Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Data Bias Optimization based Association Reasoning Model for Road Risk Detection

도로 위험 탐지를 위한 데이터 편향성 최적화 기반 연관 추론 모델

  • Ryu, Seong-Eun (Data Mining Lab., Division of Computer Science and Engineering, Kyonggi University) ;
  • Kim, Hyun-Jin (Data Mining Lab., Division of Computer Science and Engineering, Kyonggi University) ;
  • Koo, Byung-Kook (Data Mining Lab., Division of Computer Science and Engineering, Kyonggi University) ;
  • Kwon, Hye-Jeong (Data Mining Lab., Division of Computer Science and Engineering, Kyonggi University) ;
  • Park, Roy C. (Department of Information Communication Software Engineering, Sangji University) ;
  • Chung, Kyungyong (Division of Computer Science and Engineering, Kyonggi University)
  • 류성은 (경기대학교 컴퓨터공학부) ;
  • 김현진 (경기대학교 컴퓨터공학부) ;
  • 구병국 (경기대학교 컴퓨터공학부) ;
  • 권혜정 (경기대학교 컴퓨터공학부) ;
  • 박찬홍 (상지대학교 정보통신소프트웨어공학과) ;
  • 정경용 (경기대학교 컴퓨터공학부)
  • Received : 2020.08.10
  • Accepted : 2020.09.20
  • Published : 2020.09.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we propose an association inference model based on data bias optimization for road hazard detection. This is a mining model based on association analysis to collect user's personal characteristics and surrounding environment data and provide traffic accident prevention services. This creates transaction data composed of various context variables. Based on the generated information, a meaningful correlation of variables in each transaction is derived through correlation pattern analysis. Considering the bias of classified categorical data, pruning is performed with optimized support and reliability values. Based on the extracted high-level association rules, a risk detection model for personal characteristics and driving road conditions is provided to users. This enables traffic services that overcome the data bias problem and prevent potential road accidents by considering the association between data. In the performance evaluation, the proposed method is excellently evaluated as 0.778 in accuracy and 0.743 in the Kappa coefficient.

본 연구에서는 도로 위험 탐지를 위한 데이터 편향성 최적화 기반 연관 추론 모델을 제안한다. 이는 사용자의 개인적 특성과 주변 환경 데이터를 수집하고 교통사고 방지 서비스를 제공하기 위한 연관분석 기반의 마이닝 모델이다. 이는 다양한 상황 변수들로 구성된 트랜잭션 데이터를 생성한다. 생성된 정보를 바탕으로 연관 패턴 분석을 통해 각 트랜잭션 내 변수들의 유의미한 연관관계를 도출한다. 분류된 범주형 데이터의 편향성을 고려하여 최적화된 지지도 및 신뢰도 값으로 가지치기를 진행한다. 추출된 상위 연관규칙을 바탕으로 사용자에게 개인 특성과 주행 도로 상황에 대한 위험 탐지모델을 제공한다. 이는 데이터 편향성 문제를 극복하고 데이터간 연관성을 고려하여 잠재적인 도로 사고를 예방하는 교통 서비스가 가능하다. 성능 평가는 제안하는 방법이 정확도에서 0.778, Kappa 계수에서 0.743로 우수하게 평가된다.

Keywords

References

  1. B. K. Dar, M. A. Shah, S. U. Islam, C. Maple, S. Mussadiq & S. Khan. (2019). Delay-aware accident detection and response system using fog computing. IEEE Access, 7, 70975-70985. https://doi.org/10.1109/access.2019.2910862
  2. Statistical Analysis of Traffic Accidents. (2019). https://www.koroad.or.kr/.
  3. C. M. Kim, E. J. Hong, K. Chung & Roy C. Park. (2020) Driver Facial Expression Analysis using LFA-CRNN based Feature Extraction for Health-Risk Decisions. Applied Sciences , 10(8), 2956-2976. https://doi.org/10.3390/app10082956
  4. Traffic Accident Information graphic. (2020). http://taas.koroad.or.kr/.
  5. A. B. Parsa, A. Movahedi, H. Taghipour, S. Derrible & A. K. Mohammadian. (2020). Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accident Analysis & Prevention, 136, 105405. https://doi.org/10.1016/j.aap.2019.105405
  6. D. Wang, Q. Liu, L. Ma, Y. Zhang & H. Cong. (2019). Road traffic accident severity analysis: A census-based study in China. Journal of safety research, 70, 135-147. https://doi.org/10.1016/j.jsr.2019.06.002
  7. K. Chung, H. Yoo & D. E. Choe. (2020). Ambient Context-based Modeling for Health Risk Assessment Using Deep Neural Network, Journal of Ambient Intelligence and Humanized Computing, 11(4), 1387-1395. https://doi.org/10.1007/s12652-018-1033-7
  8. J. C. Kim & K. Chung. (2019). Associative Feature Information Extraction using Text Mining from Health Big Data. Wireless Personal Communications, 105(2), 691-707. https://doi.org/10.1007/s11277-018-5722-5
  9. S. Zhu. (2019). Research on data mining of education technical ability training for physical education students based on Apriori algorithm. Cluster Computing, 22(6), 14811-14818. https://doi.org/10.1007/s10586-018-2420-8
  10. S. Canale, S. Leonardi & G Pappalardo. (2005). The reliability of the urban road network: Accident forecast models. Proceedings of the III International Congress SIIV-People, Land, Environment and Transport Infrastructures, 22-24, Italy.
  11. T. Beshah & S. Hill. (2010). Mining road traffic accident data to improve safety: role of road-related factors on accident severity in Ethiopia. AAAI Spring, 3(10), 221-226.
  12. 2019 Traffic Accident Information. (2019). https://www.data.go.kr/data/15003493/fileData.do
  13. Hazardous Road Forecasting System. (2020). http://taas.koroad.or.kr/.
  14. K. D. Rajab. (2019). New Associative Classification Method Based on Rule Pruning for Classification of Datasets. IEEE Access, 7, 157783-157795. https://doi.org/10.1109/access.2019.2950374
  15. J. Landis & G. G. Richard (1977). The Measurement of Observer Agreement for Categorial Data. Biometrics, 159-174.