Sensor fusion for activity identification

A system to monitor human activity using multiple sensors comprising:

• a mobile device comprising:
• a plurality of sensors;
• a dedicated processing unit receiving data from the plurality of sensors, the dedicated processing unit to process sensor data,
• the dedicated processing unit further comprising a calculating logic to compare a first estimation of a user activity statistic based on data from a first sensor with a second estimation of a user activity statistic based on data from a second sensor, and calculating the user activity statistic based on the first estimation and the second estimation, wherein the calculated user activity statistic is a result of a weighted combination of the first estimation and the second estimation;
• and
• a central processing unit to perform functions in the mobile device;
• and
• a server coupled to the mobile device via a network, the server providing a remote calculating logic to perform a portion of the calculations for the calculating logic in the mobile device.