The code repository for the paper "Assessing the potential of data augmentation in EEG functional connectivity for early detection of Alzheimer's disease".
Combine the separate data files into one file considering the processing in the following steps
Decompose the EEG time series into multiple modes with classical/serial/multivariate mode decomposition
Split the dataset into the training set and the testing set, and generate the artifical data with the training set
Calculate the functional connectivity with the EEG signals in the training/testing set
Evaluate the model performance on the augmented dataset, including BrainNet CNN, ResNet-18, and EEGNet
Collect and calculate the classification performance of three models
The code for multivariate mode decomposition is from http://freesourcecode.net/matlabprojects/5896/Multivariate-Empirical-Mode-Decomposition-Matlab-Code.