Invention Grant
- Patent Title: Method for generating a personalized classifier for human motion activities of a mobile or wearable device user with unsupervised learning
-
Application No.: US16783569Application Date: 2020-02-06
-
Publication No.: US11096593B2Publication Date: 2021-08-24
- Inventor: Mahesh Chowdhary , Arun Kumar , Ghanapriya Singh , Rajendar Bahl
- Applicant: STMicroelectronics, Inc. , STMicroelectronics International N.V.
- Applicant Address: US TX Coppell; NL Schiphol
- Assignee: STMicroelectronics, Inc.,STMicroelectronics International N.V.
- Current Assignee: STMicroelectronics, Inc.,STMicroelectronics International N.V.
- Current Assignee Address: US TX Coppell; NL Schiphol
- Agency: Crowe & Dunlevy
- Main IPC: A61B5/0205
- IPC: A61B5/0205 ; A63B69/00 ; A61B5/00 ; A61B5/024 ; A61B5/11 ; G16H40/63 ; A61B5/0245 ; A61B5/22 ; G16H50/20

Abstract:
Motion activity data is collected from at least one sensor. An initial motion activity classifier function is applied to the motion activity data to produce an initial motion activity posteriorgram. Pre-processing and segmenting the motion activity data into windows produces segmented motion activity data from which sensor specific features are extracted. An updated motion activity classifier function is generated from the extracted sensor specific features. Subsequent motion activity data is also collected from the at least one sensor, and the updated motion activity classifier function is applied to the subsequent motion activity data to produce an updated motion activity posteriorgram.
Public/Granted literature
Information query