Modified-DBSCAN Clustering for Identifying Traffic Accident Prone Locations

详细信息    查看全文

• 关键词：Traffic accident prone locations ; DBSCAN clustering ; Kurtosis
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9937
• 期：1
• 页码：99-105
• 全文大小：193 KB
• 参考文献：1.Oppe, S.: Development of traffic and traffic safety: global trends and incidental fluctuations. Accid. Anal. Prev. 23(5), 413–422 (1991)CrossRef
  2.Wright, C.C., Abbess, C.R., Jarrett, D.F.: Estimating the regression-to-mean effect associated with road accident black spot treatment: towards a more realistic approach. Accid. Anal. Prev. 20(3), 199–214 (1988)CrossRef
  3.Larsen, L.: Methods of multidisciplinary in-depth analyses of road traffic accidents. J. Hazard. Materials 111(1–3), 115–122 (2004)CrossRef
  4.Fang, S., Guo, Z., Yang, Z.: A new identification method for accident prone location on highway. J. Traffic Transp. Eng. 1, 91–98 (2001)
  5.Yannis, G., Gollas, J., Kanellaidis, G.: A comparative analysis of the potential of international road accident data piles. IATSS Res. 22, 111–120 (2000)
  6.Saccomanno, F.F., Grossi, R., Greco, D., Mehmood, A.: A mehmood identifying black spots along highway SS107 in Southern italy using two models. J. Transp. Eng. 127(6), 515–522 (2001)CrossRef
  7.Qin, X., Ng, M., Reyes, P.E.: Identifying crash-prone locations with quantile regression. Accid. Anal. Prev. 42(6), 1531–1537 (2010)CrossRef
  8.Xie, L., Chaozhong, W., Lyn, N., Gao, Y.: Accident-prone section identification approach based on improved clustering algorithm. J. Wuhan Univ. Technol. (Transp. Sci. Eng.) (4), 904–908 (2014)
  9.Ester, M., Kriegel, H.-P., Sander, J., Xiaowei, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, pp. 226–231 (1996)
  10.Ertoz, L., Steinbach, M., Kumar, V.: Finding clusters of different sizes, shapes, and densities in noisy, high dimensional data. In: Proceedings of Second SIAM International Conference on Data Mining, pp. 47–58 (2003)
  
• 作者单位：Chenlu Qiu (21)
  Huiying Xu (21)
  Yongqiang Bao (21)
  
  21. Traffic Management Research Institute of the Ministry of Public Security, Wuxi, 214151, Jiangsu, China
  
• 丛书名：Intelligent Data Engineering and Automated Learning ¨C IDEAL 2016
• ISBN：978-3-319-46257-8
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9937

文摘

Road traffic accidents, especially expressway traffic accidents, have become a severe problem in China. Under this condition, identification of road traffic accident prone locations is in urgent need. This work proposes a modification of DBSCAN clustering algorithm with parameters \(\varepsilon \) and \(\text {minPts}\) carefully chosen for identifying traffic accident prone locations. Experimental results on traffic accident datasets of three national expressways are given, demonstrating the effectiveness of the proposed algorithm.