Application of neural network analysis to automatic detection of road surface conditions utilizing tire noise from vehicles
Wuttiwat Kongrattanaprasert, Hideyuki Nomura, Tomoo Kamakura, Koji Ueda · 2009 ICCAS-SICE · 2009
This paper proposes a new method for automatically detecting the states of the road surface from tire noises of vehicles. The methods are based on a Fast Fourier Transform analysis, an artificial neural network, and the mathematical theory of evidence. The proposed classification is carried out in sets of multiple neural networks using the learning vector quantization networks. The outcomes of the networks are then integrated using the voting decision making scheme. It seems then feasible to detect passively and readily the states of the surface: i.e., as a rule of thumb, dry, wet, snowy and slushy state, automatically. The classification results in the validation set were greater than 80% in accuracy.