AR model (b)unconventional linear, non-stationary AR approach. The second approach is a novel technique and exploits the notion of partial correlation for learning from data. A detailed analysis of the marginal distributions of the data from Indian conditions (used here), revealed a predominantly log-normal behavior. This aspect was incorporated into the above proposed predictive models and statistically optimal prediction schemes in the lognormal sense are utilized for all predictions. Both the above temporal predictive modeling approaches predict ahead in time at each segment independently. For real-time bus travel time prediction, one however needs to predict across multiple segments ahead in space. Towards a complete solution, the study also proposes an intelligent procedure to perform (real-time) multi-section ahead travel-time predictions based on either of the above proposed temporal models. Results showed a clear improvement in prediction accuracy using the proposed methods,
12 citations
TL;DR: This study analyses travel time data obtained from buses fitted with GPS devices in Chennai, India to understand its variation over time and space and developed a real-time bus travel time prediction method using a deep learning approach, Long and Short-Term Memory (LSTM) networks.
12 citations
TL;DR: A new traffic network state prediction model for freeways based on a generative adversarial framework is proposed that can effectively predict future traffic network states and is superior to the baselines.
Abstract: Traffic state prediction plays an important role in intelligent transportation systems, but the complex spatial influence of traffic networks and the non-stationary temporal nature of traffic states make it a challenging task. In this study, a new traffic network state prediction model for freeways based on a generative adversarial framework is proposed. The generator based on the long short-term memory networks is adopted to generate future traffic states, and a discriminator with multiple fully connected layers is applied to simultaneously ensure the prediction accuracy. The results of experiments show that the proposed framework can effectively predict future traffic network states and is superior to the baselines.
8 citations
References
More filters
TL;DR: The effectiveness of the proposed method to predict freeway travel times using a linear model in which the coefficients vary as smooth functions of the departure time is demonstrated by applying the method to two real-life loop detector data sets.
Abstract: Effective prediction of travel times is central to many advanced traveler information and transportation management systems. In this paper we propose a method to predict freeway travel times using a linear model in which the coefficients vary as smooth functions of the departure time. The method is straightforward to implement, computationally efficient and applicable to widely available freeway sensor data. We demonstrate the effectiveness of the proposed method by applying the method to two real-life loop detector data sets. The first data set––on I-880––is relatively small in scale, but very high in quality, containing information from probe vehicles and double loop detectors. On this data set the prediction error ranges from 5% for a trip leaving immediately to 10% for a trip leaving 30 min or more in the future. Having obtained encouraging results from the small data set, we move on to apply the method to a data set on a much larger spatial scale, from Caltrans District 12 in Los Angeles. On this data set, our errors range from about 8% at zero lag to 13% at a time lag of 30 min or more. We also investigate several extensions to the original method in the context of this larger data set.
324 citations
"Performance Comparison of Bus Trave..." refers methods in this paper
...The various reported techniques for bus travel time prediction include prediction using average speed techniques (4), step-wise linear regression techniques (5), time-varying coefficient (TVC) linear regression model techniques (6), time series analysis techniques (7–8) and filtering techniques (3, 9)....
[...]
TL;DR: An approach is presented for estimating future travel times on a freeway using flow and occupancy data from single-loop detectors and historical travel-time information and linear regression, with the stepwise-variable-selection method and more advanced tree-based methods.
Abstract: An approach is presented for estimating future travel times on a freeway using flow and occupancy data from single-loop detectors and historical travel-time information. Linear regression, with the stepwise-variable-selection method and more advanced tree-based methods, is used. The analysis considers forecasts ranging from a few minutes into the future up to an hour ahead. Leave-a-day-out cross-validation was used to evaluate the prediction errors without underestimation. The current traffic state proved to be a good predictor for the near future, up to 20 min, whereas historical data are more informative for longer-range predictions. Tree-based methods and linear regression both performed satisfactorily, showing slightly different qualitative behaviors for each condition examined in this analysis. Unlike preceding works that rely on simulation, real traffic data were used. Although the current implementation uses measured travel times from probe vehicles, the ultimate goal is an autonomous system that r...
288 citations
"Performance Comparison of Bus Trave..." refers methods in this paper
...The various reported techniques for bus travel time prediction include prediction using average speed techniques (4), step-wise linear regression techniques (5), time-varying coefficient (TVC) linear regression model techniques (6), time series analysis techniques (7–8) and filtering techniques (3, 9)....
[...]
TL;DR: In this article, a method for dealing with probe data along with conventional detector data to estimate traffic states is proposed, where probe data are integrated into the observation equation of the Kalman filter, in which state equations are represented by a macroscopic traffic-flow model.
Abstract: Traffic information from probe vehicles has great potential for improving the estimation accuracy of traffic situations, especially where no traffic detector is installed. A method for dealing with probe data along with conventional detector data to estimate traffic states is proposed. The probe data were integrated into the observation equation of the Kalman filter, in which state equations are represented by a macroscopic traffic-flow model. Estimated states were updated with information from both stationary detectors and probe vehicles. The method was tested under several traffic conditions by using hypothetical data, giving considerably improved estimation results compared to those estimated without probe data. Finally, the application of the proposed method was extended to the estimation and short-term prediction of travel time. Travel times were obtained indirectly through the conversion of speeds estimated or predicted by the proposed method. Experimental results show that the performance of travel-time estimation or prediction is comparable to that of some existing methods.
267 citations
TL;DR: One of the first attempts at real-time short-term prediction of travel time for ITS applications in Indian traffic conditions is presented, using global positioning system data collected from public transportation buses plying on urban roadways in the city of Chennai, India.
Abstract: Travel time information is a vital component of many intelligent transportation systems (ITS) applications. In recent years, the number of vehicles in India has increased tremendously, leading to severe traffic congestion and pollution in urban areas, particularly during peak periods. A desirable strategy to deal with such issues is to shift more people from personal vehicles to public transport by providing better service (comfort, convenience and so on). In this context, advanced public transportation systems (APTS) are one of the most important ITS applications, which can significantly improve the traffic situation in India. One such application will be to provide accurate information about bus arrivals to passengers, leading to reduced waiting times at bus stops. This needs a real-time data collection technique, a quick and reliable prediction technique to calculate the expected travel time based on real-time data and informing the passengers regarding the same. The scope of this study is to use global positioning system data collected from public transportation buses plying on urban roadways in the city of Chennai, India, to predict travel times under heterogeneous traffic conditions using an algorithm based on the Kalman filtering technique. The performance of the proposed algorithm is found to be promising and expected to be valuable in the development of APTS in India. The work presented here is one of the first attempts at real-time short-term prediction of travel time for ITS applications in Indian traffic conditions.
179 citations
"Performance Comparison of Bus Trave..." refers background or methods in this paper
...The various reported techniques for bus travel time prediction include prediction using average speed techniques (4), step-wise linear regression techniques (5), time-varying coefficient (TVC) linear regression model techniques (6), time series analysis techniques (7–8) and filtering techniques (3, 9)....
[...]
...Providing real-time bus arrival information to passengers can make bus transport userfriendly and enhance its competitiveness with other modes of transport (2, 3)....
[...]
13 Jun 2007
TL;DR: From the results it was found that SVM is a viable alternative for short-term prediction problems when the amount of data is less or noisy in nature and the performance of SVM with ANN, real time, and historic approach is carried out.
Abstract: A vast majority of urban transportation systems in North America are equipped with traffic surveillance systems that provide real time traffic information to traffic management centers. The information from these are processed and provided back to the travelers in real time. However, the travelers are interested to know not only the current traffic information, but also the future traffic conditions predicted based on the real time data. These predicted values inform the drivers on what they can expect when they make the trip. Travel time is one of the most popular variables which the users are interested to know. Travelers make decisions to bypass congested segments of the network, to change departure time or destination etc., based on this information. Hence it is important that the predicted values be as accurate as possible. A number of different forecasting methods have been proposed for travel time forecasting including historic method, real-time method, time series analysis, and artificial neural networks (ANN). This paper examines the use of a machine learning technique, namely support vector machines (SVM), for the short-term prediction of travel time. While other machine learning techniques, such as ANN, have been extensively studied, the reported applications of SVM in the field of transportation engineering are very few. A comparison of the performance of SVM with ANN, real time, and historic approach is carried out. Data from the TransGuide Traffic Management center in San Antonio, Texas, USA is used for the analysis. From the results it was found that SVM is a viable alternative for short-term prediction problems when the amount of data is less or noisy in nature.
134 citations
"Performance Comparison of Bus Trave..." refers methods in this paper
...Among several artificial intelligence techniques, the most significant methods include Artificial Neural Network (ANN) (10), Support Vector Regression (SVR) (11), and k-Nearest Neighbor (k-NN) classifier (12)....
[...]