Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Short-Term Prediction of Vehicle Speed on Main City Roads using the k-Nearest Neighbor Algorithm

k-Nearest Neighbor 알고리즘을 이용한 도심 내 주요 도로 구간의 교통속도 단기 예측 방법

  • Rasyidi, Mohammad Arif (Department of Electrical and Computer Engineering, Pusan National University) ;
  • Kim, Jeongmin (Department of Electrical and Computer Engineering, Pusan National University) ;
  • Ryu, Kwang Ryel (Department of Electrical and Computer Engineering, Pusan National University)
  • Received : 2014.01.28
  • Accepted : 2014.03.02
  • Published : 2014.03.28
Download PDF
⟨ Previous Next ⟩

Abstract

Traffic speed is an important measure in transportation. It can be employed for various purposes, including traffic congestion detection, travel time estimation, and road design. Consequently, accurate speed prediction is essential in the development of intelligent transportation systems. In this paper, we present an analysis and speed prediction of a certain road section in Busan, South Korea. In previous works, only historical data of the target link are used for prediction. Here, we extract features from real traffic data by considering the neighboring links. After obtaining the candidate features, linear regression, model tree, and k-nearest neighbor (k-NN) are employed for both feature selection and speed prediction. The experiment results show that k-NN outperforms model tree and linear regression for the given dataset. Compared to the other predictors, k-NN significantly reduces the error measures that we use, including mean absolute percentage error (MAPE) and root mean square error (RMSE).

교통속도는 교통 문제를 해결하기 위한 중요한 지표 중 하나이다. 이를 이용하여 교통혼잡 탐지, 주행 시간 예측, 도로 설계와 같은 다양한 문제 해결에 활용할 수 있다. 따라서 정확한 교통속도 예측은 지능형 교통 시스템의 개발에 있어 필수적인 요소라고 할 수 있다. 본 논문에서는 대한민국 부산시의 특정 도로를 대상으로 교통 속도에 대한 분석 및 예측을 수행하였다. 과거 연구에서는 대상 도로의 속도 예측을 위해 과거 대상 도로의 교통속도 이력 데이터만을 사용하였다. 그러나 실제 대상 도로의 교통 상황은 인접한 도로의 교통 상황의 영향을 받게 된다. 따라서 본 논문에서는 실제 부산시의 과거 교통속도 이력 데이터를 기반으로 대상 도로와 인접 도로를 모두 고려하여 교통속도 예측 모델의 학습을 위한 속성을 추출하였다. 이와 같이 후보 속성들을 추출 한 후 선형 회귀 (linear regression), 모델 트리 (model tree) 및 k-nearest neighbor (k-NN) 기법을 이용하여 속성의 부분집합 선택 (feature subset selection)과 교통속도 예측 모델 생성을 수행하였다. 실험 결과 주어진 교통 데이터에서 k-NN 기법은 선형 회귀 및 모델 트리 기법에 비해 평균절대백분율오차 (mean absolute percent error, MAPE)와 제곱근평균제곱오차 (root mean squared error, RMSE) 측면에서 더 나은 성능을 보임을 확인하였다.

Keywords

References

  1. Billah, B., M. L. King, R. D. Snyder, and A. B. Koehler, "Exponential smoothing model selection for forecasting," International Journal of Forecasting, Vol.22, No.2(2006), 239-247. https://doi.org/10.1016/j.ijforecast.2005.08.002
  2. Boiman, O., E. Shechtman, and M. Irani, "In defense of Nearest-Neighbor based image classification," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2008), 1-8.
  3. Dudani, S. A., "The Distance-Weighted k-Nearest-Neighbor Rule," IEEE Transactions on System, Man, and Cybernetics, Vol.6, No.4(1976), 325-327.
  4. Fernandez-Rodriguez, F., S. Sosvilla-Rivero, and J. Andrada-Felix, "Exchange-rate forecasts with simultaneous nearest-neighbour methods: evidence from the EMS," International Journal of Forecasting, Vol.15, No.4(1999), 383-392. https://doi.org/10.1016/S0169-2070(99)00003-5
  5. Kim, T. Y., K. J. Oh, C. Kim, and J. D. Do, "Artificial neural networks for non-stationary time series," Neurocomputing, Vol.61(2004), 439-447. https://doi.org/10.1016/j.neucom.2004.04.002
  6. Matei, O., P. C. Pop, and H. Valean, "Optical character recognition in real environments using neural networks and k-nearest neighbor," Applied Intelligence, Vol.39, No.4 (2013), 739-748. https://doi.org/10.1007/s10489-013-0456-2
  7. Mizrach, B., "Multivariate nearest-neighbour forecasts of ems exchange rates," Journal of Applied Econometrics, Vol.7(1992), S151-S163. https://doi.org/10.1002/jae.3950070511
  8. Nottingham, Q. J. and D. F. Cook, "Local linear regression for estimating time series data," Computational Statistics & Data Analysis, Vol.37, No.2(2001), 209-217. https://doi.org/10.1016/S0167-9473(01)00006-8
  9. Rout, M., B. Majhi, R. Majhi, and G. Panda, "Forecasting of currency exchange rates using an adaptive ARMA model with differential evolution based training," Journal of King Saud University - Computer and Information Sciences, Vol.26, No.1(2014), 7-18. https://doi.org/10.1016/j.jksuci.2013.01.002
  10. Russel, S. J. and P. Norvig, Artificial Intelligence: A Modern Approach, 3rd edition, Pearson Education, 2010.
  11. Sattari, M. T., M. Pal, H. Apaydin, and F. Ozturk, "M5 model tree application in daily river flow forecasting in Sohu Stream, Turkey," Water Resources, Vol.40, No.3(2013), 233-242. https://doi.org/10.1134/S0097807813030123
  12. Sun, H., H. X. Liu, H. Xiao, R. R. He, and B. Ran, "Short term traffic forecasting using the local linear regression model," Proceedings of the 82nd Annual Meeting of the Transportation Research Board, Washington, USA, 2003.
  13. Wu, C. H., J. M. Ho, and D.T. Lee, "Travel-Time Prediction With Support Vector Regression," IEEE Transactions on Intelligent Transportation Systems, Vol.5, No.4(2004), 276-281. https://doi.org/10.1109/TITS.2004.837813
  14. Xie, Y., Y. Zhang, and Z. Ye, "Short-Term Traffic Volume Forecasting Using Kalman Filter with Discrete Wavelet Decomposition," Computer-Aided Civil and Infrastructure Engineering, Vol.22(2007), 326-334. https://doi.org/10.1111/j.1467-8667.2007.00489.x
  15. Yankov, D., D. DeCoste, and E. Keogh, "Ensembles of Nearest Neighbor Forecasts," Lecture Notes in Computer Science, Vol.4212(2006), 545-556.

Cited by

  1. 거리척도와 앙상블 기법을 활용한 지가 추정 vol.46, pp.2, 2014, https://doi.org/10.22640/lxsiri.2016.46.2.43
  2. 온라인 리뷰 분석을 통한 상품 평가 기준 추출: LDA 및 k-최근접 이웃 접근법을 활용하여 vol.26, pp.1, 2014, https://doi.org/10.13088/jiis.2020.26.1.097