An introduction to Brain Computer Interface both from a theoretical and a practical point of view of data acquisition and data analysis through Machine Learning techniques.
Lectures recordings are available on our YouTube channel https://youtu.be/84q-bjevPAQ
- Introduction to Modern Brain-Computer Interface Design
- A review of classification algorithms for EEG-based brain–computer interfaces
- Deep learning-based electroencephalography analysis: a systematic review
During the first lecture on Brain Computer Interfaces, held on 12/12/2022, we introduce some basic definitions, principles of EEG signals acquisition up to analyzing a first dataset (available in BCIIV_calib_ds1a.mat) and understanding its main features. Matlab code to open this dataset in Matlab and Matlab file we used to preprocess them are respectively Open_dataset.m and Pre_process_data.m. Then we analyzed data following the steps in L_1.ipynb In Lecture_1.pptx we share slides of the first theorethical part while in BCIcompIV_dataset_description.pdf the description of the experimental protocol and subjects characteristics are available. For more information see: https://www.bbci.de/competition/iv/desc_1.html.
The second lesson is an overview of various methods of feature extraction and later EEG-signal classification Lecture_2.pptx. Much of the lesson was spent solving the notebook L_2_Student.ipynb using data described in Lecture 1.
L_2_SOL.ipynb contains some ideas on how to conclude the problem assigned in class.