King's College London

Research portal

Instance-based classification with ant colony optimization

Research output: Contribution to journalArticlepeer-review

Standard

Instance-based classification with ant colony optimization. / Salama, Khalid M.; Abdelbar, Ashraf M.; Helal, Ayah; Freitas, Alex A.

In: Intelligent Data Analysis, Vol. 21, No. 4, 19.08.2017, p. 913-944.

Research output: Contribution to journalArticlepeer-review

Harvard

Salama, KM, Abdelbar, AM, Helal, A & Freitas, AA 2017, 'Instance-based classification with ant colony optimization', Intelligent Data Analysis, vol. 21, no. 4, pp. 913-944. https://doi.org/10.3233/IDA-160031

APA

Salama, K. M., Abdelbar, A. M., Helal, A., & Freitas, A. A. (2017). Instance-based classification with ant colony optimization. Intelligent Data Analysis, 21(4), 913-944. https://doi.org/10.3233/IDA-160031

Vancouver

Salama KM, Abdelbar AM, Helal A, Freitas AA. Instance-based classification with ant colony optimization. Intelligent Data Analysis. 2017 Aug 19;21(4):913-944. https://doi.org/10.3233/IDA-160031

Author

Salama, Khalid M. ; Abdelbar, Ashraf M. ; Helal, Ayah ; Freitas, Alex A. / Instance-based classification with ant colony optimization. In: Intelligent Data Analysis. 2017 ; Vol. 21, No. 4. pp. 913-944.

Bibtex Download

@article{59f4c3faa666498da179f1ec27dea94d,
title = "Instance-based classification with ant colony optimization",
abstract = "Instance-based learning (IBL) methods predict the class label of a new instance based directly on the distance between the new unlabeled instance and each labeled instance in the training set, without constructing a classification model in the training phase. In this paper, we introduce a novel class-based feature weighting technique, in the context of instance-based distance methods, using the Ant Colony Optimization meta-heuristic. We address three different approaches of instance-based classification: k-Nearest Neighbours, distance-based Nearest Neighbours, and Gaussian Kernel Estimator. We present a multi-archive adaptation of the ACO? algorithm and apply it to the optimization of the key parameter in each IBL algorithm and of the class-based feature weights. We also propose an ensemble of classifiers approach that makes use of the archived populations of the ACO? algorithm. We empirically evaluate the performance of our proposed algorithms on 36 benchmark datasets, and compare them with conventional instance-based classification algorithms, using various parameter settings, as well as with a state-of-the-art coevolutionary algorithm for instance selection and feature weighting for Nearest Neighbours classifiers.",
keywords = "data mining, machine learning, instance-based learning, swarm intelligence",
author = "Salama, {Khalid M.} and Abdelbar, {Ashraf M.} and Ayah Helal and Freitas, {Alex A.}",
year = "2017",
month = aug,
day = "19",
doi = "10.3233/IDA-160031",
language = "Undefined/Unknown",
volume = "21",
pages = "913--944",
journal = "Intelligent Data Analysis",
publisher = "IOS Press",
number = "4",

}

RIS (suitable for import to EndNote) Download

TY - JOUR

T1 - Instance-based classification with ant colony optimization

AU - Salama, Khalid M.

AU - Abdelbar, Ashraf M.

AU - Helal, Ayah

AU - Freitas, Alex A.

PY - 2017/8/19

Y1 - 2017/8/19

N2 - Instance-based learning (IBL) methods predict the class label of a new instance based directly on the distance between the new unlabeled instance and each labeled instance in the training set, without constructing a classification model in the training phase. In this paper, we introduce a novel class-based feature weighting technique, in the context of instance-based distance methods, using the Ant Colony Optimization meta-heuristic. We address three different approaches of instance-based classification: k-Nearest Neighbours, distance-based Nearest Neighbours, and Gaussian Kernel Estimator. We present a multi-archive adaptation of the ACO? algorithm and apply it to the optimization of the key parameter in each IBL algorithm and of the class-based feature weights. We also propose an ensemble of classifiers approach that makes use of the archived populations of the ACO? algorithm. We empirically evaluate the performance of our proposed algorithms on 36 benchmark datasets, and compare them with conventional instance-based classification algorithms, using various parameter settings, as well as with a state-of-the-art coevolutionary algorithm for instance selection and feature weighting for Nearest Neighbours classifiers.

AB - Instance-based learning (IBL) methods predict the class label of a new instance based directly on the distance between the new unlabeled instance and each labeled instance in the training set, without constructing a classification model in the training phase. In this paper, we introduce a novel class-based feature weighting technique, in the context of instance-based distance methods, using the Ant Colony Optimization meta-heuristic. We address three different approaches of instance-based classification: k-Nearest Neighbours, distance-based Nearest Neighbours, and Gaussian Kernel Estimator. We present a multi-archive adaptation of the ACO? algorithm and apply it to the optimization of the key parameter in each IBL algorithm and of the class-based feature weights. We also propose an ensemble of classifiers approach that makes use of the archived populations of the ACO? algorithm. We empirically evaluate the performance of our proposed algorithms on 36 benchmark datasets, and compare them with conventional instance-based classification algorithms, using various parameter settings, as well as with a state-of-the-art coevolutionary algorithm for instance selection and feature weighting for Nearest Neighbours classifiers.

KW - data mining

KW - machine learning

KW - instance-based learning

KW - swarm intelligence

U2 - 10.3233/IDA-160031

DO - 10.3233/IDA-160031

M3 - Article

VL - 21

SP - 913

EP - 944

JO - Intelligent Data Analysis

JF - Intelligent Data Analysis

IS - 4

ER -

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454