Method and system for fall detection and motion analysis

• US 20060282021A1
• Filed: 03/09/2006
• Published: 12/14/2006
• Est. Priority Date: 05/03/2005
• Status: Abandoned Application

• Current Assignee: Aware Technologies, Inc. (Idhasoft Limited)
• Original Assignee: Aware Technologies, Inc. (Idhasoft Limited)
• Inventors: Elledge, Christopher, DeVaul, Richard W., Barkalow, Daniel, Carlton-Foss, John
• Application Number:
  US11/372,843
• Publication Number:
  US 20060282021A1
• Time in Patent Office: Days
• US Class Current: 600/595
• CPC Class Codes: A61B 2560/0209 adapted for power saving
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/002 Monitoring the patient using a local or closed circuit, e.g. in a room or building A61B5/0017 takes precedence
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/0024 for multiple sensor units attached to the patient, e.g. using a body or personal area network
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/1112 Global tracking of patients, e.g. by using GPS
• CPC Class Codes: A61B 5/1117 Fall detection
• CPC Class Codes: A61B 5/1135 by monitoring thoracic expansion
• CPC Class Codes: A61B 5/411 Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
• CPC Class Codes: A61B 5/6804 Garments; Clothes
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule
• CPC Class Codes: G08B 21/043 detecting an emergency event, e.g. a fall
• CPC Class Codes: G08B 21/0446 worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait
• CPC Class Codes: G08B 25/009 Signalling of the alarm condition to a substation whose identity is signalled to a central station, e.g. relaying alarm signals in order to extend communication range
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A motion analysis telemonitor system includes a wearable monitoring device that monitors the activity level and movements of a person wearing the device. The wearable monitoring device is able to determine whether the person has fallen through a model analysis technique using characteristic movements of a fall. The wearable device generally transmits data and alerts over a short distance to a console. The console, in turn, transmits data and alerts to a monitoring center. The motion analysis telemonitor system is also able to monitor progression of disease through changes in movement, also fatigue and other performance factors.

Claims

1. A wearable device for a remote monitoring system, the wearable device positioned on the body of a person, comprising:

a data receiver to receive sensor data transmitted from at least one sensor positioned on the person;

an analysis device to take the sensor data as input, the analysis device to analyze the sensor data and to generate a report; and

a transmitter to transmit the report to an external device.

2. The wearable device of claim 1 wherein the analysis device further comprises at least one stored model of movement characteristic of a particular condition, the analysis device to use the at least one stored model to analyze the sensor data.

3. The wearable device of claim 2 wherein one of the at least one stored models holds data characteristic of a fall.

4. The wearable device of claim 2 wherein the analysis device provides an indicator of how closely the sensor data matches data of the at least one stored model.

5. The wearable device of claim 4 wherein the analysis device uses Bayesian classification to determine how closely the sensor data matches data of the at least one stored model.

6. The wearable device of claim 1 wherein the at least one sensor comprises an accelerometer.

7. The wearable device of claim 6 wherein the at least one sensor further comprises an impact detector.

8. The wearable device of claim 1 further comprising a data diary for retaining collected data for monitoring the wearer of the wearable device over a period of time.

9. The wearable device of claim 1 further comprising a data diary for retaining classifications of collected data for monitoring the wearer of the wearable device over a period of time.

10. The wearable device of claim 8 wherein the collected data is raw data from the at least one sensor.

11. The wearable device of claim 8 wherein the collected data is analyzed data from the analysis device.

12. A wearable device for a remote monitoring system, the wearable device positioned on the body of a person, comprising:

a data receiver to receive data from at least one sensor positioned on the person;

an analysis device to take the data as input, the analysis device including a stored model of fall characteristics, the analysis device to analyze the received data using the stored model to determine if the person has had a fall; and

a transmitter to transmit a fall report to an external device.

13. The wearable of claim 12 wherein the analysis device further includes a data classifier, the analysis device to use that data classifier to analyze the received data with regard to the stored model.

14. The wearable of claim 13 wherein the model is organized into data classes and the data classifier determines whether a fall has taken place by determining the data class of the received data.

15. The wearable device of claim 12 wherein the wearable device calculates features from the data stream and applies Bayesian statistics to determine a match to the stored models.

16. A method for sensing whether a person has fallen, comprising the steps of:

receiving data from a sensor located on the body of the person;

analyzing the data using a stored model having at least one data pattern characteristic of a fall; and

generating a fall report in response to the analyzing step.

17. The method of claim 16 further comprising the step of transmitting the fall report to an external device.

18. The method of claim 16 wherein the receiving step further comprises receiving data from a plurality of sensors located on the body of the person.

19. The method of claim 16 further comprising the step of transforming the data received from the sensor to obtain features indicating a particular condition of the person.

20. The method of claim 19 wherein the particular condition is a fall.

21. The method of claim 19 wherein the step of analyzing further comprises analyzing the transformed data using the stored model.

22. The method of claim 16 further comprising the steps of:

retrieving at least one data match between the data from the sensor and the model; and

determining a degree of matching for the at least one data match.

23. A fall detection system, comprising:

a wearable device having at least one sensor and at least one stored data model, the wearable device able to detect through analysis of sensor data with regard to the at least one stored data model whether a wearer of the wearable device has fallen, the wearable device further having a transmitter to transmit a report of a condition of the wearer; and

a console wherein the console has a receiver to receive a report from the wearable device, the console to transmit an alert to a monitoring center in response to the report.

24. The fall detection system of claim 23 wherein the transmitter in the wearable device is a short-range transmitter.

25. The fall detection system of claim 23 further comprising a wireless local area network and wherein the wearable device transmits the report to the console over the wireless local area network.

26. The fall detection system of claim 23 wherein the console includes a mobile power source whereby the fall detection system is usable away from a fixed location.

27. The fall detection system of claim 26 wherein the console is a cellular telephone.

28. The fall detection system of claim 26 wherein the console further comprises a locator device.

29. The fall detection system of claim 26 wherein the wearable device further comprises a locator device.