SYSTEM AND METHOD FOR SNORE DETECTION AND CONFIRMATION

• US 20070287896A1
• Filed: 06/05/2007
• Published: 12/13/2007
• Est. Priority Date: 06/08/2006
• Status: Active Grant

• Current Assignee: Adidas AG
• Original Assignee: Adidas AG
• Inventors: Myers, Lance, Derchak, P., Lucia, Gary
• Granted Patent: US 8,177,724 B2
• Time in Patent Office: Days
• US Class Current: 600/301
• CPC Class Codes: A61B 5/1135 by monitoring thoracic expansion
• CPC Class Codes: A61B 5/4806 Sleep evaluation A61B5/4821 takes precedence; devices for inducing sleep A61M21/02
• CPC Class Codes: A61B 5/6805 Vests

Abstract

The invention provides a method for determining when a person is snoring by determining a candidate snore event by detecting the occurrence of a person'"'"'s breath, and detecting the occurrence of a sound event. The method further includes confirming that the candidate snore event is not an isolated snore event by determining that breaths immediately preceding and following the candidate snore event include other candidate snore events.

Claims

1. A method for determining when a person is snoring, the method comprising:

determining a candidate snore event, which comprises;

detecting the occurrence of a person'"'"'s breath; and

detecting the occurrence of a sound event; and

confirming that the candidate snore event is not an isolated snore event by determining that breaths immediately preceding and following the candidate snore event include other candidate snore events.

2. The method of claim 1, wherein the occurrence of a breath is detected when the person'"'"'s breath has a volume that is less than a breath threshold.

3. The method of claim 2, wherein the breath threshold is about 1.25 liters.

4. The method of claim 1, wherein detecting the occurrence of a sound event comprises measuring sound energy in the vicinity of a person'"'"'s mouth and nose to sample sound energy.

5. The method of claim 4, wherein the sampled sound energy is the mean of at least 30 sound energy samples that are sampled at frequency of about 1500 Hz.

6. The method of claim 4, wherein the occurrence of a sound event is detected when the sampled sound energy is greater than a sound event threshold and lasts longer than a sound event period.

7. The method of claim 6, wherein the sound event period is about 50 milliseconds.

8. The method of claim 6, wherein the occurrence of a sound event is detected when a peak sound energy occurrence ratio is greater than a threshold ratio, the peak sound energy occurrence ratio being the temporal location of the peak sound energy expressed as a fraction relative to the total duration of the sampled sound energy.

9. The method of claim 8, wherein the threshold ratio is about 10%.

10. The method of claim 6, wherein the occurrence of a sound event is determined to be a candidate snore event when the pitch of the sampled sound energy is greater than a minimum pitch and less than a maximum pitch.

11. The method of claim 10, wherein the relative minimum pitch is about 14 and the relative maximum pitch is about 28.

12. The method of claim 6, wherein the occurrence of sound event is determined to be a candidate snore event when the fraction of the sampled sound energy that occurs during inspiration is greater than an inspiration threshold.

13. The method of claim 12, wherein the inspiration threshold is about 80%.

14. The method of claim 1, wherein a candidate snore event is confirmed as not an isolated snore event by:

processing at least five breaths immediately preceding and following the candidate snore event, and

detecting other candidate snore events in at least three of the at least five preceding or following breaths.

15. The method of claim 14, further comprising:

processing at least seven breaths immediately preceding and following the candidate snore event, and

classifying the candidate snore event as an isolated snore event if none of the at least seven breaths immediately preceding and following the candidate snore event includes another candidate snore event.

16. The method of claim 1, wherein the detecting and confirming of candidate snore events is computer-implemented.

17. A system for determining a snore event comprising:

a processor; and

a computer readable memory operatively coupled to the processor and configured with instructions for causing the processor to perform the method of claim 1.

18. A monitoring system for determining a snore event comprising:

a processor;

a computer readable memory operatively coupled to the processor and configured with instructions for causing the processor to perform the method of claim 1;

and

a monitoring garment operatively coupled to the processor for providing respiratory and sound data from a monitored person.

19. A program product comprising a computer readable memory operatively coupled to a processor and configured with instructions for causing the processor to perform the method of claim 1.

20. A method for determining a snore event, comprising:

detecting the occurrence of a person'"'"'s breath when the person'"'"'s breath has a volume that is less than a breath threshold;

detecting the occurrence of a sound event from sound energy sampled near a person'"'"'s mouth and/or nose when;

the sampled sound energy is greater than a sound event threshold and lasts longer than a sound event period;

a peak sound energy occurrence ratio is greater than a threshold ratio, the peak sound energy occurrence ratio being the temporal location of the peak sound energy expressed as a fraction relative to the total duration of the sampled sound energy; and

determining that the detected sound event is a candidate snore event when;

a pitch of the sampled sound energy of the sound event is greater than a minimum sound energy pitch and less than a maximum sound energy pitch; and

a fraction of the sampled sound energy that occurs during inspiration is greater than an inspiration threshold.