Browse > Article
http://dx.doi.org/10.3745/KTCCS.2017.6.4.189

Arrival Time Estimation for Bus Information System Using Hidden Markov Model  

Park, Chul Young (순천대학교 전기.전자.정보통신공학과)
Kim, Hong Geun (순천대학교 전기.전자.정보통신공학과)
Shin, Chang Sun (순천대학교 정보통신공학과)
Cho, Yong Yun (순천대학교 정보통신공학과)
Park, Jang Woo (순천대학교 정보통신공학과)
Publication Information
KIPS Transactions on Computer and Communication Systems / v.6, no.4, 2017 , pp. 189-196 More about this Journal
Abstract
BIS(Bus Information System) provides the different information related to buses including predictions of arriving times at stations. BIS have been deployed almost all cities in our country and played active roles to improve the convenience of public transportation systems. Moving average filters, Kalman filter and regression models have been representative in forecasting the arriving times of buses in current BIS. The accuracy in prediction of arriving times depends largely on the forecasting algorithms and traffic conditions considered when forecasting in BIS. In present BIS, the simple prediction algorithms are used only considering the passage times and distances between stations. The forecasting of arrivals, however, have been influenced by the traffic conditions such as traffic signals, traffic accidents and pedestrians ets., and missing data. To improve the accuracy of bus arriving estimates, there are big troubles in building models including the above problems. Hidden Markov Models have been effective algorithms considering various restrictions above. So, we have built the HMM forecasting models for bus arriving times in the current BIS. When building models, the data collected from Sunchean City at 2015 have been utilized. There are about 2298 stations and 217 routes in Suncheon city. The models are developed differently week days and weekend. And then the models are conformed with the data from different districts and times. We find that our HMM models can provide more accurate forecasting than other existing methods like moving average filters, Kalmam filters, or regression models. In this paper, we propose Hidden Markov Model to obtain more precise and accurate model better than Moving Average Filter, Kalman Filter and regression model. With the help of Hidden Markov Model, two different sections were used to find the pattern and verified using Bootstrap process.
Keywords
Bus Information System; Hiddel Markov Model; Traffic Flow; Travel Speed Estimation;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 H. G. Kim, C. Y. Park, D. C. Shin, C. S. Shin, Y. Y. Cho, and J. W. Park, "A Study on Traffic Analysis Using Bus Information System," The KIPS Transactions on Computer and Communication Systems, Vol.5. No.9, pp.261-267, 2016.   DOI
2 S. H. Lee, B. S. Moon, and B. J. Park, "The Bus Arrival Time Prediction using Bus Delay Time," Journal of Korean Society of Transportation, Vol.28, No.1, pp. 125-134, Febrary, 2010.
3 L. R. RABINER, 1989, "A tutorial on Hidden Markov Models and Selected Applications in Speech Recognition," IEEE, Vol.77, No.2, Febrary.
4 I. Visser., 2011, "Seven things to remember about hidden Markov models: A tutorial on Markovian models for time series", Journal of Mathematical Psychology, Vol.55, pp. 403-415, July.   DOI
5 S. H. Lee, B. S. Moon, and B. J. Park, "The Bus Arrival Time Prediction using Markov Chain," The Journal of The Korea Institute of Intelligent Transport Systems, Vol.8, No.3, pp.1-10, June, 2009.
6 B. S. Choi, H. C. Kang, S, K, Lee, and S. T. Han, "A Study for Traffic Forecasting Using Traffic Statistic Information," The Korean Journal of Applied Statistics, Vol.22, No.6, pp. 1177-1190, October, 2009.   DOI
7 T. G. Kim, H. C. Ahn, and S. G. Kim, "Predictive Modeling of the Bus Arrival Time on the Arterial using Real-Time BIS Data," Journal of The Korean Society of Civil Engineers, Vol.29, No.1, pp.1-9, January, 2009.