Sound-induced sleep method and a system therefor

• US 9,999,743 B2
• Filed: 06/11/2014
• Issued: 06/19/2018
• Est. Priority Date: 06/11/2013
• Status: Active Grant

• Current Assignee: Agency For Science Technology and Research
• Original Assignee: Agency For Science Technology and Research
• Inventors: Pan, Yaozhang, Yu, Juanhong, Guan, Cuntai, Ng, Keong Andrew, Chan, Ti Eu, Zhang, Zhou
• Primary Examiner(s): Cox, Thaddeus
• Application Number:
  US14/898,094
• Publication Number:
  US 20160151602A1
• Time in Patent Office: 1,469 Days
• CPC Class Codes: A61B 5/374 Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
• CPC Class Codes: A61B 5/4812 Detecting sleep stages or cycles
• CPC Class Codes: A61B 5/4836 Diagnosis combined with treatment in closed-loop systems or methods A61B5/0036 takes precedence
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61M 2021/0027 by the hearing sense
• CPC Class Codes: A61M 21/02 for inducing sleep or relaxation, e.g. by direct nerve stimulation, hypnosis, analgesia for massage A61H; electrotherapy A61N, e.g. applying alternating or intermittent electric currents for producing anaesthesia A61N1/36021
• CPC Class Codes: A61M 2230/04 Heartbeat characteristics, e.g. ECG, blood pressure modulation
• CPC Class Codes: A61M 2230/10 Electroencephalographic signals

Abstract

A method and system for sound-induced sleep is provided. The method includes detecting brainwave signals of a subject. The method further includes analyzing the brainwave signals to determine a current sleepy state of the subject and selecting a sound in response to the current sleepy state based on a quantified association index between the brainwave signals and acoustical features of the sound. The method further more includes playing the sound to the subject.

Claims

1. A method for sound-induced sleep comprising:

detecting brainwave signals of a subject;

analyzing the brainwave signals to determine a current sleepy state of the subject;

selecting a sound in response to the current sleepy state of the subject based on a quantified association index between the brainwave signals of the subject and acoustical features of the sound, wherein the current sleepy state of the subject comprises a sleepy state of the subject and a non-sleepy state of the subject, and wherein the quantified association index is obtained by determining a correlation between brainwave signals of the subject and the acoustical features of the sound, the correlation being expressed using a Canonical Correlation Analysis which simultaneously maximizes the correlation between the brainwave signals of the subject and the acoustical features of the sound and maximizes a discrimination between the sleepy state of the subject and the non-sleepy state of the subject; and

playing the sound to the subject.

2. The method of claim 1, wherein analyzing the brainwave signals comprises analyzing the brainwave signals to further determine a sleep stage and playing the sound comprises playing the sound at a predetermined volume determined in response to the sleep stage.

3. The method of claim 2, wherein the sleep stage comprises a stage selected from the group comprising a wake stage, a light sleep stage N1, a light sleep stage N2, a deep sleep stage N3 and a rapid eye movement (REM) sleep stage.

4. The method of claim 3, wherein playing the sound at the predetermined volume determined in response to the sleep stage comprises playing the sound at a predetermined starting volume in the wake stage, playing the sound at a fading volume fading off from a predetermined starting volume and subsequently discontinuing the sound in the light sleep stage N1, the light sleep stage N2, the deep sleep stage and the REM sleep stage.

5. The method of claim 1, further comprising:

providing a sleep quality report indicating total sleeping hours, sleep start/end times, and a ratio of light/deep/REM sleep stage durations.

6. The method of claim 1, wherein selecting the sound comprises selecting the sound in accordance with a preset sequence of sounds.

7. The method of claim 1, further comprising:

presetting a modelling correspondence between the current sleepy state and the brainwave signals,

wherein the modelling correspondence is calibrated by manually determining the current sleepy state from an appearance of the subject.

8. The method of claim 1, wherein the acoustical features comprise a feature selected from the group comprising music signal global energy, tempo, brightness, roughness, Mel-frequency cepstral coefficient, pitch, inharmonicity, key, chromagram, mode, tonal centroid and period entropy.

9. The method of claim 1, wherein the acoustical features are computed from ambient music and natural sounds.

10. A system for sound-induced sleep comprising:

a detector module configured to detect brainwave signals of a subject;

an analyzer module configured to analyze the brainwave signals to determine a current sleepy state of the subject, wherein the current sleepy state of the subject comprises a sleepy state of the subject and a non-sleepy state of the subject;

a processor module configured to select a sound in response to the current sleepy state based on a quantified association index between the brainwave signals and acoustical features of the sound, wherein the processor module obtains the quantified association index by determining a correlation between the brainwave signals and the acoustical features of the sound, the correlation being expressed using a Canonical Correlation Analysis which simultaneously maximizes the correlation between the brainwave signals of the subject and the acoustical features of the sound and maximizes a discrimination between the sleepy state of the subject and the non-sleepy state of the subject; and

a player module configured to play the sound to the subject.

11. The system of claim 10, wherein the analyzer module is further configured to analyze the brainwave signals to determine a sleep stage and the player module is further configured to play the sound at a predetermined volume determined in response to the sleep stage.

12. The system of claim 11, wherein the sleep stage comprises a stage selected from the group comprising a wake stage, a light sleep stage N1, a light sleep stage N2, a deep sleep stage N3 and a rapid eye movement sleep stage (REM).

13. The system of claim 12, wherein the player module is further configured to play the sound at a predetermined starting volume in the wake stage, play the sound at a fading volume fading off from the predetermined starting volume and subsequently stop playing the sound in the light sleep stage N1, the light sleep stage N2, the deep sleep stage and the REM sleep stage.

14. The system of claim 10, wherein the processor module is further configured to provide a sleep quality report indicating total sleeping hours, sleep start/end times, and a ratio of light/deep/REM sleep stage durations.

15. The system of claim 10, wherein the processor module is further configured to select the sound in accordance with a preset sequence of sound.

16. The system of claim 10, further comprising:

a modelling module configured to preset a modelling correspondence between the current sleepy state and the brainwave signals,

wherein the modelling correspondence is calibrated by manually determining the current sleepy state from an appearance of the subject.

17. The system of claim 10, wherein the acoustical features comprise a feature selected from the group comprising music signal global energy, tempo, brightness, roughness, Mel-frequency cepstral coefficient, pitch, inharmonicity, key, chromagram, mode, tonal centroid and period entropy.

18. The system of claim 10, wherein the acoustical features are computed from ambient music and natural sounds.

19. The system of claim 10, further comprising:

three preprocessors configured to extract from the detected brainwave signals to;

detect a noise level, obtain subject-specific baselines, and extract sleep-aware features comprising spindle, K-complex, delta filter band, theta filter band, alpha filter band, sigma filter band, beta filter band and gamma filter band.