Academic Journals Database
Disseminating quality controlled scientific knowledge

Acoustic Signal Based Fault Detection in Motorcycles – A Comparative Study of Classifiers

Author(s): Basavaraj S. Anami | Veerappa B. Pagi

Journal: International Journal of Image, Graphics and Signal Processing
ISSN 2074-9074

Volume: 5;
Issue: 1;
Start page: 8;
Date: 2013;
Original page

Keywords: Acoustic fault detection | ANN classifier | Support vector machines | K-nearest neighbour classifier | DTW classifier

The sound patterns generated by the vehicles give a clue of the health conditions. The paper presents the fault detection of motorcycles based on the acoustic signals. Simple temporal and spectral features are used as input to four types of classifiers, namely, dynamic time warping (DTW), artificial neural network (ANN), k-nearest neighbor (k-NN) and support vector machine (SVM), for a suitability study in automatic fault detection. Amongst these classifiers the k-NN is found to be simple and suitable for this work. The overall classification accuracy exhibited by k-NN classifier is over 90%. The work finds applications in automatic surveillance, detection of non-compliance with traffic rules, identification of unlawful mixture of fuel, detection of over-aged vehicles on road, vehicle fault diagnosis and the like.
Save time & money - Smart Internet Solutions      Why do you need a reservation system?