EEG signal analysis by using SVM and ELM

Brain Computer Interface (BCI) is a communication interface between the brain and an external device and is often used to assist, augment, or repair human cognitive or sensory-motor functions. One type of brain signal used in BCI systems is the electroencephalogram (EEG). In this project, the two EEG signals that were analyzed were obtained by recording the EEG activity that was occurring when a person was moving their arms for the first case and their legs for the second case. These EEG signals were processed using a power line rejection notch filter, power spectral density analysis, Principal Component Analysis (PCA), and finally the mathematical based machine learning analysis using both Support Vector Machine (SVM) and Extreme Learning Machine (ELM). Machine learning is used to generate a model that could be used to accurately predict whether a person is moving their arms or their legs by applying the EEGs as inputs to the generated model and reading the output of the model. The goal of this project is to compare the performance of SVM and ELM by using the accuracy of classification that each model produces.