<![CDATA[Alzheimer’s disease is a major public health concern characterized by progressive cognitive decline due to irreversible neuronal damage. Alzheimer’s disease represents a major global health concern in the twenty-first century. Although magnetic resonance imaging (MRI) is widely used for early diagnosis, manual interpretation is time-consuming and subject to variability. This study proposes an automated classification system based on the lightweight MobileNetV3 architecture to improve diagnostic efficiency. The model leverages depthwise separable convolutions to reduce computational complexity while maintaining high performance. MobileNetV3 models is then evaluated using appropriate metrics to assess the effectiveness of the proposed classification approach. Data augmentation techniques, including random rotation and flipping, are applied to enhance model generalization. Experimental results demonstrate that the MobileNetV3 Small model achieves superior performance, with an accuracy and F1-score of approximately 0.94, compared to 0.90 for the MobileNetV3 Large model. These findings indicate that the compact architecture provides better efficiency and reliability for Alzheimer’s disease classification. The proposed approach is suitable for deployment in resource-constrained medical environments.]]>
Copyrights © 2026
