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

• Published in: Computer modeling in engineering & sciences Vol. 144; no. 2; pp. 2445 - 2480
• Main Authors: Houssein, Essam H., Saber, Eman, Samee, Nagwan Abdel
• Format: Journal Article
• Language: English
• Published: Henderson Tech Science Press 2025
• Subjects: Algorithms; CAD; Classification; Computer aided design; Datasets; Evolutionary computation; Eye diseases; Global optimization; Heuristic methods; Optimization; Particle swarm optimization; Support vector machines
• ISSN: 1526-1506; 1526-1492; 1526-1506
• DOI: 10.32604/cmes.2025.069184

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.