DETECTING ACCIDENTS IN MOTORSPORTS BY USING ANOMALY DETECTION

原文（中文）

A system for detecting accidents in motorsports is configured to obtain measurement data from measurement units incorporated in or attached to a plurality of vehicles. The measurement data comprises data points. Each of the data points comprises a value for each of multiple variables. The system is configured to perform an anomaly detection algorithm on these data points. The anomaly detection algorithm is an improvement of the extended isolation forest algorithm in which a remaining data point is assigned to a first or second subtree based on which side of a hyperplane it lies. Each coordinate value of an intercept point of the hyperplane is determined by selecting a variable corresponding to the coordinate, determining an interval where a distance between values of the variable of consecutive data points of the remaining data points is maximal, and selecting a value for the coordinate on the interval.