CN104706318A - Sleep analysis method and device - Google Patents
Sleep analysis method and device Download PDFInfo
- Publication number
- CN104706318A CN104706318A CN201310687525.2A CN201310687525A CN104706318A CN 104706318 A CN104706318 A CN 104706318A CN 201310687525 A CN201310687525 A CN 201310687525A CN 104706318 A CN104706318 A CN 104706318A
- Authority
- CN
- China
- Prior art keywords
- time section
- monitoring time
- activity
- sub
- eigenvalue
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a sleep analysis method and device. The method includes the steps that multi-axis accelerated speed data collected within each subsidiary monitoring period of a person to be monitored are acquired according to the preset sampling frequency; based on the multi-axis accelerated speed data collected within each subsidiary monitoring period of the person to be monitored, the activity of the person to be monitored within each subsidiary monitoring period is determined; for each subsidiary monitoring period, according to the activity in a subsidiary monitoring period included in a period window corresponding to the subsidiary monitoring period, the activity characteristic value of the person to be monitored within each subsidiary monitoring period is determined, and a dynamic threshold value of the activity characteristic value within the monitoring period is determined as well; the activity characteristic value within each subsidiary monitoring period is compared with the dynamic threshold value, so that a first sleep analysis result of the person to be monitored in a sleeping state or a waking state within each subsidiary monitoring period is acquired. By the adoption of the method, waking and sleeping classification accuracy is improved.
Description
Technical field
The present invention relates to signal analysis field, particularly relate to a kind of sleep analysis method and device.
Background technology
Sleep study is the important component part of hypnosphy and electroencephalography, one of focus of scientific research in the Ye Shi world today.Polysomnography is current internationally recognized sleep monitor " goldstandard ", and by being attached to person to be monitored electrode with it, the indexs such as the blood oxygen of record tester, electrocardio, eye are dynamic, lower limb is dynamic, brain is electric, judge the sleep quality of person to be monitored.But Polysomnography equipment manufacturing cost is expensive, along with the progress of science and technology, to the research of sleep monitor gradually to the future development of miniaturization and family oriented.By gathering the multiaxis acceleration information between user's sleep period, this feature of acceleration when utilizing the acceleration between user's sleep period to be less than clear-headed, carries out analysis of keeping alert while in bed.
In existing technical scheme, the multiaxis acceleration information of person to be monitored is gathered by acceleration transducer, this multiaxis acceleration information is divided into multiple subdata section, by the movable number of times within the time period of subdata section correspondence by judging to obtain to multiaxis acceleration information, as the activity in this time period, and when the activity in this time period is greater than a fixed threshold, determine that person to be monitored is waking state within this time period, otherwise, for sleep state, each subdata section is analyzed, finally obtain the sleep analysis result of person to be monitored in whole monitoring time section.Subsequent treatment can also be carried out to this sleep analysis result, such as, when of short duration regaining consciousness has appearred in person to be monitored in long sleep procedure, then this of short duration clear-headed state is judged to sleep, when person to be monitored has occurred of short duration sleep in process of regaining consciousness for a long time, then the state of this microsleep is judged to clear-headed.
But for different persons to be monitored, sleep habit is different, quieter between presumable person's sleep period to be monitored, and often move between some possibility sleep period, this just causes the classification accuracy of keeping alert while in bed based on fixed threshold judgement lower.
Summary of the invention
The embodiment of the present invention provides a kind of sleep analysis method and device, in order to solve the problem lower based on the classification accuracy of keeping alert while in bed of fixed threshold judgement existed in prior art.
The multiaxis acceleration information of the person to be monitored that the embodiment of the present invention provides a kind of acquisition to gather in every sub-monitoring time section according to default sample frequency, described multiaxis acceleration information comprises multiple multiaxis acceleration, wherein, a monitoring time section comprises multiple sub-monitoring time section;
Respectively based on the multiaxis acceleration information of the person described to be monitored gathered in every sub-monitoring time section, determine the activity of described person to be monitored in every sub-monitoring time section;
Respectively for every sub-monitoring time section, according to the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, determine the activity eigenvalue of described person to be detected in every sub-monitoring time section, wherein, the time period window of sub-monitoring time section correspondence comprises this sub-monitoring time section and some sub-monitoring time sections before and after it;
According to the activity eigenvalue in multiple sub-monitoring time section described in monitoring time section, determine the dynamic threshold of activity eigenvalue in described monitoring time section;
Respectively the activity eigenvalue in every sub-monitoring time section and described dynamic threshold are compared, obtain the first sleep analysis result that described person to be monitored is sleep state or waking state in every sub-monitoring time section.
The method that theres is provided of the embodiment of the present invention is provided, based on the activity of sub-monitoring time section, and the activity of other sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, determine the activity eigenvalue of sub-monitoring time section; According to the activity eigenvalue of monitoring time section sub-in whole monitoring time section, determine the dynamic threshold of activity eigenvalue in whole monitoring time section; Judge that person to be monitored is still clear-headed every sub-monitoring time section sleep according to dynamic threshold.Compared to prior art, improve the accuracy rate of classification of keeping alert while in bed.
The embodiment of the present invention also provides a kind of sleep analysis device, comprising:
Data capture unit, for obtaining the multiaxis acceleration information of the person to be monitored gathered in every sub-monitoring time section according to default sample frequency, described multiaxis acceleration information comprises multiple multiaxis acceleration, and wherein, a monitoring time section comprises multiple sub-monitoring time section;
Activity determining unit, for respectively based on the multiaxis acceleration information of the person described to be monitored gathered in every sub-monitoring time section, determines the activity of described person to be monitored in every sub-monitoring time section;
Activity eigenvalue determining unit, for respectively for every sub-monitoring time section, according to the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, determine the activity eigenvalue of described person to be detected in every sub-monitoring time section, wherein, the time period window of sub-monitoring time section correspondence comprises this sub-monitoring time section and some sub-monitoring time sections before and after it;
Dynamic threshold determining unit, for according to the activity eigenvalue in multiple sub-monitoring time section described in monitoring time section, determines the dynamic threshold of activity eigenvalue in described monitoring time section;
Processing unit, for the activity eigenvalue in every sub-monitoring time section and described dynamic threshold being compared respectively, obtains the first sleep analysis result that described person to be monitored is sleep state or waking state in every sub-monitoring time section.
The further feature of the application and advantage will be set forth in the following description, and, partly become apparent from description, or understand by implementing the application.The object of the application and other advantages realize by structure specifically noted in write description, claims and accompanying drawing and obtain.
Accompanying drawing explanation
Accompanying drawing is used to provide a further understanding of the present invention, and forms a part for description, is used from explanation the present invention, is not construed as limiting the invention with the embodiment of the present invention one.In the accompanying drawings:
One of flow chart of the sleep analysis method that Fig. 1 provides for the embodiment of the present invention;
The flow chart two of the sleep analysis method that Fig. 2 provides for the embodiment of the present invention;
Fig. 3 carries out the flow chart of sleep analysis for low frequency multiaxis acceleration information that the embodiment of the present invention provides;
The structural representation of the sleep analysis device that Fig. 4 provides for the embodiment of the present invention.
Detailed description of the invention
Treat human observer to keep alert while in bed the implementation of accuracy rate of classification to provide to improve, embodiments provide a kind of sleep analysis method and device, below in conjunction with Figure of description, the preferred embodiments of the present invention are described, be to be understood that, preferred embodiment described herein, only for instruction and explanation of the present invention, is not intended to limit the present invention.And when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.
The embodiment of the present invention provides a kind of sleep analysis method, and idiographic flow as shown in Figure 1, comprising:
Step 101, obtain the multiaxis acceleration information of the person to be monitored gathered in every sub-monitoring time section according to default sample frequency, this multiaxis acceleration information comprises multiple multiaxis acceleration, and wherein, a monitoring time section comprises multiple sub-monitoring time section.
Step 102, respectively based on the multiaxis acceleration information of this person to be monitored gathered in every sub-monitoring time section, determine the activity of this person to be monitored in every sub-monitoring time section.
Step 103, respectively for every sub-monitoring time section, according to the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, determine the activity eigenvalue of this person to be detected in every sub-monitoring time section, wherein, the time period window of sub-monitoring time section correspondence comprises this sub-monitoring time section and some sub-monitoring time sections before and after it.
Step 104, according to the activity eigenvalue in sub-monitoring time section the plurality of in monitoring time section, determine the dynamic threshold of activity eigenvalue in this monitoring time section.
Step 105, respectively the activity eigenvalue in every sub-monitoring time section to be compared with this dynamic threshold, obtain the first sleep analysis result that this person to be monitored is sleep state or waking state in every sub-monitoring time section.
In the embodiment of the present invention, multiaxis acceleration information can be gathered by acceleration transducer, can will treat human observer sleep analysis the whole night as a monitoring time section, this monitoring time section is divided into multiple sub-monitoring time section, the multiaxis acceleration information of every sub-monitoring time section is analyzed.
The method that theres is provided of the embodiment of the present invention is provided, based on the activity of sub-monitoring time section, and the activity of other sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, determine the activity eigenvalue of sub-monitoring time section; According to the activity eigenvalue of monitoring time section sub-in whole monitoring time section, determine the dynamic threshold of activity eigenvalue in whole monitoring time section; Judge that person to be monitored is still clear-headed every sub-monitoring time section sleep according to dynamic threshold.Compared to prior art, improve the accuracy rate of classification of keeping alert while in bed.
Below in conjunction with accompanying drawing, with specific embodiment, method provided by the invention and device and corresponding system are described in detail.Method detailed step as shown in Figure 2, comprising:
Step 201, to gather the multiaxis acceleration information of person to be monitored in monitoring time section carry out bandpass filtering.The multiaxis acceleration that user's physical activity produces has a frequency range, carries out bandpass filtering, mainly in order to remove interference to multiaxis acceleration.
Step 202, by filtered data, sample to the multiaxis acceleration information in every sub-monitoring time section according to default sample frequency, wherein, sub-monitoring time section can be set to 1 minute.
Step 203, based on the multiaxis acceleration information after sampling, determine the activity of person to be monitored in every sub-monitoring time section.
Wherein, when in this sub-monitoring time section, the multiaxis acceleration of sampled point is greater than predetermined acceleration threshold value, determine that this person to be monitored is movable in the moment that this sampled point is corresponding, this sampled point is determined according to default sample frequency; By the total degree of person's activity to be monitored determined in this sub-monitoring time section, be defined as the activity of person to be monitored in this sub-monitoring time section.
Calculating about activity has multiple method, and can select threshold method, zero passage method, area-method etc., the present embodiment selects threshold method to carry out the determination of activity.
Step 204, determine average, the variance of the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, respectively as average, the variance of activity in the time period window of this sub-monitoring time section correspondence, and determine that in this time period window, activity is greater than the number of the sub-monitoring time section of default activity.
Time period window can be set to 5 minutes, sub-monitoring time section is 1 minute, the then sub-monitoring time section that comprises of the time period window of this sub-monitoring time section correspondence, be the sub-monitoring time section of each 2 minutes correspondences before and after current sub-monitoring time section and current sub-monitoring time section, determine average and the variance of these 5 sub-monitoring time section activities.
In step 205, average, variance and this time period window to activity in this time period window, activity is greater than the number of the sub-monitoring time section of default activity, be weighted summation, obtain the activity eigenvalue in this sub-monitoring time section, activity eigenvalue is called PS value.
The determination of PS value can also be determined according to the maximum of other sub-monitoring time section activities in the logarithm of the activity of sub-monitoring time section current in time period window, current sub-monitoring time section activity and this time period window and variable quantity etc., and weight coefficient is empirical value.
Step 206, the average determining the multiple PS values in monitoring time section in multiple sub-monitoring time section and variance, respectively as average and the variance of PS value in monitoring time section.
Step 207, based on the average of PS value in this monitoring time section and variance, determine the dynamic threshold of PS value.
When the mean and variance sum of activity eigenvalue in this monitoring time section is greater than the first default activity eigenvalue threshold, this first default eigenvalue threshold is defined as the dynamic threshold of activity eigenvalue in this monitoring time section;
Activity eigenvalue threshold is preset when the mean and variance sum of activity eigenvalue in this monitoring time section is not more than first, and when in this monitoring time section, the mean and variance sum of activity eigenvalue is less than the second default activity eigenvalue threshold, this second default activity eigenvalue threshold is defined as the dynamic threshold of activity eigenvalue in this monitoring time section, wherein, this second default activity eigenvalue threshold is less than this first default activity eigenvalue threshold;
Activity eigenvalue threshold is preset when the mean and variance sum of activity eigenvalue in this monitoring time section is not more than first, and when the mean and variance sum of activity eigenvalue is not less than the second default eigenvalue threshold in this monitoring time section, the mean and variance sum of activity eigenvalue in this monitoring time section is defined as the dynamic threshold of activity eigenvalue in this monitoring time section.
Step 208, the dynamic threshold of PS value in the PS value in sub-monitoring time section and this monitoring time section to be compared, obtain the first sleep analysis result of person to be monitored in sub-monitoring time section.
Wherein, when the activity eigenvalue of group monitoring time section is greater than the dynamic threshold of activity eigenvalue in this monitoring time section, determine that person to be monitored is waking state in this sub-monitoring time section;
When the activity eigenvalue of group monitoring time section is not more than the dynamic threshold of activity eigenvalue in this monitoring time section, determine that person to be monitored is waking state in this sub-monitoring time section.
In the method that above-described embodiment provides, additive method can also be adopted about dynamic threshold value determination method, as maximum between-cluster variance algorithm, it is a kind of adaptive threshold method, based on multiple threshold value, for each threshold value, will regain consciousness and sleep as two classifications, calculate inter-class variance, using make the inter-class variance of two classes maximum threshold value as final threshold value; According to different threshold values, entropy threshold method, determines that every sub-monitoring time section is probability that is clear-headed or sleep, and the entropy of correspondence, determines the threshold value that entropy can be made maximum; Minimum error method, the method derives from Bayes minimum error sorting technique, Eb (T) is the probability that target class (regaining consciousness) mistake assigns to background classes (sleep), Eo (T) is the probability that background classes (sleep) mistake assigns to target class (regaining consciousness), total probability of error E (T)=Eb (T)+Eo (T), make E (T) get minima, be optimal classification method.
In addition, some user may read a book, play the customs such as mobile phone before sleeping, the multiaxis acceleration information frequency that sort of activity brings is lower, only adopt above-mentioned processing procedure likely can be judged as sleep state, therefore, the embodiment of the present invention also provides a kind of method of low frequency multiaxis acceleration information being carried out to sleep analysis, and concrete steps as shown in Figure 3, comprising:
Step 301, low-pass filtering is carried out to the multiaxis acceleration information of person to be monitored in monitoring time section, obtain the low frequency multiaxis acceleration information in every sub-monitoring time section.
Step 302, determine the complexity of low frequency multiaxis acceleration information in every sub-monitoring time section respectively.
Wherein, the defining method of complexity can have multiple, this programme first can determine the extreme value number of low frequency multiaxis acceleration information and the difference of adjacent maximum and minimum in sub-monitoring time section, these two parameters are weighted summation, determine the complexity of low frequency multiaxis acceleration information in sub-monitoring time section.
Step 303, according to the average of low frequency multiaxis acceleration information complexity in the multiple sub-monitoring time section in monitoring time section and variance, determine the dynamic threshold of this complexity in this monitoring time section.Determination about complexity dynamic threshold can be identical with above-mentioned PS value dynamic threshold value determination method, do not repeat them here.
Step 304, whether be greater than the dynamic threshold of this complexity according to the complexity of low frequency multiaxis acceleration information in sub-monitoring time section, determine person to be monitored second sleep analysis result for sleep state or waking state in this sub-monitoring time section.
When the mean and variance sum of complexity in this monitoring time section is greater than the first default complexity threshold, this first default complexity threshold is defined as the dynamic threshold of complexity in this monitoring time section;
Complexity threshold is preset when the mean and variance sum of complexity in this monitoring time section is not more than first, and when in this monitoring time section, the mean and variance sum of complexity is less than the second default complexity threshold, this second default complexity threshold is defined as the dynamic threshold of complexity in this monitoring time section, wherein, this second default complexity threshold is less than this first default complexity threshold;
Complexity threshold is preset when the mean and variance sum of complexity in this monitoring time section is not more than first, and when the mean and variance sum of complexity is not less than the second default complexity threshold in this monitoring time section, the average of complexity in this monitoring time section and variance sum are defined as the dynamic threshold of complexity in this monitoring time section.
Step 305, be sleep state for above-mentioned first sleep analysis result and the second sleep analysis result is the sub-monitoring time section of waking state, determine that the 3rd sleep analysis result of this sub-monitoring time section is waking state.Wherein, using the 3rd sleep analysis result as the sleep analysis result final in monitoring time section of person to be monitored.The sleep state can also treating human observer based on the 3rd sleep analysis result is further analyzed.
Based on same inventive concept, according to the sleep analysis method that the above embodiment of the present invention provides, correspondingly, another embodiment of the present invention additionally provides sleep analysis device, and apparatus structure schematic diagram as shown in Figure 4, specifically comprises:
Data capture unit 401, for obtaining the multiaxis acceleration information of the person to be monitored gathered in every sub-monitoring time section according to default sample frequency, this multiaxis acceleration information comprises multiple multiaxis acceleration, and wherein, a monitoring time section comprises multiple sub-monitoring time section;
Activity determining unit 402, for respectively based on the multiaxis acceleration information of this person to be monitored gathered in every sub-monitoring time section, determines the activity of this person to be monitored in every sub-monitoring time section;
Activity eigenvalue determining unit 403, for respectively for every sub-monitoring time section, according to the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, determine the activity eigenvalue of this person to be detected in every sub-monitoring time section, wherein, the time period window of sub-monitoring time section correspondence comprises this sub-monitoring time section and some sub-monitoring time sections before and after it;
Dynamic threshold determining unit 404, for according to the activity eigenvalue in sub-monitoring time section the plurality of in monitoring time section, determines the dynamic threshold of activity eigenvalue in this monitoring time section;
Processing unit 405, for the activity eigenvalue in every sub-monitoring time section and this dynamic threshold being compared respectively, obtains the first sleep analysis result that this person to be monitored is sleep state or waking state in every sub-monitoring time section.
Further, activity determining unit 402, specifically for when in this sub-monitoring time section, the multiaxis acceleration of sampled point is greater than predetermined acceleration threshold value, determine that this person to be monitored is movable in the moment that this sampled point is corresponding, this sampled point is determined according to default sample frequency; And by determining the total degree of this person's activity to be monitored in this sub-monitoring time section, be defined as the activity of this person to be monitored in this sub-monitoring time section.
Further, activity eigenvalue determining unit 403, specifically for determining average, the variance of the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, respectively as average, the variance of activity in the time period window of this sub-monitoring time section correspondence;
Determine that in this time period window, activity is greater than the number of the sub-monitoring time section of default activity;
The number of the sub-monitoring time section of default activity is greater than to activity in the average of activity in this time period window, variance and this time period window, is weighted summation, obtains the activity eigenvalue in this sub-monitoring time section;
Dynamic threshold determining unit 404, specifically for: average and the variance of determining the multiple activity eigenvalues in monitoring time section in the plurality of sub-monitoring time section, respectively as average and the variance of activity eigenvalue in this monitoring time section;
When the mean and variance sum of activity eigenvalue in this monitoring time section is greater than the first default activity eigenvalue threshold, this first default eigenvalue threshold is defined as the dynamic threshold of activity eigenvalue in this monitoring time section;
Activity eigenvalue threshold is preset when the mean and variance sum of activity eigenvalue in this monitoring time section is not more than first, and when in this monitoring time section, the mean and variance sum of activity eigenvalue is less than the second default activity eigenvalue threshold, this second default activity eigenvalue threshold is defined as the dynamic threshold of activity eigenvalue in this monitoring time section, wherein, this second default activity eigenvalue threshold is less than this first default activity eigenvalue threshold;
Activity eigenvalue threshold is preset when the mean and variance sum of activity eigenvalue in this monitoring time section is not more than first, and when the mean and variance sum of activity eigenvalue is not less than the second default eigenvalue threshold in this monitoring time section, the mean and variance sum of activity eigenvalue in this monitoring time section is defined as the dynamic threshold of activity eigenvalue in this monitoring time section.
Further, processing unit 405, when the activity eigenvalue specifically for group monitoring time section is greater than the dynamic threshold of activity eigenvalue in this monitoring time section, determines that person to be monitored is waking state in this sub-monitoring time section; And the activity eigenvalue of group monitoring time section is when being not more than the dynamic threshold of activity eigenvalue in this monitoring time section, determine that person to be monitored is waking state in this sub-monitoring time section.
Further, said apparatus, also comprises: low-frequency data processing unit 406, for carrying out low-pass filtering to the multiaxis acceleration information in the plurality of sub-monitoring time section according to predeterminated frequency, obtains the low frequency multiaxis acceleration information in every sub-monitoring time section;
Determine the complexity of low frequency multiaxis acceleration information in every sub-monitoring time section respectively;
According to average and the variance of low frequency multiaxis acceleration information complexity in the plurality of sub-monitoring time section in this monitoring time section, determine the dynamic threshold of this complexity in this monitoring time section;
Whether be greater than the dynamic threshold of this complexity according to the complexity of low frequency multiaxis acceleration information in sub-monitoring time section, determine that this person to be monitored is the second sleep analysis result of sleep state or waking state in this sub-monitoring time section;
Be sleep state for the first sleep analysis result and the second sleep analysis result is the sub-monitoring time section of waking state, determine that the 3rd sleep analysis result of this sub-monitoring time section is waking state.
Further, low-frequency data processing unit 406, determine the complexity of low frequency multiaxis acceleration information in a sub-monitoring time section, specifically for determining the extreme value number of low frequency multiaxis acceleration information and the difference of adjacent maximum and minimum in this sub-monitoring time section; And to the extreme value number of low frequency multiaxis acceleration information and the difference of adjacent maximum and minimum in this sub-monitoring time section, be weighted summation, determine the complexity of low frequency multiaxis acceleration information in sub-monitoring time section.
Further, low-frequency data processing unit 406, determine the dynamic threshold of complexity in this monitoring time section, during specifically for being greater than the first default complexity threshold when the mean and variance sum of complexity in this monitoring time section, this first default complexity threshold is defined as the dynamic threshold of complexity in this monitoring time section;
Complexity threshold is preset when the mean and variance sum of complexity in this monitoring time section is not more than first, and when in this monitoring time section, the mean and variance sum of complexity is less than the second default complexity threshold, this second default complexity threshold is defined as the dynamic threshold of complexity in this monitoring time section, wherein, this second default complexity threshold is less than this first default complexity threshold;
Complexity threshold is preset when the mean and variance sum of complexity in this monitoring time section is not more than first, and when the mean and variance sum of complexity is not less than the second default complexity threshold in this monitoring time section, the average of complexity in this monitoring time section and variance sum are defined as the dynamic threshold of complexity in this monitoring time section.
The function of above-mentioned each unit may correspond to the respective handling step in flow process shown in Fig. 1 to Fig. 3, does not repeat them here.
To sum up be somebody's turn to do, the scheme that the embodiment of the present invention provides, obtain the multiaxis acceleration information of the person to be monitored gathered in every sub-monitoring time section according to default sample frequency; Respectively based on the multiaxis acceleration information of this person to be monitored gathered in every sub-monitoring time section, determine the activity of this person to be monitored in every sub-monitoring time section; And respectively for every sub-monitoring time section, according to the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, determine the activity eigenvalue of this person to be detected in every sub-monitoring time section; And according to the activity eigenvalue in sub-monitoring time section the plurality of in monitoring time section, determine the dynamic threshold of activity eigenvalue in this monitoring time section; Respectively the activity eigenvalue in every sub-monitoring time section and this dynamic threshold are compared, obtain the first sleep analysis result that this person to be monitored is sleep state or waking state in every sub-monitoring time section.Adopt the method that the embodiment of the present invention provides, compared to prior art, improve the accuracy rate of classification of keeping alert while in bed.
The sleep analysis device that the embodiment of the application provides realizes by computer program.Those skilled in the art should be understood that; above-mentioned Module Division mode is only the one in numerous Module Division mode; if be divided into other modules or do not divide module, as long as sleep analysis device has above-mentioned functions, all should within the protection domain of the application.
The application describes with reference to according to the flow chart of the method for the embodiment of the present application, equipment (system) and computer program and/or block diagram.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block diagram and/or square frame and flow chart and/or block diagram and/or square frame.These computer program instructions can being provided to the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device to produce a machine, making the instruction performed by the processor of computer or other programmable data processing device produce device for realizing the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer-readable memory that works in a specific way of vectoring computer or other programmable data processing device, the instruction making to be stored in this computer-readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, make on computer or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computer or other programmable devices is provided for the step realizing the function of specifying in flow chart flow process or multiple flow process and/or block diagram square frame or multiple square frame.
Obviously, those skilled in the art can carry out various change and modification to the present invention and not depart from the spirit and scope of the present invention.Like this, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification.
Claims (14)
1. a sleep analysis method, is characterized in that, comprising:
Obtain the multiaxis acceleration information of the person to be monitored gathered in every sub-monitoring time section according to default sample frequency, described multiaxis acceleration information comprises multiple multiaxis acceleration, and wherein, a monitoring time section comprises multiple sub-monitoring time section;
Respectively based on the multiaxis acceleration information of the person described to be monitored gathered in every sub-monitoring time section, determine the activity of described person to be monitored in every sub-monitoring time section;
Respectively for every sub-monitoring time section, according to the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, determine the activity eigenvalue of described person to be detected in every sub-monitoring time section, wherein, the time period window of sub-monitoring time section correspondence comprises this sub-monitoring time section and some sub-monitoring time sections before and after it;
According to the activity eigenvalue in multiple sub-monitoring time section described in monitoring time section, determine the dynamic threshold of activity eigenvalue in described monitoring time section;
Respectively the activity eigenvalue in every sub-monitoring time section and described dynamic threshold are compared, obtain the first sleep analysis result that described person to be monitored is sleep state or waking state in every sub-monitoring time section.
2. the method for claim 1, is characterized in that, based on the multiaxis acceleration information of the person described to be monitored gathered in sub-monitoring time section, determines the activity of described person to be monitored in this sub-monitoring time section, specifically comprises:
When in this sub-monitoring time section, the multiaxis acceleration of sampled point is greater than predetermined acceleration threshold value, determine that described person to be monitored is movable in the moment that this sampled point is corresponding, described sampled point is determined according to default sample frequency;
By determining the total degree of described person's activity to be monitored in this sub-monitoring time section, be defined as the activity of described person to be monitored in this sub-monitoring time section.
3. the method for claim 1, is characterized in that, according to the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, determines the activity eigenvalue of described person to be detected in every sub-monitoring time section, specifically comprises:
Determine average, the variance of the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, respectively as average, the variance of activity in the time period window of this sub-monitoring time section correspondence;
Determine that in this time period window, activity is greater than the number of the sub-monitoring time section of default activity;
The number of the sub-monitoring time section of default activity is greater than to activity in the average of activity in this time period window, variance and this time period window, is weighted summation, obtains the activity eigenvalue in this sub-monitoring time section;
According to the activity eigenvalue in multiple sub-monitoring time section described in monitoring time section, determine the dynamic threshold of activity eigenvalue in described monitoring time section, specifically comprise:
Determine average and the variance of the multiple activity eigenvalues in monitoring time section in described multiple sub-monitoring time section, respectively as average and the variance of activity eigenvalue in described monitoring time section;
When the mean and variance sum of activity eigenvalue in described monitoring time section is greater than the first default activity eigenvalue threshold, preset described first the dynamic threshold that eigenvalue threshold is defined as activity eigenvalue in described monitoring time section;
Activity eigenvalue threshold is preset when the mean and variance sum of activity eigenvalue in described monitoring time section is not more than first, and when in described monitoring time section, the mean and variance sum of activity eigenvalue is less than the second default activity eigenvalue threshold, the dynamic threshold that activity eigenvalue threshold is defined as activity eigenvalue in described monitoring time section is preset by described second, wherein, the described second default activity eigenvalue threshold is less than the described first default activity eigenvalue threshold;
Activity eigenvalue threshold is preset when the mean and variance sum of activity eigenvalue in described monitoring time section is not more than first, and when the mean and variance sum of activity eigenvalue is not less than the second default eigenvalue threshold in described monitoring time section, the mean and variance sum of activity eigenvalue in described monitoring time section is defined as the dynamic threshold of activity eigenvalue in described monitoring time section.
4. the method for claim 1, it is characterized in that, the dynamic threshold of activity eigenvalue in activity eigenvalue in sub-monitoring time section and described monitoring time section is compared, obtains the first sleep analysis result of person to be monitored in sub-monitoring time section, specifically comprise:
When the activity eigenvalue of group monitoring time section is greater than the dynamic threshold of activity eigenvalue in described monitoring time section, determine that person to be monitored is waking state in this sub-monitoring time section;
When the activity eigenvalue of group monitoring time section is not more than the dynamic threshold of activity eigenvalue in described monitoring time section, determine that person to be monitored is waking state in this sub-monitoring time section.
5. the method for claim 1, is characterized in that, after obtaining the multiaxis acceleration information of the person to be monitored gathered in every sub-monitoring time section according to default sample frequency, also comprises:
According to predeterminated frequency, low-pass filtering is carried out to the multiaxis acceleration information in described multiple sub-monitoring time section, obtains the low frequency multiaxis acceleration information in every sub-monitoring time section;
Determine the complexity of low frequency multiaxis acceleration information in every sub-monitoring time section respectively;
According to average and the variance of low frequency multiaxis acceleration information complexity in the described multiple sub-monitoring time section in described monitoring time section, determine the dynamic threshold of this complexity in described monitoring time section;
Whether be greater than the dynamic threshold of described complexity according to the complexity of low frequency multiaxis acceleration information in sub-monitoring time section, determine that described person to be monitored is the second sleep analysis result of sleep state or waking state in this sub-monitoring time section;
Be sleep state for the first sleep analysis result and the second sleep analysis result is the sub-monitoring time section of waking state, determine that the 3rd sleep analysis result of this sub-monitoring time section is waking state.
6. method as claimed in claim 5, is characterized in that, determine the complexity of low frequency multiaxis acceleration information in a sub-monitoring time section, specifically comprise:
Determine the extreme value number of low frequency multiaxis acceleration information and the difference of adjacent maximum and minimum in described sub-monitoring time section;
To the extreme value number of low frequency multiaxis acceleration information and the difference of adjacent maximum and minimum in described sub-monitoring time section, be weighted summation, determine the complexity of low frequency multiaxis acceleration information in sub-monitoring time section.
7. method as claimed in claim 5, is characterized in that, determine the dynamic threshold of complexity in described monitoring time section, specifically comprise:
When the mean and variance sum of complexity in described monitoring time section is greater than the first default complexity threshold, preset described first the dynamic threshold that complexity threshold is defined as complexity in described monitoring time section;
Complexity threshold is preset when the mean and variance sum of complexity in described monitoring time section is not more than first, and when in described monitoring time section, the mean and variance sum of complexity is less than the second default complexity threshold, the dynamic threshold that complexity threshold is defined as complexity in described monitoring time section is preset by described second, wherein, the described second default complexity threshold is less than the described first default complexity threshold;
Complexity threshold is preset when the mean and variance sum of complexity in described monitoring time section is not more than first, and when the mean and variance sum of complexity is not less than the second default complexity threshold in described monitoring time section, the average of complexity in described monitoring time section and variance sum are defined as the dynamic threshold of complexity in described monitoring time section.
8. a sleep analysis device, is characterized in that, comprising:
Data capture unit, for obtaining the multiaxis acceleration information of the person to be monitored gathered in every sub-monitoring time section according to default sample frequency, described multiaxis acceleration information comprises multiple multiaxis acceleration, and wherein, a monitoring time section comprises multiple sub-monitoring time section;
Activity determining unit, for respectively based on the multiaxis acceleration information of the person described to be monitored gathered in every sub-monitoring time section, determines the activity of described person to be monitored in every sub-monitoring time section;
Activity eigenvalue determining unit, for respectively for every sub-monitoring time section, according to the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, determine the activity eigenvalue of described person to be detected in every sub-monitoring time section, wherein, the time period window of sub-monitoring time section correspondence comprises this sub-monitoring time section and some sub-monitoring time sections before and after it;
Dynamic threshold determining unit, for according to the activity eigenvalue in multiple sub-monitoring time section described in monitoring time section, determines the dynamic threshold of activity eigenvalue in described monitoring time section;
Processing unit, for the activity eigenvalue in every sub-monitoring time section and described dynamic threshold being compared respectively, obtains the first sleep analysis result that described person to be monitored is sleep state or waking state in every sub-monitoring time section.
9. device as claimed in claim 8, it is characterized in that, described activity determining unit, specifically for when in this sub-monitoring time section, the multiaxis acceleration of sampled point is greater than predetermined acceleration threshold value, determine that described person to be monitored is movable in the moment that this sampled point is corresponding, described sampled point is determined according to default sample frequency; And by determining the total degree of described person's activity to be monitored in this sub-monitoring time section, be defined as the activity of described person to be monitored in this sub-monitoring time section.
10. device as claimed in claim 8, it is characterized in that, described activity eigenvalue determining unit, specifically for determining average, the variance of the activity in the sub-monitoring time section that the time period window of this sub-monitoring time section correspondence comprises, respectively as average, the variance of activity in the time period window of this sub-monitoring time section correspondence;
Determine that in this time period window, activity is greater than the number of the sub-monitoring time section of default activity;
The number of the sub-monitoring time section of default activity is greater than to activity in the average of activity in this time period window, variance and this time period window, is weighted summation, obtains the activity eigenvalue in this sub-monitoring time section;
Described dynamic threshold determining unit, specifically for:
Determine average and the variance of the multiple activity eigenvalues in monitoring time section in described multiple sub-monitoring time section, respectively as average and the variance of activity eigenvalue in described monitoring time section;
When the mean and variance sum of activity eigenvalue in described monitoring time section is greater than the first default activity eigenvalue threshold, preset described first the dynamic threshold that eigenvalue threshold is defined as activity eigenvalue in described monitoring time section;
Activity eigenvalue threshold is preset when the mean and variance sum of activity eigenvalue in described monitoring time section is not more than first, and when in described monitoring time section, the mean and variance sum of activity eigenvalue is less than the second default activity eigenvalue threshold, the dynamic threshold that activity eigenvalue threshold is defined as activity eigenvalue in described monitoring time section is preset by described second, wherein, the described second default activity eigenvalue threshold is less than the described first default activity eigenvalue threshold;
Activity eigenvalue threshold is preset when the mean and variance sum of activity eigenvalue in described monitoring time section is not more than first, and when the mean and variance sum of activity eigenvalue is not less than the second default eigenvalue threshold in described monitoring time section, the mean and variance sum of activity eigenvalue in described monitoring time section is defined as the dynamic threshold of activity eigenvalue in described monitoring time section.
11. devices as claimed in claim 8, it is characterized in that, described processing unit, when the activity eigenvalue specifically for group monitoring time section is greater than the dynamic threshold of activity eigenvalue in described monitoring time section, determines that person to be monitored is waking state in this sub-monitoring time section; And the activity eigenvalue of group monitoring time section is when being not more than the dynamic threshold of activity eigenvalue in described monitoring time section, determine that person to be monitored is waking state in this sub-monitoring time section.
12. devices as claimed in claim 8, it is characterized in that, described device, also comprise: low-frequency data processing unit, for carrying out low-pass filtering to the multiaxis acceleration information in described multiple sub-monitoring time section according to predeterminated frequency, obtain the low frequency multiaxis acceleration information in every sub-monitoring time section;
Determine the complexity of low frequency multiaxis acceleration information in every sub-monitoring time section respectively;
According to average and the variance of low frequency multiaxis acceleration information complexity in the described multiple sub-monitoring time section in described monitoring time section, determine the dynamic threshold of this complexity in described monitoring time section;
Whether be greater than the dynamic threshold of described complexity according to the complexity of low frequency multiaxis acceleration information in sub-monitoring time section, determine that described person to be monitored is the second sleep analysis result of sleep state or waking state in this sub-monitoring time section;
Be sleep state for the first sleep analysis result and the second sleep analysis result is the sub-monitoring time section of waking state, determine that the 3rd sleep analysis result of this sub-monitoring time section is waking state.
13. devices as claimed in claim 12, it is characterized in that, described low-frequency data processing unit, determine the complexity of low frequency multiaxis acceleration information in a sub-monitoring time section, specifically for determining the extreme value number of low frequency multiaxis acceleration information and the difference of adjacent maximum and minimum in described sub-monitoring time section; And to the extreme value number of low frequency multiaxis acceleration information and the difference of adjacent maximum and minimum in described sub-monitoring time section, be weighted summation, determine the complexity of low frequency multiaxis acceleration information in sub-monitoring time section.
14. devices as claimed in claim 12, it is characterized in that, described low-frequency data processing unit, determine the dynamic threshold of complexity in described monitoring time section, during specifically for being greater than the first default complexity threshold when the mean and variance sum of complexity in described monitoring time section, preset described first the dynamic threshold that complexity threshold is defined as complexity in described monitoring time section;
Complexity threshold is preset when the mean and variance sum of complexity in described monitoring time section is not more than first, and when in described monitoring time section, the mean and variance sum of complexity is less than the second default complexity threshold, the dynamic threshold that complexity threshold is defined as complexity in described monitoring time section is preset by described second, wherein, the described second default complexity threshold is less than the described first default complexity threshold;
Complexity threshold is preset when the mean and variance sum of complexity in described monitoring time section is not more than first, and when the mean and variance sum of complexity is not less than the second default complexity threshold in described monitoring time section, the average of complexity in described monitoring time section and variance sum are defined as the dynamic threshold of complexity in described monitoring time section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310687525.2A CN104706318B (en) | 2013-12-16 | 2013-12-16 | A kind of sleep analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310687525.2A CN104706318B (en) | 2013-12-16 | 2013-12-16 | A kind of sleep analysis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104706318A true CN104706318A (en) | 2015-06-17 |
| CN104706318B CN104706318B (en) | 2018-02-23 |
Family
ID=53406402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310687525.2A Active CN104706318B (en) | 2013-12-16 | 2013-12-16 | A kind of sleep analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104706318B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105496362A (en) * | 2015-12-15 | 2016-04-20 | 成都麦杰康科技有限公司 | Sleep state monitoring system and method |
| CN105559751A (en) * | 2015-12-14 | 2016-05-11 | 安徽华米信息科技有限公司 | Method, device and wearable device for monitoring states of light activities |
| CN105640508A (en) * | 2016-03-30 | 2016-06-08 | 安徽华米信息科技有限公司 | Realtime sleep monitoring method and device and intelligent wearable equipment |
| CN106175696A (en) * | 2016-09-14 | 2016-12-07 | 广州视源电子科技股份有限公司 | Sleep state monitoring method and system |
| CN106388786A (en) * | 2016-12-14 | 2017-02-15 | 广东技术师范学院 | Processing method acquiring data based on intelligent ring |
| CN106580332A (en) * | 2015-10-20 | 2017-04-26 | 中国移动通信集团公司 | Motion detection method, device and equipment |
| CN106774006A (en) * | 2017-01-22 | 2017-05-31 | 成都图灵创想科技有限责任公司 | Computerized flat knitting machine striker detection means and method |
| CN106913313A (en) * | 2015-12-28 | 2017-07-04 | 中国移动通信集团公司 | A kind of sleep monitor method and system |
| CN107638165A (en) * | 2016-07-20 | 2018-01-30 | 平安科技（深圳）有限公司 | A kind of sleep detection method and device |
| CN108324251A (en) * | 2018-03-25 | 2018-07-27 | 东莞市华睿电子科技有限公司 | A kind of sleep quality of human body monitoring data processing method |
| CN108606882A (en) * | 2018-03-23 | 2018-10-02 | 合肥工业大学 | Intelligent wheelchair control system based on myoelectricity and acceleration self adaptive control |
| TWI642409B (en) * | 2017-05-22 | 2018-12-01 | 研鼎智能股份有限公司 | Sleep analysis method |
| CN109062396A (en) * | 2018-07-24 | 2018-12-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for controlling devices |
| CN109620158A (en) * | 2018-12-28 | 2019-04-16 | 惠州Tcl移动通信有限公司 | Method, intelligent terminal and the storage device of Sleep-Monitoring |
| WO2019137110A1 (en) * | 2018-01-12 | 2019-07-18 | 安徽华米信息科技有限公司 | Method for monitoring status of wearable apparatus, device, and wearable apparatus |
| CN110338804A (en) * | 2019-07-02 | 2019-10-18 | 中山大学 | Human body liveness appraisal procedure based on action recognition |
| CN114040703A (en) * | 2019-07-05 | 2022-02-11 | 国立大学法人东京大学 | Sleep arousal determination device and program |
| CN117582211A (en) * | 2017-08-18 | 2024-02-23 | 飞比特有限公司 | Automatic detection of respiratory disorders |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020005784A1 (en) * | 1998-10-30 | 2002-01-17 | Balkin Thomas J. | System and method for predicting human cognitive performance using data from an actigraph |
| US20040111041A1 (en) * | 2002-12-04 | 2004-06-10 | Quan Ni | Sleep detection using an adjustable threshold |
| US20100100004A1 (en) * | 2008-10-16 | 2010-04-22 | Koninklijke Nederlandse Akademie Van Wetenschappen | Skin Temperature Measurement in Monitoring and Control of Sleep and Alertness |
| US7996076B2 (en) * | 2007-04-02 | 2011-08-09 | The Regents Of The University Of Michigan | Automated polysomnographic assessment for rapid eye movement sleep behavior disorder |
| US8280501B2 (en) * | 2010-04-16 | 2012-10-02 | Dyna Dx Corporation | Systems and methods for quantitatively characterizing slow wave activities and states in sleep |
| US20120289867A1 (en) * | 2011-05-12 | 2012-11-15 | Fujitsu Limited | State determining device and state determination method |
-
2013
- 2013-12-16 CN CN201310687525.2A patent/CN104706318B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020005784A1 (en) * | 1998-10-30 | 2002-01-17 | Balkin Thomas J. | System and method for predicting human cognitive performance using data from an actigraph |
| US20040111041A1 (en) * | 2002-12-04 | 2004-06-10 | Quan Ni | Sleep detection using an adjustable threshold |
| US7996076B2 (en) * | 2007-04-02 | 2011-08-09 | The Regents Of The University Of Michigan | Automated polysomnographic assessment for rapid eye movement sleep behavior disorder |
| US20100100004A1 (en) * | 2008-10-16 | 2010-04-22 | Koninklijke Nederlandse Akademie Van Wetenschappen | Skin Temperature Measurement in Monitoring and Control of Sleep and Alertness |
| US8280501B2 (en) * | 2010-04-16 | 2012-10-02 | Dyna Dx Corporation | Systems and methods for quantitatively characterizing slow wave activities and states in sleep |
| US20120289867A1 (en) * | 2011-05-12 | 2012-11-15 | Fujitsu Limited | State determining device and state determination method |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106580332B (en) * | 2015-10-20 | 2019-08-13 | 中国移动通信集团公司 | A kind of method, device and equipment of motion detection |
| CN106580332A (en) * | 2015-10-20 | 2017-04-26 | 中国移动通信集团公司 | Motion detection method, device and equipment |
| CN105559751B (en) * | 2015-12-14 | 2018-06-12 | 安徽华米信息科技有限公司 | Monitor the method, apparatus and wearable device of micro- active state |
| CN105559751A (en) * | 2015-12-14 | 2016-05-11 | 安徽华米信息科技有限公司 | Method, device and wearable device for monitoring states of light activities |
| WO2017101755A1 (en) * | 2015-12-14 | 2017-06-22 | 安徽华米信息科技有限公司 | Micro-activity state monitoring and wearable device |
| US10624575B2 (en) | 2015-12-14 | 2020-04-21 | Anhui Huami Information Technology Co., Ltd. | Monitoring sleep using microactivity states |
| CN105496362B (en) * | 2015-12-15 | 2018-08-31 | 成都麦杰康科技有限公司 | Sleep state monitors system and method |
| CN105496362A (en) * | 2015-12-15 | 2016-04-20 | 成都麦杰康科技有限公司 | Sleep state monitoring system and method |
| CN106913313A (en) * | 2015-12-28 | 2017-07-04 | 中国移动通信集团公司 | A kind of sleep monitor method and system |
| CN105640508A (en) * | 2016-03-30 | 2016-06-08 | 安徽华米信息科技有限公司 | Realtime sleep monitoring method and device and intelligent wearable equipment |
| CN107638165A (en) * | 2016-07-20 | 2018-01-30 | 平安科技（深圳）有限公司 | A kind of sleep detection method and device |
| CN106175696B (en) * | 2016-09-14 | 2019-02-01 | 广州视源电子科技股份有限公司 | Sleep state monitoring method and system |
| CN106175696A (en) * | 2016-09-14 | 2016-12-07 | 广州视源电子科技股份有限公司 | Sleep state monitoring method and system |
| CN106388786A (en) * | 2016-12-14 | 2017-02-15 | 广东技术师范学院 | Processing method acquiring data based on intelligent ring |
| CN106774006A (en) * | 2017-01-22 | 2017-05-31 | 成都图灵创想科技有限责任公司 | Computerized flat knitting machine striker detection means and method |
| CN106774006B (en) * | 2017-01-22 | 2023-12-29 | 成都图灵创想科技有限责任公司 | Device and method for detecting firing pin of computerized flat knitting machine |
| TWI642409B (en) * | 2017-05-22 | 2018-12-01 | 研鼎智能股份有限公司 | Sleep analysis method |
| CN117582211A (en) * | 2017-08-18 | 2024-02-23 | 飞比特有限公司 | Automatic detection of respiratory disorders |
| WO2019137110A1 (en) * | 2018-01-12 | 2019-07-18 | 安徽华米信息科技有限公司 | Method for monitoring status of wearable apparatus, device, and wearable apparatus |
| CN108606882A (en) * | 2018-03-23 | 2018-10-02 | 合肥工业大学 | Intelligent wheelchair control system based on myoelectricity and acceleration self adaptive control |
| CN108606882B (en) * | 2018-03-23 | 2019-09-10 | 合肥工业大学 | Intelligent wheelchair control system based on myoelectricity and acceleration self adaptive control |
| CN108324251A (en) * | 2018-03-25 | 2018-07-27 | 东莞市华睿电子科技有限公司 | A kind of sleep quality of human body monitoring data processing method |
| CN109062396A (en) * | 2018-07-24 | 2018-12-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for controlling devices |
| CN109062396B (en) * | 2018-07-24 | 2020-01-21 | 百度在线网络技术（北京）有限公司 | Method and device for controlling equipment |
| CN109620158A (en) * | 2018-12-28 | 2019-04-16 | 惠州Tcl移动通信有限公司 | Method, intelligent terminal and the storage device of Sleep-Monitoring |
| CN110338804A (en) * | 2019-07-02 | 2019-10-18 | 中山大学 | Human body liveness appraisal procedure based on action recognition |
| CN114040703A (en) * | 2019-07-05 | 2022-02-11 | 国立大学法人东京大学 | Sleep arousal determination device and program |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104706318B (en) | 2018-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104706318A (en) | Sleep analysis method and device | |
| US10856777B2 (en) | Method and device for identifying human movement state | |
| CN104215257B (en) | High-precision and high pseudo-step removing human step-counting method integrating power consumption management | |
| CN110916636A (en) | BCG signal heart rate calculation method and system based on dynamic second-order differential threshold | |
| US9477640B2 (en) | Neural signal processing and/or interface methods, architectures, apparatuses, and devices | |
| CN106200943B (en) | Virtual reality device control method, device and system | |
| CN106648080A (en) | Equipment control method and device based on brain wave | |
| CN104049761A (en) | Electro-oculogram detection method and device | |
| CN106227355A (en) | A kind of Intelligent bracelet of the bright screen that realizes raising one's hand | |
| CN106667439B (en) | A kind of noise-reduction method and device of electrocardiosignal | |
| CN108478215A (en) | EEG Noise Cancellation, storage medium based on wavelet analysis and device | |
| CN114190953A (en) | Training method and system of electroencephalogram signal noise reduction model for electroencephalogram acquisition equipment | |
| JP6975265B2 (en) | Computing devices, non-transient computer-readable storage media, methods for removing artifacts in electroencephalogram (EEG) signals, and computer programs | |
| CN107280659A (en) | Electrocardiosignal processing method and system | |
| CN117918863A (en) | Method and system for processing brain electrical signal real-time artifacts and extracting features | |
| CN104720798A (en) | Fatigue detection method and system based on electroencephalogram frequency features | |
| CN111839847A (en) | Myoelectric prosthesis control method, myoelectric prosthesis control device, electronic equipment and computer readable medium | |
| CN104720799A (en) | Fatigue detection method and system based on low-frequency electroencephalogram signals | |
| CN112070141B (en) | SSVEP asynchronous classification method integrating attention detection | |
| CN104706366A (en) | Distraction testing method, device and system | |
| Wang et al. | A shallow convolutional neural network for classifying MI-EEG | |
| CN115969398B (en) | Blink detection method and device | |
| KR101577994B1 (en) | Movement artifact removing method for removing movement artifact from brainwave | |
| CN110507320B (en) | Electroencephalogram signal filtering method and equipment | |
| CN114533010A (en) | Heart rate detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |