Signal-embedded signatures

• US 9,690,904 B1
• Filed: 02/02/2015
• Issued: 06/27/2017
• Est. Priority Date: 09/09/2013
• Status: Active Grant

• Current Assignee: Healthy.io, Ltd.
• Original Assignee: Scanadu Incorporated
• Inventors: Zizi, Martin
• Primary Examiner(s): Schaetzle, Kennedy
• Application Number:
  US14/612,287
• Time in Patent Office: 876 Days
• Field of Search: None
• 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 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/6898 Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/44 Program or device authentication
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: H04B 15/005 Reducing noise, e.g. humm, from the supply

Abstract

In accordance with one embodiment, a method for a health scanning system is disclosed. The method includes receiving at least one electrical physiological data signal (PDS); suppressing a Direct Current (DC) signal component of the PDS to emphasize the Alternating Current (AC) signal component of the PDS; isolating the signal noise in the AC signal component of the PDS; and extracting a noise signature from the signal noise in the PDS. The noise signature, after calibration, can be used to uniquely identify a known user from other users.

Claims

1. A method for a health scanning system, the method comprising:

receiving an initial physiological data stream for a known user;

calibrating a scanner to the known user to obtain a calibrated noise signature for the initial physiological data stream of the known user;

storing the calibrated noise signature for the known user into a noise signature database associated with profile information for the known user;

receiving a subsequent physiological data stream from an unknown user;

extracting a noise signature from the subsequent physiological data stream for the unknown user; and

comparing the extracted noise signature with the calibrated noise signature in the noise signature database to determine a match or no match;

wherein a match is determined for the unknown user to validate as the known user and the method further includes

extracting the profile information from the noise signature database for the known user;

allowing the unknown user to access user medical records associated with the known user; and

appending the profile information to the subsequent physiological data stream to store as a part of the user medical records associated with the known user.

2. The method of claim 1, wherein the profile includes at least one of:

a name;

an address;

a phone number;

an account number;

or

a social security number.

3. The method of claim 1, where no match is determined and the method further comprises:

determining the unknown user did not complete a calibration of the scanner; and

calibrating the scanner for the unknown user.

4. The method of claim 1, wherein no match is determined and the method further comprises:

determining the unknown user completed a calibration of the scanner; and

repeating the following steps one or more times to determine if a match can be made;

the receiving of a subsequent physiological data stream,

the extracting of a noise signature, and

the comparing of the extracted noise signature.

5. The method of claim 1, wherein no match is determined and the method further comprises:

indicating an error; and

rejecting the unknown user.

6. The method of claim 1, wherein

the calibrated noise signature is due to molecular variations in the known user, and

the known user is a human being.

7. The method of claim 1, wherein a match is determined and the method further comprises:

allowing access to at least one of a secured system, a secured device, or a secured database.

8. The method of claim 1, further comprising:

suppressing a direct current (DC) signal component of the physiological data stream to emphasize an alternating current (AC) signal component of the physiological data stream;

isolating a signal noise in the AC signal component of the physiological data stream; and

extracting a noise signature from the signal noise to form the calibrated noise signature.

9. The method of claim 1, further comprising:

generating physiological information in response to the physiological data stream; and

associating the physiological information with the calibrated noise signature.