Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/20250
Title: Automatic taxonomic classification of fish based on their acoustic signals
Authors: Noda, Juan J.
Travieso-González, Carlos M. 
Sánchez-Rodríguez, David 
UNESCO Clasification: 2401 Biología animal (zoología)
Keywords: Biological acoustic analysis
Bioacoustic taxonomy identification
Fish acoustic signal
Hydroacoustic sensors
Species mapping
Issue Date: 2016
Journal: Applied Sciences (Basel) 
Abstract: Fish as well as birds, mammals, insects and other animals are capable of emitting sounds for diverse purposes, which can be recorded through microphone sensors. Although fish vocalizations have been known for a long time, they have been poorly studied and applied in their taxonomic classification. This work presents a novel approach for automatic remote acoustic identification of fish through their acoustic signals by applying pattern recognition techniques. The sound signals are preprocessed and automatically segmented to extract each call from the background noise. Then, the calls are parameterized using Linear and Mel Frequency Cepstral Coefficients (LFCC and MFCC), Shannon Entropy (SE) and Syllable Length (SL), yielding useful information for the classification phase. In our experiments, 102 different fish species have been successfully identified with three widely used machine learning algorithms: K-Nearest Neighbors (KNN), Random Forest (RF) and Support Vector Machine (SVM). Experimental results show an average classification accuracy of 95.24%, 93.56% and 95.58%, respectively.
URI: http://hdl.handle.net/10553/20250
ISSN: 2076-3417
DOI: 10.3390/app6120443
Source: Applied Sciences Basel [ISSN 2076-3417], v. 6 (12), p. 443
Rights: by
Appears in Collections:Artículos
XML (29,18 kB)
Text (2,11 kB)
Thumbnail
Adobe PDF (6,25 MB)
Thumbnail
Adobe PDF (6,25 MB)
Show full item record

SCOPUSTM   
Citations

32
checked on Oct 6, 2024

WEB OF SCIENCETM
Citations

25
checked on Oct 6, 2024

Page view(s)

68
checked on Apr 13, 2024

Download(s)

183
checked on Apr 13, 2024

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.