EEG Signal Analysis
EEG signal analysis aims to extract meaningful information from brain electrical activity, primarily for understanding cognitive processes and developing brain-computer interfaces (BCIs). Current research emphasizes improving the accuracy and robustness of EEG analysis by addressing challenges like noise and inter-subject variability, focusing on advanced deep learning architectures such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and graph neural networks (GNNs), often incorporating techniques like contrastive learning and self-supervised pretraining. These advancements hold significant potential for improving clinical diagnostics (e.g., seizure detection, depression diagnosis), enhancing BCIs, and furthering our understanding of brain function.
Papers
ConvConcatNet: a deep convolutional neural network to reconstruct mel spectrogram from the EEG
Xiran Xu, Bo Wang, Yujie Yan, Haolin Zhu, Zechen Zhang, Xihong Wu, Jing Chen
Self-supervised speech representation and contextual text embedding for match-mismatch classification with EEG recording
Bo Wang, Xiran Xu, Zechen Zhang, Haolin Zhu, YuJie Yan, Xihong Wu, Jing Chen