Serial combination of multiple classifiers for automatic blue whale calls recognition

Authors:
Mohammed Bahoura;Yvan Simard
Affiliations:
Department of Engineering, Université du Québec í Rimouski, 300, allée des Ursulines, Rimouski, Qc, Canada G5L 3A1;Marine Sciences Institute, Université du Québec í Rimouski, 310, allée des Ursulines, Rimouski, Qc, Canada G5L 3A1 and Maurice Lamontagne Institute, Fisheries and Oceans Canada ...
Venue:
Expert Systems with Applications: An International Journal
Year:
2012

Citing 7
Cited 0

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Combination of multiple classifiers for the customer's purchase behavior prediction

Decision Support Systems - Special issue: Agents and e-commerce business models
Chirplet Transform Applied to Simulated and Real Blue Whale (Balaenoptera musculus) Calls

ICISP '08 Proceedings of the 3rd international conference on Image and Signal Processing
Financial distress prediction based on serial combination of multiple classifiers

Expert Systems with Applications: An International Journal
Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classes

Computers in Biology and Medicine
Blue whale calls classification using short-time Fourier and wavelet packet transforms and artificial neural network

Digital Signal Processing
An effective combination based on class-wise expertise of diverse classifiers for predictive toxicology data mining

ADMA'06 Proceedings of the Second international conference on Advanced Data Mining and Applications

Quantified Score

Hi-index	12.05

Visualization

Abstract

In this paper, we propose a serial combination architecture of classifiers for automatic blue whale calls recognition. Based on class's best selection operator, the proposed system uses a best classifier for D call class followed by another one that efficiently discriminate the A and B calls. The first classifier uses the short-time Fourier transform to characterize the patterns, while the second uses the chirplet transform. Both classifiers are based on multi-layer perceptron neural network. The classification performance (95.55%) of the proposed system outperforms all tested single classifiers. The other advantages of the system are no requirement for adjusting a series of parameters and simple feature extraction.