the KNN classifier performed better compared to SVM and RF. The best sensitivity and specificity achieved by KNN confirm the validity of the classification model. Our classification results clearly exhibit increased accuracy in the WM task. To the best of our knowledge, the performance of classification measures confirms the robustness of our methodology, as well as the highest accuracy obtained with KNN in the classification of brain aging using a graph theory network. The age-related differences in EEG networks reflect the process of normal aging. However, the absence of age-dependent changes in elderly individuals can probably render them vulnerable to cognitive decline, dementia, and AD. This study highlighted the potential of a working memory-based technique to evaluate age-related alterations in a functional brain network and its associated mechanism, thus affecting memory in elderly populations.
