EEG Data Augmentation Method Based on the Gaussian Mixture Model

Traditional methods of electroencephalograms(EEG) data augmentation, such as segmentation-reassembly and noise mixing, suffer from data distortion that can alter the original temporal and spatial feature distributions of the brain signals. Deep learning-based methods for generating augmentation EEG data, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), have shown promising performance but require a large number of comparative learning samples for model training. To address these issues, this paper introduces an EEG data augmentation method based on Gaussian Mixture Model microstates, which retains the spatiotemporal dynamic features of the EEG signals in the generated data. The method first performs Gaussian mixture clustering on data samples of the same class, using the product of the probability coefficients and weight matrices of each Gaussian model as corresponding microstate features. Next, it randomly selects two EEG data samples of the same type, analyzes the similarity of the main components of the microstate features, and swaps the similar main components to form new Gaussian mixture model features. Finally, new data is generated according to the Gaussian mixture model using the respective model probabilities, weights, means, and variances. Experimental results on publicly available datasets demonstrate that the proposed method effectively characterizes the original data's spatiotemporal and microstate features, improving the accuracy of subject task classification.