Unsupervised Hybrid Deep Feature Encoder for Robust Feature Learning from Resting-State EEG Data

• Published in: 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Vol. 2024; pp. 1 - 5
• Main Authors: Yue, Yuan, Deng, Jeremiah D., Chakraborti, Tapabrata, De Ridder, Dirk, Manning, Patrick
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.07.2024
• Subjects: Accuracy; Algorithms; Benchmark testing; Biological system modeling; Brain - physiology; Brain modeling; Cluster Analysis; Data models; Deep Learning; Electroencephalography; Electroencephalography - methods; Engineering in medicine and biology; Feature Encoder; Feature extraction; Feature Selection; Humans; Machine Learning; Representation learning; Rest - physiology; Resting-state EEG classification; Signal Processing, Computer-Assisted; Unsupervised Machine Learning; Variational Autoencoder
• DOI: 10.1109/EMBC53108.2024.10781741

EEG classification is a challenging task due to the nonstationary nature of EEG data and the covariance shift induced by cross-subject variance. Recently, various machine learning and deep learning models have been developed to learn robust features for inter-subject EEG classification tasks. However, current existing models are designed based on active task-related EEG, with a lack of investigation into learning robust feature representation from resting-state EEG data. Given the differences in the nature of brain activities captured by resting-state and active task-related EEG, existing models might not be applicable to resting-state EEG. This study proposed an unsupervised hybrid deep feature encoder to learn robust feature representation in resting-state EEG data. It involves using a Variational Autoencoder (VAE) to learn latent feature representation, followed by a further feature selection conducted through a non-task-related sample-level proximity classification using K-means clustering. We demonstrate the efficiency of our proposed model through significantly improved classification accuracies compared to benchmark models, as well as the high between-subject separability manifested by the learned feature representation.