Bus arrival time prediction at bus stop with multiple routes

Yu, Bin; Lam, William H. K.; Tam, Mei Lam

doi:10.1016/j.trc.2011.01.003

Cited by 278 publications

(156 citation statements)

References 20 publications

Supporting

Mentioning

154

Contrasting

Unclassified

Order By: Relevance

“…Some recent studies begin to integrate two or more algorithms together to make full use of goodness of each method. To the best of our knowledge, the existing literature is rarely found to predict bus arrival time using multiple routes data, except for the research done by Yu et al (2011) adopted all algorithms mentioned above separately to predict arrival time with multiple transit routes data. His study proves using multiple transit routes data can get a better prediction performance.…”

Section: Literaturementioning

confidence: 99%

Bus arrival time prediction using mixed multi-route arrival time data at previous stop

Hua

Wang

et al. 2017

Transport

View full text Add to dashboard Cite

Abstract. The primary objective of this paper is to develop models to predict bus arrival time at a target stop using actual multi-route bus arrival time data from previous stop as inputs. In order to mix and fully utilize the multiple routes bus arrival time data, the weighted average travel time and three Forgetting Factor Functions (FFFs) -F1, F2 and F3 -are introduced. Based on different combinations of input variables, five prediction models are proposed. Three widely used algorithms, i.e. Support Vector Machine (SVM), Artificial Neutral Network (ANN) and Linear Regression (LR), are tested to find the best for arrival time prediction. Bus location data of 11 road segments from Yichun (China), covering 12 bus stops and 16 routes, are collected to evaluate the performance of the proposed approaches. The results show that the newly introduced parameters, the weighted average travel time, can significantly improve the prediction accuracy: the prediction errors reduce by around 20%. The algorithm comparison demonstrates that the SVM and ANN outperform the LR. The FFFs can also affect the performance errors: F1 is more suitable for ANN algorithm, while F3 is better for SVM and LR algorithms. Besides, the virtual road concept in this paper can slightly improve the prediction accuracy and halve the time cost of predicted arrival time calculation.

show abstract

Section: Literaturementioning

confidence: 99%

Bus arrival time prediction using mixed multi-route arrival time data at previous stop

Hua

Wang

et al. 2017

Transport

View full text Add to dashboard Cite

show abstract

“…The processing of tracking data from fleet management and passenger counting systems is the basis of these procedures. Methods of artificial neural networks, search for the k-nearest neighbours and linear regression are commonly used in these algorithms (Yu et al 2011). Bajwa et al (2008) investigated the mode and departure time choice processes of passengers and devised different model specifications for a combined mode and departure-time choice-model, which takes the delays also into consideration.…”

Section: Literature Review -Related Workmentioning

confidence: 99%

Method for Analysis and Prediction of Dwell Times at Stops in Local Bus Transportation

Csiszár

Sándor

2016

Transport

View full text Add to dashboard Cite

Abstract. The punctuality of local public bus transportation contributes to the service quality and has impact on mode choice. Appropriate planning and control measures as well as adequate passenger information require efficient analysis and prediction methods. Advanced fleet tracking systems provide enough data for these research purposes. The main factors that cause schedule deviation has been identified through the analysis of the data. As important time elements of the journey time are dwell times at stops, the research focused on it; however, the elaborated database structure is adequate also for analysis of the other time elements, which coincides with our further research intentions too. Innovative methods based on the historical data have been elaborated for the prediction of dwell times. The essence of the method: multi-variate analysis of the dwell times by exploration of the significant influencing factors, and then prediction of times based on the factors describing the certain situations. Soundness of the methods has been verified with examples, and the results well approximated the real values.

show abstract

“…SVM was developed by Vapnik [14,15], which is characterized by a specific type of learning algorithms. It has been successfully applied to solve some classic problems, such as incident detection [16], traffic-pattern recognition [17], passenger head recognition [18], and travel time prediction [7,8,[19][20][21]. SVM is used to find regular pattern and makes use of them to analyse the unknowns.…”

Section: S Zhong Et Al: a Hybrid Model Based On Support Vector Machmentioning

confidence: 99%

A Hybrid Model Based on Support Vector Machine for Bus Travel-Time Prediction

Zhong¹,

et al. 2015

PROMET

View full text Add to dashboard Cite

show abstract

Bus arrival time prediction at bus stop with multiple routes

Cited by 278 publications

References 20 publications

Bus arrival time prediction using mixed multi-route arrival time data at previous stop

Bus arrival time prediction using mixed multi-route arrival time data at previous stop

Method for Analysis and Prediction of Dwell Times at Stops in Local Bus Transportation

A Hybrid Model Based on Support Vector Machine for Bus Travel-Time Prediction

Contact Info

Product

Resources

About