US 12,072,348 B2
Fall detection system using a combination of accelerometer, audio input and magnetometer
Ram David Adva Fish, Menlo Park, CA (US); Henry Messenger, Campbell, CA (US); Leonid Baryudin, San Francisco, CA (US); Soroush Salehian Dardashti, Mountain View, CA (US); and Evgenia Goldshtein, Madison, NJ (US)
Assigned to Nice North America LLC, Carlsbad, CA (US)
Filed by Nice North America LLC, Carlsbad, CA (US)
Filed on Feb. 1, 2019, as Appl. No. 16/265,779.
Application 16/265,779 is a continuation of application No. 15/499,625, filed on Apr. 27, 2017, granted, now 10,309,980.
Application 15/499,625 is a continuation of application No. 14/465,489, filed on Aug. 21, 2014, granted, now 9,648,478.
Application 14/465,489 is a continuation of application No. 13/237,857, filed on Sep. 20, 2011, granted, now 8,843,101.
Claims priority of provisional application 61/516,479, filed on Apr. 4, 2011.
Claims priority of provisional application 61/516,480, filed on Apr. 4, 2011.
Claims priority of provisional application 61/404,379, filed on Oct. 4, 2010.
Prior Publication US 2019/0170783 A1, Jun. 6, 2019
Int. Cl. G01P 1/07 (2006.01); H04M 1/72421 (2021.01); H04W 4/90 (2018.01)
CPC G01P 1/07 (2013.01) [H04M 1/72421 (2021.01); H04W 4/90 (2018.02); H04M 2201/40 (2013.01); H04M 2250/02 (2013.01); H04M 2250/12 (2013.01)] 20 Claims
OG exemplary drawing
 
11. A method comprising:
receiving, at a processor, a set of measurement data including accelerometer data, magnetometer data and audio data;
receiving category information for the set of measurement data, the category information identifying a first set of measurement data categorized as indicative of a suspected fall, based on the accelerometer data, a second set of measurement data categorized as indicative of an activity of daily life (ADL) based on physical movement of users, and a third set of measurement data categorized as an inconclusive event;
training, using the processor, a fall model and training an ADL model using the set of measurement data and the category information; and
wherein the fall model and the ADL model are used to classify unclassified measurement data as indicative of a fall or an ADL, the ADL model classifying at least talking and walking as ADL events, and wherein the fall model is used to re-confirm whether the first set of measurement data categorized as indicative of the suspected fall indicates a fall.