The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Optimize TOD Time-Division with Dynamic Time Warping Distance-based Non-Hierarchical Cluster Analysis

동적 타임 워핑 거리 기반 비 계층적 군집분석을 활용한 TOD 시간분할 최적화

  • Hwang, Jae-Yeon (Univ. of Hannam) ;
  • Park, Minju (Dept. of Big Data Application, Univ. of Hannam) ;
  • Kim, Yongho (Dept. of Metropolitan Transport, Korea Transport Institute) ;
  • Kang, Woojin (Dept. of Metropolitan Transport, Korea Transport Institute)
  • 황재연 (한남대학교 빅데이터 응용학과) ;
  • 박민주 (한남대학교 빅데이터 응용학과) ;
  • 김영호 (한국교통연구원 광역교통연구본부) ;
  • 강우진 (한국교통연구원 광역교통연구본부)
  • Received : 2021.07.14
  • Accepted : 2021.10.11
  • Published : 2021.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, traffic congestion in the city is continuously increasing due to the expansion of the living area centered in the metropolitan area and the concentration of population in large cities. New road construction has become impossible due to the increase in land prices in downtown areas and limited sites, and the importance of efficient data-based road operation is increasingly emerging. For efficient road operation, it is essential to classify appropriate scenarios according to changes in traffic conditions and to operate optimal signals for each scenario. In this study, the Dynamic Time Warping model for cluster analysis of time series data was applied to traffic volume and speed data collected at continuous intersections for optimal scenario classification. We propose a methodology for composing an optimal signal operation scenario by analyzing the characteristics of the scenarios for each data used for classification.

최근 수도권 중심의 생활권역 확장과 대도시로의 인구 집중으로 도시 내의 교통 혼잡이 지속적으로 증가하고 있다. 도심지의 땅값 상승과 한정된 부지로 인해 새로운 도로 건설은 불가능하게 되었고, 데이터 기반의 효율적인 도로 운영의 중요성이 점점 부각되고 있다. 효율적인 도로 운영을 위해서는 교통상황의 변화에 따른 적절한 TOD 시간분할과 TOD 시간분할을 통한 최적의 신호 운영 방안이 필수적이다. 본 연구에서는 최적의 TOD 시간 분할을 위해 연속된 교차로에서 수집된 교통량과 속도 데이터에 시계열 데이터의 군집 분석을 위한 동적 타임 워핑 모델을 적용하였다. 시간 분할을 위해 활용된 데이터별 군집의 특성을 분석하여 최적의 신호 운영 시나리오를 구성하기 위한 시간 분할 방법론을 제안하고자 한다.

Keywords

Acknowledgement

이 논문은 2021년도 정부(교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임(No. 2020R1I1A3074217).

References

  1. Cho J., Jung H., Nam Bui K. H. and Yi H.(2020), "Image Generation-based Traffic Density Classification for Large-Scale Urban Road Networks," KIISE Transactions on Computing Practices, vol. 26, no. 11, pp.499-506. https://doi.org/10.5626/ktcp.2020.26.11.499
  2. Hua J. and Faghri A.(2005), "Dynamic Traffic Pattern Classification Using Artificial Neural Networks," Transportation Research Record, vol. 1399, pp.14-19.
  3. Jang C.(2020), From machine learning with Python optimization concepts learned with linear algebra and statistics to deep learning using tensorflow, BJpulic, p.138.
  4. Jeong Y., Kim D., Kim Y., Hwang K. and Kim Y.(2008), "Determination of TOD Plan Breaking Points Using a Clustering Analysis," Korean Society of Road Engineers, pp.341-347.
  5. Jia L., Yang L., Kong Q. and Lin S.(2006), "Study of Artificial Immune Clustering Algorithm and Its Applications to Urban Traffic Control," International Journal of Information Technology, vol. 12, no. 3, pp.1-6.
  6. Lantz B.(2020), Machine Learning with R, Acorn, pp.388-389, p.400.
  7. Lee I., Lee H. and Kim Y.(2011), "Optimization of TIME-OF-DAY and Estimation on the Field Application for Arterial Road," Journal of Korean Society of Transportation, vol. 29, no. 4, pp.113-123.
  8. Lee J., Kim J. and Park B.(Brian)(2011), "A genetic algorithm-based procedure for determining optimal time-of-day break points for coordinated actuated traffic signal systems," KSCE Journal of Civil Engineering, vol. 15, pp.197-203. https://doi.org/10.1007/s12205-011-1093-0
  9. Lee Y., Ko M. and Choi D.(2019), "Pattern and Energy Intensity Analysis of Monthly Gas Energy Consumption in Apartment Using Dynamic Time Warping Hierarchical Clustering," The Korean Society of Living Environmental System, vol. 26, no. 1, pp.134-139. https://doi.org/10.21086/ksles.2019.02.26.1.134