KR102004219B1 - A system of detecting sleep disturbance using a microvibration sensor and a sound sensor - Google Patents

Abstract

The present invention relates to a system of detecting a sleep disorder based on a micro vibration sensor and a sound sensor which measures micro vibration by a micro vibration sensor installed on a pillow, and measures a sound by a sound sensor to detect sleep apnea or snoring symptoms and record detected symptoms or automatically generate a report. The system of detecting a sleep disorder based on a micro vibration sensor and a sound sensor comprises: a respiration signal detection unit to detect a respiration signal from the micro vibration sensor, and detect a cycle, a phase, and a peak of the respiration signal from the respiration signal; an apnea section estimation unit to estimate a section of a predetermined size around the peak from the respiration signal as an apnea section (hereafter, first apnea section); a respiration sound extraction unit to receive a sound signal, detect a noise signal, remove the noise signal from the sound signal to extract a respiration sound, detect a sound signal in the first apnea section as the noise signal, and extract a cycle and a phase of the extracted respiration sound from the respiration signal; and a snoring detection unit to compare the cycle and the phase of the respiration sound with the cycle and the phase of the respiration signal to detect a snoring symptom if a level of the respiration sound exceeds a predetermined reference level. A camera is operated if a biosignal such as a heart rate exceeds a predetermined range to photograph and store an image only in a required situation to minimize power consumption of a battery.

Description

Technical Field [0001] The present invention relates to a micro-vibration sensor and a sound sensor based sleep disturbance detection system,

In the present invention, microvibration is measured by a micro vibration sensor installed on a pillow, sound is measured at a smart terminal such as a smart phone, sleep apnea or snoring is detected, the detected symptoms are recorded, , A micro vibration sensor and a sound sensor based sleep disorder detection system.

In general, people with sleep disorders usually have two or more disorders such as insomnia, sleeping breathing difficulties, narcolepsy, restless legs syndrome, which can lead to aggravation of medical, neurological and psychiatric disorders, Infarction, stroke, and the like.

In particular, respiratory disturbance during sleep is a phenomenon in which the respiration is temporarily reduced or cut off due to narrowed or obstructed airway, which may result in narrowing of the airway space due to fattening, or the elasticity of airway muscles may fall and cause it to fall down. It may occur when the airway is narrowed. At this time, the narrow airway causes air to pass through, causing the pharynx and larynx to vibrate, causing snoring. When the snoring becomes severe, sleep apnea, which suddenly stops breathing, is triggered and the sleep cycle is broken because it does not reach deep sleep . Sleep apnea is characterized by at least 10 seconds of sleep apnea or more than 5 times per hour or more than 30 times of 7 hours.

Sleep is repeated with a Rapid Eye Movement (REM) and a Non-Rapid Eye Movement (Non-REM) cycle of about 90 to 120 minutes, usually 4 to 6 cycles a night, People say that when they wake up in the morning because they do not have enough oxygen in their brains, they complain of headaches and because of the broken sleep cycle they have not recovered from fatigue during the night, so they often get drowsy during the day.

To prevent this, there is proposed a technique of a snoring prevention pillow using an acoustic sensor to detect and prevent snoring [Patent Literatures 1 and 2]. When the snoring is sensed through the acoustic sensor, the prior art drives a motor installed therein and presses the throat of the human body to expand the snoring. In particular, there have been various techniques for detecting snoring by measuring acoustic signals of snoring [Patent Documents 3 and 4]. That is, the prior art collects sound signals, extracts frequency bands in which the snoring signals are concentrated in the collected sound signals, analyzes the snoring sounds using a smart terminal such as a smart phone, Technologies.

In addition to the sound (or sound) of the snoring, techniques for detecting the snoring using the vibration and preventing the snoring are proposed (Patent Document 5). The prior art senses that the head of a sleeping person touches the pillow using a capacitive sensor, and senses snoring by measuring a snoring sound and a snoring sound using a sound sensor or a vibration sensor.

In addition, a smart functional pillow is provided, and a technique of measuring a sleep pattern by measuring a variety of biological information such as brain waves, pressure of the head, body temperature, snoring sound, and analyzing the sleeping disorder has been proposed [Patent Document 6].

As described above, in many cases, the recognition of sleep disorder (including snoring) is often performed through sound. However, in this case, it is difficult to distinguish snoring due to the side person when two or more people sleep in the same space, and in the case of sleeping in the ON state of a TV or an audio apparatus, it is often a mistake of snoring due to sound. Further, even when a vibration sensor is used in addition to the acoustic sensor, a specific method of detecting a sleeping disorder such as a snoring by using an acoustic signal and a vibration signal is not proposed.

Korean Patent Registration No. 10-1299679 (published on March 27, 2013) Korean Patent Registration No. 10-1481006 (published on January 14, 2015) Korean Patent Laid-Open Publication No. 10-2016-0096905 (published on August 17, 2016) Korean Registered Patent No. 10-1388661 (issued April 24, 2014) Korean Registered Patent No. 10-1762116 (issued on August 1, 2017) Korean Registered Patent No. 10-1763302 (published on July 31, 2017)

The object of the present invention is to solve the above-mentioned problems, and it is an object of the present invention to provide a pneumatic pressure sensor which measures minute vibrations by means of a micro vibration sensor provided on a pillow, measures sound in a smart terminal such as a smart phone, detects sleep apnea or snoring And to provide a micro vibration sensor and a sound sensor based sleeping disorder detection system that records detected symptoms or automatically generates a report.

In order to accomplish the above object, the present invention relates to a fine vibration sensor and a sound sensor-based sleeping disorder detection system for receiving a fine vibration signal from a fine vibration sensor and receiving a sound signal from a smart terminal, A respiration signal detector for detecting a signal, a period, a phase, and a peak of a respiration signal from the respiration signal; An apnea interval estimator for estimating an apnea interval (hereinafter, referred to as a first apnea interval) of a predetermined magnitude from the respiration signal around the peak; A sound signal is received and a noise signal is detected and a noise signal is removed from a sound signal to extract a breathing sound. The sound signal in the first apnea interval is detected as the noise signal, and the breathing sound is extracted from the extracted breathing sound. A breathing sound extracting unit for extracting a period and a phase; And a snoring detecting unit for detecting a snoring symptom by comparing a period and a phase of the breathing sound with a period and a phase of the respiration signal when the size of the breathing sound is out of a predetermined reference size, do.

According to another aspect of the present invention, there is provided a micro-vibration sensor and a sound sensor-based sleep disturbance detection system, wherein the respiration signal detection unit amplifies the micro-vibration signal to generate a digital signal, filters the generated digital signal with a low- And extracts a positive peak representing the peak from the waveform of the respiration signal and a negative peak representing the lowest point and sets the time between the adjacent positive peaks at the positive peak to the period of the respiratory signal .

According to another aspect of the present invention, there is provided a sleeping disorder detection system based on a micro vibration sensor and a sound sensor, wherein the apnea interval estimator estimates an interval in which a signal change is less than a predetermined reference deviation for a time longer than at least 1/2 of a period of a respiration signal, And the breath sound extracting unit detects a sound signal in the second apnea interval as a noise signal.

According to another aspect of the present invention, there is provided a micro-vibration sensor and a sound sensor-based sleep detection system, wherein the breath sound extraction unit detects a frequency or a frequency band of the noise signal, generates a noise filter using the detected frequency or frequency band, And extracting a respiration signal by filtering the noise signal from the sound signal using the noise filter.

Further, in the present invention, in the micro-vibration sensor and the sound sensor-based sleeping disorder detection system, the snoring detection unit estimates that the period of the breathing sound is 1/2 of the period of the breathing signal, , 360 °, and 720 ° are estimated to correspond to phases of -90 °, 180 °, and 270 °, respectively, of the respiration signal. If the phases and phases of the signals corresponding to each other are within a predetermined error range, And the measured respiration sound is determined as a snoring signal of the snoring of the user.

In addition, the present invention provides a micro-vibration sensor and a sound sensor-based sleeping-disorder detection system, wherein the system includes an analysis result including a feature extracted from the sound signal and the vibration signal, And a sleep quality creating unit for creating a report on the state of the user.

As described above, according to the micro-vibration sensor and the sound sensor-based sleep disturbance detection system according to the present invention, sleep apnea is detected by a micro-vibration sensor, snoring is detected by a sound sensor, Thus, an effect of more accurately detecting sleep apnea and snoring can be obtained.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram of an entire system for implementing the present invention. FIG.
FIG. 2 is an exemplary view of a micro-vibration sensor according to an embodiment of the present invention, which is an example of a sensor inserted into a pillow and (b) a sensor inserted into a pad.
3 is a block diagram of a configuration of a smart terminal according to an embodiment of the present invention;
4 is a block diagram of a configuration of a micro-vibration sensor and a sound sensor-based sleep detection system according to an embodiment of the present invention.
FIG. 5 illustrates a process of detecting a breathing signal by a breathing signal detecting unit according to an embodiment of the present invention. FIG.
FIG. 6 is an exemplary graph illustrating a breathing signal according to an embodiment of the present invention. FIG.
FIG. 7 is a graph showing a unit of a breathing signal according to an embodiment of the present invention; FIG.
8 is a graph illustrating a sound signal and a breathing pattern during sleep according to an embodiment of the present invention.
9 is a graph illustrating a sound pattern during apnea according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the drawings.

In the description of the present invention, the same parts are denoted by the same reference numerals, and repetitive description thereof will be omitted.

First, the overall system configuration for carrying out the present invention will be described with reference to Fig.

1, the entire system for implementing the present invention includes a micro-vibration sensor 90 inserted into a pad or inserted in a pad, a smart terminal 10 such as a user's smart phone, A client 20 for detecting a sleeping disorder, and a detection management server 30 for analyzing a micro vibration signal or an acoustic signal or managing a sleeping disorder. The smart terminal 10 and the detection management server 30 are connected to each other through a network 80 such as the Internet and a mobile communication network. In addition, a database 40 for storing sleep disturb signals or detection results can be additionally configured. And a sound detection sensor 11 for sensing a sound.

First, the micro-vibration sensor 90 is a sensor for measuring micro-vibrations. The micro-vibration sensor 90 is inserted into a pillow or a pad such as a pillow pad, and senses a minute vibration caused by respiration or the like. For example, a piezoelectric sensor such as a piezo sensor sold by Emfit can be used. Such a micro vibration sensor can sense minute vibration and is sensitive to small pressure and sound.

In Fig. 2, (a) shows an example in which the micro-vibration sensor 90 is inserted into the pillow, and (b) shows an example in which it is inserted into the pad. The pad surrounds the surface of the pillow or is inserted inside the outer surface of the pillow. Therefore, when the user puts the head on the pillow, the micro-vibration sensor 90 is placed close to or close to the head of the user to measure the micro-vibration due to breathing or the like.

The fine vibration sensor 90 includes short-range wireless communication means such as Wi-Fi, Bluetooth, and infrared rays, and transmits the measured fine vibration signal to the smart terminal 10 or the client 20.

Next, the smart terminal 10 is a smart terminal having ordinary computing functions such as a smart phone, a tablet, a tablet PC, and a notebook, as a mobile terminal used by a user. In particular, the smart terminal 10 is a terminal to which an application or a mobile application (or an app or an application) can be installed and executed. Or the smart terminal 10 may be a terminal used exclusively for sleep disorder or health care.

As shown in FIG. 3, the smart terminal 10 is provided with a sound detection sensor 11 such as a microphone, and receives sound (or sound). That is, the smart terminal 10 receives a sound signal (or an acoustic signal). Alternatively, the sound detection sensor 11 may be configured to independently transmit the sensed value to the smart terminal 10 through wired / wireless communication (wireless communication such as wired or Bluetooth).

The smart terminal 10 also includes a communication unit 14 including short-range wireless communication means such as WiFi, Bluetooth, and infrared rays, and receives a fine vibration signal from the fine vibration sensor 90.

The communication unit 14 of the smart terminal 10 is provided with communication means for performing data communication with a broadband communication network such as a wifi or a local communication network or the like and is connected to the detection management server 30 To perform data communication.

The smart terminal 10 includes a display 12 for displaying sleeping breath information, sleep breathing disorder detection results and the like on the screen, an input device 13 such as a touch screen or a button, a central processing unit 18 such as a mobile CPU, . A memory (not shown) for storing other data, and the like.

Next, the client 20 is a mobile application (or app, application) installed in the smart terminal 10 and is a program system that interlocks with the detection management server 30 or independently provides a service.

That is, the client 20 receives the sensed micro-vibration signal from the micro-vibration sensor 90 and receives the sensed sound signal from the sound sensing sensor 11 of the smart terminal 10.

In addition, the client 20 monitors the sleep state by detecting a sleep apnea or snoring symptom using a micro vibration signal and a sound signal. At this time, the micro vibration signal and the sound signal may be transmitted to the detection management server 30, the detection result may be received from the server 30, and the detection result may be stored or displayed on the display 12.

Alternatively, the client 20 can output via the output device such as the display 12 or the speaker (not shown) or output a predetermined alarm message to the predetermined (predetermined) time when the degree of sleep apnea or snoring symptom is equal to or greater than a predetermined level (For example, a guardian terminal, a medical institution, an emergency institution, etc.).

Next, the detection management server 30, as a normal application server, analyzes the microvibration signal and the sound signal to detect sleep apnea or snoring symptoms, or monitors and records the user's sleep state.

On the other hand, the client 20 and the detection management server 30 can be implemented according to a method of configuring a normal client and a server. That is, the functions of the entire system can be shared according to the performance of the client, the server and the traffic volume. As an example, the client 20 receives a fine vibration signal or a sound signal from the fine vibration sensor 90 or the sound detection sensor 11 and transmits the fine vibration signal or the sound signal to the detection management server 30, And can store or display the sleep state, sleep disorder, and the like. As another example, when the client 20 receives the microvibration signal or the sound signal from the microvibration sensor 90 or the sound detection sensor 11 and analyzes it, detects the sleep apnea or snoring symptom, ) Can only record or backup the results detected for each user. In addition, the client 20 performs most of the functions, and the detection management server 30 can perform the server operation only when the user subscribes and registers separately. The above examples are merely illustrative examples and can be implemented in various sharing forms according to the configuration method of the server-client.

Hereinafter, a server-client system including the client 20 and the detection management server 30 will be referred to as a detection and management system 300. [ For convenience of explanation, it is assumed that the detection and management system 300 is driven by the smart terminal 10.

Next, the database 40 stores a signal filter DB 41 for storing a filter for pre-processing a micro vibration signal or a sound signal, a noise signal filter, and the like, and analysis results such as a sleep state or a sleeping disorder result analyzed from the signal And a sleep breathing record DB 42. [ However, the configuration of the database 40 is only a preferred embodiment. In the development of a specific device, the database 40 may have a different structure in consideration of ease of access and retrieval, efficiency, and the like.

Next, a micro vibration sensor and a sound sensor-based sleeping disorder detection system according to an embodiment of the present invention will be described in more detail with reference to FIG. The sleep-disorder detection and management method according to the present invention is a server-client system comprising a client (20) and a detection management server (30).

4, the sleep disturbance detection system according to the present invention includes a respiration signal detection unit 31 for detecting a respiration signal using a micro-vibration signal, an apnea interval estimation unit 32 for estimating an apnea interval from the respiration signal, A breathing sound extracting unit 33 for receiving a sound signal and detecting a noise signal and removing the sound signal from the sound signal to extract a breathing sound, and a snoring detecting unit 34 for detecting a snoring symptom. In addition, the apparatus may further comprise a sleep apnea detector 35 for detecting a sleep apnea symptom by checking a characteristic of the vibration signal, a sleep quality generator 36 for generating a report on the sleep apnea state such as sleep quality, and the like .

First, the respiration signal detecting unit 31 receives the fine vibration signal sensed by the fine vibration sensor 90, and detects the respiration signal from the fine vibration signal.

As described above, the micro-vibration sensor 90 is inserted into a pillow or inserted into a pad, and measures pressure or vibration generated by respiration during sleep, and outputs it as a signal. The respiration signal detection unit 31 receives the measured fine vibration signal from the fine vibration sensor 90.

The respiration signal detection unit 31 amplifies the fine vibration signal and removes noise using a predetermined filter. The microvibration signal may include noise due to vibration of the surrounding environment in addition to vibration due to breathing. Therefore, a signal filter for extracting only minute vibrations due to breathing is set in advance, and noise is removed by filtering with the corresponding signal filter. Preferably, a band of a fine vibration signal due to breathing is set in advance, and a band filter for filtering a signal outside the band can be used as a noise removing filter.

5, the respiration signal detecting unit 31 generates a digital signal after amplifying the original signal collected from the micro-vibration sensor 90, such as a piezo sensor, through a data transmitter or the like, (FIR filter) to detect the breathing signal.

An example of the detected respiration signal is shown in Fig. As shown in FIG. 6, the respiration signal is represented by a waveform having a constant period, and a positive peak and a negative peak appearing at a certain period in the waveform. At this time, the time between positive peaks at positive peaks is set as the period of the respiration signal.

In addition, the breathing signal detecting unit 31 extracts a period and a phase or a breathing rate (BR) from the breathing signal. Since respiration occurs according to a certain period and phase, the minute vibration or respiration signal by respiration also has a certain period and phase.

Next, the apnea interval estimator 32 estimates an apnea interval from the detected respiration signal.

The apnea interval is a section in which breathing is stopped, which is a transition from inhalation to exhalation or from exhalation to exhalation. That is, breathing is temporarily stopped at the moment when it is switched from inhalation to exhalation or vice versa.

FIG. 7 shows the unit waveform in one cycle in more detail in the respiration signal as in FIG. As shown in FIG. 7, the respiration signal has a positive peak (P-Peak) representing the highest signal value and a negative peak (N-Peak) representing the lowest signal value.

When the user breathes, the pressure gradually increases, so that the measured value measured by the fine vibration sensor 90 increases, and the signal value of the respiration signal detected from this increases. At the point where the user breathe briefly to stop breathing to exhale, or just before that, the pressure rises to the maximum and the breathing signal has the highest value. Thus, the positive peak point is formed at the portion that is switched from the inspiration to the expiration, and conversely, the negative peak is formed at the portion that is switched from the expiration to the inspiration.

Thus, the apnea interval is the apnea interval around the peak point of the respiration signal. That is, a section having a predetermined size around the peak in the respiration signal is set as the apnea interval. The size of the interval is a predetermined value set in advance through experiment or accumulation of data.

As described above, the front and rear sections around the peak of the respiration signal will be referred to as a first apnea interval.

In addition, the apnea interval estimator 32 detects the sleep apnea interval by checking BR (respiration rate) with respect to the respiration signal.

The sleep apnea interval by the respiratory rate is an interval of apnea caused by sleep disturbances, which is less than the normal number of breaths. In other words, it refers to the period in which apnea occurs during a longer period compared to the normal respiratory cycle. In the sleep apnea interval, there is no change in vibration or pressure because the respiration does not proceed. Preferably, the interval (less than a predetermined reference deviation) during which the signal is not changed for a time longer than at least 1/2 of the period of the respiration signal is referred to as a sleep apnea interval or a second apnea interval.

That is, the apnea interval estimator 32 sets the interval in which the signal change is lower than the predetermined reference deviation for the time longer than at least 1/2 of the period of the respiration signal as the second apnea interval.

Next, the breathing sound extracting unit 33 receives a sound signal, detects a noise signal, and extracts the breathing sound by removing it from the sound signal.

First, the breath sound extracting unit 33 receives a sound signal and detects a noise signal from the sound signal of the apnea interval. At this time, the respiration signal and the respiration signal are synchronized in time, and a sound signal corresponding to the apnea interval is detected as a noise signal.

The apnea interval is a section where the exhalation and the exhalation are reversed, and the respiration is temporarily stopped. Therefore, the sound signal generated in the apnea interval is very likely to be noise. For example, the input sound signal may include noise caused by external noise such as a person sleeping in the vicinity or a TV in addition to the sound caused by breathing.

If the size of the sound signal of the apnea interval is greater than a predetermined minimum size (or minimum reference size, first reference size), the breath sound extraction unit 33 determines the sound signal as a noise signal and detects the noise signal. At this time, the apnea interval detects a noise signal for both the first apnea interval and the second apnea interval.

Then, the breathing sound extracting unit 33 extracts (generates) the breathing sound by filtering out the noise signal from the sounding signal. Preferably, the frequency or frequency band of the noise signal is detected, and the noise filter is generated in the detected frequency band. Then, the generated noise filter is used to filter the noise signal from the sound signal to extract the respiration signal.

In addition, the breathing sound extracting unit 33 extracts the period, phase, and sound size from the noise-removed breathing sound.

As shown in FIG. 8, since the noise signal (or the breathing sound or the breathing sound signal) from which the noise is removed is the sound (or sound) generated by the breathing during sleep, a breathing sound is generated according to a certain period and phase of breathing . Therefore, the sound caused by breathing during sleep has a constant period and phase. That is, since the sound generated during breathing by the snoring is due to breathing, the breathing sound has a certain period and phase.

Preferably, the breathing sound extracting unit 33 first extracts the sound volume of the breathing sound and, if the sound volume is larger than a predetermined minimum reference size (hereinafter referred to as a second reference size) .

If the user does not have a snoring breathing disorder such as snoring, the sound from breathing may be hardly audible. Therefore, the period and phase of the breathing sound (or sound signal) are extracted only when the breathing sound (or the sound signal) is at least a predetermined size.

Next, the snoring detector 34 detects the snoring symptom using the period and phase of the respiration signal, and the size, period, and phase of the breath sound.

First, the snoring detection unit 34 recognizes the snoring symptom when the sound volume of the breath sounds is out of a predetermined reference range (or reference size, normal range, hereinafter referred to as the third reference size). Preferably, the reference size (or the third reference size) is set within 40 dB, and if the sound size is greater than 40 dB, the snoring is determined to be a symptom of snoring.

In addition, the snoring detector 34 compares the period and phase of the breathing signal with the period and phase of the breathing signal to check whether the breathing sound is the user's. In the negative peak of the respiration signal, the positive peak interval is the period of inhalation, and a breathing sound (or snoring sound) occurs in this period. In addition, it exhales in the negative peak interval from the positive peak, and breathing sound (snoring sound) occurs in this interval for one cycle.

Therefore, the period of the breathing sound is half the period of the breathing signal. The phases of 0, 360, and 720 degrees of respiration sound correspond to phases of -90 degrees, 180 degrees, and 270 degrees, respiration signals, respectively. That is, if the mutually corresponding periods and phases of the two signals are within a predetermined error range, the measured respiration sound is determined to be the user's snoring sound signal.

Next, the sleep apnea detection unit 35 detects the sleep apnea symptom by checking the characteristics of the respiration signal.

The apnea state is detected from the respiration signal. The apnea state is a state without breathing, so bouncing (vibration) of the body does not occur. Therefore, it is detected that no vibration is generated and it is judged as an apnea state.

When the sleep apnea detection unit 35 detects a period in which the signal change is shorter than a predetermined reference deviation for at least a period longer than a period of the respiration signal, the sleep apnea detection unit 35 detects the interval as the sleep apnea interval. That is, the sleep apnea detector 35 determines that the second apnea interval obtained previously is a sleep apnea interval.

Preferably, the sleep apnea detection unit 35 determines that the detected second apnea interval is sleep apnea if it meets a preset condition (hereinafter referred to as sleep apnea condition). The apnea condition is a condition set by the number of occurrences of the sleep apnea interval (second apnea interval), the total time, and the like. For example, if the number of occurrences is at least five times, and the total duration of the interval is five minutes or more, an apnea condition may be set.

In another embodiment, the sleep apnea detection unit 35 may check the reference or the range (or the normal range, the reference range, etc.) of the measured breathing time in advance, and if it is out of the reference range, I know. That is, when the apnea time BR is equal to or greater than a predetermined time (for example, 10 seconds), it is judged to be sleep apnea.

Next, the sleep quality preparation unit 36 creates a report on the sleep breathing state such as sleep quality.

The sleep quality generating unit 36 generates a report on the sleep state using the sound signal and the vibration signal measured during sleep. In other words, the characteristics extracted from the sound signal and the vibration signal, and the statistics about them are reported.

The extracted features and their statistics included in the report include the period and phase on the time series of the sound signal or the vibration signal, the size of the signal, the sleep apnea time, the snoring time, and the like. In addition, the characteristics of a certain period such as day, week, and month are calculated as statistics (average, deviation, etc.), and the calculated statistics are included as analysis data.

Although the present invention has been described in detail with reference to the above embodiments, it is needless to say that the present invention is not limited to the above-described embodiments, and various modifications may be made without departing from the spirit of the present invention.

10: Smart terminal 11: Sound detection sensor
12: display 13: input device
14: communication unit 18: central processing unit
20: client 30: detection management server
31: respiration signal detection unit 32: apnea interval estimation unit
33: breathing sound extraction unit 34: snoring detection unit
35: sleep apnea detection unit 36:
40: Database 41: Signal Filter DB
42: Sleep breathing record DB 80: Network

Claims (6)

A fine vibration sensor and a sound sensor based sleeping disorder detection system for receiving a fine vibration signal from a fine vibration sensor and receiving a sound signal from a sound detection sensor,
A respiration signal detector for detecting a respiration signal from the microvibration signal and detecting a period, a phase, and a peak of a respiration signal from the respiration signal;
An apnea interval estimator for estimating an apnea interval (hereinafter, referred to as a first apnea interval) of a predetermined magnitude from the respiration signal around the peak;
A sound signal is received and a noise signal is detected and a noise signal is removed from a sound signal to extract a breathing sound. The sound signal in the first apnea interval is detected as the noise signal, and the breathing sound is extracted from the extracted breathing sound. A breathing sound extracting unit for extracting a period and a phase; And
And a snoring detecting unit for detecting a snoring symptom by comparing a period and a phase of the breathing sound with a period and a phase of the respiration signal when the size of the breathing sound is out of a predetermined reference size, Vibration sensor and sound sensor based sleep disorder detection system.
The method according to claim 1,
The respiration signal detector detects a respiration signal by filtering the generated digital signal with a low-pass filter, and generates a positive peak indicating a peak from the waveform of the respiration signal. And a negative peak indicating the lowest point is extracted and a time between adjacent positive peaks at a positive peak is set as a period of a breathing signal.
The method according to claim 1,
Wherein the apnea interval estimation unit estimates a second apnea interval in which a signal change is less than a predetermined reference deviation for at least a period longer than a period of a respiration signal,
Wherein the breathing sound extractor detects a sound signal in the second apnea interval as a noise signal.
The method according to claim 1,
The breathing sound extracting unit detects a frequency or a frequency band of the noise signal, generates a noise filter using the detected frequency or frequency band, and extracts a breathing signal by filtering the noise signal from the sound signal using the generated noise filter And a sound sensor based sleep disturbance detection system.
The method according to claim 1,
The snoring detection unit estimates that the period of the breathing sound is 1/2 of the period of the breathing signal, and the phases of 0, 360, and 720 degrees of the breathing sound are -90 degrees and 180 degrees , And 270 degrees. When the phases and phases of the signals corresponding to each other are within a predetermined error range, the measured respiration sound is determined to be the user's snoring sound signal. Vibration sensor and sound sensor based sleep disorder detection system.
The system of claim 1,
Further comprising a sleep quality generating unit for generating an analysis result including a feature extracted from the sound signal and the vibration signal and a statistic value of the extracted feature in a report on the sleep state, Sensor based sleep disturbance detection system.

Images