Method for generating a personalized classifier for human motion activities of a mobile or wearable device user with unsupervised learning

A sensor chip mounted on a printed circuit board (PCB) and electrically coupled to a system on chip (SOC) mounted on the PCB via at least one conductive trace, the sensor chip comprising:

• at least one sensing device;
• and
• a control circuit configured to:
• collect initial motion activity data from the at least one sensing device;
• generate an initial probabilistic context of the printed circuit board relative to its surroundings from the initial collected motion activity data using a motion activity classifier function;
• store the collected motion activity data in a training data set;
• update the motion activity classifier function using the training data set;
• collect subsequent motion activity data from the at least one sensor of the electronic device;
• and
• generate a subsequent probabilistic context of the electronic device relative to its surroundings from the subsequently collected motion activity data using the updated motion activity classifier function.

A method of operating an electronic device, comprising:

• collecting motion activity data from at least one sensor of the electronic device;
• generating probabilistic context of the electronic device relative to its surroundings from the collected motion activity data using a motion activity classifier function;
• storing the collected motion activity data in a training data set;
• updating the motion activity classifier function using the training data set;
• and
• updating the probabilistic context of the electronic device relative to its surroundings using the updated motion activity classifier function.