Multi-Model Approach for Alzheimer Disease Detection and Classification

Alzheimer’s disease is a leading cause of concern for an older demographic. The progression of the disease is marked by a decline in cognitive abilities and an inability to care for themselves. Hence, it is very important to detect Alzheimer’s disease in its early stages. The SVM and CNN are the models generally used for the detection and classification of Alzheimer’s disease which yielded promising results. In this work, SVM and EfficientNetB0 is used in tandem to improve the performance. The results obtained show that the proposed method gives better results as compared to individual models. As for CNN (EfficientNetB0), it has good performance with a more efficient use of resources by scaling the model’s depth, width, and resolution in a balanced manner. In this paper, we propose combining these two models where SVM and CNN are used together to get the best possible results.