Detection of Risk Riding Events for Delivery Scooter : Methodology and Application

Eunsol Cho; Young Jo; Yeseo Gu; Cheol Oh; Gunwoo Lee

doi:10.7470/jkst.2023.41.1.019

All Issue

2023 Vol.41, Issue 1 Preview Page Next Page

Article

Detection of Risk Riding Events for Delivery Scooter : Methodology and Application 배달 이륜차 위험 이벤트 검지 기법 개발 및 활용

28 February 2023. pp. 19-34

PDF XML

Abstract

Traffic safety issues associated with food delivery scooters have been arising because the rapid growth of the delivery service market in Korea due to the impact of COVID-19 has resulted in an increase in crashes. However, less efforts have been conducted to develop technical countermeasures to improve the traffic safety of delivery scooters. The purpose of this study is to develop a method to detect risk riding events that are potentially leading to crashes based on the analysis of inertial measurement unit (IMU) sensor data. A support vector machine (SVM) was adopted to develop the proposed methodology using data obtained from the Korean 100 naturalistic riding study (K-100NRS). As a result of evaluating the performance of the model by separating the train set and the test set at a ratio of 7:3, classification accuracy of 99.5% was obtained. In addition, this study presented a riding safety monitoring framework as an application of the proposed method. The results of this study are expected to be used as a fundamental data to prepare for riding safety management systems that contribute to enhancing the safety of food delivery scooters.

Keywords

delivery scooter

naturalistic riding data

rider safety

risky riding event

support vector machine

비대면 음식 배달 서비스 수요 증가는 이륜차 교통사고의 증가를 초래하고 있다. 주문량 할당으로 인한 배송 시간의 제한은 라이더의 무리한 운전으로 이어지기 때문에 배달 이륜차의 위험운전행동 및 교통사고 발생 가능성이 높아질 수 있다. 따라서 배달 이륜차의 교통사고를 효과적으로 예방하기 위한 체계적인 교통안전 관리 대책이 요구되는 상황이다. 효과적인 배달 이륜차의 교통안전관리 대책 마련을 위해서는 배달 이륜차의 실제 주행자료를 분석하여 주행특성을 분석할 필요가 있다. 본 연구의 목적은 배달 이륜차 라이더 주행특성 기반의 위험 이벤트 검지 기법을 개발하고 활용방안을 제시하는 것이다. 한국에서는 2021년 7월 30일부터 11월 16일까지 배달업에 종사하고 있는 라이더 100명의 이륜차에 GPS 및 IMU 센서를 설치하여 실제 주행자료를 수집하는 Korean 100 naturalistic riding study(K-100NRS) 프로젝트가 수행되었다. 본 연구에서는 Korean 100 naturalistic riding study(K-100NRS) 프로젝트에서 30명의 라이더들이 2021년 8월 20일 하루 동안 주행한 자료를 활용하였다. 주행자료를 활용하여 위험이벤트와 일반이벤트를 분류하는 서포트 벡터 머신 모델을 개발하고 위험 이벤트 검지 기법을 개발하였다. 주행특성자료를 입력자료로 사용하여 사고 또는 near miss와 같은 위험이벤트를 분류해내는 서포트 벡터 머신 기반의 검지 기법을 개발하였다. Train set과 test set을 7:3의 비율로 분리하여 모형의 성능을 평가한 결과 99.5%의 분류 정확도를 얻을 수 있었다. 본 연구에서는 개발된 검지 기법을 활용하여 라이더별로 안전운행 수준을 평가하고 교통안전 모니터링을 위한 프레임워크를 제시하였다. 본 연구의 결과는 배달 이륜차만의 특성을 고려한 교통안전 모니터링 시스템을 설계하는데 기초자료로 활용될 수 있을 것으로 기대된다.

키워드

배달 이륜차

주행 자료

라이더 안전

위험 주행 이벤트

서포트 벡터 머신

References

Abdullah D. M., Abdulazeez A. M. (2021), Machine Learning Applications based on SVM Classification A Review, Qubahan Academic Journal, 1(2), 81-90. 10.48161/qaj.v1n2a50

Attal F., Boubezoul A., Samé A., Oukhellou L. (2015, April), Powered-Two-Wheeler safety critical events recognition using a mixture model with quadratic logistic proportions, In ESANN 2015-23rd European Symposium on Artificial Neural Networks, 421.

Attal F., Boubezoul A., Samé A., Oukhellou L., Espié S. (2018), Powered Two-wheelers Critical Events Detection and Recognition Using Data-driven Approaches, IEEE Transactions on Intelligent Transportation Systems, 19(12), 4011-4022. 10.1109/TITS.2018.2797065

Automobile Management Act Enforcement Rules, Section 2.

Balasubramaniam V. (2021), Artificial Intelligence Algorithm with SVM Classification Using Dermascopic Images for Melanoma Diagnosis, Journal of Artificial Intelligence and Capsule Networks, 3(1), 34-42. 10.36548/jaicn.2021.1.003

Boubezoul A., Espie S., Larnaudie B., Bouaziz S. (2013), A Simple Fall Detection Algorithm for Powered Two Wheelers, Control Engineering Practice, 21(3), 286-297. 10.1016/j.conengprac.2012.10.009

Chandra M. A., Bedi S. S. (2021), Survey on SVM and Their Application in Image Classification, International Journal of Information Technology, 13(5), 1-11. 10.1007/s41870-017-0080-1

Cortes C., Vapnik, V. (1995). Support-vector networks. Machine learning, 20, 273-297. 10.1007/BF00994018

Cossalter V., Bellati A., Cafaggi V. (2005), Exploratory Study of the Dynamic Behaviour of Motorcycle-rider during Incipient Fall Events, In In the 19th International Technical Conference on the Enhanced Safety of Vehicles Conference (ESV) in Washington, DC, 6-9.

Cossalter V., Lot R., Tavernini D. (2013), Optimization of the Centre of Mass Position of a Racing Motorcycle in Dry and Wet Track by Means of the “Optimal Maneuver Method”, In 2013 IEEE International Conference on Mechatronics (ICM), 412-417, IEEE. 10.1109/ICMECH.2013.6518572

European Commission (2009), 2-Wheeler behavior and safety.

Gelmini S., Strada S. C., Tanelli M., Savaresi S. M., De Tommasi C. (2020), A Novel Crash Detection Algorithm for Scooters, IEEE Transactions on Intelligent Vehicles, 6(1), 88-99. 10.1109/TIV.2020.3028462

Ham J., Jung H., Choi S. (2018), A Study on the Characteristics of Delivery Incident and Social Insurance and Accident Insurance -Focused on Delivery Workers of Food Service Using Motorcycles: The Journal of Humanities and Social science, 9(4), 1557-1572. 10.22143/HSS21.9.4.108

Iqbal A., Iqbal A., Ali H., Ehatisham-ul-Haq M., Arsalan A., Raheel A. (2021), Fall Detection of Riders Using Inertial Sensors: A Smart Helmet, In 2021 International Bhurban Conference on Applied Sciences and Technologies (IBCAST), 620-624, IEEE. 10.1109/IBCAST51254.2021.9393170

Jeju Research Institute (2020), Two-wheeled Vehicle’s Traffic Safety and Problems.

Korea Occupational Safety and Health Agency (2021), Occupational Accident Statistics.

Lim, J., Kim, H., Cho, H., & Lee, H. (2021). A Study on the Driving Behavior of Delivery Two Wheeled Vehicles - Focusing on Apartment Complexes. Journal of Korea Academia-Industrial cooperation Society, 22(9), 19-27. 10.5762/KAIS.2021.22.9.19

Manan M. M. A., Ho J. S., Arif S. T. M. S. T., Ghani M. R. A., Várhelyi A. (2017), Factors Associated with Motorcyclists’ Speed Behaviour on Malaysian Roads, Transportation Research Part F: Traffic Psychology and Behaviour, 50, 109-127. 10.1016/j.trf.2017.08.006

Mathur A., Foody G. M. (2008), Multiclass and Binary SVM Classification: Implications for Training and Classification Users, IEEE Geoscience and Remote Sensing Letters, 5(2), 241-245. 10.1109/LGRS.2008.915597

Polat K., Güneş, S. (2009). A new method to forecast of Escherichia coli promoter gene sequences: Integrating feature selection and Fuzzy-AIRS classifier system. Expert Systems with Applications, 36(1), 57-64. 10.1016/j.eswa.2007.09.010

Traffic Accident Analysis System(TAAS), Available Online:http://taas.koroad.or.kr/

Vapnik, V. (1999). The nature of statistical learning theory. Springer science & business media. 10.1007/978-1-4757-3264-1

Virginia Tech Transportation Institute (2011), The MSF 100 Motorcyclists Naturalistic Study.

Virginia Tech Transportation Institute (2015), Overview of the MSF 100 Naturalistic Riding Study.

Vlahogianni E. I., Yannis G., Golias J. C., Eliou N., Lemonakis P. (2011), Identifying Riding Profiles Parameters from High Resolution Naturalistic Riding Data, In Proceedings of the 3rd International Conference on Road Safety and Simulation (RSS2011), September, 14-16.

Vlahogianni E. I., Yannis G., Golias J. C. (2013), Critical Power Two Wheeler Driving Patterns at the Emergence of an Incident, Accident Analysis & Prevention, 58, 340-345. 10.1016/j.aap.2012.12.02623375128

Will S., Metz B., Hammer T., Mörbe M., Henzler M., Harnischmacher F., Matschl G. (2020), Methodological Considerations Regarding Motorcycle Naturalistic Riding Investigations Based on the Use of g-g Diagrams for Rider Profile Detection, Safety Science, 129, 104840. 10.1016/j.ssci.2020.104840

Information

Publisher :Korean Society of Transportation
Publisher(Ko) :대한교통학회
Journal Title :Journal of Korean Society of Transportation
Journal Title(Ko) :대한교통학회지
Volume : 41
No :1
Pages :19-34
Received Date : 2022-06-30
Revised Date : 2022-07-27
Accepted Date : 2023-02-01
DOI :https://doi.org/10.7470/jkst.2023.41.1.019

Journal of Korean Society of Transportation ISSN:1229-1366(Print) 2234-4217(Online) 대한교통학회지

All Issue