A comparative study of thyroid data classification based on GA, BPSO, and ACO metaheuristics approaches

Anxhela Gjecka; Majlinda Fetaji

doi:10.1117/12.3011406

19 December 2023 A comparative study of thyroid data classification based on GA, BPSO, and ACO metaheuristics approaches

Anxhela Gjecka, Majlinda Fetaji

Author Affiliations +

Proceedings Volume 12936, International Conference on Mathematical and Statistical Physics, Computational Science, Education and Communication (ICMSCE 2023); 129360Q (2023) https://doi.org/10.1117/12.3011406
Event: International Conference on Mathematical and Statistical Physics, Computational Science, Education and Communication (ICMSCE 2023), 2023, Istanbul, Turkey

Abstract

The accurate classification depends on identifying the important attributes and removing those with lower weights. The selection of attributes helps reduce noise and increases classification accuracy Using a dataset on thyroid disorders, this study compares and contrasts three alternative feature-selection techniques. The objective is to choose an ideal subset with pertinent properties that provide maximum accuracy. To select the features, a genetic algorithm, practical swarm optimization, and ant colony optimization were considered. Simultaneously, the performance of each algorithm is evaluated. The ranking is based on the accuracy provided by each algorithm. The findings indicate that ACO gives a significantly high accuracy which captures the value of 99.5% followed by PSO with 93% accuracy, while the genetic algorithm came out lower for binary data after capturing the result with 92% accuracy for future selection.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Anxhela Gjecka and Majlinda Fetaji "A comparative study of thyroid data classification based on GA, BPSO, and ACO metaheuristics approaches", Proc. SPIE 12936, International Conference on Mathematical and Statistical Physics, Computational Science, Education and Communication (ICMSCE 2023), 129360Q (19 December 2023); https://doi.org/10.1117/12.3011406

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available