Invention Application
- Patent Title: AUTOMATIC SENSOR TRACE VALIDATION USING MACHINE LEARNING
-
Application No.: US17905101Application Date: 2021-02-25
-
Publication No.: US20230091197A1Publication Date: 2023-03-23
- Inventor: Mark Edwards , Vivek Singh , Bogdan Georgescu , Ankur Kapoor
- Applicant: Siemens Healthcare Diagnostics Inc.
- Applicant Address: US NY Tarrytown
- Assignee: Siemens Healthcare Diagnostics Inc.
- Current Assignee: Siemens Healthcare Diagnostics Inc.
- Current Assignee Address: US NY Tarrytown
- International Application: PCT/US2021/019731 WO 20210225
- Main IPC: G06F11/07
- IPC: G06F11/07 ; G06N3/08 ; G06N3/0455

Abstract:
The disclosure provides a computer-implemented method for detecting a failure of a device, wherein the device is connected to a sensor, the method comprising: receiving, by a machine learning model, a trace signal from the sensor indicating a status of the device; encoding, by the machine learning model, the trace signal into a plurality of vector representations; and determining, by the machine learning model, whether the trace signal is valid or invalid based on the plurality of vector representations.
Public/Granted literature
- US12124325B2 Automatic sensor trace validation using machine learning Public/Granted day:2024-10-22
Information query