A Study of Safety Accident Prediction Model (Focusing on Military Traffic Accident Cases)

doi:10.15683/kosdi.2021.9.30.427

All Issue

2021 Vol.17, Issue 3 Preview Page Next Page

Original Article

A Study of Safety Accident Prediction Model (Focusing on Military Traffic Accident Cases) 안전사고 예측모형 개발 방안에 관한 연구(군 교통사고 사례를 중심으로): 기재석¹ㆍ홍명기²*
Jae-Sug Ki¹, Myeong-Gi Hong²*; ¹Professor, Department of Sports ICT Convergence, Sangmyung University. Seoul, Republic of Korea
²PhD, Department of Sports ICT Convergence, Sangmyung University. Seoul, Republic of Korea

30 September 2021. pp. 427-441

PDF

Abstract

Purpose: This study proposes a method for developing a model that predicts the probability of traffic accidents in advance to prevent the most frequent traffic accidents in the military. Method: For this purpose, CRISP-DM (Cross Industry Standard Process for Data Mining) was applied in this study. The CRISP-DM process consists of 6 stages, and each stage is not unidirectional like the Waterfall Model, but improves the level of completeness through feedback between stages. Results: As a result of modeling the same data set as the previously constructed accident investigation data for the entire group, when the classification criterion was 0.5, Significant results were derived from the accuracy, specificity, sensitivity, and AUC of the model for predicting traffic accidents. Conclusion: In the process of designing the prediction model, it was confirmed that it was difficult to obtain a meaningful prediction value due to the lack of data. The methodology for designing a predictive model using the data set was proposed by reorganizing and expanding a data set capable of rational inference to solve the data shortage.

Keywords

Accident Cause Information

Predictive Model

Exploratory Factor Analysis

Machine Learning

Traffic Accident

연구목적: 본 연구는 군에서 가장 많이 발생하는 교통사고의 예방을 위해 부대별로 교통사고가 발생할 확률을 사전에 예측하는 모형의 개발 방안을 제시하는 것이다. 연구방법: 이를 위해 CRISP-DM(Cross Industry Standard Process for Data Mining) 방법론을 적용하였다. CRISP-DM 프로세스는 6단계로 구성되어 있고, 각 단계는 Waterfall Model처럼 일방향으로 구성되어 있지 않고 단계 간 피드백을 통하여 단계별 완성도를 높이게 되어 있다. 연구결과: 전체 집단을 대상으로 기 구축된 사고조사 데이터와 동일한 데이터 세트(data set)를 구축하여 모델링한 결과 분류기준 0.5로 했을 때, 교통사고예측을 위한 모형의 정확도, 특이도, 민감도, AUC에서 의미있는 결과치를 도출하였다. 결론: 예측모형을 설계하는 과정에서 데이터의 부족으로 인해 의미 있는 예측값을 얻기 어려운 문제점이 확인되었다. 이를 해결하기 위해 합리적 추론이 가능한 데이터 세트(data set)를 재구성 및 확대하여 데이터 부족을 해소하고, 이를 활용한 예측모형을 설계할 수 있는 방법론을 제시하였다.

키워드

사고요인정보

예측모형

탐색적 요인분석

머신러닝

교통사고

References

Choi, H.-Y., Min, Y.-H. (2015). "Intelligent information systems; Introduction to deep learning and major issues." Korea Information Processing Society, Vol. 22, No. 1, pp. 7-15.
Choi, W., Kim, Y., Jang, D., Kim, G., Jeong, Y. (2017). "A study on the development of a fire risk prediction model for manufacturing facilities using artificial neural networks." Magazine of The Korean Society of Hazard Mitigation, Vol. 17, No. 1, pp.161-167. 10.9798/KOSHAM.2017.17.1.161
Jo, I.-H. (2016). Data analysis-based Accident Prediction Service for Reducing Traffic Accidents. National Information Society Agency, NIAⅡ-RER-D-16017. Seoul.
Jeong, J.-U., Lee, S.-J. (2020). "Analysis of characteristics of hazardous chemical transport vehicle accidents in Korea." Journal of the Society of Disaster Information, Vol. 16, No. 2, pp. 310-317.
Kim, D., Kim, D.-K., Lee, C. (2013). Safety Performance Functions Reflecting Categorical Impact of Exposure Variables for Freeways. Transportation Research Board Annual Meeting, Korea. 10.3141/2398-08
Lee, G.-H., Roh, J.-H. (2015). "Development of a traffic accident prediction model using probability parameter - Targeting the 4 intersections of the metropolitan area and Busan Metropolitan City." Journal of the Korean ITS Society, Vol. 14, No. 6, pp. 91-99.
Lee, S. (2012). "Comparison of initial center selection methods in K-means clustering." Internet Information Society, Vol. 13, No. 6, pp. 1-8. 10.7472/jksii.2012.13.6.1
Pan, G., Fu, L., Thakali, L. (2017). "Development of a global road safety performance function using deep neural networks." International Journal of Transportation Science and Technology, Vol. 6, No. 3, pp. 159-173. 10.1016/j.ijtst.2017.07.004
Park, J.-B. (2015). Development of a Prediction Model for Traffic Accidents Using Probability Parameters. Ph.D. Dissertation, University of Seoul Graduate School.
Simon, W.P., Mattew, G.K., Fred L.M, (2010). Statistical and Econometric Method ForTransportation Data Analysis. CRC Press, New York.
Yoo, J.-D. (2018). Development of a Prediction Model for Highway Traffic Accidents Using Deep Learning. Ph.D. Dissertation, Graduate School of Ajou University.
Yun, Y., Lee, J., Kim, J., Kim, Y. (2020). "Detection scheme of heart and respiration signals for a driver of car with a doppler radar." Journal of the Society of Disaster Information, Vol. 16, No. 1, pp. 87-95.

Information

Publisher :The Korean Society of Disaster Information
Publisher(Ko) :한국재난정보학회
Journal Title :Journal of the Society of Disaster Information
Journal Title(Ko) :한국재난정보학회논문집
Volume : 17
No :3
Pages :427-441
DOI :https://doi.org/10.15683/kosdi.2021.9.30.427

[1] Choi, H.-Y., Min, Y.-H. (2015). "Intelligent information systems; Introduction to deep learning and major issues." Korea Information Processing Society, Vol. 22, No. 1, pp. 7-15.

[2] Choi, W., Kim, Y., Jang, D., Kim, G., Jeong, Y. (2017). "A study on the development of a fire risk prediction model for manufacturing facilities using artificial neural networks." Magazine of The Korean Society of Hazard Mitigation, Vol. 17, No. 1, pp.161-167. 10.9798/KOSHAM.2017.17.1.161

[3] Jo, I.-H. (2016). Data analysis-based Accident Prediction Service for Reducing Traffic Accidents. National Information Society Agency, NIAⅡ-RER-D-16017. Seoul.

[4] Jeong, J.-U., Lee, S.-J. (2020). "Analysis of characteristics of hazardous chemical transport vehicle accidents in Korea." Journal of the Society of Disaster Information, Vol. 16, No. 2, pp. 310-317.

[5] Kim, D., Kim, D.-K., Lee, C. (2013). Safety Performance Functions Reflecting Categorical Impact of Exposure Variables for Freeways. Transportation Research Board Annual Meeting, Korea. 10.3141/2398-08

[6] Lee, G.-H., Roh, J.-H. (2015). "Development of a traffic accident prediction model using probability parameter - Targeting the 4 intersections of the metropolitan area and Busan Metropolitan City." Journal of the Korean ITS Society, Vol. 14, No. 6, pp. 91-99.

[7] Lee, S. (2012). "Comparison of initial center selection methods in K-means clustering." Internet Information Society, Vol. 13, No. 6, pp. 1-8. 10.7472/jksii.2012.13.6.1

[8] Pan, G., Fu, L., Thakali, L. (2017). "Development of a global road safety performance function using deep neural networks." International Journal of Transportation Science and Technology, Vol. 6, No. 3, pp. 159-173. 10.1016/j.ijtst.2017.07.004

[9] Park, J.-B. (2015). Development of a Prediction Model for Traffic Accidents Using Probability Parameters. Ph.D. Dissertation, University of Seoul Graduate School.

[10] Simon, W.P., Mattew, G.K., Fred L.M, (2010). Statistical and Econometric Method ForTransportation Data Analysis. CRC Press, New York.

[11] Yoo, J.-D. (2018). Development of a Prediction Model for Highway Traffic Accidents Using Deep Learning. Ph.D. Dissertation, Graduate School of Ajou University.

[12] Yun, Y., Lee, J., Kim, J., Kim, Y. (2020). "Detection scheme of heart and respiration signals for a driver of car with a doppler radar." Journal of the Society of Disaster Information, Vol. 16, No. 1, pp. 87-95.

Journal of the Society of Disaster Information ISSN:1976-2208(Print) 2671-5287(Online) 한국재난정보학회논문집

All Issue