Analysing the effects of combining fitness scaling and inversion in genetic algorithms

Séamus Hill; John Newell; Colm O'Riordan

Analysing the effects of combining fitness scaling and inversion in genetic algorithms

Séamus Hill, John Newell, Colm O'Riordan

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

3 Citations (Scopus)

Abstract

Genetic Algorithms in their original form as presented by Holland [10] included four operators selection, reproduction, mutation and inversion. Today most attention is given to selection, crossover and mutation, whereas inversion is rarely used. In this paper we compare the effectiveness of an inversion operator in a basic GA, and in a GA using fitness scaling. Results indicate that at higher levels of epistasis inversion is more useful in a basic GA than a GA with fitness scaling.

Original language	English (Ireland)
Title of host publication	16TH IEEE International Conference on Tools with Artificial Intelligence (ICTAI) 2004
Editors	T.M. Khoshgoftaar
Pages	380-387
Number of pages	8
Publication status	Published - 1 Jan 2004
Event	Proceedings - 16th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2004 - Boca Raton, FL, United States Duration: 15 Nov 2004 → 17 Nov 2004

Publication series

Name	1082-3409

Conference

Conference	Proceedings - 16th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2004
Country/Territory	United States
City	Boca Raton, FL
Period	15/11/04 → 17/11/04

Authors (Note for portal: view the doc link for the full list of authors)

Authors
Seamus Hill, John Newell and Colm O'Riordan.

Cite this

@inproceedings{b205b16af33e44d3b3a7555be8b9bc99,

title = "Analysing the effects of combining fitness scaling and inversion in genetic algorithms",

abstract = "Genetic Algorithms in their original form as presented by Holland [10] included four operators selection, reproduction, mutation and inversion. Today most attention is given to selection, crossover and mutation, whereas inversion is rarely used. In this paper we compare the effectiveness of an inversion operator in a basic GA, and in a GA using fitness scaling. Results indicate that at higher levels of epistasis inversion is more useful in a basic GA than a GA with fitness scaling.",

author = "S{\'e}amus Hill and John Newell and Colm O'Riordan",

year = "2004",

month = jan,

day = "1",

language = "English (Ireland)",

isbn = "076952236X",

series = "1082-3409",

pages = "380--387",

editor = "T.M. Khoshgoftaar",

booktitle = "16TH IEEE International Conference on Tools with Artificial Intelligence (ICTAI) 2004",

note = "Proceedings - 16th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2004 ; Conference date: 15-11-2004 Through 17-11-2004",

}

Hill, S, Newell, J & O'Riordan, C 2004, Analysing the effects of combining fitness scaling and inversion in genetic algorithms. in TM Khoshgoftaar (ed.), 16TH IEEE International Conference on Tools with Artificial Intelligence (ICTAI) 2004. 1082-3409, pp. 380-387, Proceedings - 16th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2004, Boca Raton, FL, United States, 15/11/04.

Analysing the effects of combining fitness scaling and inversion in genetic algorithms. / Hill, Séamus; Newell, John ; O'Riordan, Colm.
16TH IEEE International Conference on Tools with Artificial Intelligence (ICTAI) 2004. ed. / T.M. Khoshgoftaar. 2004. p. 380-387 (1082-3409).

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

TY - GEN

T1 - Analysing the effects of combining fitness scaling and inversion in genetic algorithms

AU - Hill, Séamus

AU - Newell, John

AU - O'Riordan, Colm

PY - 2004/1/1

Y1 - 2004/1/1

N2 - Genetic Algorithms in their original form as presented by Holland [10] included four operators selection, reproduction, mutation and inversion. Today most attention is given to selection, crossover and mutation, whereas inversion is rarely used. In this paper we compare the effectiveness of an inversion operator in a basic GA, and in a GA using fitness scaling. Results indicate that at higher levels of epistasis inversion is more useful in a basic GA than a GA with fitness scaling.

AB - Genetic Algorithms in their original form as presented by Holland [10] included four operators selection, reproduction, mutation and inversion. Today most attention is given to selection, crossover and mutation, whereas inversion is rarely used. In this paper we compare the effectiveness of an inversion operator in a basic GA, and in a GA using fitness scaling. Results indicate that at higher levels of epistasis inversion is more useful in a basic GA than a GA with fitness scaling.

UR - https://www.scopus.com/pages/publications/16244400785

M3 - Conference Publication

AN - SCOPUS:16244400785

SN - 076952236X

T3 - 1082-3409

SP - 380

EP - 387

BT - 16TH IEEE International Conference on Tools with Artificial Intelligence (ICTAI) 2004

A2 - Khoshgoftaar, T.M.

T2 - Proceedings - 16th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2004

Y2 - 15 November 2004 through 17 November 2004

ER -

Analysing the effects of combining fitness scaling and inversion in genetic algorithms

Abstract

Publication series

Conference

Authors (Note for portal: view the doc link for the full list of authors)

Other files and links

Fingerprint

Cite this