Hand Gesture Data Collection Procedure Using a Myo Armband for Machine Learning

In 2015, the Battlefield Information Processing Branch investigated using machine learning ML to identify military hand gestures. A Naive Bayes model was trained and created as an initial test. Naturally, the capability of the model relies on the quality and quantity of the training data. Therefore, the data collection is an important and necessary step in building a ML classifier. This report describes the procedure used to collect arm gesture movement data using a Myo armband. The source code for this work is included as an Appendix.