Combining one class fuzzy KNN’s

Risultato della ricerca: Conference contribution

8 Citazioni (Scopus)

Abstract

This paper introduces a parallel combination of N > 2 one class fuzzy KNN (FKNN) classifiers. The classifier combination consists of a new optimization procedure based on a genetic algorithm applied to FKNN’s, that differ in the kind of similarity used. We tested the integration techniques in the case of N = 5 similarities that have been recently introduced to face with categorical data sets. The assessment of the method has been carried out on two public data set, the Masquerading User Data (www.schonlau.net) and the badges database on the UCI Machine Learning Repository (http://www.ics.uci.edu/~mlearn/). Preliminary results show the better performance obtained by the fuzzy integration respect to the crisp one.
Lingua originaleEnglish
Titolo della pubblicazione ospiteApplications of Fuzzy Sets Theory
Pagine152-160
Numero di pagine9
Stato di pubblicazionePublished - 2007

Serie di pubblicazioni

NomeLECTURE NOTES IN ARTIFICIAL INTELLIGENCE

Fingerprint

Classifiers
Classifier Combination
Fuzzy Classifier
Nominal or categorical data
Repository
Learning systems
Machine Learning
Genetic algorithms
Genetic Algorithm
Optimization
Similarity
Class

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cita questo

Di Gesu', V., & Lo Bosco, G. (2007). Combining one class fuzzy KNN’s. In Applications of Fuzzy Sets Theory (pagg. 152-160). (LECTURE NOTES IN ARTIFICIAL INTELLIGENCE).

Combining one class fuzzy KNN’s. / Di Gesu', Vito; Lo Bosco, Giosue'.

Applications of Fuzzy Sets Theory. 2007. pag. 152-160 (LECTURE NOTES IN ARTIFICIAL INTELLIGENCE).

Risultato della ricerca: Conference contribution

Di Gesu', V & Lo Bosco, G 2007, Combining one class fuzzy KNN’s. in Applications of Fuzzy Sets Theory. LECTURE NOTES IN ARTIFICIAL INTELLIGENCE, pagg. 152-160.
Di Gesu' V, Lo Bosco G. Combining one class fuzzy KNN’s. In Applications of Fuzzy Sets Theory. 2007. pag. 152-160. (LECTURE NOTES IN ARTIFICIAL INTELLIGENCE).
Di Gesu', Vito ; Lo Bosco, Giosue'. / Combining one class fuzzy KNN’s. Applications of Fuzzy Sets Theory. 2007. pagg. 152-160 (LECTURE NOTES IN ARTIFICIAL INTELLIGENCE).
@inproceedings{4205a4b291c545498df4f32cdbea0bb6,
title = "Combining one class fuzzy KNN’s",
abstract = "This paper introduces a parallel combination of N > 2 one class fuzzy KNN (FKNN) classifiers. The classifier combination consists of a new optimization procedure based on a genetic algorithm applied to FKNN’s, that differ in the kind of similarity used. We tested the integration techniques in the case of N = 5 similarities that have been recently introduced to face with categorical data sets. The assessment of the method has been carried out on two public data set, the Masquerading User Data (www.schonlau.net) and the badges database on the UCI Machine Learning Repository (http://www.ics.uci.edu/~mlearn/). Preliminary results show the better performance obtained by the fuzzy integration respect to the crisp one.",
author = "{Di Gesu'}, Vito and {Lo Bosco}, Giosue'",
year = "2007",
language = "English",
isbn = "978-3-540-73399-7; 978-3-540-73400-0",
series = "LECTURE NOTES IN ARTIFICIAL INTELLIGENCE",
pages = "152--160",
booktitle = "Applications of Fuzzy Sets Theory",

}

TY - GEN

T1 - Combining one class fuzzy KNN’s

AU - Di Gesu', Vito

AU - Lo Bosco, Giosue'

PY - 2007

Y1 - 2007

N2 - This paper introduces a parallel combination of N > 2 one class fuzzy KNN (FKNN) classifiers. The classifier combination consists of a new optimization procedure based on a genetic algorithm applied to FKNN’s, that differ in the kind of similarity used. We tested the integration techniques in the case of N = 5 similarities that have been recently introduced to face with categorical data sets. The assessment of the method has been carried out on two public data set, the Masquerading User Data (www.schonlau.net) and the badges database on the UCI Machine Learning Repository (http://www.ics.uci.edu/~mlearn/). Preliminary results show the better performance obtained by the fuzzy integration respect to the crisp one.

AB - This paper introduces a parallel combination of N > 2 one class fuzzy KNN (FKNN) classifiers. The classifier combination consists of a new optimization procedure based on a genetic algorithm applied to FKNN’s, that differ in the kind of similarity used. We tested the integration techniques in the case of N = 5 similarities that have been recently introduced to face with categorical data sets. The assessment of the method has been carried out on two public data set, the Masquerading User Data (www.schonlau.net) and the badges database on the UCI Machine Learning Repository (http://www.ics.uci.edu/~mlearn/). Preliminary results show the better performance obtained by the fuzzy integration respect to the crisp one.

UR - http://hdl.handle.net/10447/16670

M3 - Conference contribution

SN - 978-3-540-73399-7; 978-3-540-73400-0

T3 - LECTURE NOTES IN ARTIFICIAL INTELLIGENCE

SP - 152

EP - 160

BT - Applications of Fuzzy Sets Theory

ER -