Method and apparatus for detection and prediction of events based on changes in behavior

• US 9,710,761 B2
• Filed: 03/15/2013
• Issued: 07/18/2017
• Est. Priority Date: 03/15/2013
• Status: Expired due to Fees

• Current Assignee: Nordic Technology Group Incorporated
• Original Assignee: Nordic Technology Group Incorporated
• Inventors: Wernevi, Erik, Apsell, Sheldon
• Primary Examiner(s): CHANG, LI WU
• Application Number:
  US13/840,155
• Publication Number:
  US 20140279740A1
• Time in Patent Office: 1,586 Days
• Field of Search: None
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A computer-implemented process for detecting and predicting events occurring to a person, includes: observing, using a sensor, a reading of a parameter of a body part of the person which is one of: horizontal location, vertical height, orientation, velocity, and time of observation, wherein the reading corresponds to less information than needed to define the person'"'"'s posture; receiving the reading into a computer memory; determining from the received reading a pattern of behavior; detecting a change in behavior; identifying from the change in behavior a combination of one or more readings corresponding to an abnormal event; and producing an alert signal when the combination of one or more readings corresponding to the abnormal event is identified. The process may be practiced using a computing machine including a computer memory; a sensor; and a computer processor.

Claims

1. A computer-implemented process for detecting and predicting events occurring to a person, comprising the steps of:

receiving a first plurality of readings for location, orientation, velocity, and time of observation of a body part;

applying a first statistical test to earliest readings in the first plurality of readings;

applying the first statistical test to all later readings in the first plurality of readings;

identifying at least one first cluster of n-dimensional behavior vectors as normal behavior from the earliest readings in the first plurality of readings, or in the earliest and in later readings in the first plurality of readings, or all of the first plurality of readings;

collecting a second plurality of readings for location, orientation, velocity, and time of observation of the body part;

constructing at least one second cluster of n-dimensional behavior vectors by applying the at least one first statistical test to the second plurality of readings;

applying a second statistical test to determine if a deviation exists between the first plurality of readings and the second plurality of readings;

determining whether an abnormal behavior exists with respect to at least one of the at least two parameters from the at least one first cluster of n-dimensional behavior vectors and the at least one second cluster of n-dimensional behavior vectors; and

adding at least one reading making up the at least one second cluster of n-dimensional behavior vectors in chronological order to the latest reading making up the at least one first cluster of n-dimensional behavior vectors to thereby form the at least one first cluster of n-dimensional behavior vectors identified as normal behavior prior to collecting a new second plurality of readings.

2. The computer-implemented process of claim 1, wherein the step of determining further comprises identifying a future abnormal behavior likely to occur.

3. The computer-implemented process of claim 1, wherein the step of observing further comprises:

sensing the parameter with respect to the person'"'"'s head.

4. The computer-implemented process of claim 1, wherein the step of observing further comprises:

sensing the parameter with respect to the person'"'"'s torso.

5. The computer-implemented process of claim 1, wherein the step of observing further comprises:

sensing the parameter with respect to one of the person'"'"'s limbs.

6. The computer-implemented process of claim 1, wherein the step of observing further comprises:

sensing the parameter with respect to a combination of two or more of the person'"'"'s head, the person'"'"'s torso, and one of the person'"'"'s limbs, wherein the combination is less than needed to define the person'"'"'s posture.

7. The computer-implemented process of claim 1, wherein the step of determining further comprises:

identifying the combination of one or more readings corresponding to the abnormal behavior when at least one other body part is obscured from the sensor.

8. The computer-implemented process of claim 3, wherein the step of determining further comprises:

identifying the combination of one or more readings corresponding to the abnormal behavior when at least one other body part is obscured from the sensor.

9. The computer-implemented process of claim 4, wherein the step of determining further comprises:

identifying the combination of one or more readings corresponding to the abnormal behavior when at least one other body part is obscured from the sensor.

10. The computer-implemented process of claim 5, wherein the step of determining further comprises:

identifying the combination of one or more readings corresponding to the abnormal behavior when at least one other body part is obscured from the sensor.

11. The computer-implemented process of claim 6, wherein the step of determining further comprises:

identifying the combination of one or more readings corresponding to the abnormal behavior when at least one other body part is obscured from the sensor.

12. The computer-implemented process of claim 1, further comprising:

computing velocity from a sequence of the readings.

13. The computer-implemented process of claim 1, further comprising:

identifying a combination of readings corresponding to a normal event.

14. The computer-implemented process of claim 13, wherein the step of identifying a pattern for normal behavior further comprises:

identifying a combination of readings representing an activity of daily living.

15. The computer-implemented process of claim 13, further comprising:

learning to differentiate between the normal event and the abnormal behavior by applying a statistical test to the sequence of readings.

16. The computer-implemented process of claim 15, wherein the statistical test is correlation.

17. The computer-implemented process of claim 1, wherein the step of observing further comprises:

sensing an output of a wearable sensor.

18. The computer-implemented process of claim 1, wherein the step of observing further comprises:

sensing an output of one of;

a visual camera and an infrared camera.

19. The computer-implemented process of claim 1, wherein the step of observing further comprises:

sensing an output of a radio-wave measuring device.

20. The computer-implemented process of claim 1, wherein the step of observing further comprises:

sensing an output of a light-wave measuring device.

21. The computer-implemented process of claim 1, further comprising:

computing horizontal location from a sequence of the readings.

22. The computer-implemented process of claim 1, further comprising:

computing vertical height from a sequence of the readings.

23. The computer-implemented process of claim 1, further comprising:

computing orientation from a sequence of the readings.

24. The computer-implemented process of claim 2, wherein the step of determining further comprises:

identifying the combination of one or more readings corresponding to the abnormal behavior when at least one other body part is obscured from the sensor.