About The Project • Built With • Usage • License • Other Projects • Contact • Download
P300 Classification for EEG-based BCI system with a Deep CNN method.
This Project utilises Matlab to run variation of a convolutional neural network (CNN) which is located in the CNN folder, these file learns from dataset located in the dataset folder which contains 15 subjects and 7 session each with 9 files of data. The .m files in the CNN folder run session 1-7, 1-3 or 4-7 to which requests the appropriate data from the dataset file using a list that is located in the SBJ-S folder which contains subject, session numbers and cell range to which the results will be printed into a spreadsheet. These spreadsheet will write over each other so the results are copied into another spreadsheet in the results folder called All_Results_Data which contains all the project and experiment results, these are then organised further into spreadsheets for results for sessions 1-3, 4-7 and 1-7. The BCI_CNN_Function.m file in the CNN folder is the convolutional neural network that can be manipulated to run different variations of the CNN to improve the session accuracy.
MatLab C# LaTeX HTML
The folder is ~6.0GB
Project Source: https://www.kaggle.com/datasets/disbeat/bciaut-p300
MatLab Files: https://github.com/lrgto/brain-computer-interface-classification-matlab/blob/main/CNN
LaTeX Thesis: https://github.com/lrgto/brain-computer-interface-classification-matlab/blob/main/Document
This is a private repository and is shared for educational purposes. Please feel free to download this repo for your own educational needs. For further infomation please direct yourself to the files listed;
License, Code of Conduct, Contributing, Changelog, Security.
This project and the index file forms an inventory supplementing a corpus which was submitted alongside a dissertation for the degree of a Masters of Science in Computer Science (Artificial Intelligence) at the University of Kent in September 2022.
Distributed under the CC-BY-SA-4.0: Creative Commons Attribution Share Alike 4.0 International License.
See LICENSE.txt for more information.
GitHub: @lrgto · LinkedIn: @lrgtomaszewski · Website: https://lrgto.github.io