Machine learning classification using EEG brain signal

Currently, we are developing a study to look at the response pattern from EEG brain signal when being delivered with different auditory stimulus at the neuronal level. The time and frequency domain features will be extracted from the EEG signal captured for analysis. Then, the response obtain will be supplied or submit to a different machine learning model for training and testing to come out with measurable predictive discrimination upon the given stimulus. Now, the focus would be: 1. Develop time and frequency domain response base on given stimulus signal 2. Use the extract response (time and frequency) as a training dataset to train five classifiers model (60% dataset for training) 3. The trained model (all these 5 classifiers) will be tested using testing dataset (40% dataset for testing) and the performance measure will be quantify using below parameters (a) sensitivity (recall) (b) specificity (precision) (c) accuracy (covers on AUC as well (area under curve) The 5 classifiers are: Support Vector Machine (SVM), K Nearest Neighbours (KNN), Elman Network (ELN), Multilayer Perceptron Neural Network (MLPNN), and Random Forest (RF) Example of outcome as per below figures Software target: MATLAB or Python. Depends on proficiency.