A data mining approach for traffic accidents, pattern extraction and test scenario generation for autonomous vehicles

The typical AV accident scenarios in the urban area obtained by clustering and association rule mining of real-world accident reports

“…Studies on accident prevention technology development and scenario generation for vehicle safety evaluation have been conducted based on real-data analysis [ [32] , [33] , [34] , [35] , [36] , [37] , [38] , [39] , [40] ]. Nitsche et al (2017) [ 32 ] derived 34 crash scenarios using clustering and association analysis and extracted 12 scenarios of accidents with a high risk of injury.…”

“…Pan et al (2021) [ 36 ] and Tan et al (2021) [ 37 ] derived accident test scenarios by clustering analysis to develop AEB/FCW technology to prevent accidents practically. Essenturk et al (2022) [ 38 ] derived traffic accident patterns through ROCK (Robust Clustering with Links) and market basket analysis using UK's STATS19 database. ROCK was performed on 26 clusters (derived from clustering) to create seven clusters, and an AV test scenario was presented.…”

A Clustering-Based Approach to Detecting Critical Traffic Road Segments in Urban Areas

“…Clustering Approach [1] traffic load analysis improved k-means clustering algorithm [2] traffic congestion analysis self-organizing maps neural network [3] traffic state classification k-medoids algorithm [4] road network level identification k-means algorithm [5] traffic congestion analysis grey relational clustering model [6] traffic accidents and pattern extraction ROCK algorithm [7] traffic accident pattern identification COOLCAT algorithm [8] traffic accident factor analysis k-means algorithm [9] road traffic accident modeling a comparative study of machine learning classifiers [10] traffic accident black spots identification HDBSCAN algorithm [11] traffic congestion analysis k-means algorithm [12] driving behavior risk analysis k-means algorithm [13] optimal path routing a modified K-medoids algorithm [14] analysis of pedestrian crash fatalities and severe injuries KDE method [15] traffic-management system DBSCAN agorithm [16] severity of traffic accident analysis DBSCAN algorithm [17] highway safety assessment k-means algorithm [18] pedestrian crash severity analysis KDE method [19] detection of road segments of spatially prolonged and high traffic accident risk a clustering algorithm based on the Gestalt principle of proximity…”

Traffic influence analysis of the area adjacent accident point on freeway in connected environment

“…At present, research on the spatio-temporal impact of traffic accidents mainly uses traffic wave theory [1,4] , traffic planning model [5] , cluster analysis method [6] , data-driven [2] and other methods to analyze the propagation of traffic waves and exploring the influencing factors of road traffic accidents. Jin Shuxin et al [3] proposed a method of dividing accidentaffected areas at three levels: point, line, and surface, and then formulate reasonable traffic accident induction strategies hierarchically to reduce the duration of regional road network accidents; Li Weijia et al [4] introduced the mixing rate of large vehicles into the traffic wave model, respectively selected the queue length and accident duration to quantitatively analyze the impact degree of accidents under interference and non-interference situations.…”