Classification of brainwaves using deep learning models
[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] The classification of brainwaves has always been a topic of high interest in the neuroscience and medical community. Currently used classification techniques require an extraction of features from the brainwave data, which has its limitations affecting the classification performance. To alleviate this problem, this study showcases the development of three different Convolutional Neural Networks (CNN), which take the spatiotemporal nature of the brainwave data into account and find the correlation between time samples along the time and frequency axes. The obtained results are compared with popular methods such as the FFT method and the Fully Connected Network model, as seen in many recent studies. In all the results, the CNN models outperform the FFT and Fully Connected Network results by a significant margin. This comparison also sheds light on certain signal characteristics affecting the model's performance.
Access is limited to the campuses of the University of Missouri.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 License.