Each year, 1.35 million people die and over 50 million are injured in traffic accidents. Over half of fatal accidents are due to aggressive driving behaviors. Machine learning analytic strategies hold promise in helping to identify aggressive driving behaviors within real world driving (RWD) datasets, but innovative strategies are required in order to achieve this promise. Herein, we introduce and define Iterative DBSCAN (I-DBSCAN), an extension of the Density Based Spatial Clustering of Applications with Noise algorithm, as one tool that can be utilized as part of a machine learning analytic strategy for identifying aggressive driving behaviors within large, unlabeled RWD datasets. Further, we provide a case example of I-DBSCAN’s application and discuss how its application can enhance efforts to identify aggressive driving and improve overall traffic safety.
Iterative DBSCAN (I-DBSCAN) to Identify Aggressive Driving Behaviors within Unlabeled Real-World Driving Data
01.10.2019
314888 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Grid-Based DBSCAN for Clustering Extended Objects in Radar Data
British Library Conference Proceedings | 2012
|DBSCAN Based Parameter Optimization of KPCA for Fault Diagnosis
Springer Verlag | 2021
|