Method and system for real-time signal classification

• US 7,827,011 B2
• Filed: 11/21/2007
• Issued: 11/02/2010
• Est. Priority Date: 05/03/2005
• Status: Expired due to Fees

• Current Assignee: Aware Incorporated (Crowley Holdings Preferred LLC)
• Original Assignee: Aware Incorporated (Crowley Holdings Preferred LLC)
• Inventors: Elledge, Christopher, DeVaul, Richard W., Barkalow, Daniel
• Primary Examiner(s): Feliciano; Eliseo Ramos
• Assistant Examiner(s): O MALLEY, MARY CATHERINE
• Application Number:
  US11/986,528
• Publication Number:
  US 20080162088A1
• Time in Patent Office: 1,077 Days
• Field of Search: 702 75- 76, 702/79, 702189-190, 703/11, 703/19, 600300-301
• US Class Current: 702/190
• CPC Class Codes: A61B 2560/0209 adapted for power saving
• 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 5/02438 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 5/4082 Diagnosing or monitoring movement diseases, e.g. Parkinson, Huntington or Tourette
• CPC Class Codes: A61B 5/411 Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
• CPC Class Codes: A61B 5/6831 Straps, bands or harnesses
• 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 5/747 in case of emergency, i.e. alerting emergency services
• CPC Class Codes: G01R 29/00 Arrangements for measuring or indicating electric quantities not covered by groups G01R19/00 - G01R27/00
• CPC Class Codes: G06F 17/16 Matrix or vector computation , e.g. matrix-matrix or matrix-vector multiplication, matrix factorization matrix transposition G06F7/78
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method to achieve an accurate, extremely low power state classification implementation is disclosed. Embodiments include a sequence that matches the data flow from the sensor transducer, through analog filtering, to digital sampling, feature computation, and classification.

Claims

1. A method for real-time signal classification, the method to be executable on a low-power processor, the method comprising:

providing a managed bandwidth signal from an accelerometer sensor;

establishing, by a processor, a time bound for executing steps in the method;

windowing, by the processor, within the time bound, the managed bandwidth signal to produce an acceleration vector based on an acceleration model;

performing, by the processor, within the time bound, feature computation using fixed point arithmetic on the vector to produce a model-compatible acceleration vector based on the acceleration model;

projecting, by the processor, within the time bound, the model-compatible acceleration vector having a first multi-dimensional factor space onto a second multi-dimensional factor space where the second multi-dimensional factor space is smaller than the first multi-dimensional factor space to produce a lower dimensional factor vector; and

evaluating, by the processor, within the time bound and using log representations, the lower dimensional factor vector against the acceleration model to produce a classification result.

2. The method of claim 1 wherein the step of providing a managed bandwidth signal further comprises:

receiving, by the processor, a signal from an analog acceleration sensor; and

filtering, by the processor, the signal to place a limit on the frequency of the signal.

3. The method of claim 2 wherein the filtering step further comprises shifting, by the processor, a center point of the signal.

4. The method of claim 2 wherein the filtering step further comprises scaling, by the processor, the amplitude of the signal.

5. The method of claim 1 wherein the step of providing a managed bandwidth signal further comprises:

receiving, by the processor, a data from a digital acceleration sensor; and

filtering, by the processor, the data to produce the managed bandwidth signal.

6. The method of claim 1 wherein the windowing step further comprises grouping, by the processor, a sequence of samples to form an acceleration vector that represents dynamic motion behavior of the signal over time.

7. The method of claim 1 wherein the step of performing feature computation further comprises transforming, by the processor, the acceleration vector from a time domain to a frequency domain.

8. The method of claim 1 wherein the step of performing feature computation further comprises digitally filtering, by the processor, the acceleration vector.

9. The method of claim 1, wherein projecting within the time bound, the model-compatible acceleration vector further comprising projecting, by the processor, within the time bound, the model-compatible acceleration vector having the first multi-dimensional factor space onto the second multi-dimensional factor space based on a lowest sampling resolution for the acceleration model, where the second multi-dimensional factor space is smaller than the first multi-dimensional factor space to produce a lower dimensional factor vector.

10. A system for real-time signal classification, the system having a lower power processor, the system comprising:

means for providing a managed bandwidth signal from an accelerometer sensor;

means for establishing a time bound for execution of classification processing in the system;

means for windowing, within the time bound, the managed bandwidth signal to produce an acceleration vector based on an acceleration model;

means for performing, within the time bound, feature computation using fixed point arithmetic on the acceleration vector to produce a model-compatible acceleration vector based on the acceleration model;

means for projecting, within the time bound, the model-compatible acceleration vector having a first multi-dimensional factor space onto a second multi-dimensional factor space where the second multi-dimensional factor space is smaller than the first multi-dimensional factor space to produce a lower dimensional factor vector; and

means for evaluating, within the time bound and using log representations, the lower dimensional factor vector against the acceleration model to produce a classification result.

11. The system of claim 10 wherein the means for providing a managed bandwidth signal further comprises:

means for receiving a signal from an analog acceleration sensor; and

means for filtering the signal to place a limit on the frequency of the signal.

12. The system of claim 11 wherein the means for filtering further comprises means for shifting a center point of the signal.

13. The system of claim 11 wherein the means for filtering further comprises means for scaling the amplitude of the signal.

14. The system of claim 10 wherein the means for providing a managed bandwidth signal further comprises:

means for receiving data from a digital acceleration sensor; and

means for filtering the data to produce the managed bandwidth signal.

15. The system of claim 10 wherein the means for windowing further comprises means for grouping a sequence of samples to form an acceleration vector that represents dynamic motion behavior of the signal over time.

16. The system of claim 10 wherein the means for performing feature computation further comprises means for transforming the acceleration vector from a time domain to a frequency domain.

17. The system of claim 10 wherein the means for performing feature computation further comprises means for digitally filtering the vector.

18. The system of claim 10 wherein the means for performing feature computation further comprises means for computing time derivatives of the acceleration vector.

19. The system of claim 10 wherein the means for performing feature computation further comprises

means for performing vector additions, vector products, and vector scaling operations, and

means for computing vector magnitudes.

20. The system of claim 10, wherein the classification result is indicative of a motion of a person.