Software for motor imagery detection

Product description

The software is designed to classify motor imagery and motor execution patterns based on EEG brain signals. It utilizes its own experimental dataset, which is freely available at https://zenodo.org/record/7893847. Using this dataset, the software applies deep learning models for binary classification – distinguishing between imagined hand movement and a resting state, and multiclass classification – distinguishing between the imagined movement of the left hand, right hand, and a resting state. The software was developed as part of the SGS-2022-016 Advanced Methods of Data Processing and Analysis project. A research paper related to the project has been published by Mouček, R., Kodera, J., Mautner, P. and Průcha, J. (2024). Augmentation of Motor Imagery Data for Brain-Controlled Robot-Assisted Rehabilitation. In Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - HEALTHINF; ISBN 978-989-758-688-0; ISSN 2184-4305, SciTePress, pages 812-819. DOI: 10.5220/0012575700003657. The source code is also available at https://gitlab.com/Dumby7/eeg-motion-detection.