Glowworm swarm optimisation for training multi-layer perceptrons

Dabiah Ahmed Alboaneen; Huaglory Tianfield; Yan Zhang

doi:10.1145/3148055.3148075

Glowworm swarm optimisation for training multi-layer perceptrons

Dabiah Ahmed Alboaneen, Huaglory Tianfield, Yan Zhang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Citations (Scopus)

428 Downloads (Pure)

Abstract

Training multi-layer perceptron (MLP) is non-trivial due to its non-linear nature and the presence of large number of local optima. Meta-heuristic algorithms may solve this problem efficiently. In this paper, we investigate the use of glowworm swarm optimisation (GSO) algorithm in training the MLP neural network. The GSO based trainer is evaluated on five classification datasets, namely Wisconsin breast cancer, BUPA liver disorders, vertebral column, exclusive OR (XOR) and balloons. The evaluations are conducted by comparing the proposed trainer with four other meta-heuristics, namely biogeography-based optimisation (BBO), genetic algorithm (GA), bat (BAT) and multi-verse optimiser (MVO) algorithms. The results show that our proposed trainer achieves better classification accuracy rate in most datasets compared to the other algorithms.

Original language	English
Title of host publication	Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT '17)
Publisher	IEEE
Pages	131-138
Number of pages	8
ISBN (Print)	9781450355490
DOIs	https://doi.org/10.1145/3148055.3148075
Publication status	Published - 5 Dec 2017

Publication series

Name	BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies

Keywords

glowworm swarm optimisation (GSO)
multi-layer perceptrons
neural network

ASJC Scopus subject areas

Information Systems
Computer Networks and Communications
Computer Science Applications

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Documents and Links

10.1145/3148055.3148075

Alboaneen, D.A. et al (2017) Glowworm swarm optimisation for training multi-layer perceptrons
© ACM, 2017. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in BDCAT '17 Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies Pages 131-138 http://doi.acm.org/10.1145/3148055.3148075
Author accepted manuscript, 1.34 MB

Cite this

Alboaneen, D. A., Tianfield, H., & Zhang, Y. (2017). Glowworm swarm optimisation for training multi-layer perceptrons. In Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT '17) (pp. 131-138 ). (BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies). IEEE. https://doi.org/10.1145/3148055.3148075

Alboaneen, Dabiah Ahmed ; Tianfield, Huaglory ; Zhang, Yan. / Glowworm swarm optimisation for training multi-layer perceptrons. Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT '17). IEEE, 2017. pp. 131-138 (BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies).

@inproceedings{6d1c2246e40e4761a277446ca02b9067,

title = "Glowworm swarm optimisation for training multi-layer perceptrons",

abstract = "Training multi-layer perceptron (MLP) is non-trivial due to its non-linear nature and the presence of large number of local optima. Meta-heuristic algorithms may solve this problem efficiently. In this paper, we investigate the use of glowworm swarm optimisation (GSO) algorithm in training the MLP neural network. The GSO based trainer is evaluated on five classification datasets, namely Wisconsin breast cancer, BUPA liver disorders, vertebral column, exclusive OR (XOR) and balloons. The evaluations are conducted by comparing the proposed trainer with four other meta-heuristics, namely biogeography-based optimisation (BBO), genetic algorithm (GA), bat (BAT) and multi-verse optimiser (MVO) algorithms. The results show that our proposed trainer achieves better classification accuracy rate in most datasets compared to the other algorithms.",

keywords = "glowworm swarm optimisation (GSO), multi-layer perceptrons, neural network",

author = "Alboaneen, {Dabiah Ahmed} and Huaglory Tianfield and Yan Zhang",

note = "Acceptance in SAN AAM: no embargo",

year = "2017",

month = dec,

day = "5",

doi = "10.1145/3148055.3148075",

language = "English",

isbn = "9781450355490",

series = "BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies",

publisher = "IEEE",

pages = "131--138 ",

booktitle = "Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT '17)",

}

Alboaneen, DA, Tianfield, H & Zhang, Y 2017, Glowworm swarm optimisation for training multi-layer perceptrons. in Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT '17). BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, IEEE, pp. 131-138 . https://doi.org/10.1145/3148055.3148075

Glowworm swarm optimisation for training multi-layer perceptrons. / Alboaneen, Dabiah Ahmed; Tianfield, Huaglory ; Zhang, Yan.

Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT '17). IEEE, 2017. p. 131-138 (BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Glowworm swarm optimisation for training multi-layer perceptrons

AU - Alboaneen, Dabiah Ahmed

AU - Tianfield, Huaglory

AU - Zhang, Yan

N1 - Acceptance in SAN AAM: no embargo

PY - 2017/12/5

Y1 - 2017/12/5

N2 - Training multi-layer perceptron (MLP) is non-trivial due to its non-linear nature and the presence of large number of local optima. Meta-heuristic algorithms may solve this problem efficiently. In this paper, we investigate the use of glowworm swarm optimisation (GSO) algorithm in training the MLP neural network. The GSO based trainer is evaluated on five classification datasets, namely Wisconsin breast cancer, BUPA liver disorders, vertebral column, exclusive OR (XOR) and balloons. The evaluations are conducted by comparing the proposed trainer with four other meta-heuristics, namely biogeography-based optimisation (BBO), genetic algorithm (GA), bat (BAT) and multi-verse optimiser (MVO) algorithms. The results show that our proposed trainer achieves better classification accuracy rate in most datasets compared to the other algorithms.

AB - Training multi-layer perceptron (MLP) is non-trivial due to its non-linear nature and the presence of large number of local optima. Meta-heuristic algorithms may solve this problem efficiently. In this paper, we investigate the use of glowworm swarm optimisation (GSO) algorithm in training the MLP neural network. The GSO based trainer is evaluated on five classification datasets, namely Wisconsin breast cancer, BUPA liver disorders, vertebral column, exclusive OR (XOR) and balloons. The evaluations are conducted by comparing the proposed trainer with four other meta-heuristics, namely biogeography-based optimisation (BBO), genetic algorithm (GA), bat (BAT) and multi-verse optimiser (MVO) algorithms. The results show that our proposed trainer achieves better classification accuracy rate in most datasets compared to the other algorithms.

KW - glowworm swarm optimisation (GSO)

KW - multi-layer perceptrons

KW - neural network

U2 - 10.1145/3148055.3148075

DO - 10.1145/3148055.3148075

M3 - Conference contribution

SN - 9781450355490

T3 - BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies

SP - 131

EP - 138

BT - Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT '17)

PB - IEEE

ER -

Alboaneen DA, Tianfield H , Zhang Y. Glowworm swarm optimisation for training multi-layer perceptrons. In Proceedings of the Fourth IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT '17). IEEE. 2017. p. 131-138 . (BDCAT 2017 - Proceedings of the 4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies). https://doi.org/10.1145/3148055.3148075

Glowworm swarm optimisation for training multi-layer perceptrons

Abstract

Publication series

Keywords

ASJC Scopus subject areas

UN SDGs

Documents and Links

Fingerprint

Cite this