Spectral autocorrelation based security system

Patent metadata

Field	Value
Publication number	US-12148276-B2
Application number	US-202217840662-A
Country	US
Kind code	B2
Filing date	Jun 15, 2022
Priority date	Jun 15, 2022
Publication date	Nov 19, 2024
Grant date	Nov 19, 2024

Abstract

According to one embodiment of the present invention, a computer-implemented method for autocorrelation based security monitoring and detection is disclosed. The computer-implemented method includes determining that input signal data transmitted to a white noise generator autocorrelates with itself at one or more time lags. The computer-implemented method further includes, responsive to determining that the input signal data transmitted to the white noise generator autocorrelates with itself at one or more time lags, determining whether an autocorrelation in the input signal data transmitted to the white noise generator matches one or more predetermined input signal data patterns associated with a known event or individual.

First claim

What is claimed is:

1. A computer-implemented method for autocorrelation based security monitoring and detection, comprising:
determining that input signal data transmitted to a white noise generator for generating white noise autocorrelates with itself at one or more time lags; and
responsive to determining that the input signal data transmitted to the white noise generator for generating white noise autocorrelates with itself at one or more time lags:
determining whether an autocorrelation in the input signal data transmitted to the white noise generator for generating white noise matches one or more predetermined input signal data patterns associated with a known event or individual.

2. The computer-implemented method of claim 1 , further comprising:
determining that the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise does not match a predetermined input signal data pattern associated with a known event or individual; and
performing a particular type of security action based, at least in part, on an input power and input frequency spectrum associated with the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise.

3. The computer-implemented method of claim 1 , further comprising:
determining that the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise matches a predetermined input signal data pattern associated with a known event;
determining whether the known event is permitted; and
responsive to determining that the known event is not permitted, performing a particular type of security action based, at least in part, on the known event.

4. The computer-implemented method of claim 3 , wherein determining whether the known event is permitted is based, at least in part, on comparing an input power and input frequency spectrum associated with the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise to a historical input power and input frequency spectrum transmitted to the white noise generator for generating white noise at a time the autocorrelation in the input signal data is detected.

5. The computer-implemented method of claim 1 , further comprising:
determining that the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise matches a predetermined input signal data pattern associated with a known individual;
determining that the known individual is located within a secure environment; and
responsive to determining that the known individual is not authorized to enter the secure environment, performing a particular type of security action.

6. The computer-implemented method of claim 1 , further comprising:
determining that the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise matches a predetermined input signal data pattern associated with a known individual; and
tracking a location of the known individual within an environment based, at least in part, on detected changes in input power with respect to the autocorrelation in the input signal data over the one or more time lags.

7. The computer-implemented method of claim 1 , wherein a predetermined input signal data pattern associated with a known individual corresponds to an input power and input frequency spectrum previously transmitted to the white noise generator for generating white noise in response to noise captured from one or more of a cadence, stride, or gait of the known individual.

8. A computer program product for autocorrelation based security monitoring and detection, comprising, the computer program product including one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions including instructions to:
determine that input signal data transmitted to a white noise generator for generating white noise autocorrelates with itself at one or more time lags; and
responsive to determining that the input signal data transmitted to the white noise generator for generating white noise autocorrelates with itself at one or more time lags:
determine whether an autocorrelation in the input signal data transmitted to the white noise generator for generating white noise matches one or more predetermined input signal data patterns associated with a known event or individual.

9. The computer program product of claim 8 , further comprising instructions to:
determine that the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise does not match a predetermined input signal data pattern associated with a known event or individual; and
perform a particular type of security action based, at least in part, on an input power and input frequency spectrum associated with the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise.

10. The computer program product of claim 8 , further comprising instructions to:
determine that the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise matches a predetermined input signal data pattern associated with a known event;
determine whether the known event is permitted; and
responsive to determining that the known event is not permitted, perform a particular type of security action based, at least in part, on the known event.

11. The computer program product of claim 10 , wherein determining whether the known event is permitted is based, at least in part, on comparing input power and input frequency spectrum associated with the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise to a historical input power and input frequency spectrum transmitted to the white noise generator for generating white noise at a time the autocorrelation in the input signal data is detected.

12. The computer program product of claim 8 , further comprising instructions to:
determine that the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise matches a predetermined input signal data pattern associated with a known individual;
determine that the known individual is located within a secure environment; and
responsive to determining that the known individual is not authorized to enter the secure environment, perform a particular type of security action.

13. The computer program product of claim 8 , further comprising instructions to:
determine that the autocorrelation in the input signal data transmitted to the white noise generator for generating white noise matches a predetermined input signal data pattern associated with a known individual; and
track a location of the known individual within an environment based, at least in part, on detected changes in input power with respect to the autocorrelation in the input signal data over the one or more time lags.

14. The computer program product of claim 8 , wherein a predetermined input signal data pattern associated with a known individual corresponds to an input power and input frequency spectrum previously transmitted to the white noise generator for generating white noise in response to noise captured from one or more of a cadence, stride, or gait of the known individual.

15. A computer system for autocorrelation based security monitoring and detection, comprising, comprising:
one

Assignees

• IBM

Inventors

• Doyle Matthew
• Judd Jeffrey N
• Tofil Timothy J
• Cocchini Matteo
• Benefield Stuart Brett
• Connor Samuel R
• Corbett Andrew

Classifications

• G06F18/2113

  by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation · CPC title

• G08B13/1672 Primary

  using sonic detecting means, e.g. a microphone operating in the audio frequency range · CPC title

• G06F18/00 Primary

  Pattern recognition · CPC title