2018 · 15 citations · 26 references
ComputingAutomotive EngineeringComputer ScienceFeature EngineeringMachine LearningTransportationIntelligent Transportation SystemsPattern RecognitionRoad SafetySupport Vector MachinesTraffic EngineeringTraffic SafetyBehavioral TypesDriving PatternsRoad Safety EngineeringSensor Orientation EstimationSupport Vector ClassificationSupport Vector Machine ClassificationSuspicious Behavior DetectionTimestamp Analysis
As the primary transportation in the urban traffic, bus plays a significant role in road safety. It would cause severe casualties if an accident occurred. To improve the safety of bus driving, we classify the specific types of latent abnormal driving behavior, which include sudden braking, lane changing casually, quick turn, fast U-turn and long time parking, and propose a method to identify the abnormal driving behavior of the bus. Firstly, we collect the acceleration, orientation and timestamp bus driving data through smartphone's accelerometer and orientation sensor. After de-nosing the collected data, we extract features in thirteen dimensions and train the naive Bayesian classifier, which is employed to detect and identify abnormal driving behaviors. The experimental results have been compared with support vector machine, and shows that the naive Bayesian classifier has an better performance than support vector machine on detecting and identifying various types of the abnormal bus driving behavior with the accuracy at 98.40%.
26
Corinna Cortes, Vladimir Vapnik · Machine Learning · 1995 · 40.5K citations · Full text
DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
Chenyi Chen, Ari Seff, Alain L. Kornhauser et al. · 2015 · 1.8K citations
Estimating driving behavior by a smartphone
Haluk Eren, Semiha Makinist · 2012 · 293 citations
Engineering, Automotive Engineering, Mechatronics Engineering +16