Armband for tracking hand motion using electrical impedance measurement

A method, comprising:

• receiving training electrical signals from sensors arranged in a two-dimensional pattern on a wearable device, the training electrical signals transmitted from a wrist or arm of a user;
• extracting training features from the training electrical signals;
• training a machine learning model using the extracted training features to determine a hand position of a hand of the wrist or arm of the user;
• receiving electrical signals from the sensors, the electrical signals transmitted from the wrist or arm of a user, the electrical signals comprising information of values of an electrical impedance;
• extracting features from the electrical signals, the features comprising the values of the electrical impedance;
• transmitting the features, which are extracted from the electrical signals measured by the sensors arranged in the two-dimensional pattern, to the machine learning model to compute an output that describes a hand position of the hand of the wrist or arm of the user;
• and
• transmitting the output to a host system.