KBRI-Computational-Brain-Modeling / Brain-Computer-Interface

Brain-Computer-Interface

Aim:

Brain-computer interface (BCI) is a technology that allows communication between a human brain and an external technology. The main aim is to analyse and accurately classify the Electroencephalography (EEG) signals which are used to record electrical activity of the brain. The objective of this project is to design and implement a system for monitoring EEG signals and to classify them with the help of different classifiers. BCI systems build a communication bridge between human brain and the external world eliminating the need for typical information delivery methods.

Technologies/ Programming Languages used:

Python Libraries required:

1. NumPy
2. SciPy
3. Tensorflow
4. Keras
5. MNE python (a widely used python library for MEG and EEG signal processing)

MATLAB

Feature Extraction techniques used:

1. Stastical features: a.) Mean b.) Power Spectral Density c.) Entropy

2. Principal Component Analysis (PCA)

Pre-Processing used:

1. Band Pass filter
2. Independent Component Analysis (ICA)

Classifiers used:

1. SVM
2. Neural networks

Dataset used:

Data set provided by Department of Medical Informatics, Institute for Biomedical Engineering, University of Technology Graz. (Gert Pfurtscheller) which is publically available. http://www.bbci.de/competition/