Open AccessDriving collision detection method based on VMD-KICA
Author(s) -
Xu Han,
Jianbing Li,
Dong Xueyu,
Xutao,
Sun Jianbang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1971/1/012008
Subject(s) - computer science , signal (programming language) , time domain , collision , support vector machine , feature (linguistics) , noise (video) , correlation coefficient , pattern recognition (psychology) , domain (mathematical analysis) , matrix (chemical analysis) , component (thermodynamics) , artificial intelligence , machine learning , mathematics , computer vision , mathematical analysis , linguistics , philosophy , materials science , physics , computer security , composite material , image (mathematics) , thermodynamics , programming language
With the rapid development of China’s transportation, higher requirements are put forward for the handling capacity of traffic accidents. Therefore, it is of great practical significance to study the effective monitoring methods of high-speed traffic accidents for timely guiding the traffic and saving the lives of the injured. The VMD is used to decompose the vehicle vibration signal, and the cross-correlation coefficient is used as the index to screen the components, and the KICA algorithm is used to extract the components of the screened component matrix, so as to further eliminate the environmental noise. The signal is recombined by the denoised components to highlight the time-domain statistical characteristics of the signal. The feature vector based on time-domain statistical parameters is constructed, and the recognition model is built by using the support vector mechanism optimized by genetic algorithm. The experimental results show that the accuracy of the method for vehicle driving state can be 95.5%.