Underwater Transient Signal Classification Using Binary Pattern Image of MFCC and Neural Network
Summary :
This paper presents a new method for classification of underwater transient signals, which employs a binary image pattern of the mel-frequency cepstral coefficients as a feature vector and a feed-forward neural network as a classifier. The feature vector is obtained by taking DCT and 1-bit quantization for the square matrix of the mel-frequency cepstral coefficients that is derived from the frame based cepstral analysis. The classifier is a feed-forward neural network having one hidden layer and one output layer, and a back propagation algorithm is used to update the weighting vector of each layer. Experimental results with underwater transient signals demonstrate that the proposed method is very promising for classification of underwater transient signals.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E91-A No.3 pp.772-774
- Publication Date
- 2008/03/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1093/ietfec/e91-a.3.772
- Type of Manuscript
- Special Section LETTER (Special Section on Signal Processing for Audio and Visual Systems and Its Implementations)
- Category
- Engineering Acoustics
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Taegyun LIM, Keunsung BAE, Chansik HWANG, Hyeonguk LEE, "Underwater Transient Signal Classification Using Binary Pattern Image of MFCC and Neural Network" in IEICE TRANSACTIONS on Fundamentals,
vol. E91-A, no. 3, pp. 772-774, March 2008, doi: 10.1093/ietfec/e91-a.3.772.
Abstract: This paper presents a new method for classification of underwater transient signals, which employs a binary image pattern of the mel-frequency cepstral coefficients as a feature vector and a feed-forward neural network as a classifier. The feature vector is obtained by taking DCT and 1-bit quantization for the square matrix of the mel-frequency cepstral coefficients that is derived from the frame based cepstral analysis. The classifier is a feed-forward neural network having one hidden layer and one output layer, and a back propagation algorithm is used to update the weighting vector of each layer. Experimental results with underwater transient signals demonstrate that the proposed method is very promising for classification of underwater transient signals.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e91-a.3.772/_p
Copy
@ARTICLE{e91-a_3_772,
author={Taegyun LIM, Keunsung BAE, Chansik HWANG, Hyeonguk LEE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Underwater Transient Signal Classification Using Binary Pattern Image of MFCC and Neural Network},
year={2008},
volume={E91-A},
number={3},
pages={772-774},
abstract={This paper presents a new method for classification of underwater transient signals, which employs a binary image pattern of the mel-frequency cepstral coefficients as a feature vector and a feed-forward neural network as a classifier. The feature vector is obtained by taking DCT and 1-bit quantization for the square matrix of the mel-frequency cepstral coefficients that is derived from the frame based cepstral analysis. The classifier is a feed-forward neural network having one hidden layer and one output layer, and a back propagation algorithm is used to update the weighting vector of each layer. Experimental results with underwater transient signals demonstrate that the proposed method is very promising for classification of underwater transient signals.},
keywords={},
doi={10.1093/ietfec/e91-a.3.772},
ISSN={1745-1337},
month={March},}
Copy
TY - JOUR
TI - Underwater Transient Signal Classification Using Binary Pattern Image of MFCC and Neural Network
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 772
EP - 774
AU - Taegyun LIM
AU - Keunsung BAE
AU - Chansik HWANG
AU - Hyeonguk LEE
PY - 2008
DO - 10.1093/ietfec/e91-a.3.772
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E91-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2008
AB - This paper presents a new method for classification of underwater transient signals, which employs a binary image pattern of the mel-frequency cepstral coefficients as a feature vector and a feed-forward neural network as a classifier. The feature vector is obtained by taking DCT and 1-bit quantization for the square matrix of the mel-frequency cepstral coefficients that is derived from the frame based cepstral analysis. The classifier is a feed-forward neural network having one hidden layer and one output layer, and a back propagation algorithm is used to update the weighting vector of each layer. Experimental results with underwater transient signals demonstrate that the proposed method is very promising for classification of underwater transient signals.
ER -
English
