WO2020184627A1 - 睡眠推定システム、睡眠推定装置、および睡眠推定方法 - Google Patents
睡眠推定システム、睡眠推定装置、および睡眠推定方法 Download PDFInfo
- Publication number
- WO2020184627A1 WO2020184627A1 PCT/JP2020/010619 JP2020010619W WO2020184627A1 WO 2020184627 A1 WO2020184627 A1 WO 2020184627A1 JP 2020010619 W JP2020010619 W JP 2020010619W WO 2020184627 A1 WO2020184627 A1 WO 2020184627A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- sleep
- blood flow
- data
- estimation system
- user
- Prior art date
Links
- 230000007958 sleep Effects 0.000 title claims abstract description 201
- 238000000034 method Methods 0.000 title claims description 26
- 230000017531 blood circulation Effects 0.000 claims abstract description 115
- 238000004364 calculation method Methods 0.000 claims description 48
- 238000001228 spectrum Methods 0.000 claims description 21
- 230000008452 non REM sleep Effects 0.000 claims description 13
- 230000036385 rapid eye movement (rem) sleep Effects 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 7
- 230000001131 transforming effect Effects 0.000 claims description 3
- 210000001061 forehead Anatomy 0.000 claims description 2
- 210000000707 wrist Anatomy 0.000 claims description 2
- 230000037007 arousal Effects 0.000 claims 1
- 238000004891 communication Methods 0.000 description 22
- 230000007704 transition Effects 0.000 description 19
- 230000033001 locomotion Effects 0.000 description 14
- 210000004556 brain Anatomy 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 230000015654 memory Effects 0.000 description 7
- 230000002503 metabolic effect Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 125000002066 L-histidyl group Chemical group [H]N1C([H])=NC(C([H])([H])[C@](C(=O)[*])([H])N([H])[H])=C1[H] 0.000 description 4
- 239000008280 blood Substances 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000004461 rapid eye movement Effects 0.000 description 4
- 230000000747 cardiac effect Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000004060 metabolic process Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 description 3
- 230000035900 sweating Effects 0.000 description 3
- 206010062519 Poor quality sleep Diseases 0.000 description 2
- 206010067493 Sleep inertia Diseases 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 210000004204 blood vessel Anatomy 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 210000005037 parasympathetic nerve Anatomy 0.000 description 2
- 230000003863 physical function Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000000283 vasomotion Effects 0.000 description 2
- 229920000742 Cotton Polymers 0.000 description 1
- 241000746998 Tragus Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 210000000577 adipose tissue Anatomy 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 210000000617 arm Anatomy 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000003925 brain function Effects 0.000 description 1
- 210000000038 chest Anatomy 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 210000003792 cranial nerve Anatomy 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 210000000624 ear auricle Anatomy 0.000 description 1
- 210000000613 ear canal Anatomy 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 210000003811 finger Anatomy 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 description 1
- 229910052753 mercury Inorganic materials 0.000 description 1
- 210000003739 neck Anatomy 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 210000001331 nose Anatomy 0.000 description 1
- 230000001020 rhythmical effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 210000004243 sweat Anatomy 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4812—Detecting sleep stages or cycles
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/026—Measuring blood flow
- A61B5/0261—Measuring blood flow using optical means, e.g. infrared light
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4806—Sleep evaluation
- A61B5/4809—Sleep detection, i.e. determining whether a subject is asleep or not
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/02028—Determining haemodynamic parameters not otherwise provided for, e.g. cardiac contractility or left ventricular ejection fraction
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/026—Measuring blood flow
- A61B5/029—Measuring or recording blood output from the heart, e.g. minute volume
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/0816—Measuring devices for examining respiratory frequency
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/42—Detecting, measuring or recording for evaluating the gastrointestinal, the endocrine or the exocrine systems
- A61B5/4261—Evaluating exocrine secretion production
- A61B5/4266—Evaluating exocrine secretion production sweat secretion
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
Definitions
- This disclosure relates to sleep estimation.
- Patent Document 1 describes a technique for detecting a sleep state.
- the sleep estimation system includes an input device for inputting user's blood flow data and a control device for calculating output data indicating the user's sleep state from the blood flow data. It has an approximater capable of calculating the output data from the blood flow data.
- the sleep estimation program according to the embodiment is a sleep estimation program for operating a computer as the control device included in the sleep estimation system.
- the sleep estimation device includes an input unit for inputting user's blood flow data, an input layer for inputting blood flow data, and a hidden layer for performing calculations based on learned parameters for outputs from the input layer. It also includes a control unit that constitutes an approximation device having an output layer that outputs the calculation result of the hidden layer as a sleeping state of the user.
- the sleep estimation method is a sleep estimation method using an approximator, and the approximator is a trained parameter for an input layer for inputting user's blood flow data and an output from the input layer.
- the hidden layer includes a step of performing an calculation based on the learned parameters on the blood flow data, and an output layer includes a step of outputting the estimated sleep state of the user based on the calculation result of the hidden layer.
- the accuracy of sleep state estimation can be improved.
- FIG. 1 is a schematic diagram of the configuration of the sleep estimation system according to the embodiment.
- the sleep estimation system 1 can estimate the user's sleep state based on the data related to the user's blood flow (blood flow data). Specifically, the sleep estimation system 1 can estimate the sleep state of the user by, for example, causing the approximator 17 shown in FIG. 2 to calculate based on the input blood flow data.
- the approximator 17 may include a so-called neural network.
- the neural network is a mathematical model that imitates the neurons of the human cranial nerve system.
- the approximator 17 may include a trained mathematical model (such as an arithmetic expression) as described below.
- the sleep estimation system 1 includes a control device 11, a storage device 12, and a bus 13.
- Various devices constituting the sleep estimation system 1 such as the control device 11 and the storage device 12 are electrically or optically connected to each other via the bus (bus) 13 and can communicate with each other.
- the control device 11 can comprehensively manage the operation of the sleep estimation system 1 by controlling other components of the sleep estimation system 1.
- the control device 11 includes at least one processor in order to provide control and processing power for performing various functions.
- the at least one processor is run as a single integrated circuit (IC) or as multiple communicable connected ICs and / or discrete circuits (Discrete Circuits). May be good.
- At least one processor can be run according to various known techniques.
- a processor may be configured to perform one or more data calculation procedures or processes by, for example, executing instructions such as a program stored in associated memory such as storage device 12, one or more circuits, units, or It may be firmware (eg, a discrete logic component).
- the processor is one or more processors, controllers, microprocessors, microcontrollers, application specific integrated circuits (ASICs), digital signal processing devices, programmable logic devices, field programmable gate arrays, or these devices or It may include any combination of configurations, or other known device and configuration combinations.
- the control device 11 of the sleep estimation system 1 includes, for example, a CPU (Central Processing Unit).
- the storage device 12 can store various information, programs, and the like for realizing the functions of the sleep estimation system 1. Specifically, the storage device 12 can store the control program 121, which is a program for controlling the sleep estimation system 1.
- the storage device 12 may include a non-temporary recording medium such as a ROM (Read Only Memory) and a RAM (Random Access Memory) that can be read by the CPU of the control device 11.
- the storage device 12 may be configured by a conventionally known technique.
- the control device 11 can realize various functions by executing the control program 121 in the storage device 12. That is, the control program 121 has a sleep estimation program for causing the computer to estimate the sleep state of the user.
- the sleep estimation system 1 according to the embodiment can form an approximator 17 capable of estimating the sleep state of the user by the control device 11 executing the control program 121 in the storage device 12.
- FIG. 2 is a schematic diagram showing the operation of the sleep estimation system shown in FIG. 1 until the sleep state of the user is estimated. Further, FIG. 3 is a diagram for explaining an example of learning of the approximator 17.
- the operation until the user's sleep state is estimated is executed by the control device 11.
- the control device 11 forms an approximator 17 capable of estimating the sleep state of the user by executing the control program 121 in the storage device 12.
- the control device 11 calculates and outputs output data (for example, the sleeping state of the user) from the user's estimation data 125 (for example, blood flow data) according to the approximator 17.
- the approximator 17 is composed of, for example, an input layer 171, a hidden layer 172, an output layer 173, and arithmetic data 124.
- the input layer 171 can transmit the input data to the hidden layer 172.
- the hidden layer 172 can perform various calculations on the data input from the input layer 171 based on the calculation data 124. Then, the hidden layer 172 can output the calculation result to the output layer 173.
- the output layer 173 can output the calculation result input from the hidden layer 172 as the output data 19.
- each layer has a unit into which a signal is input / output as a constituent unit.
- the sleep estimation system 1 can improve the accuracy of the calculation result by learning the approximator 17.
- Learning means adjusting the strength of coupling between units, the bias of coupling, and the like so that the output layer 173 outputs a correct calculation result in the approximator 17.
- the output data 19 based on the learning data 122 is compared with the teacher data 123, which is the answer data prepared in advance, and the calculation data 124 is generated so that the output data 19 approaches the teacher data 123. It means to adjust.
- the sleep estimation system 1 according to the embodiment can improve the estimation accuracy by adjusting the calculation data 124 by so-called supervised learning using the learning data 122 and the teacher data 123.
- the learning data 122 is example data for training the approximator 17.
- the learning data 122 includes information based on human metabolism (metabolic information).
- the metabolic information includes, for example, information on blood flow, respiration, sweating, body temperature, body movement, and the like.
- Metabolism information may be acquired in advance using an arbitrary measuring device.
- Information on blood flow may be measured using, for example, a blood flow sensor such as a laser Doppler blood flow meter, an ultrasonic blood flow meter, and a photoelectric pulse wave meter.
- information on respiration may be acquired as sound using, for example, a microphone, or as movement of the thorax using an acceleration sensor, such as the depth or speed of respiration. ..
- an acceleration sensor such as the depth or speed of respiration.
- sweating for example, cotton or the like may be attached to an arbitrary part of the body, and the amount or weight of absorbed sweat may be acquired as the amount of sweating.
- information on body temperature may be acquired by, for example, a thermistor, an infrared sensor, and a thermometer such as a mercury thermometer.
- Information on body movement may be measured using, for example, an acceleration sensor and a pressure sensor.
- a plurality of the above-mentioned various measured information may be combined as metabolic information used by the sleep estimation system 1.
- the metabolic information used by the sleep estimation system 1 may be such that the behavior differs between waking up and sleeping, or the behavior changes according to the depth of sleep.
- the learning data 122 was associated with metabolic information with personal information and lifestyle habits that could affect circulatory system mechanisms such as age, gender, height, body fat, drinking habits, and smoking habits. It may be a thing.
- blood flow data can be used as learning data 122.
- the blood flow data may be data including various variables calculated based on the blood flow.
- the blood flow data includes, for example, data on at least one of blood flow, heart rate, heart rate interval, cardiac output, blood flow height, and coefficient of variation of vasomotion (basomotion). All you need is.
- Blood flow is the amount of blood flowing through a blood vessel per unit time.
- Heart rate is the number of heartbeats per unit time.
- the heartbeat interval is the interval between heartbeats.
- Cardiac output is the amount of blood pumped by a single heartbeat.
- Blood flow height is the difference between the maximum and minimum blood flow in a single heartbeat.
- Basomotion is a spontaneous and rhythmic movement of contraction and expansion of blood vessels.
- the coefficient of variation of the bass motion is a value showing the fluctuation of the blood flow generated based on the bass motion as a variation.
- the teacher data 123 is the data of the answer associated with the learning data 122.
- the sleep estimation system 1 can use the data in which the sleep state of the person who acquired the blood flow data is associated with the blood flow data of the learning data 122 as the teacher data 123. ..
- the teacher data 123 includes, for example, data in which the transition of the sleep state is associated with the transition of blood flow, data in which the transition of the sleep state is associated with the transition of the heart rate, and heartbeat interval.
- the sleep state of the user may be measured by any measuring device capable of acquiring the sleep state when the learning data 122 is acquired.
- any measuring device capable of acquiring the sleep state when the learning data 122 is acquired.
- blood flow data is acquired by a blood flow sensor
- brain waves are measured using an electroencephalograph to acquire user sleep state data associated with blood flow data, which is learning data 122. be able to.
- the arithmetic data 124 is data related to the arithmetic of the approximator 17, including data such as constants and variables of arithmetic expressions such as arithmetic expressions, biases and weights, and operators. Further, the arithmetic data 124 includes learned parameters such as a mathematical model. In the calculation data 124, the bias and the weight define the strength of the coupling between the units in the approximator 17. Therefore, the sleep estimation system 1 can adjust the calculation result of the approximator 17 by adjusting constants and variables such as bias and weight by learning.
- the adjustment method of the calculation data 124 for example, an error back propagation method, a gradient descent method, or the like may be adopted.
- the calculation data 124 adjusted by learning may be stored in the storage device 12 as the learned calculation data 124.
- the adjustment method is not limited to the above example as long as the calculation data 124 can be adjusted so that the estimation accuracy of the sleep state is improved by learning.
- the learning data 122 is input to the input layer 171.
- the hidden layer 172 the calculation based on the calculation data 124 is executed on the learning data 122.
- the calculation result of the hidden layer 172 is output as output data 19 from the output layer 173.
- the approximator 17 compares the teacher data 123 with the output data 19, and adjusts the calculation data 124 so that the error becomes small.
- the sleep estimation system 1 can train the neural network by using the learning data 122, the teacher data 123, and the calculation data 124. As a result, the sleep estimation system 1 can improve the estimation accuracy of the sleep state.
- the learning of the approximator 17 may be performed by another device regardless of the sleep estimation system 1.
- the storage device 12 of the sleep estimation system 1 stores the learned calculation data 124 generated by another device. Further, it is not necessary for the storage device 12 to store the learning data 122 and the teacher data 123.
- the learned calculation data 124 generated by another device is received by the communication device 14 through the information communication network 2, and the control device 11 stores the learned calculation data 124 received by the communication device 14 in the storage device 12. be able to. Further, the learned calculation data 124 generated by another device may be stored in the removable memory included in the storage device 12.
- the sleep estimation system 1 can estimate the sleep state of the user by using the learned approximator 17. Specifically, the sleep estimation system 1 can estimate the sleep state by calculating the input estimation data 125 with the approximator 17. In this case, first, the estimation data 125 is input to the input layer 171. Next, in the hidden layer 172, the calculation is executed on the estimation data 125 based on the calculation data 124. Then, the output data 19 which is the calculation result is output from the output layer 173 as the estimated sleep state.
- the estimation data 125 is input to the trained approximator 17 and is data for estimating the sleep state of the user.
- the learning data 122 may be the same type of data as the estimation data 125. That is, when it is desired to estimate the sleep state of the user based on the information on the blood flow, the estimation data 125 and the learning data 122 may be blood flow data.
- metabolic information such as blood flow data is acquired using a measuring device that measures the metabolism of a user who wants to estimate the sleep state, and the metabolic information acquired using the measuring device is used as estimation data 125 as an approximator. It is input to 17.
- the sleep estimation system 1 can estimate the sleep state of the user based on the estimation data 125.
- FIG. 4 is a schematic diagram showing an example of the transition of brain waves related to sleep.
- Sleep states can be classified based on, for example, brain waves.
- the sleep state is a state in which the user is awake, in a light sleep such as REM sleep (RapidEyeMovementsleep, REMsleep), or a non-REM sleep (Non-RapidEyeMovementsleep, Non-). It can be classified into a state of deep sleep such as REM sleep).
- non-rem sleep can be further classified according to the depth of sleep. For example, non-rem sleep may be classified into stage 1, stage 2, stage 3, and stage 4 in order of light sleep.
- Brain waves are classified into four waves, ⁇ wave, ⁇ wave, ⁇ wave and ⁇ wave, in order from the one with the longest wavelength.
- the ⁇ wave is, for example, an electroencephalogram having a frequency of about 38 Hz to 14 Hz.
- the ⁇ wave is, for example, an electroencephalogram having a frequency of about 14 Hz to 8 Hz.
- Theta wave is, for example, an electroencephalogram having a frequency of about 8 Hz to 4 Hz.
- the delta wave is, for example, an electroencephalogram having a frequency of about 4 Hz to 0.5 Hz.
- a person is sleeping when theta and delta waves are superior to beta and alpha waves.
- "dominant” means that the proportion of a certain wave in the measured electroencephalogram increases. It is known that the dominant brain wave changes periodically in the range of theta wave and delta wave during sleep (Fig. 4).
- the ratio of theta waves contained in brain waves is less than the predetermined value, the person is in REM sleep, and when the ratio of theta waves is more than the predetermined value, and when the ⁇ wave is dominant, the person is non-REM. It is in a state of sleep (Fig. 4).
- REM sleep is sleep accompanied by rapid eye movement (REM).
- Non-REM sleep is sleep that does not involve rapid eye movements.
- the sleep state was estimated by the electroencephalogram acquired by the electroencephalograph.
- handling an electroencephalograph and acquiring electroencephalograms requires a high degree of specialized knowledge.
- the installation of the electroencephalograph is complicated. Therefore, it is difficult for the user to easily acquire the brain wave, and it is difficult for the user to easily grasp his / her own sleep state.
- the sleep estimation system 1 can estimate the sleep state of the user based on the blood flow data. Handling a device that measures blood flow and acquiring blood flow data does not require a high degree of expertise compared to an electroencephalograph. In addition, the device for measuring blood flow is easier to install than an electroencephalograph. That is, the user can acquire his / her own blood flow data relatively easily. Therefore, according to the sleep estimation system 1, the user can easily grasp his / her own sleep state.
- sleep inertia For example, if you wake up while you are in deep sleep, you will be drowsy or drowsy immediately after awakening, and the brain will not work well (so-called sleep inertia).
- a relatively shallow sleep state such as stage 1 or 2 of non-rem sleep as the wake-up timing, it becomes difficult to fall into sleep inertia. Therefore, according to the sleep estimation system 1, the user can grasp the optimum wake-up timing, sleep cycle, and the like, so that the usefulness can be improved.
- the sleep estimation system 1 can estimate the sleep state of the user based on the blood flow data.
- the blood flow volume included in the blood flow data is an index including various factors related to blood flow such as heart rate, heart rate interval, cardiac output, blood flow wave height, and bass motion. Therefore, when the blood flow rate data is used as the learning data 122, the sleep estimation system 1 can learn the approximator 17 based on various elements related to the blood flow, and thus can improve the usefulness. it can.
- the parasympathetic nerves of the human body are enhanced when falling asleep. Since the basomotion is easily affected by the action of the parasympathetic nerve, the coefficient of variation of the basomotion tends to fluctuate greatly with the transition of the sleep state. In other words, the transition of the sleep state and the transition of the coefficient of variation of the bass motion tend to show a relatively high correlation. Therefore, the sleep estimation system 1 can effectively learn the approximator 17 regarding the correlation between the sleep state and the blood flow by using the data of the coefficient of variation of the bass motion included in the blood flow data as the learning data 122. Therefore, the estimation accuracy can be improved.
- blood flow may be affected not only by the sleep state but also by the surrounding environment during sleep.
- the blood flow rate becomes lower than expected when the blood flow data acquisition site is cooled by the wind of the air conditioner or the like.
- the heart rate is a value based on the heartbeat, and the measurement error due to the surrounding environment tends to be relatively small. Therefore, the sleep estimation system 1 can improve the estimation accuracy by using the heart rate data included in the blood flow data as the learning data 122.
- the sleep states that can be estimated by the sleep estimation system 1 are, for example, awakening of the user, REM sleep, and non-REM sleep. That is, the user can grasp the transition of his / her sleep state.
- the sleep estimation system 1 can estimate the state of non-rem sleep for each stage. Specifically, the sleep estimation system 1 can estimate which stage of stages 1 to 4 the non-rem sleep is in based on the blood flow data. Therefore, according to the sleep estimation system 1, the user can grasp an appropriate wake-up timing, sleep cycle, and the like.
- the learning of the approximator 17 may be performed for each sleep state. For example, learning data 122 and teacher data 123 during awakening, learning data 122 and teacher data 123 during REM sleep, and learning data 122 and teacher data 123 during non-REM sleep, respectively, for calculation data for each sleep state.
- the weighting of 124 may be performed.
- the acquisition site of blood flow data included in the learning data 122 may be, for example, ears, fingers, wrists, arms, forehead, nose, or neck. Further, blood flow data may be acquired from the ear region, for example, the concha, ear canal, earlobe, or tragus. As a result, the user can select the site for acquiring the blood flow data, so that the sleep estimation system 1 can improve the convenience.
- the control device 11 may include a plurality of CPUs. Further, the control device 11 may include at least one DSP. Further, all the functions of the control device 11 or some functions of the control device 11 may be realized by a hardware circuit that does not require software to realize the functions.
- the storage device 12 may include a non-temporary recording medium other than ROM and RAM that can be read by a computer. The storage device 12 may include, for example, a small hard disk drive and an SSD (Solid State Drive). Further, the storage device 12 may be a memory such as a USB (Universal Serial Bus) memory that can be attached to and detached from the sleep estimation system 1.
- USB Universal Serial Bus
- the sleep estimation system 1 includes a communication device 14 capable of communicating with an arbitrary external electronic device, a display device 15 capable of displaying various above tables such as the system of the sleep estimation system 1 and the sleep state of the user, and a sleep estimation system.
- An input device 16 capable of inputting various information and signals may be further provided in 1.
- the communication device 14, the display device 15, and the input device 16 may be electrically or optically connected to each other via the bus 13.
- the communication device 14 can be connected to an information communication network 2 such as the Internet that enables the sleep estimation system 1 to be connected to an external device by wired or wireless communication. That is, the communication device 14 can communicate with other devices such as a cloud server and a web server through the information communication network 2. Then, the communication device 14 can input various information received from the information communication network 2 to the control device 11. Further, the communication device 14 can transmit the information received from the control device 11 to the information communication network 2.
- an information communication network 2 such as the Internet that enables the sleep estimation system 1 to be connected to an external device by wired or wireless communication. That is, the communication device 14 can communicate with other devices such as a cloud server and a web server through the information communication network 2. Then, the communication device 14 can input various information received from the information communication network 2 to the control device 11. Further, the communication device 14 can transmit the information received from the control device 11 to the information communication network 2.
- the display device 15 can display various information such as characters, symbols, and figures under the control of the control device 11.
- the display device 15 can be configured by a conventionally known technique such as a liquid crystal display or an organic EL display.
- the input device 16 can output the data input from the user to the control device 11 as a signal.
- the input device 16 may be an interface capable of outputting signals based on user operations such as a keyboard, a mouse, and a touch panel. Further, when an interface capable of outputting signals and displaying various information based on user operations such as a touch panel is used, the display device 15 and the input device 16 may function as one. As a result, the convenience of the sleep estimation system 1 can be improved.
- the input device 16 may be configured by a conventionally known technique.
- the learning data 122, the teacher data 123, the calculation data 124, and the estimation data 125 may be input to the control device 11 via the communication device 14 or the input device 16. These input data may be stored in the storage device 12. Further, the teacher data 123 and the calculation data 124 may be stored in the storage device 12 in advance. Further, the storage device 12 may store the data obtained by collecting the learning data 122 and the teacher data 123 as the supervised learning data.
- the display device 15 may display the estimated sleep state of the user. Further, the output data 19 output as the sleeping state of the user may be used in another device. In this case, the output data 19 may be output to the outside via the communication device 14 or the like.
- FIG. 5 is a schematic view showing a configuration of the sleep estimation system 1 according to another embodiment.
- the sleep estimation system 1 further includes a sensor device 20 that acquires blood flow data.
- the sleep estimation system 1 has a light emitting unit that irradiates the test site of the user with light, and a light receiving unit that receives interference light including light scattered by the blood flow of the user. 20 may be further provided.
- the control device 11 can acquire blood flow data based on the frequency spectrum of the output of the light receiving unit. As a result, the sleep estimation system 1 can improve convenience.
- the sensor device 20 and the other device may be electrically and optically connected to each other by the bus 13. Further, the sensor device 20 may be able to communicate with each device of the sleep estimation system 1 through the information communication network 2.
- the information communication network 2 includes, for example, at least one of a wireless network and a wired network.
- the information communication network 2 includes, for example, a wireless LAN (Local Area Network), the Internet, and the like.
- the sensor device 20 may be, for example, a laser Doppler blood flow meter.
- the laser Doppler blood flow meter includes a light emitting unit that irradiates a user's test site with light, a light receiving unit that receives light, and a control device that acquires blood flow data.
- the sensor device 20 can measure the blood flow by utilizing the Doppler effect.
- the frequency of the scattered light scattered by the flowing blood shifts (Doppler shift) due to the Doppler effect. Since the light emitted from a general fluorescent lamp or the like contains light of various frequencies with various intensities, it is difficult to grasp the change in frequency due to the Doppler shift. On the other hand, since laser light is light that contains light of a specific frequency extremely predominantly, it is easy to observe a change in frequency due to Doppler shift. Therefore, the sensor device 20 can measure the blood flow by using the interference light including the scattered light.
- the sensor device 20 acquires a beat signal (also referred to as a beat signal) generated by the interference of light from a stationary substance and scattered light from a moving substance by the Doppler effect.
- the beat signal is a relationship between intensity and time.
- the sensor device 20 can acquire the relationship between the frequency and the intensity of the output of the light receiving unit as a frequency spectrum by Fourier transforming the beat signal.
- the frequency and frequency intensity of the output of the light receiving unit depend on the Doppler effect. That is, the frequency spectrum changes depending on the flow rate or flow velocity of blood. Therefore, the sensor device 20 can calculate the blood flow data based on the frequency spectrum.
- the frequency spectrum has a frequency range in which the intensity tends to decrease with a change in flow (for example, an increase in flow rate or flow velocity) and a frequency range in which the intensity tends to increase. Therefore, the control device of the sensor device 20 may acquire the blood flow data by selecting a frequency band suitable for acquiring the blood flow data from the frequencies of the acquired frequency spectrum. As a result, the sensor device 20 can improve the accuracy of the blood flow data included in the learning data 122, the teacher data 123, and the estimation data 125. That is, the sleep estimation system 1 can improve the estimation accuracy of the sleep state.
- the blood flow data included in the learning data 122, the teacher data 123, and the estimation data 125 may remain in the frequency spectrum.
- the frequency spectrum may be data that has undergone arbitrary conversion.
- the sleep estimation system 1 may use the data (converted data) acquired by wavelet transforming the frequency spectrum as blood flow data. By the wavelet transform, the frequency spectrum is weighted by the measurement time for each frequency component. That is, the conversion data is data including the time change of the frequency spectrum. As a result, the sleep estimation system 1 has more features to learn, so that the accuracy of estimating the sleep state can be improved.
- the sensor device 20 calculates the coefficient of variation of the bass motion as blood flow data.
- the sensor device 20 Fourier transforms the beat signal (first beat signal) to acquire a frequency spectrum.
- the sensor device 20 filters the frequency spectrum so that only the frequency range including the component of the bassomotion remains.
- the sensor device 20 Fourier inverse transforms the filtered frequency spectrum and acquires the beat signal (second beat signal) again.
- the sensor device 20 can calculate the coefficient of variation of the intensity of the second beat signal as the coefficient of variation of the bass motion.
- the sleep estimation system 1 according to the embodiment can use the calculated coefficient of variation of the bass motion as blood flow data used as learning data 122 or estimation data 125.
- the sleep estimation system 1 has been explained in detail.
- the neural network may be a convolutional neural network (CNN: Convolutional Neural Network), a recurrent neural network (RNN: Recurrent Neural Network), an LSTM (Long Short Term Memory), or the like.
- CNN Convolutional Neural Network
- RNN Recurrent Neural Network
- LSTM Long Short Term Memory
- the learning model of the approximator 17 is not limited to the one shown in the above embodiment as long as the sleep estimation system 1 can estimate the sleep state of the user based on the learning data 122.
- the various examples described above can be applied in combination as long as they do not contradict each other. And it is understood that innumerable examples not illustrated can be assumed without departing from the scope of this disclosure.
- the sleep estimation system 1 calculates an input device 16 for inputting user blood flow data (estimation data 125) and output data 19 indicating the user's sleep state based on the blood flow data.
- the approximator 17 includes a control device 11 that transmits the blood flow data to the approximator and executes the processing of the calculation, and the approximator is learning data including data of the same type as the blood flow data.
- the learning process is performed using 122 and the teacher data 123 including the same kind of data as the output data related to the learning data.
- the sleep estimation system 1 described in the above embodiment may be configured as one device (sleep estimation device) having each device as a functional unit.
- the sleep estimation device according to one embodiment is for an input unit (for example, a communication device 14, an input device 16, etc.) for inputting a user's blood flow data, an input layer for inputting blood flow data, and an output from the input layer.
- a control unit for example, a control device
- an approximator for example, an approximator 17 having a hidden layer that performs an operation based on the learned parameters and an output layer that outputs the calculation result of the hidden layer as a sleeping state of the user. 11
- the sleep estimation device has a sensor unit (for example, a sensor device 20) including a light emitting unit that irradiates a user's test site with light and a light receiving unit that receives interference light including light scattered by the user's blood flow. ), May be further provided. Then, the control unit may acquire blood flow data based on the frequency spectrum of the output of the light receiving unit.
- a sensor unit for example, a sensor device 20
- the control unit may acquire blood flow data based on the frequency spectrum of the output of the light receiving unit.
- Each step executed by the control program 121 included in the sleep estimation system 1 described in the above embodiment may be interpreted as an invention of the sleep estimation method.
- the input layer for inputting the user's blood flow data the hidden layer for performing the calculation based on the learned parameters for the output from the input layer, and the calculation result of the hidden layer for the user's sleep.
- the sleep estimation method includes a step in which the input layer transmits the blood flow data input to the approximator to the hidden layer, a step in which the hidden layer performs calculations based on the learned parameters on the blood flow data, and an output.
- the layer includes a step of outputting an estimated sleep state of the user based on the calculation result of the hidden layer.
- the sleep estimation method may include a step (learning process) of preparing the approximator using the learning data 122 and the teacher data 123.
- the light emitting portion of the sensor device 20 irradiates the test site of the user with light, and the light receiving portion of the sensor device 20 emits interference light including light scattered by the user's blood flow.
- the control device 11 may further include a step of receiving light and a step of acquiring blood flow data based on the frequency spectrum of the output of the light receiving unit.
- Sleep estimation system (sleep estimation device) 11 Control device (control unit) 12 Storage device 121 Control program 122 Learning data 123 Teacher data 124 Calculation data 125 Estimating data 13 Bus 14 Communication device (input unit) 15 Display device 16 Input device (input unit) 17 Approximator 171 Input layer 172 Hidden layer 173 Output layer 19 Output data 20 Sensor device (sensor unit) 2 Information and communication network
Abstract
Description
図5は、他の実施形態に係る睡眠推定システム1が有する構成を示す概略図である。
上記の実施形態で説明した睡眠推定システム1は、各装置を機能部として有する、一つの装置(睡眠推定装置)として構成されてもよい。一実施形態に係る睡眠推定装置は、ユーザの血流データを入力する入力部(例えば、通信装置14、入力装置16など)と、血流データを入力する入力層、入力層からの出力に対して学習済みパラメータに基づく演算を行なう隠れ層、および隠れ層の演算結果をユーザの睡眠状態として出力する出力層、を有する近似器(例えば、近似器17)を構成する制御部(例えば、制御装置11)と、を備える。
上記の実施形態で説明した睡眠推定システム1が有する制御プログラム121が実行する各工程は、睡眠推定方法の発明として解釈されてもよい。一実施形態に係る睡眠推定方法は、ユーザの血流データを入力する入力層、入力層からの出力に対して学習済みパラメータに基づく演算を行なう隠れ層、および隠れ層の演算結果をユーザの睡眠状態として出力する出力層、を有する近似器を用いて、ユーザの睡眠状態を推定する睡眠推定方法である。睡眠推定方法は、入力層が、近似器に入力された血流データを隠れ層に送信する工程と、隠れ層が、血流データに対して、学習済みパラメータに基づく演算を行なう工程と、出力層が、隠れ層の演算結果に基づいてユーザの推定睡眠状態を出力する工程と、を備える。
11 制御装置(制御部)
12 記憶装置
121 制御プログラム
122 学習用データ
123 教師データ
124 演算用データ
125 推定用データ
13 バス
14 通信装置(入力部)
15 表示装置
16 入力装置(入力部)
17 近似器
171 入力層
172 隠れ層
173 出力層
19 出力データ
20 センサ装置(センサ部)
2 情報通信網
Claims (15)
- ユーザの血流データを入力する入力装置と、
前記血流データから前記ユーザの睡眠状態を示す出力データを演算する制御装置と、を備え、
前記制御装置は、前記血流データから前記出力データを演算可能な近似器を有している、睡眠推定システム。 - 請求項1に記載の睡眠推定システムであって、
前記血流データは、血流量、バソモーションの変動係数、および心拍数の少なくとも一つに関するデータを含む、睡眠推定システム。 - 請求項1または2に記載の睡眠推定システムであって、
前記睡眠状態は、覚醒、レム睡眠、およびノンレム睡眠を示す状態を含む、睡眠推定システム。 - 請求項3に記載の睡眠推定システムであって、
前記ノンレム睡眠は、ステージ1~4のノンレム睡眠を含む、睡眠推定システム。 - 請求項1~4のいずれかに記載の睡眠推定システムであって、
前記近似器は、入力層からの出力に対して学習済みパラメータに基づく演算を行なう隠れ層を有し、
前記学習済みパラメータは、前記近似器において、前記血流データと前記睡眠状態との関係を重み付けしたパラメータである、睡眠推定システム。 - 請求項5のいずれかに記載の睡眠推定システムであって、
前記学習済みパラメータは、前記近似器において、前記血流データと前記睡眠状態との関係を、前記睡眠状態ごとに重み付けしたパラメータである、睡眠推定システム。 - 請求項1~6のいずれかに記載の睡眠推定システムであって、
前記血流データの取得部位は、耳、指、手首、額、鼻、または首である、睡眠推定システム。 - 請求項1~7のいずれかに記載の睡眠推定システムであって、
前記ユーザの被検部位に光を照射する発光部、および前記ユーザの血流によって散乱された前記光を含む干渉光を受光する受光部、を有するセンサ装置、をさらに備え、
前記制御装置は、前記受光部の出力の周波数スペクトルに基づいて、前記血流データを取得する、睡眠推定システム。 - 請求項8に記載の睡眠推定システムであって、
前記制御装置は、前記周波数スペクトルの周波数帯域を選択して、前記血流データを取得する、睡眠推定システム。 - 請求項8または9に記載の睡眠推定システムであって、
前記血流データは、前記周波数スペクトルをウェーブレット変換したデータを含む、睡眠推定システム。 - 請求項1~10のいずれかに記載の睡眠推定システムが備えている前記制御装置としてコンピュータを機能させるための、睡眠推定プログラム。
- ユーザの血流データを入力する入力部と、
前記血流データを入力する入力層、前記入力層からの出力に対して学習済みパラメータに基づく演算を行なう隠れ層、および前記隠れ層の演算結果を前記ユーザの睡眠状態として出力する出力層、を有する近似器を構成する制御部と、を備える、睡眠推定装置。 - 請求項12に記載の睡眠推定装置であって、
前記ユーザの被検部位に光を照射する発光部、および前記ユーザの血流によって散乱された前記光を含む干渉光を受光する受光部、を有するセンサ部、をさらに備え、
前記制御部は、前記受光部の出力の周波数スペクトルに基づいて、前記血流データを取得する、睡眠推定装置。 - 近似器を用いた睡眠推定方法であって、
前記近似器は、ユーザの血流データを入力する入力層、前記入力層からの出力に対して学習済みパラメータに基づく演算を行なう隠れ層、および前記隠れ層の演算結果を前記ユーザの睡眠状態として出力する出力層、を有し、
前記入力層が、前記近似器に入力された前記血流データを前記隠れ層に送信する工程と、
前記隠れ層が、前記血流データに対して、前記学習済みパラメータに基づく演算を行なう工程と、
前記出力層が、前記隠れ層の演算結果に基づいて前記ユーザの推定睡眠状態を出力する工程と、を備える、睡眠推定方法。 - 請求項14に記載の睡眠推定方法であって、
前記近似器に入力される前記血流データは、
センサ装置の発光部によって、前記ユーザの被検部位に光が照射され、
前記センサ装置の受光部によって、前記ユーザの血流によって散乱された前記光を含む干渉光が受光され、
前記受光部の出力の周波数スペクトルに基づいて取得された前記血流データである、睡眠推定方法。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/437,632 US20220142564A1 (en) | 2019-03-11 | 2020-03-11 | Sleep estimation system, sleep estimation device, and method of estimating sleep |
JP2021505112A JPWO2020184627A1 (ja) | 2019-03-11 | 2020-03-11 | |
KR1020217028266A KR20210124369A (ko) | 2019-03-11 | 2020-03-11 | 수면 추정 시스템, 수면 추정 장치, 및 수면 추정 방법 |
EP20769440.7A EP3939502A4 (en) | 2019-03-11 | 2020-03-11 | SLEEP ESTIMATING SYSTEM, SLEEP ESTIMATING DEVICE AND SLEEP ESTIMATING METHOD |
CN202080018420.6A CN113518583A (zh) | 2019-03-11 | 2020-03-11 | 睡眠推定系统、睡眠推定装置以及睡眠推定方法 |
JP2023093406A JP2023111958A (ja) | 2019-03-11 | 2023-06-06 | 睡眠推定システム、睡眠推定装置、および睡眠推定方法 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2019043448 | 2019-03-11 | ||
JP2019-043448 | 2019-03-11 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020184627A1 true WO2020184627A1 (ja) | 2020-09-17 |
Family
ID=72426650
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2020/010619 WO2020184627A1 (ja) | 2019-03-11 | 2020-03-11 | 睡眠推定システム、睡眠推定装置、および睡眠推定方法 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20220142564A1 (ja) |
EP (1) | EP3939502A4 (ja) |
JP (2) | JPWO2020184627A1 (ja) |
KR (1) | KR20210124369A (ja) |
CN (1) | CN113518583A (ja) |
WO (1) | WO2020184627A1 (ja) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09201343A (ja) * | 1996-01-26 | 1997-08-05 | Kunihiko Mitsubuchi | 覚醒状態及び睡眠深度の検出方法 |
JP2005198829A (ja) * | 2004-01-15 | 2005-07-28 | Seiko Epson Corp | 生体情報解析装置、生体情報解析方法、制御プログラムおよび記録媒体 |
JP2007199025A (ja) * | 2006-01-30 | 2007-08-09 | Univ Nihon | 睡眠センサー付身体装着装置 |
JP2016096886A (ja) * | 2014-11-19 | 2016-05-30 | シャープ株式会社 | 睡眠状態判定システム |
US20170215808A1 (en) * | 2016-02-01 | 2017-08-03 | Verily Life Sciences Llc | Machine learnt model to detect rem sleep periods using a spectral analysis of heart rate and motion |
JP2018161432A (ja) | 2017-03-27 | 2018-10-18 | 公立大学法人名古屋市立大学 | 睡眠状態の評価 |
JP2018202130A (ja) * | 2017-05-30 | 2018-12-27 | アルパイン株式会社 | 状態推定装置、情報処理装置、状態推定システム |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006130268A1 (en) * | 2005-06-01 | 2006-12-07 | Medtronic, Inc. | Correlating a non-polysomnographic physiological parameter set with sleep states |
JP4685705B2 (ja) * | 2006-05-18 | 2011-05-18 | 日本電信電話株式会社 | 携帯型生体情報モニタ |
US8660799B2 (en) * | 2008-06-30 | 2014-02-25 | Nellcor Puritan Bennett Ireland | Processing and detecting baseline changes in signals |
WO2014210588A1 (en) * | 2013-06-28 | 2014-12-31 | North Carolina State University | Systems and methods for determining sleep patterns and circadian rhythms |
JP6595479B2 (ja) * | 2013-12-18 | 2019-10-23 | コーニンクレッカ フィリップス エヌ ヴェ | 心臓特性または呼吸特性に基づき睡眠除波活動をエンハンスするシステム及び方法 |
JP6703893B2 (ja) * | 2015-12-01 | 2020-06-03 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカPanasonic Intellectual Property Corporation of America | 体調推定装置、及び、体調推定システム |
US11207021B2 (en) * | 2016-09-06 | 2021-12-28 | Fitbit, Inc | Methods and systems for labeling sleep states |
CN106725382A (zh) * | 2016-12-28 | 2017-05-31 | 天津众阳科技有限公司 | 基于动作和hrv测量的睡眠状态判别系统及方法 |
EP3624681A4 (en) * | 2017-05-18 | 2021-03-10 | Advanced Brain Monitoring, Inc. | SYSTEMS AND METHODS FOR DETECTION AND MANAGEMENT OF PHYSIOLOGICAL PROFILES |
-
2020
- 2020-03-11 WO PCT/JP2020/010619 patent/WO2020184627A1/ja unknown
- 2020-03-11 JP JP2021505112A patent/JPWO2020184627A1/ja active Pending
- 2020-03-11 CN CN202080018420.6A patent/CN113518583A/zh active Pending
- 2020-03-11 EP EP20769440.7A patent/EP3939502A4/en active Pending
- 2020-03-11 KR KR1020217028266A patent/KR20210124369A/ko not_active Application Discontinuation
- 2020-03-11 US US17/437,632 patent/US20220142564A1/en active Pending
-
2023
- 2023-06-06 JP JP2023093406A patent/JP2023111958A/ja active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09201343A (ja) * | 1996-01-26 | 1997-08-05 | Kunihiko Mitsubuchi | 覚醒状態及び睡眠深度の検出方法 |
JP2005198829A (ja) * | 2004-01-15 | 2005-07-28 | Seiko Epson Corp | 生体情報解析装置、生体情報解析方法、制御プログラムおよび記録媒体 |
JP2007199025A (ja) * | 2006-01-30 | 2007-08-09 | Univ Nihon | 睡眠センサー付身体装着装置 |
JP2016096886A (ja) * | 2014-11-19 | 2016-05-30 | シャープ株式会社 | 睡眠状態判定システム |
US20170215808A1 (en) * | 2016-02-01 | 2017-08-03 | Verily Life Sciences Llc | Machine learnt model to detect rem sleep periods using a spectral analysis of heart rate and motion |
JP2018161432A (ja) | 2017-03-27 | 2018-10-18 | 公立大学法人名古屋市立大学 | 睡眠状態の評価 |
JP2018202130A (ja) * | 2017-05-30 | 2018-12-27 | アルパイン株式会社 | 状態推定装置、情報処理装置、状態推定システム |
Non-Patent Citations (1)
Title |
---|
See also references of EP3939502A4 |
Also Published As
Publication number | Publication date |
---|---|
JP2023111958A (ja) | 2023-08-10 |
CN113518583A (zh) | 2021-10-19 |
EP3939502A1 (en) | 2022-01-19 |
JPWO2020184627A1 (ja) | 2020-09-17 |
EP3939502A4 (en) | 2022-11-30 |
KR20210124369A (ko) | 2021-10-14 |
US20220142564A1 (en) | 2022-05-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200100679A1 (en) | Sleep Monitoring and Stimulation | |
US8442632B2 (en) | Method and apparatus for affecting the autonomic nervous system | |
JP7191159B2 (ja) | コンピュータプログラム、及び、被験者の感情状態を提供する方法 | |
CN112005311B (zh) | 用于基于睡眠架构模型向用户递送感官刺激的系统和方法 | |
WO2018042512A1 (ja) | 活動量処理装置、活動量処理方法、及び、活動量処理プログラム | |
US10307100B2 (en) | Methods and systems of controlling a subject's body feature having a periodic wave function | |
US10172530B2 (en) | Biological information processing system and method of controlling biological information processing system | |
CN113228200A (zh) | 用于确定警觉性水平的系统和方法 | |
EP3758590A1 (en) | Systems and methods for modulating physiological state | |
CN112384131A (zh) | 用于使用神经网络来增强被递送给用户的感官刺激的系统和方法 | |
CN113272908A (zh) | 用于利用感官刺激增强rem睡眠的系统和方法 | |
WO2020184627A1 (ja) | 睡眠推定システム、睡眠推定装置、および睡眠推定方法 | |
JP6597900B2 (ja) | 生体リズムの検出装置、検出方法、及び、検出プログラム | |
US20230302253A1 (en) | Systems, methods, and devices for measurement, identification, and generation of sleep state models | |
US20220059210A1 (en) | Systems, methods, and devices for custom sleep age implementation | |
Kuo et al. | An EOG-based automatic sleep scoring system and its related application in sleep environmental control | |
WO2022030623A1 (ja) | 睡眠推定装置、睡眠推定システム、ウェアラブル機器、及び睡眠推定方法 | |
JP2023522838A (ja) | ウイルス感染の非侵襲的予測、検出、及びモニタリングを行う方法及びシステム | |
WO2022181168A1 (ja) | 刺激提示システム、刺激提示方法、プログラム、および、モデル生成システム | |
WO2024090350A1 (ja) | 情報処理装置、情報処理方法及びプログラム | |
EP4334955A1 (en) | Systems, methods, and devices for custom sleep age implementation | |
Xing et al. | Contribution of Timescale Patterns to Photoplethysmography-based Blood Pressure Estimation | |
Akiyama et al. | A Method for Estimating Stress and Relaxed States Using a Pulse Sensor for QOL Visualization | |
JPWO2019151195A1 (ja) | 電子機器、推定システム、制御方法及び制御プログラム | |
JP2020146166A (ja) | 生体情報測定システム及び生体情報測定装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20769440 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20217028266 Country of ref document: KR Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2021505112 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2020769440 Country of ref document: EP Effective date: 20211011 |