Paper Contents
Abstract
The ability to extract meaningful patterns from vast amounts of malaria-related medical images is crucial for accurate and efficient malaria diagnosis. Traditional diagnostic methods, which often rely on manual microscopic analysis, are time-consuming, labor-intensive, and prone to human error. To address these challenges, this study presents a hybrid deep learning approach that integrates CNN-based feature extraction with the Double Hidden Layer Extreme Learning Machine (ELM) algorithm. The CNN model extracts critical parasite-related features from malaria-infected blood smear images, leveraging architectures like AlexNet, VGG16, and ResNet50 for deep feature representation. These extracted features are then classified using a Double Hidden Layer ELM, which enhances learning efficiency and improves classification accuracy. The proposed model effectively captures complex patterns in malaria-infected images while reducing computational complexity. By automating feature extraction and classification, this approach improves diagnostic accuracy, reduces processing time, and enhances scalability for large-scale malaria screening. The integration of CNN and ELM establishes a robust, scalable, and high-performance malaria detection framework, facilitating faster and more reliable clinical decision-making..
Copyright
Copyright © 2025 Ratanparkhe Vaishnavi . This is an open access article distributed under the Creative Commons Attribution License.
