A Survey of Spatio-Temporal EEG data Analysis: from Models to Applications
Pengfei Wang, Huanran Zheng, Silong Dai, Yiqiao Wang, Xiaotian Gu, Yuanbin Wu, Xiaoling Wang
TL;DR
This survey addresses the challenge of extracting meaningful representations, discriminative patterns, and generative insights from EEG data by outlining three complementary fronts: self supervised representation learning, discriminative architectures including GNNs and foundation/LLM models, and generative EEG applications. It synthesizes methods across contrastive learning, masked autoencoders, graphbased modeling, and foundation and LLMbased approaches, with emphasis on time series preprocessing, graph construction, and crossmodal generation. Key contributions include a structured taxonomy of EEG SSL methods, a curated view of foundation and LLMbased EEG modeling, and a survey of EEGtoimage and EEGtoText generation pipelines, along with datasets and evaluation metrics. The work highlights practical implications for robust EEG analysis, clinical translation, and open science through open source resources and a forwardlooking agenda for multimodal, scalable, and clinically usable EEG AI systems.
Abstract
In recent years, the field of electroencephalography (EEG) analysis has witnessed remarkable advancements, driven by the integration of machine learning and artificial intelligence. This survey aims to encapsulate the latest developments, focusing on emerging methods and technologies that are poised to transform our comprehension and interpretation of brain activity. We delve into self-supervised learning methods that enable the robust representation of brain signals, which are fundamental for a variety of downstream applications. We also explore emerging discriminative methods, including graph neural networks (GNN), foundation models, and large language models (LLMs)-based approaches. Furthermore, we examine generative technologies that harness EEG data to produce images or text, offering novel perspectives on brain activity visualization and interpretation. The survey provides an extensive overview of these cutting-edge techniques, their current applications, and the profound implications they hold for future research and clinical practice. The relevant literature and open-source materials have been compiled and are consistently being refreshed at \url{https://github.com/wpf535236337/LLMs4TS}