Training a Φ-machine classifier using feature scaling-space

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Efficient classification of signal patterns plays a vital role in data mining and other computational intelligence applications. This paper presents a reciprocal-sigmoid model for pattern classification. The proposed classifier can be considered as a «-machine since it preserves the theoretical advantage of linear machines where the weight parameters can be estimated in a single step. To handle possible over-fitting when using high order models, the classifier is trained using multiple samples of uniformly scaled pattern features. The classifier is empirically evaluated using benchmark data sets for statistical evidence.

Original languageEnglish
Title of host publication2006 IEEE International Conference on Industrial Informatics, INDIN'06
Pages1334-1339
Number of pages6
DOIs
Publication statusPublished - 2007 Dec 1
Event2006 IEEE International Conference on Industrial Informatics, INDIN'06 - Singapore, Singapore
Duration: 2006 Aug 162006 Aug 18

Other

Other2006 IEEE International Conference on Industrial Informatics, INDIN'06
CountrySingapore
CitySingapore
Period06/8/1606/8/18

Fingerprint

Classifiers
Pattern recognition
Artificial intelligence
Data mining

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Cite this

Toh, K. A. (2007). Training a Φ-machine classifier using feature scaling-space. In 2006 IEEE International Conference on Industrial Informatics, INDIN'06 (pp. 1334-1339). [4053588] https://doi.org/10.1109/INDIN.2006.275853
Toh, Kar A. / Training a Φ-machine classifier using feature scaling-space. 2006 IEEE International Conference on Industrial Informatics, INDIN'06. 2007. pp. 1334-1339
@inproceedings{524940b3feb04a11833520b00550af30,
title = "Training a Φ-machine classifier using feature scaling-space",
abstract = "Efficient classification of signal patterns plays a vital role in data mining and other computational intelligence applications. This paper presents a reciprocal-sigmoid model for pattern classification. The proposed classifier can be considered as a «-machine since it preserves the theoretical advantage of linear machines where the weight parameters can be estimated in a single step. To handle possible over-fitting when using high order models, the classifier is trained using multiple samples of uniformly scaled pattern features. The classifier is empirically evaluated using benchmark data sets for statistical evidence.",
author = "Toh, {Kar A.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/INDIN.2006.275853",
language = "English",
isbn = "0780397010",
pages = "1334--1339",
booktitle = "2006 IEEE International Conference on Industrial Informatics, INDIN'06",

}

Toh, KA 2007, Training a Φ-machine classifier using feature scaling-space. in 2006 IEEE International Conference on Industrial Informatics, INDIN'06., 4053588, pp. 1334-1339, 2006 IEEE International Conference on Industrial Informatics, INDIN'06, Singapore, Singapore, 06/8/16. https://doi.org/10.1109/INDIN.2006.275853

Training a Φ-machine classifier using feature scaling-space. / Toh, Kar A.

2006 IEEE International Conference on Industrial Informatics, INDIN'06. 2007. p. 1334-1339 4053588.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Training a Φ-machine classifier using feature scaling-space

AU - Toh, Kar A.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Efficient classification of signal patterns plays a vital role in data mining and other computational intelligence applications. This paper presents a reciprocal-sigmoid model for pattern classification. The proposed classifier can be considered as a «-machine since it preserves the theoretical advantage of linear machines where the weight parameters can be estimated in a single step. To handle possible over-fitting when using high order models, the classifier is trained using multiple samples of uniformly scaled pattern features. The classifier is empirically evaluated using benchmark data sets for statistical evidence.

AB - Efficient classification of signal patterns plays a vital role in data mining and other computational intelligence applications. This paper presents a reciprocal-sigmoid model for pattern classification. The proposed classifier can be considered as a «-machine since it preserves the theoretical advantage of linear machines where the weight parameters can be estimated in a single step. To handle possible over-fitting when using high order models, the classifier is trained using multiple samples of uniformly scaled pattern features. The classifier is empirically evaluated using benchmark data sets for statistical evidence.

UR - http://www.scopus.com/inward/record.url?scp=38949213324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38949213324&partnerID=8YFLogxK

U2 - 10.1109/INDIN.2006.275853

DO - 10.1109/INDIN.2006.275853

M3 - Conference contribution

SN - 0780397010

SN - 9780780397019

SP - 1334

EP - 1339

BT - 2006 IEEE International Conference on Industrial Informatics, INDIN'06

ER -

Toh KA. Training a Φ-machine classifier using feature scaling-space. In 2006 IEEE International Conference on Industrial Informatics, INDIN'06. 2007. p. 1334-1339. 4053588 https://doi.org/10.1109/INDIN.2006.275853