This week for capstone I spent the majority of my time organizing the classification algorithm approach to our EMG data. A major decision factor going into this classification of the data depends on how the data is recorded. I found that if the data is recorded in a continuous stream of repeated actions, the best approach is to use wavelet transform on the data in order to identify a basis function and the scaled and shifted versions of it. This is helpful for features extraction. For generalized classification I believe the most straight forward approach is now to use PCA to reduce the dimensionality of the 5 channel data and then use SVM to find a linear hyperplane that separates the data. Because we are classifying between more than two classes, I decided we should use the approach of comparing each class to all the rest of the data points, as opposed to comparing one class to each other individual class. This upcoming week we are presenting a demo of our complete system. Things are mostly on track, we will be having two final integration tests in order to incorporate the classification portion of the project as well. This upcoming week will be spent refining the algorithms to optimize speed, efficiency, and accuracy to ensure that we meet our target goals for the project.