Traveling time prediction in scheduled transportation with journey segments

Gal, Avigdor; Mandelbaum, Avishai; Schnitzler, François; Senderovich, Arik; Weidlich, Matthias

doi:10.1016/j.is.2015.12.001

Cited by 90 publications

(52 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[9][10][11] Specifically,in the work of Sinn et al, 10 Kernel Regression was used on the Dublin bus data in order to predict the traveling time for bus line number 046A, the same line that we have used for our evaluation. [9][10][11] Specifically,in the work of Sinn et al, 10 Kernel Regression was used on the Dublin bus data in order to predict the traveling time for bus line number 046A, the same line that we have used for our evaluation.…”

Section: Related Workmentioning

confidence: 99%

A real‐time bus‐subway transfer scheme recommendation systems

Zhang

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Bus and subway service is an important public transportation. Besides the major goal of carrying passengers around, providing accurate and reliable travel information for passengers is also an important business consideration. The route and its traveling time can directly affect the number of people choosing the line. Traditional approaches to obtain route and its traveling time rely on historical experience, which are both non-scalable and incomplete. The wide adoptions of On Board Units (OBUs) in public transportation provide new opportunities. In this paper, we associate bus GPS data with station locations to derive the traveling time between two stations and make a short forecast. To our best knowledge, this is the first paper that utilizes real-time bus GPS data and subway arrival station data to design route and give its traveling time for a passenger.

show abstract

Section: Related Workmentioning

confidence: 99%

A real‐time bus‐subway transfer scheme recommendation systems

Zhang

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Gal et al. () combined queuing theory and machine learning to forecast the bus travel time, with the main concept of predicting travel time based on queuing theory and identifying outliers of the travel time by using machine learning. RF is one of the algorithms that was used in Gal's research for the detection of outliers in scheduled transportation.…”

Section: Introductionmentioning

confidence: 99%

“…In general, Moreira's work focused on business transit in macroscopical aspect, which did not consider characteristics of buses and bus data, for example, bus dwell time, traffic conditions. Gal et al (2015) combined queuing theory and machine learning to forecast the bus travel time, with the main concept of predicting travel time based on queuing theory and identifying outliers of the travel time by using machine learning. RF is one of the algorithms that was used in Gal's research for the detection of outliers in scheduled transportation.…”

Section: Introductionmentioning

confidence: 99%

“…RF is one of the algorithms that was used in Gal's research for the detection of outliers in scheduled transportation. Gal et al (2015) used the travel time of the preceding 1 bus as an estimate of the predicted one. Different from these researches, we propose a hybrid model, which combines RF and near neighbors, to forecast the travel time considering current traffic conditions both on current segment and next segments.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Wang

Shan

et al. 2017

Computer aided Civil Eng

137

View full text Add to dashboard Cite

The 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.

show abstract

“…Here, a schedule determines when a patient undergoes a specific examination or treatment. Another example of multi-stage scheduled processes is public transportation, where schedules determine which vehicle serves a certain route at a specific time [4].…”

Section: Introductionmentioning

confidence: 99%