On the application of bio-inspired optimization algorithms to fuzzy C-Means clustering of time series

Muhammad Marwan Muhammad Fuad

On the application of bio-inspired optimization algorithms to fuzzy C-Means clustering of time series

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Abstract

Fuzzy c-means clustering (FCM) is a clustering method which is based on the partial membership concept. As with the other clustering methods, FCM applies a distance to cluster the data. While the Euclidean distance is widely-used to perform the clustering task, other distances have been suggested in the literature. In this paper we study the use of a weighted combination of metrics in FCM clustering of time series where the weights in the combination are the outcome of an optimization process using differential evolution, genetic algorithms, and particle swarm optimization as optimizers. We show how the overfitting phenomenon interferes in the optimization process that the optimal results obtained during the training stage degrade during the testing stage as a result of overfitting.

Original language	English
Title of host publication	ICPRAM 2015 - Proceedings of the International Conference on Pattern Recognition Applications and Methods, Volume 1, Lisbon, Portugal, 10-12 January, 2015
Editors	Maria De Marsico, Mario Figueiredo, Ana Fred
Publisher	SciTePress
Pages	348-353
Number of pages	6
Volume	1
ISBN (Electronic)	9789897580765
Publication status	Published - 2015
Externally published	Yes
Event	4th International Conference on Pattern Recognition Applications and Methods - Lisbon, Portugal Duration: 10 Jan 2015 → 12 Jan 2015 Conference number: 4th

Publication series

Name	ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings
Volume	1

Conference

Conference	4th International Conference on Pattern Recognition Applications and Methods
Abbreviated title	ICPRAM 2015
Country/Territory	Portugal
City	Lisbon
Period	10/01/15 → 12/01/15

Keywords

Data mining
Differential evolution
Distance metrics
Fuzzy C-Means clustering
Genetic algorithms
Overfitting
Particle swarm optimization
Time series

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Cite this

Fuad, M. M. M. (2015). On the application of bio-inspired optimization algorithms to fuzzy C-Means clustering of time series. In M. De Marsico, M. Figueiredo, & A. Fred (Eds.), ICPRAM 2015 - Proceedings of the International Conference on Pattern Recognition Applications and Methods, Volume 1, Lisbon, Portugal, 10-12 January, 2015 (Vol. 1, pp. 348-353). (ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings; Vol. 1). SciTePress.

On the application of bio-inspired optimization algorithms to fuzzy C-Means clustering of time series. / Fuad, Muhammad Marwan Muhammad.

ICPRAM 2015 - Proceedings of the International Conference on Pattern Recognition Applications and Methods, Volume 1, Lisbon, Portugal, 10-12 January, 2015. ed. / Maria De Marsico; Mario Figueiredo; Ana Fred. Vol. 1 SciTePress, 2015. p. 348-353 (ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Fuad, MMM 2015, On the application of bio-inspired optimization algorithms to fuzzy C-Means clustering of time series. in M De Marsico, M Figueiredo & A Fred (eds), ICPRAM 2015 - Proceedings of the International Conference on Pattern Recognition Applications and Methods, Volume 1, Lisbon, Portugal, 10-12 January, 2015. vol. 1, ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings, vol. 1, SciTePress, pp. 348-353, 4th International Conference on Pattern Recognition Applications and Methods, Lisbon, Portugal, 10/01/15.

Fuad MMM. On the application of bio-inspired optimization algorithms to fuzzy C-Means clustering of time series. In De Marsico M, Figueiredo M, Fred A, editors, ICPRAM 2015 - Proceedings of the International Conference on Pattern Recognition Applications and Methods, Volume 1, Lisbon, Portugal, 10-12 January, 2015. Vol. 1. SciTePress. 2015. p. 348-353. (ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings).

Fuad, Muhammad Marwan Muhammad. / On the application of bio-inspired optimization algorithms to fuzzy C-Means clustering of time series. ICPRAM 2015 - Proceedings of the International Conference on Pattern Recognition Applications and Methods, Volume 1, Lisbon, Portugal, 10-12 January, 2015. editor / Maria De Marsico ; Mario Figueiredo ; Ana Fred. Vol. 1 SciTePress, 2015. pp. 348-353 (ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings).

@inproceedings{25ba79bae2304afe94fa890531d24c62,

title = "On the application of bio-inspired optimization algorithms to fuzzy C-Means clustering of time series",

abstract = "Fuzzy c-means clustering (FCM) is a clustering method which is based on the partial membership concept. As with the other clustering methods, FCM applies a distance to cluster the data. While the Euclidean distance is widely-used to perform the clustering task, other distances have been suggested in the literature. In this paper we study the use of a weighted combination of metrics in FCM clustering of time series where the weights in the combination are the outcome of an optimization process using differential evolution, genetic algorithms, and particle swarm optimization as optimizers. We show how the overfitting phenomenon interferes in the optimization process that the optimal results obtained during the training stage degrade during the testing stage as a result of overfitting.",

keywords = "Data mining, Differential evolution, Distance metrics, Fuzzy C-Means clustering, Genetic algorithms, Overfitting, Particle swarm optimization, Time series",

author = "Fuad, {Muhammad Marwan Muhammad}",

year = "2015",

language = "English",

volume = "1",

series = "ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings",

publisher = "SciTePress",

pages = "348--353",

editor = "{De Marsico}, Maria and Mario Figueiredo and Ana Fred",

booktitle = "ICPRAM 2015 - Proceedings of the International Conference on Pattern Recognition Applications and Methods, Volume 1, Lisbon, Portugal, 10-12 January, 2015",

address = "Portugal",

note = "4th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2015 ; Conference date: 10-01-2015 Through 12-01-2015",

}

TY - GEN

T1 - On the application of bio-inspired optimization algorithms to fuzzy C-Means clustering of time series

AU - Fuad, Muhammad Marwan Muhammad

N1 - Conference code: 4th

PY - 2015

Y1 - 2015

N2 - Fuzzy c-means clustering (FCM) is a clustering method which is based on the partial membership concept. As with the other clustering methods, FCM applies a distance to cluster the data. While the Euclidean distance is widely-used to perform the clustering task, other distances have been suggested in the literature. In this paper we study the use of a weighted combination of metrics in FCM clustering of time series where the weights in the combination are the outcome of an optimization process using differential evolution, genetic algorithms, and particle swarm optimization as optimizers. We show how the overfitting phenomenon interferes in the optimization process that the optimal results obtained during the training stage degrade during the testing stage as a result of overfitting.

AB - Fuzzy c-means clustering (FCM) is a clustering method which is based on the partial membership concept. As with the other clustering methods, FCM applies a distance to cluster the data. While the Euclidean distance is widely-used to perform the clustering task, other distances have been suggested in the literature. In this paper we study the use of a weighted combination of metrics in FCM clustering of time series where the weights in the combination are the outcome of an optimization process using differential evolution, genetic algorithms, and particle swarm optimization as optimizers. We show how the overfitting phenomenon interferes in the optimization process that the optimal results obtained during the training stage degrade during the testing stage as a result of overfitting.

KW - Data mining

KW - Differential evolution

KW - Distance metrics

KW - Fuzzy C-Means clustering

KW - Genetic algorithms

KW - Overfitting

KW - Particle swarm optimization

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=84938865386&partnerID=8YFLogxK

M3 - Conference proceeding

AN - SCOPUS:84938865386

VL - 1

T3 - ICPRAM 2015 - 4th International Conference on Pattern Recognition Applications and Methods, Proceedings

SP - 348

EP - 353

BT - ICPRAM 2015 - Proceedings of the International Conference on Pattern Recognition Applications and Methods, Volume 1, Lisbon, Portugal, 10-12 January, 2015

A2 - De Marsico, Maria

A2 - Figueiredo, Mario

A2 - Fred, Ana

PB - SciTePress

T2 - 4th International Conference on Pattern Recognition Applications and Methods

Y2 - 10 January 2015 through 12 January 2015

ER -

On the application of bio-inspired optimization algorithms to fuzzy C-Means clustering of time series

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this