DOI QR코드

DOI QR Code

효율적인 교통 체계 구축을 위한 Conv-LSTM기반 사거리 모델링 및 교통 체증 예측 알고리즘 연구

Conv-LSTM-based Range Modeling and Traffic Congestion Prediction Algorithm for the Efficient Transportation System

  • 이승용 (동서대학교 소프트웨어학과) ;
  • 서부원 (동서대학교 소프트웨어학과) ;
  • 박승민 (동서대학교 소프트웨어학과)
  • 투고 : 2023.02.16
  • 심사 : 2023.04.17
  • 발행 : 2023.04.30

초록

인공 지능이 발전함에 따라 예측 시스템은 우리의 삶에 필수적인 기술 중 하나로 자리를 잡았다. 이러한 기술의 성장에도 불구하고, 21세기 사거리 교통 체증은 계속해서 문제 되어 왔다. 본 논문에서는 Conv-LSTM(: Convolutional-Long Short-Term Memory) 알고리즘을 이용한 사거리 교통 체증 예측 시스템을 제안한다. 제안한 시스템은 교통 체증이 발생하는 사거리에 시간대별 교통 정보를 학습한 데이터를 모델링 한다. 시간의 흐름에 따라 기록된 교통량 데이터로 교통 체증을 예측하며. 예측된 결과를 기반으로 사거리 교통 신호를 제어하고, 일정한 교통량으로 유지한다. VDS(: Vehicle Detection System)센서를 활용하여 도로 혼잡도 데이터를 정의하고, 교통을 원활하게 하기 위하여 각각의 교차로를 Conv-LSTM 알고리즘기반 네트워크 시스템으로 구성하였다.

With the development of artificial intelligence, the prediction system has become one of the essential technologies in our lives. Despite the growth of these technologies, traffic congestion at intersections in the 21st century has continued to be a problem. This paper proposes a system that predicts intersection traffic jams using a Convolutional LSTM (Conv-LSTM) algorithm. The proposed system models data obtained by learning traffic information by time zone at the intersection where traffic congestion occurs. Traffic congestion is predicted with traffic volume data recorded over time. Based on the predicted result, the intersection traffic signal is controlled and maintained at a constant traffic volume. Road congestion data was defined using VDS sensors, and each intersection was configured with a Conv-LSTM algorithm-based network system to facilitate traffic.

키워드

과제정보

본 논문은 2022년도 동서대학교 "Dongseo Cluster Project"지원에 의하여 이루어진 것임.(DSU-2022002)

참고문헌

  1. Y. Kim, D. Kim, and S. Lee, "Prediction of Temperature and Heat Wave Occurrence for Summer Season Using Machine Learning," J. of Korean Society of Disaster and Security, vol. 13, no. 2, June. 2020, pp. 27-38.
  2. J. Jo, "Time Series Data Processing Deep Learning system for Prediction of Hospital Outpatient Number," J. of the Korea Institute of Electronic Communication Sciences, vol. 16, no. 2, Apr. 2021, pp. 313-318.
  3. S. Jung, J. Koh, and S. Lee, "Recurrent Neural Network based Prediction System of Agricultural Photovoltaic Power Generation," J. of the Korea Institute of Electronic Communication Sciences, vol. 17, no. 5, Oct. 2022, pp. 825-832.
  4. H. Kwon, J. Yoo, and L. Yang, "A Hybrid Inference System for Efficiently Controlling Reversible Lane," J. of the Korea Society of Computer and Information, vol. 17, no. 11, Nov. 2012, pp. 19-26. https://doi.org/10.9708/jksci/2012.17.11.019
  5. S. Kang, "Calculation of appropriate speed limits for urban roads using traffic information big data," Doctoral Thesis, University of Seoul, 2017.
  6. G. Baek, J. Lee, and M. Park, "Development of Auto Traffic Light Control System for Prevention of Traffic Jam," J. of the Convergence Signal Processing Society, vol. 15, no. 4, Oct. 2014, pp. 148-154.
  7. G. Lee and S. Lee, "Universal Prediction System Realization Using RNN," The J. of Korean Institute of Information Technology, vol. 16, no. 10, Oct. 2018, pp. 11-20. https://doi.org/10.14801/jkiit.2018.16.10.11
  8. S. Hochreiter, and J. Schmidhuber, "Long Short-Term Memory", Neural Comput, vol. 9, no. 8, Nov. 1997, pp. 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  9. M. Aqib, R. Mehmood, A. Alzahrani, I. Katib, A. Albeshri, and S. Altowaijri, "Smarter Traffic Prediction Using Big Data, In-Memory Computing, Deep Learning and GPUs," Sensors, vol. 19, no. 9, May. 2019, pp. 2206-2239. https://doi.org/10.3390/s19092206
  10. Y. Lv, Y. Duan, W. Kang, Z. Li, and F. Wang, "Traffic Flow Prediction With Big Data: A Deep Learning Approach," in IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 2, Apr. 2015, pp. 865-873.