A Comprehensive Survey on Emerging Techniques and Technologies in Spatio-Temporal EEG Data Analysis DOI Creative Commons
Pengfei Wang, Huanran Zheng,

Silong Dai

et al.

Chinese journal of information fusion., Journal Year: 2024, Volume and Issue: 1(3), P. 183 - 211

Published: Dec. 15, 2024

In recent years, the field of electroencephalography (EEG) analysis has witnessed remarkable advancements, driven by integration machine learning and artificial intelligence. This survey aims to encapsulate latest developments, focusing on emerging methods technologies that are poised transform our comprehension interpretation brain activity. The structure this paper is organized according categorization within community, with representation as foundational concept encompasses both discriminative generative approaches. We delve into self-supervised enable robust signals, which fundamental for a variety downstream applications. Within realm methods, we explore advanced techniques such graph neural networks (GNN), foundation models, approaches based large language models (LLMs). On front, examine leverage EEG data produce images or text, offering novel perspectives activity visualization interpretation. provides an extensive overview these cutting-edge techniques, their current applications, profound implications they hold future research clinical practice. relevant literature open-source materials have been compiled consistently updated at https://github.com/wpf535236337/LLMs4TS.

Language: Английский

A Comprehensive Survey on Emerging Techniques and Technologies in Spatio-Temporal EEG Data Analysis DOI Creative Commons
Pengfei Wang, Huanran Zheng,

Silong Dai

et al.

Chinese journal of information fusion., Journal Year: 2024, Volume and Issue: 1(3), P. 183 - 211

Published: Dec. 15, 2024

In recent years, the field of electroencephalography (EEG) analysis has witnessed remarkable advancements, driven by integration machine learning and artificial intelligence. This survey aims to encapsulate latest developments, focusing on emerging methods technologies that are poised transform our comprehension interpretation brain activity. The structure this paper is organized according categorization within community, with representation as foundational concept encompasses both discriminative generative approaches. We delve into self-supervised enable robust signals, which fundamental for a variety downstream applications. Within realm methods, we explore advanced techniques such graph neural networks (GNN), foundation models, approaches based large language models (LLMs). On front, examine leverage EEG data produce images or text, offering novel perspectives activity visualization interpretation. provides an extensive overview these cutting-edge techniques, their current applications, profound implications they hold future research clinical practice. relevant literature open-source materials have been compiled consistently updated at https://github.com/wpf535236337/LLMs4TS.

Language: Английский

Citations

0