Methods for using a biometric parameter in the identification of persons

• US 8,065,529 B2
• Filed: 05/21/2007
• Issued: 11/22/2011
• Est. Priority Date: 05/21/2007
• Status: Active Grant

• Current Assignee: UT-Battelle LLC
• Original Assignee: UT-Battelle LLC
• Inventors: Hively, Lee M.
• Primary Examiner(s): ZIA, SYED
• Application Number:
  US11/804,966
• Publication Number:
  US 20080294907A1
• Time in Patent Office: 1,646 Days
• Field of Search: None
• US Class Current: 713/186
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/6814 Head

Abstract

Brain waves are used as a biometric parameter to provide for authentication and identification of personnel. The brain waves are sampled using EEG equipment and are processed using phase-space distribution functions to compare digital signature data from enrollment of authorized individuals to data taken from a test subject to determine if the data from the test subject matches the signature data to a degree to support positive identification.

Claims

1. A method for processing data to provide positive identification of a person, comprising:

acquiring a plurality of sets of data for at least one channel of human brain wave data from at least one first person for the purpose of providing an enrollment signature;

acquiring a plurality of sets of data for at least one channel of human brain wave data from at least one second person for the purpose of providing a test signature;

computing at least one measure of dissimilarity between the enrollment signature and the test signature for distribution functions derived from at least one of a connected phase space and a non-connected phase space;

comparing said measure of dissimilarity to a threshold in which exceeding the threshold results in non-confirmation of an identity of the second person being also an identity of the first person and in which not exceeding the threshold results in confirmation of the identity of the second person being also the identity of the first person; and

signaling an observer that the second person'"'"'s identity has either been confirmed or not confirmed.

2. The method of claim 1, further comprising:

determining true positive indications for confirming the second person'"'"'s identity for each channel of data in the plurality of sets of data;

calculating a true positive indication rate for confirming the second person'"'"'s identity for each channel of data; and

comparing true positive indication rates for respective channels to determine at least one channel with a greatest channel-consistent total-true rate in said at least one channel.

3. The method of claim 1, further comprising:

determining true negative indications for not confirming the second person'"'"'s identity for each channel of data in the plurality of sets of data;

calculating a true negative indication rate for not confirming the second person'"'"'s identity for each channel of data; and

comparing true negative indication rates for respective channels to determine at least one channel with a greatest channel-consistent true negative indication rate in said at least one channel.

4. The method of claim 1, wherein the second person is a live and present human being.

5. The method of claim 1, wherein the brain wave data comprises at least one channel of EEG data that is analyzed to create the enrollment signature of the first person and at least one channel of EEG data that is analyzed to represent the second person.

6. The method of claim 1, further comprising filtering out confounding artifact data from the plurality of sets of data before computing the connected phase space for the channel data.

7. A method for new use of brain wave data, the method comprising:

computing a measure of dissimilarity for at least one distribution function derived from at least one of a connected phase space and a non-connected phase space for brain wave data providing an enrollment signature for a known human person and for brain wave data providing a test signature from a test human person;

comparing said measure of dissimilarity to a threshold in which exceeding the threshold results in non-confirmation of a test human person'"'"'s identity being that of the known human person and in which not exceeding the threshold results in confirmation of the test human person'"'"'s identity being that of the known human person; and

signaling an observer that the test subject'"'"'s identity has either been confirmed or not confirmed.

8. The method of claim 7, further comprising:

determining true positive indications of condition change for confirming the test human person'"'"'s identity for each channel of data in a plurality of sets of data;

calculating a true positive indication rate for confirming the test human person'"'"'s identity for each channel of data; and

comparing true positive indication rates for respective channels to determine at least one channel with a greatest channel-consistent true rate in said at least one channel.

9. The method of claim 7, further comprising:

determining true negative indications of condition change for not confirming the test human person'"'"'s identity for each channel of data in the plurality of sets of data;

calculating a true negative indication rate for not confirming the test human person'"'"'s identity for each channel of data; and

comparing true negative indication rates for respective channels to determine at least one channel with a greatest channel-consistent true negative indication rate in said at least one channel.

10. The method of claim 7, wherein the test human person is provided by a live and present human being.

11. The method of claim 7, wherein the brain wave data comprises at least one channel of EEG data that is analyzed to create the enrollment signature for the known human person and at least one channel of data that is analyzed to represent the test human person.

12. The method of claim 7, further comprising

acquiring a plurality of sets of data for at least one channel of human brain wave from at least one known human person for a purpose of providing the enrollment signature for the known human person;

acquiring a plurality of sets of data for at least one channel of human brain wave data from at least one test human person for a purpose of providing the test signature.

13. The method of claim 7, further comprising filtering out confounding artifact data from the brain wave data.