Identification by analysis of physiometric variation

• US 6,993,378 B2
• Filed: 06/25/2002
• Issued: 01/31/2006
• Est. Priority Date: 06/25/2001
• Status: Active Grant

• Current Assignee: Leidos, Inc. (Leidos Holdings, Inc.)
• Original Assignee: Science Applications International Corporation
• Inventors: Meyer, Rodney P., Wiederhold, Mark D., Irvine, John M., Israel, Steven A.
• Primary Examiner(s): Getzow, Scott M.
• Application Number:
  US10/178,839
• Publication Number:
  US 20030135097A1
• Time in Patent Office: 1,316 Days
• Field of Search: 600/508, 600/509, 600/529, 600/532, 382/115
• US Class Current: 600/509
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/1102 Ballistocardiography
• CPC Class Codes: A61B 5/117 Identification of persons methods or arrangements for recognising patterns, e.g. fingerprints, G06F18/00, G06V40/00; identification of persons by analysing their voice or speech G10L17/00
• CPC Class Codes: A61B 5/1455 using optical sensors, e.g. spectral photometrical oximeters
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 7/00 Instruments for auscultation
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/15 Biometric patterns based on physiological signals, e.g. heartbeat, blood flow

Abstract

Methods involving extraction of information from the inherent variability of physiometrics, including data on cardiovascular and pulmonary functions such as heart rate variability, characteristics of ECG traces, pulse, oxygenation of subcutaneous blood, respiration rate, temperature or CO₂ content of exhaled air, heart sounds, and body resonance, can be used to identify individual subjects, particularly humans. Biometric data for use in the methods can be obtained either from contact sensors or at a distance. The methods can be performed alone or can be fused with previous identification algorithms.

Claims

1. A method of identifying a subject, comprising steps of:

(a) comparing a first and a second set of biometric parameters extracted from a heart rate variability measurement, wherein

(1) the first set of biometric parameters is associated with a first subject, and

(2) the second set of biometric parameters is associated with a second subject; and

(b) identifying the first subject as the second subject if the first set and second set correlate, and identifying the first subject as different from the second subject if the first and second sets do not correlate.

2. The method of claim 1 further comprising the step of analyzing the heart rate variability measurement of the first subject to extract the first set of biometric parameters.

3. The method of claim 2 further comprising the step of acquiring the heart rate variability measurement from the first subject.

4. The method of claim 1 wherein the first set of biometric parameters is compared to a plurality of second sets of biometric parameters, wherein individual members of the plurality are each associated with a different, third subject.

5. The method of claim 1 further comprising applying a low pass filter to the heart rate variability measurement.

6. The method of claim 5 wherein the low pass filter is a 40 Hz low pass filter.

7. The method of claim 1 wherein the heart rate variability is measured using a standoff measuring technique.

8. A method of compiling a database comprising sets of biometric parameters each associated with an individual subject, comprising steps of:

(a) acquiring heart rate variability measurements from a plurality of individual subjects;

(b) analyzing the heart rate variability measurements to extract sets of biometric parameters, wherein each set of biometric parameters is associated with an individual subject; and

(c) compiling the sets of biometric parameters into a database, wherein individual sets of biometric parameters are each correlated with the individual subjects from which the heart rate variability measurements were obtained.

9. The method of claim 8 further comprising applying a low pass filter to the heart rate variability measurements.

10. The method of claim 9 wherein the low pass filter is a 40 Hz low pass filter.

11. A method for identifying a subject according to a periodic physiological process of the subject, the method comprising steps of:

measuring the periodic physiological process for a period of time to generate biometric data, the period of time being sufficient such that the biometric data contains data corresponding to a plurality of cycles of the physiological process;

extracting a plurality of the cycles of the biometric data; and

estimating a first plurality of coefficients based on the plurality of cycles.

12. The method of claim 11, further including the step of determining a periodicity of the biometric data.

13. The method of claim 11, further including the step of normalizing the plurality of cycles, the step of estimating including estimating the plurality of coefficients based on the plurality of normalized cycles.

14. The method of claim 11, wherein the periodic physiological process is a heartbeat or pulse.

15. The method of claim 11, wherein the periodic physiological process is respiration.

16. The method of claim 11, wherein the step of estimating includes regressing the cycles on a polynomial function over time.

17. The method of claim 11, further including the step of comparing the first plurality of coefficients with a second plurality of coefficients.

18. The method of claim 11 wherein the periodic physiological process is measured using a standoff measuring technique.

19. A method for identifying a subject according to heart activity of the subject, the method comprising the steps of:

measuring the heart activity over a period of time sufficient so as to include a plurality of heartbeats to generate heart activity data;

aligning heart activity data corresponding to each of the plurality of heartbeats; and

identifying the subject according to the heart activity data.

20. The method of claim 19, further including the step of identifying at least one feature of the heart activity data, the method of identifying including identifying the subject according to the at least one feature.

21. The method of claim 19, further including the step of applying a lowpass filter to the heart activity data.

22. The method of claim 21, wherein the lowpass filter is a 40 Hz lowpass filter.

23. The method of claim 19 wherein the heart activity is measured using a standoff measuring technique.

24. A method for identifying a subject according to respiration of the subject, the method comprising steps of:

measuring the respiration to generate respiration data, wherein the respiration data includes a temperature change associated with inhalation and exhalation of the subject; and

identifying the subject based on the respiration data.

25. The method of claim 24, wherein the step of measuring includes measuring the respiration using a standoff measuring technique.

26. The method of claim 24 further comprising applying a low pass filter to the respiration data.

27. The method of claim 26 wherein the low pass filter is a 40 Hz low pass filter.

28. A method for identifying a subject according to at least one of a cardiac and a respiratory physiological process of the subject, the method comprising steps of:

measuring the physiological process to generate biometric data;

estimating a coefficient from the biometric data; and

identifying the subject according to the coefficient.

29. The method of claim 28 further comprising applying a low pass filter to the biometric data.

30. The method of claim 29 wherein the physiological process is a cardiac process and the low pass filter is a 40 Hz low pass filter.

31. The method of claim 29 wherein the physiological process is a respiratory process and the low pass filter is a 60 Hz low pass filter.

32. The method of claim 28 wherein the physiological process is measured using a standoff measuring technique.