Open Access

ARTICLE

An Improved Animated Oat Optimization Algorithm with Particle Swarm Optimization for Dry Eye Disease Classification

Essam H. Houssein^1,*, Eman Saber¹, Nagwan Abdel Samee²

1 Faculty of Computers and Information, Minia University, Minia, 61519, Egypt
2 Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, 11671, Saudi Arabia

* Corresponding Author: Essam H. Houssein. Email:

(This article belongs to the Special Issue: Advanced Computational Intelligence Techniques, Uncertain Knowledge Processing and Multi-Attribute Group Decision-Making Methods Applied in Modeling of Medical Diagnosis and Prognosis)

Computer Modeling in Engineering & Sciences 2025, 144(2), 2445-2480. https://doi.org/10.32604/cmes.2025.069184

Received 17 June 2025; Accepted 13 August 2025; Issue published 31 August 2025

Abstract

The diagnosis of Dry Eye Disease (DED), however, usually depends on clinical information and complex, high-dimensional datasets. To improve the performance of classification models, this paper proposes a Computer Aided Design (CAD) system that presents a new method for DED classification called (IAOO-PSO), which is a powerful Feature Selection technique (FS) that integrates with Opposition-Based Learning (OBL) and Particle Swarm Optimization (PSO). We improve the speed of convergence with the PSO algorithm and the exploration with the IAOO algorithm. The IAOO is demonstrated to possess superior global optimization capabilities, as validated on the IEEE Congress on Evolutionary Computation 2022 (CEC’22) benchmark suite and compared with seven Metaheuristic (MH) algorithms. Additionally, an IAOO-PSO model based on Support Vector Machines (SVMs) classifier is proposed for FS and classification, where the IAOO-PSO is used to identify the most relevant features. This model was applied to the DED dataset comprising 20,000 cases and 26 features, achieving a high classification accuracy of 99.8%, which significantly outperforms other optimization algorithms. The experimental results demonstrate the reliability, success, and efficiency of the IAOO-PSO technique for both FS and classification in the detection of DED.

---

Keywords

---