Evaluation of Machine Learning Algorithms for Classification of EEG Signals
www.mdpi.com
Feb. 25, 2024, 9:17 p.m.
The model of Medium-ANN achieved the best performance metrics, with an AUC average of 0.9998, Cohen’s Kappa coefficient of 0.9552, Matthews correlation coefficient of 0.9819, and loss of 0.0147. These findings enable the approach to be applied to different scenarios, such as robotic prosthesis implementation, where the utilization of physical qualities is an acceptable alternative when hardware resources are restricted, or in embedded systems or edge computing devices, which have the advantages of low cost, small size, portability, low power consumption, and reliable communication with the BCI.