US 11,688,264 B2
System and method for patient movement detection and fall monitoring
Shuchuan Jack Cheng, Potomac, MD (US); and Yuan-Ming Fleming Lure, Potomac, MD (US)
Assigned to MS TECHNOLOGIES, Rockville, MD (US)
Filed by MS Technologies, Rockville, MD (US)
Filed on Jan. 11, 2023, as Appl. No. 18/153,345.
Application 18/153,345 is a continuation in part of application No. 17/992,722, filed on Nov. 22, 2022.
Application 17/992,722 is a continuation of application No. 17/970,330, filed on Oct. 20, 2022.
Application 17/970,330 is a continuation in part of application No. 17/866,021, filed on Jul. 15, 2022.
Application 17/866,021 is a continuation in part of application No. 17/857,963, filed on Jul. 5, 2022.
Application 17/857,963 is a continuation of application No. 17/559,680, filed on Dec. 22, 2021.
Application 17/559,680 is a continuation of application No. 17/116,686, filed on Dec. 9, 2020, granted, now 11,380,181, issued on Jul. 5, 2022.
Claims priority of provisional application 63/400,745, filed on Aug. 24, 2022.
Claims priority of provisional application 63/150,335, filed on Feb. 17, 2021.
Prior Publication US 2023/0140093 A1, May 4, 2023
Int. Cl. G08B 21/00 (2006.01); G08B 21/04 (2006.01); G06N 20/00 (2019.01); G08B 27/00 (2006.01); G01S 13/62 (2006.01)
CPC G08B 21/043 (2013.01) [G01S 13/62 (2013.01); G06N 20/00 (2019.01); G08B 27/005 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A system for patient movement detection and fall monitoring, comprising:
a computing device comprising a memory, a processor, and a non-volatile data storage device; and
a monitoring server comprising a first plurality of programming instructions stored in the memory of, and operating on the processor of, the computing device, wherein the first plurality of programming instructions, when operating on the processor, cause the computing device to:
receive event data, the event data comprising at least video data and a spectrogram representing a digital signal;
use the spectrogram to detect a fall or activity by feeding the spectrogram into a classifier network comprising one or more neural networks, wherein the one or more neural networks are trained to output an event classification, wherein the event classification classifies an event as a fall or activity;
logically link the video data to the output of the classifier network;
create an event log comprising the output of the classifier network and the video data;
store the event log in a database; and
generate an alert notification, the alert notification comprising the event log.