The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jan. 12, 2021

Filed:

Aug. 02, 2017
Applicant:

Panasonic Intellectual Property Management Co., Ltd., Osaka, JP;

Inventors:

Yoshikuni Sato, Osaka, JP;

Toru Nakada, Kyoto, JP;

Yoshihide Sawada, Kyoto, JP;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 3/04 (2006.01); G16H 50/20 (2018.01); G06N 3/08 (2006.01); G16H 20/30 (2018.01); G16H 40/63 (2018.01);
U.S. Cl.
CPC ...
G16H 50/20 (2018.01); G06N 3/0436 (2013.01); G06N 3/08 (2013.01); G16H 20/30 (2018.01); G16H 40/63 (2018.01); G06N 3/0445 (2013.01); G06N 3/0472 (2013.01);
Abstract

An apparatus generates motor function estimation information by performing a process including calculating, using a sensor value of a subject, a feature vector corresponding to a feature value of a feature in a time segment, acquiring a first weight vector using the feature vector and a motor ability value of the subject, calculating a gradient vector with respect to the feature vector, determining a new time segment in the predetermined time period and a new feature value based on the new time segment, calculating, using the sensor value, a feature candidate vector corresponding to a feature value of the new feature in the new time segment, determining a feature candidate vector satisfying a predetermined condition associated with a gradient vector based on a difference between the feature candidate vector and the feature vector, and correcting the first weight vector to a second weight vector using the feature candidate vector.


Find Patent Forward Citations

Loading…