In recent years, electric scooters have become one of the emerging modes of short-distance transportation. As the number of people using electric scooters increases, so does the number of their traffic accidents. Therefore, it is extremely important and urgent to pay attention to the safety of electric scooters. In view of the fact that the traditional DBSCAN clustering algorithm needs to determine the Eps and MinPts values by experience, which is not accurate enough, this paper adopts a self-adaptive algorithm to determine the parameters of the DBSCAN algorithm. This algorithm determines the Eps and MinPts values by the distribution of the data itself, so as to improve the accuracy of the algorithm. This paper conducted a case study using data collected from the STATS19 road safety database as an example, and identified six accident blackspots. The clustering results were compared with the MDA-DBSCAN algorithm. The results show that the algorithm has better accuracy and adaptability in black spot identification, and provides more accurate data support and decision basis for urban traffic safety management.

Jiaoxuan Chen, Xiaoqiang Zhang. Accident Black Spots Identification of Electric Scooter Based on Self-Adaptive DBSCAN Algorithm. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 10: 119-124. https://doi.org/10.25236/AJCIS.2024.071016.

[1] Corno M, Savaresi S M. Design and Control of an All-in-the-Wheel Assisted Kick Scooter. IEEE/ASME Transactions on Mechatronics, 2016, 21(4): 1858~1867

[2] Kopplin C S, Brand B M, Reichenberger Y. Consumer acceptance of shared e-scooters for urban and short-distance mobility. Transportation Research Part D: Transport and Environment, 2021, 91: 102680

[3] Sanders R L, Branion-Calles M, Nelson T A. To scoot or not to scoot: Findings from a recent survey about the benefits and barriers of using E-scooters for riders and non-riders. Transportation Research Part A: Policy and Practice, 2020, 139: 217~227

[4] Lee K J, Yun C H, Yun M H. Contextual risk factors in the use of electric kick scooters: An episode sampling inquiry. Safety Science, 2021, 139: 105233

[5] Dong C, Chang N, Dong C, et al. Overview of the identification of traffic accident-prone locations driven by big data. d, 2023, 2(1): 67~76

[6] Guo Ling, Zhou Jibiao, Dong sheng, et al. Analysis of Urban Road Traffic Accidents Based onImproved K-means Algorithm. China J. Highw. Transp., 2018, 31(4): 270~279

[7] Lin Nanting, Hu Lin, Lin Miao, et al. Black spot identification and analysis of traffic accidents based on time series clustering[J].J Changsha Univ Sci Tech(Nat Sci),2023,20(2):45-54.

[8] Wang Yingzhi, Wang Lijun .An Identification Method of Traffic Accident Black Point Based on Street-Network Spatial-Temporal Kernel Density Estimation. Scientia Geographica Sinica ,2019 ,39(8): 1238 -1245.

[9] Bíl M, Andrášik R, Janoška Z. Identification of hazardous road locations of traffic accidents by means of kernel density estimation and cluster significance evaluation. Accident Analysis & Prevention, 2013, 55: 265~273

[10] Bíl M, Andrášik R, Nezval V, et al. Identifying locations along railway networks with the highest tree fall hazard. Applied Geography, 2017, 87: 45~53

[11] Elvik R. A survey of operational definitions of hazardous road locations in some European countries. Accident Analysis & Prevention, 2008, 40(6): 1830~1835

[12] Geng Chao, Peng Yuhua. Identification method of traffic accident black spots based ondynamic segmentation and DBSCAN algorithm.Journal of Chang an University(Natural Science Edition), 2018, 38(5): 131~138 

[13] Zhang Yunfei, Zhang Zhexu, Zhu Fangqi. Identification of highway accident black spots based on spatio-temporal density clustering. Bulletin of Surveying and Mapping, 2022(10): 73~79

[14] Li Wenjie, Yan Shiqiang, Jiang ying, et al. Research on Method of Self-Adaptive Determination of DBSCAN Algorithm Parameters. Computer Engineering and Applications, 2019, 55(5): 1-7+148