AHA-AO: Artificial Hummingbird Algorithm with Aquila Optimization for Efficient Feature Selection in Medical Image Classification

This paper presents a system for medical image diagnosis that uses transfer learning (TL) and feature selection techniques. The main aim of TL on pre-trained models such as MobileNetV3 is to extract features from raw images. Here, novel optimization algorithm called the Artificial Hummingbird Algorithm based Aquila Optimization (AHA-AO) proposed. AHA-AO used select only most relevant ensure improvement overall model classification. Our methodology was evaluated using four datasets, namely, ISIC-2016, PH2, Chest-XRay, Blood-Cell. We compared proposed with five popular algorithms. obtained an accuracy 87.30% ISIC-2016 dataset, 97.50% PH2 86.90% Chest-XRay 88.60% Blood-cell dataset. outperformed other Moreover, developed faster than during process determining features. successfully improved performance speed deep models.