Classification and feature selection for microarray cancer dataset using an improved African vulture optimisation algorithm Online publication date: Mon, 02-Oct-2023
by K. Balakrishnan; R. Dhanalakshmi
International Journal of Mathematics in Operational Research (IJMOR), Vol. 26, No. 1, 2023
Abstract: The African vulture optimisation algorithm (AVOA) is a recently developed metaheuristic algorithm that imitates the eating and movement patterns of authentic African vultures. AVOA's convergence accuracy and stability, like that of various state-of-the-art metaheuristics, will degrade as optimisation problems get more complicated and variable. Furthermore, the traditional AVOA only searches in one direction, limiting its convergence capacity and causing stagnation at local minima. To address these shortcomings, this work offers LOBL-AVOA, a better version of AVOA hybridised with the lens opposition-based learning (LOBL) technique for classification. The LOBL enhances global exploratory capacity while preventing premature convergence. The suggested LOBL-AVOA findings are compared to traditional AVOA results. The efficacy of LOBL-AVOA is assessed employing six high-dimensional microarray datasets and three distinct classifiers such as support vector machine (SVM), K-nearest-neighbour (KNN) and random forest (RF). As an outcome, the proposed method surpasses traditional AVOA in terms of convergence capability, statistical analysis and classification accuracy.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Mathematics in Operational Research (IJMOR):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com