Method for monitoring of activity and fall

• US 10,299,704 B2
• Filed: 03/01/2017
• Issued: 05/28/2019
• Est. Priority Date: 12/09/2004
• Status: Active Grant

• Current Assignee: Gescloc Incorporated
• Original Assignee: Groupe Everclose, Inc.
• Inventors: Cloutier, Christian, Fortin, Regis
• Primary Examiner(s): Hindenburg, Max
• Application Number:
  US15/446,503
• Publication Number:
  US 20170172464A1
• Time in Patent Office: 818 Days
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/1117 Fall detection
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/4818 Sleep apnoea
• CPC Class Codes: A61B 5/681 Wristwatch-type devices
• CPC Class Codes: G08B 21/0288 Attachment of child unit to child/article
• CPC Class Codes: G08B 21/0415 detecting absence of activity per se
• CPC Class Codes: G08B 21/0446 worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait

Abstract

A method for monitoring activity of a subject in an environment, comprising providing at least one sensing assembly in the environment of the subject; providing a server communicating with at least one of: i) the subject and ii) the at least one sensing assembly; generating property vectors from data collected by the at least one sensing assembly; characterizing activity of the subject from the property vectors; and having a result of said characterizing step accessible to the server.

Claims

1. A method for monitoring activity and fall of a subject, comprising:

measuring acceleration data using a human kinetic sensor (HKS) assembly placed at an upper trunk of the subject

said HKS assembly comprising a sensing unit configured for sensing a low G acceleration at a low frequency sampling range and a high G acceleration at a high frequency sampling range,

said acceleration data being correlated to the spine of the subject due to a placement of the sensing unit at the upper trunk of the subject to yield behaviour indicators and threshold levels associated with characteristics the subject and an activity nature, state and level for a given environment and time;

processing the acceleration data in the low G acceleration into data reflecting a three-dimensional vectorial position of the upper body of the subject as being directly correlated with an orientation of the entire spine and body of the subject due to said placement of the HKS assembly at the upper trunk of the subject to yield a posture for a range of human activities in the given environment and time;

processing the acceleration data in the low G acceleration to;

recognize an activity of the subject,

determine a phase, a state of the phase, levels of file activity over time, thresholds and controlled parameters range for the subject and the given environment and time,

yield movement level, energy level and critical level threshold, and

control parameters range for the subject and the given environment and time; and

processing the acceleration data in the high G acceleration and low G acceleration into data identifying a fall event and determining the severity of the fall event based on at least one of said thresholds or said controlled parameters.

2. The method of claim 1, further comprising remotely monitoring the HKS assembly worn by the subject under a wireless sensor area network (WISAN) to detect emergency situations that require support for the subject.

3. The method of claim 1, further comprising at least one sensing assembly in the environment of the subject for sensing at least one parameter of the environment, said parameter comprising, presence of the subject in a zone covered by a wireless sensor network area (WISAN), said at least one sensing assembly being integrated in a communication base that manages the WISAN and links to an external network and a server.

4. The method of claim 1, wherein the HKS assembly is placed at the base of the back of the neck of the subject.

5. The method of claim 1, littler comprising combining measurements and analysis of other sensors worn by the subject to the measured acceleration data to perform activity profiling, efficient positioning and allowance level for individual characteristics and locations.

6. The method of claim 1, further comprising determining spatial displacements and variations of position of the upper trunk of the subject based on the processed acceleration data measured by said sensing unit in the low G acceleration to yield orientation of the upper body of the subject in space.

7. The method of claim 1, wherein the HKS assembly further includes a wearing sensor for confirming the subject is wearing the HKS assembly.

8. The method of claim 1, further comprising monitoring a usage of the HKS assembly over time or reminding the subject to wear the HKS assembly.

9. The method of claim 1, farther comprising

positioning a wrist sensor at an arm of the subject, said wrist sensor being configured for sensing the low G acceleration at the low frequency sampling range and a high G acceleration at the high frequency sampling range of the arm of the subject to assess an activity level of the subject, said arm being preferentially the writing arm or the subject.

10. The method of claim 9, further comprising measuring and processing the low G acceleration and the high G acceleration to determine a velocity, movement and position in space of the arm.

11. The method of claim 10, further comprising using the wrist sensor in combination with the HKS assembly for activity assessment and recognition and to yield the phase, the state of the phase and the levels of activity over time of the subject for the given environment and time.

12. The method of claim 1, further comprising defining and characterizing activity levels using the processed acceleration data and indicators (NE, NM, INC) from of each part of the body of the subject wearing a sensor unit body posture, and a change in a position of the subject in the environment over time.

13. The method of claim 1, further comprising determining a natural posture of the subject by correcting the processed acceleration data for the subject at rest with an offset correcting internal errors of the sensing unit and a positioning of the sensing unit on the body of the subject.

14. The method of claim 1, further comprising determining whether the subject is lying on the floor, lying on a bed, seated, kneeling down, or standing up to assess the levels of activity of the subject or identify and yield a severity indicator for the subject.

15. The method of claim 1, further comprising using an on-bed presence detector to manage allowance and threshold of critical level for lying posture of the subject in the given environment and time.

16. The method of claim 12, further comprising:

determining spatial displacement and variations of a position of the upper trunk of the subject based on the processed acceleration data measured by said sensing unit in the low G acceleration to yield a movement level indicator (NM) of the subject; and

determining movement intensity of the subject over a period time based on the processed acceleration data measured by said sensing unit in the low G acceleration and the high G acceleration to yield an energy level indicator (NE) of the subject.

17. The method of claim 1, further comprising, defining a gain (KM) for a movement level and a gain (KE) for the energy level of the subject, said KM and KE being used as weighting factors to adjust indicator values to critical levels for characteristics of the subject and the given environment and time.

18. The method of claim 1, further comprising identifying the fall event of the subject by measuring a gradient and amplitude of shock waves based on the processed acceleration data measured by said sensing unit in comparison to an adjustable threshold.

19. The method of claim 1, further comprising determining the severity of the fall event as a fall indicator, said fall indicator using the sum of values of amplitudes measured during the fall event assessing impacts and indicating a severity value that assesses the fall event.

20. The method of claim 1, further correlating a heartbeat, a respiration rate and an upper body movement of the subject to the processed acceleration data to assess activity levels and critical states corresponding to a problem or activity levels indicating a potentially deficient well-being or normal sate of the subject.

21. The method of claim 1, further comprising determining a critical level for an awareness phase of the subject in cross correlation with heartbeats and a respiration rate of the subject to differentiate a normal state of the subject from a critical state, the awareness phase comprising:

a null phase indicating no heartbeat and no respiration;

an apnea phase indicating heartbeats and no respiration;

a coma phase indicating hearthbeats and respirations but posture and movement levels incoherent for the given environment and time;

rest phase;

faintness phase;

low to high level of activity; and

hyperactivity.

22. A method for monitoring sleep activity of a subject, comprising

measuring acceleration data from at least one kinetic sensor being worn by the subject and a sleep sensor located where the subject is sleeping to yield movement levels of the subject, said kinetic sensor comprising at least one of:

a sensing unit configured for sensing acceleration data comprising a low G acceleration at a low frequency sampling range and a high G acceleration at a high frequency sampling range, said acceleration data being correlated to the spine of the subject due to a placement of the sensing unit at the upper trunk of the subject to yield behaviour indicators and threshold levels associated with characteristics the subject and an activity nature, state and level for a given environment and time, and

a wrist sensor located at an arm of the subject, said wrist sensor being configured for sensing acceleration data comprising the low G acceleration at the low frequency sampling range and the high G acceleration at the high frequency sampling range of the arm of the subject to assess an activity level of the subject.