Skip to content

Noah-marc/BCI-classification-models

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

BCI-classification-models

With this project we tried to solve a BCI classification problem by using different preprocessing methods (PCA, select-k-best, etc.) and algorithms (SVM, KNN, Bayesian classifier) to maximize the performance of each model. We then further used different evaluation methods (balanced accuracy scores, confusion matrices) to determine which model worked best for our given problem. The main result is that generally the SVM performed better than the 2 other models. However, note that the results are not necessarily representative, since changing some steps or methods, might improve the performance of a model significantly

The dataset used is the Dataset V from the BCI competition III. In general, it contains precomputed PSD-values for each of the three subjects. Each subject did one of 3 distinct tasks, which we try to correctly classify in the project. The Dataset provided some training data as well as test data, for which the labels are now publicly available as well. More info about the dataset can be found here: https://www.bbci.de/competition/iii/#data_set_v

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published