Classification and de-noising of communication signals using kernel principal component analysis (KPCA)

G. Koutsogiannis, J.J. Soraghan

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

This paper is concerned with the classification and de-noising problem for non-linear signals. It is known that using kernel functions, a non-linear signal can be transformed into a linear signal in a higher dimensional space. In that feature space, a linear algorithm can be applied to a non-linear problem. It is proposed that using the principal components extracted from the feature space, the signal can be classified correctly in its input space. Additionally, it is shown how this classification process' can be used to de-noise DQPSK communication signals

Conference

Conference2002 IEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleICASSP 2002
CountryUnited States
CityOrlando
Period13/05/0217/05/02

Fingerprint

Principal component analysis
Communication

Keywords

  • classification
  • de-noising
  • communication signals
  • kernel principal component analysis
  • kpca
  • artificial neural networks
  • transforms
  • support vector machines
  • principal component analysis
  • noise measurement
  • kernel
  • feature extraction

Cite this

Koutsogiannis, G., & Soraghan, J. J. (2002). Classification and de-noising of communication signals using kernel principal component analysis (KPCA). II-1677-II1680. Paper presented at 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, Orlando, United States. https://doi.org/10.1109/ICASSP.2002.5744942
Koutsogiannis, G. ; Soraghan, J.J. / Classification and de-noising of communication signals using kernel principal component analysis (KPCA). Paper presented at 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, Orlando, United States.4 p.
@conference{846bce1fbe22469b81e05c03cbbdd0c9,
title = "Classification and de-noising of communication signals using kernel principal component analysis (KPCA)",
abstract = "This paper is concerned with the classification and de-noising problem for non-linear signals. It is known that using kernel functions, a non-linear signal can be transformed into a linear signal in a higher dimensional space. In that feature space, a linear algorithm can be applied to a non-linear problem. It is proposed that using the principal components extracted from the feature space, the signal can be classified correctly in its input space. Additionally, it is shown how this classification process' can be used to de-noise DQPSK communication signals",
keywords = "classification, de-noising, communication signals, kernel principal component analysis , kpca, artificial neural networks , transforms , support vector machines, principal component analysis, noise measurement, kernel , feature extraction",
author = "G. Koutsogiannis and J.J. Soraghan",
year = "2002",
month = "5",
doi = "10.1109/ICASSP.2002.5744942",
language = "English",
pages = "II--1677--II1680",
note = "2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2002 ; Conference date: 13-05-2002 Through 17-05-2002",

}

Koutsogiannis, G & Soraghan, JJ 2002, 'Classification and de-noising of communication signals using kernel principal component analysis (KPCA)' Paper presented at 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, Orlando, United States, 13/05/02 - 17/05/02, pp. II-1677-II1680. https://doi.org/10.1109/ICASSP.2002.5744942

Classification and de-noising of communication signals using kernel principal component analysis (KPCA). / Koutsogiannis, G.; Soraghan, J.J.

2002. II-1677-II1680 Paper presented at 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, Orlando, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Classification and de-noising of communication signals using kernel principal component analysis (KPCA)

AU - Koutsogiannis, G.

AU - Soraghan, J.J.

PY - 2002/5

Y1 - 2002/5

N2 - This paper is concerned with the classification and de-noising problem for non-linear signals. It is known that using kernel functions, a non-linear signal can be transformed into a linear signal in a higher dimensional space. In that feature space, a linear algorithm can be applied to a non-linear problem. It is proposed that using the principal components extracted from the feature space, the signal can be classified correctly in its input space. Additionally, it is shown how this classification process' can be used to de-noise DQPSK communication signals

AB - This paper is concerned with the classification and de-noising problem for non-linear signals. It is known that using kernel functions, a non-linear signal can be transformed into a linear signal in a higher dimensional space. In that feature space, a linear algorithm can be applied to a non-linear problem. It is proposed that using the principal components extracted from the feature space, the signal can be classified correctly in its input space. Additionally, it is shown how this classification process' can be used to de-noise DQPSK communication signals

KW - classification

KW - de-noising

KW - communication signals

KW - kernel principal component analysis

KW - kpca

KW - artificial neural networks

KW - transforms

KW - support vector machines

KW - principal component analysis

KW - noise measurement

KW - kernel

KW - feature extraction

U2 - 10.1109/ICASSP.2002.5744942

DO - 10.1109/ICASSP.2002.5744942

M3 - Paper

SP - II-1677-II1680

ER -

Koutsogiannis G, Soraghan JJ. Classification and de-noising of communication signals using kernel principal component analysis (KPCA). 2002. Paper presented at 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, Orlando, United States. https://doi.org/10.1109/ICASSP.2002.5744942