A user-wearable electronic device includes a housing configured to be worn or embedded in a device worn by an employee, one or more sensors disposed in the housing, including a first sensor to sense motion of the employee and produce raw activities of daily work (ADW) data. One or more processors in the electronic device or an intermediary device generate, for time periods in a sequence of successive time periods, ADW identification information by processing the raw ADW data using one or more neural networks pre-trained to recognize a predefined set of ADWs. Each pre-trained neural network includes a plurality of neural network layers, including at least one layer that includes a recurrent neural network. Reports that include ADW information corresponding to the generated ADW identification information for one or more time periods in the sequence of time periods are transmitted to a monitoring system.
展开▼
