MYO EMG big data

MYO is an armband that is used to detect electric pulses from your arm which can later be used to detect a certain movement. These electric pulses are detected by 8 different sensors in the armband which go around your arm. Before MYO only released a version of the armband which detected predefined movements but later released an SDK version which let coders be able to receive the raw data gathered from the electric pulses. One of the many difficulties is to program personalized movements with the electric pulses. The reason for this is that exactly the same movement can give extremely different data as seen in the image below:

This depends on muscle complexity, BMI, arm length, injuries, among other things. For this it necessary, in order to do machine learning, that a large data set is made with a variety of people in order for the machine learning algorithm to detect the exact movement of the user, or at least make a very good assumption of what it is. Big data algorithms are needed in order to have arm movement detection programs which can easily be used for anyone with a wide variety of characteristics. This becomes much more simple if the detection is being programmed for a person or a specific group of people since the training data wont be much different from the testing data.

For more information: http://developerblog.myo.com/big-data/