Brain-Computer Interface (BCI) has become an established technology to interconnect a human brain and an external device. One of the most popular protocols for BCI is based on the extraction of the so-called P300 wave from EEG recordings. P300 wave is an event-related potential with a latency of 300 ms after the onset of a rare stimulus. In this paper, we used deep learning architectures, namely convolutional neural networks (CNNs), to improve P300-based BCIs.
Required Python libraries: numpy, scipy, pandas, matplotlib, openpyxl, jupyter
1. Extract the whole content of the zip file into a folder
2. Run the Jupyter Notebook: Analysis_and_Figures_P3CNET_Paper.ipynb
3. The notebook generates all the figures and data reported in the paper.
The dataset contains also the Python code to implement the two CNNs with Tensorflow and Keras:
The data acquisition process begins with capturing EEG signals from 20 healthy skilled volunteers who gave their written consent before performing the experiments. Each volunteer was asked to repeat an experiment for 10 times at different frequencies; each experiment was trigger by a visual stimulus.
EEG brain recordings of ADHD and non-ADHD individuals during gameplay of a brain controlled game, recorded with an EMOTIV EEG headset. It can be used to design and test methods to detect individuals with ADHD.
For details, please see:
Alaa Eddin Alchalabi, S. Shirmohammadi, A. N. Eddin and M. Elsharnouby, “FOCUS: Detecting ADHD Patients by an EEG-Based Serious Game”, IEEE Transactions on Instrumentation and Measurement, Vol. 67, No. 7, July 2018, pp. 1512-1520.