EEG Data Processing with Machine Learning

Electroencephalography (EEG) has emerged as a powerful tool for monitoring and understanding brain activity. In recent years, the use of machine learning techniques has significantly enhanced the analysis of EEG data, offering valuable insights into neurological conditions, cognitive processes, and...

Full description

Saved in:
Bibliographic Details
Published in2024 23rd International Symposium on Electrical Apparatus and Technologies (SIELA) pp. 1 - 6
Main Authors Ivanov, Aleksandar, Cerbulescu, Cristina
Format Conference Proceeding
LanguageEnglish
Published IEEE 12.06.2024
Subjects
Data processing
EEG
Electroencephalography
Independent component analysis
Machine learning
Neural activity
Pipelines
Visualization
Online AccessGet full text
DOI10.1109/SIELA61056.2024.10637835

Cover

More Information
Summary:Electroencephalography (EEG) has emerged as a powerful tool for monitoring and understanding brain activity. In recent years, the use of machine learning techniques has significantly enhanced the analysis of EEG data, offering valuable insights into neurological conditions, cognitive processes, and mental states. This paper presents a series of experiments where various machine learning techniques were used for processing real EEG data at different stages of the pipeline. To test the data obtained during visual stimulation session with human subjects, Independent Component Analysis, clustering and autoencoders were the chosen techniques. Analysis and evaluation of tested methods is provided.
DOI:10.1109/SIELA61056.2024.10637835