CN109793497B - Sleep state identification method and device - Google Patents
Sleep state identification method and device Download PDFInfo
- Publication number
- CN109793497B CN109793497B CN201711146375.9A CN201711146375A CN109793497B CN 109793497 B CN109793497 B CN 109793497B CN 201711146375 A CN201711146375 A CN 201711146375A CN 109793497 B CN109793497 B CN 109793497B
- Authority
- CN
- China
- Prior art keywords
- sleep state
- sleep
- time point
- data
- observation time
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 230000001133 acceleration Effects 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 238000007637 random forest analysis Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000005070 sampling Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Abstract
The application discloses a sleep state identification method, which comprises the following steps: acquiring sleep data of an observation object at an observation time point; inputting sleep data into a sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of an observation object at an observation time point; the sleep state pre-recognizer is generated by training according to known sleep data of a sleep state in advance; and taking a pre-recognition result of which the repetition rate exceeds a preset threshold value as the sleep state of the observation time point from a plurality of pre-recognition results of a plurality of observation time points continuously adjacent to the observation time point. According to the method and the device, the sleep state pre-recognizer generated by training according to the known sleep data of the sleep state in advance is used for recognizing the sleep data, and the experience rule is not relied on, so that the method and the device have high accuracy and adaptability. The application also discloses a sleep state recognition device, which has the same beneficial effects.
Description
Technical Field
The present disclosure relates to the field of sleep detection technologies, and in particular, to a sleep state identification method and apparatus.
Background
With the development of sleep detection technology, many portable smart wearable devices with sleep state recognition function have entered the market.
At present, the sleep state identification method in the prior art is mostly based on experience rules, and particularly, the comparison result between signals such as acceleration obtained by measurement and the like and a preset experience threshold is used as an identification basis. The commonly used determination index includes the number of times of the movement of the observation object in unit time, the number of times of the signal intensity or the signal integral area of the observation object in unit time respectively exceeding a preset threshold, and the like.
It can be seen that the basis of these recognition methods in the prior art is a single rule of thumb, and in fact, the sleep state is difficult to describe by a simple rule of index, even the observation target in the sleep state has movements such as turning, getting up, etc. with different frequencies, amplitudes, accelerations and intensities in different time periods, and varies from person to person, and these are difficult to be generalized uniformly by a simple rule of thumb, and are more difficult to be applied to all observation targets. Therefore, the sleep state identification method in the prior art tends to have a large error and is poor in adaptability.
Therefore, what kind of sleep state identification method and apparatus is adopted to effectively improve accuracy and adaptability is a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
The application aims to provide a sleep state identification method and a sleep state identification device so as to effectively improve accuracy and adaptability.
In order to solve the above technical problem, the present application provides a sleep state identification method, including:
acquiring sleep data of an observation object at an observation time point;
inputting the sleep data into a sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of the observation object at the observation time point; the sleep state pre-recognizer is generated by training according to known sleep data of a sleep state in advance;
and taking a pre-recognition result with the repetition rate exceeding a preset threshold value as the sleep state of the observation time point from a plurality of pre-recognition results of a plurality of observation time points continuously adjacent to the observation time point.
Optionally, the sleep data is acceleration data.
Optionally, the method further comprises:
after the sleep data of the observation object at the observation time point are acquired and before the sleep data are input into the sleep state pre-recognizer, filtering processing is carried out on the sleep data.
Optionally, the method further comprises:
after the sleep data are subjected to filtering processing and before the sleep data are input into a sleep state pre-recognizer, respectively calculating statistical characteristic values of the sleep data of the observation object in a preset time period before and after the observation time point;
the inputting the sleep data into a sleep state pre-recognizer, and the acquiring the pre-recognition result of the sleep state of the observation object at the observation time point comprises:
and inputting the sleep data and the statistical characteristic value into the sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of the observation object at the observation time point.
Optionally, the statistical characteristic value is a standard deviation.
Optionally, the pre-generation of the sleep state pre-recognizer according to the training of the sleep data with known sleep state in advance includes:
the sleep state pre-recognizer is generated by adopting a random forest algorithm or a radial basis function kernel support vector machine algorithm according to the known sleep data of the sleep state in advance.
Optionally, the method further comprises:
and after the pre-recognition result with the repetition rate exceeding a preset threshold value is taken as the sleep state of the observation time point, carrying out fine tuning training on the sleep state recognizer according to the sleep data and the sleep state.
The present application further provides a sleep state recognition apparatus, including:
an acquisition module: the sleep data acquisition unit is used for acquiring the sleep data of an observation object at an observation time point;
a pre-recognition module: the sleep state pre-recognizer is used for inputting the sleep data into the sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of the observation object at the observation time point; the sleep state pre-recognizer is generated by training according to known sleep data of a sleep state in advance;
a confirmation module: and the sleep state judging unit is used for judging the sleep state of the observation time point from a plurality of pre-recognition results of a plurality of observation time points continuously adjacent to the observation time point, wherein the pre-recognition result of which the repetition rate exceeds a preset threshold value is taken as the sleep state of the observation time point.
Optionally, the method further comprises:
a preprocessing module: the sleep data acquisition module is used for acquiring the sleep data of the user.
Optionally, the method further comprises:
a calculation module: the statistical characteristic value of the sleep data of the observation object in a preset time period before and after the observation time point is calculated;
the pre-recognition module is specifically configured to:
and inputting the sleep data and the statistical characteristic value into the sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of the observation object at the observation time point.
The sleep state identification method provided by the application comprises the following steps: acquiring sleep data of an observation object at an observation time point; inputting the sleep data into a sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of the observation object at the observation time point; the sleep state pre-recognizer is generated by training according to known sleep data of a sleep state in advance; and taking a pre-recognition result with the repetition rate exceeding a preset threshold value as the sleep state of the observation time point from a plurality of pre-recognition results of a plurality of observation time points continuously adjacent to the observation time point.
Therefore, compared with the prior art, in the sleep state identification method provided by the application, the effective sleep state identification result can be obtained according to the sleep data through the sleep state pre-identifier generated by training according to the known sleep data of the sleep state in advance. Because the training process of the sleep state pre-recognizer does not depend on experience rules, the accuracy can be guaranteed. Meanwhile, according to the method, different sleep state pre-recognizers can be established for different user groups, so that the adaptability to individual differences of users can be improved. The sleep state identification device provided by the application can realize the sleep state identification method and also has the beneficial effects.
Drawings
In order to more clearly illustrate the technical solutions in the prior art and the embodiments of the present application, the drawings that are needed to be used in the description of the prior art and the embodiments of the present application will be briefly described below. Of course, the following description of the drawings related to the embodiments of the present application is only a part of the embodiments of the present application, and it will be obvious to those skilled in the art that other drawings can be obtained from the provided drawings without any creative effort, and the obtained other drawings also belong to the protection scope of the present application.
Fig. 1 is a flowchart of a sleep state identification method according to an embodiment of the present disclosure;
fig. 2 is a block diagram illustrating a sleep state identification apparatus according to an embodiment of the present disclosure;
fig. 3 is a comparison diagram of pre-recognition results of a sleep state recognition method according to an embodiment of the present application;
fig. 4 is a comparison diagram of the final recognition result of the sleep state recognition method provided in the embodiment of the present application;
fig. 5 is a ROC graph of a sleep state pre-recognizer using a random forest algorithm according to an embodiment of the present disclosure.
Detailed Description
The core of the application is to provide a sleep state identification method and a sleep state identification device so as to effectively improve accuracy and adaptability.
In order to more clearly and completely describe the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a sleep state identification method according to an embodiment of the present application, which mainly includes the following steps:
step 1: and acquiring sleep data of the observation object at the observation time point.
Specifically, the sleep data is preferably acceleration data acquired by an accelerometer, and is preferably a three-axis acceleration; of course, other data such as the acquired heart rate data may be used. The acquisition frequency, that is, the reciprocal of the interval time between two adjacent observation time points, can also be selected and designed by a person skilled in the art, and the acquisition frequency is not limited in the present application; but preferably can be selected in the range of 20 to 30 Hz.
Step 2: and inputting the sleep data into a sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of the observation object at the observation time point.
The sleep state pre-recognizer is generated by training according to the sleep data with known sleep states in advance.
Specifically, the identification basis adopted by the application is sleep data with known sleep states, the known information is utilized, a software method is adopted, and a certain algorithm programming training is carried out, so that a sleep state pre-identifier can be established, the pre-identifier can carry out pre-identification on the input sleep data, and the pre-identification result of the sleep state is output. The so-called pre-recognition result includes two states, "sleep" and "awake", and may be specifically represented by digital signals "1" and "0". Therefore, in the process of establishing the sleep state pre-recognizer, only input and output are needed to be used for information, and a specific rule which is met between the input and the output does not need to be clearly described, so that the sleep state pre-recognizer is not limited by the rule, and the sleep state pre-recognizer can have better precision as long as enough training data are obtained.
And step 3: and taking a pre-recognition result of which the repetition rate exceeds a preset threshold value as the sleep state of the observation time point from a plurality of pre-recognition results of a plurality of observation time points continuously adjacent to the observation time point.
Specifically, after the pre-recognition result of each observation time point is obtained by the sleep state pre-recognizer, the pre-recognition result may be further processed to obtain a final output result. Since the observation target is not completely motionless in the sleep state, especially in a period of time just falling asleep, the sleep state may be misjudged by the sleep data acquired by the accelerometer or the like. In order to reduce errors, the final recognition result may be determined based on a plurality of pre-recognition results of a plurality of observation time points consecutively adjacent to the observation time point to be currently recognized. Specifically, the pre-recognition result with the repetition rate exceeding a preset threshold value in the plurality of pre-recognition results may be used as the sleep state of the current observation time point to be recognized. Of course, the preset threshold is generally 50%, for example, when 501 of 1000 pre-recognition results are "sleep", the sleep state can be determined as "sleep".
The plurality of observation time points continuously adjacent to the observation time point to be currently identified is, but not limited to, recommended to be centered on the observation time point to be currently identified, i.e., uniformly distributed before and after the observation time point, and the number thereof may be selected by those skilled in the art. In general, the pre-recognition results for all observation time points within 10-20 minutes from the current time point to be observed may be selected.
Therefore, in the sleep state recognition method provided by the embodiment of the application, the effective sleep state recognition result can be obtained according to the sleep data through the sleep state pre-recognizer generated by training according to the known sleep data of the sleep state in advance. Because the training process of the sleep state pre-recognizer does not depend on experience rules, the accuracy can be guaranteed. Meanwhile, according to the method, different sleep state pre-recognizers can be established for different user groups, so that the adaptability to individual differences of users can be improved.
The sleep state identification method provided by the application is based on the embodiment as follows:
optionally, the method further comprises:
after acquiring the sleep data of the observation object at the observation time point and before inputting the sleep data into the sleep state pre-recognizer, the sleep data is subjected to filtering processing.
Specifically, an arithmetic mean filtering method, a median filtering method, a gaussian filtering method, or the like may be employed, or the down-sampling may be performed directly. The selection and arrangement can be made by those skilled in the art, and the embodiment of the present application is not limited thereto.
For example, when the sampling frequency is 25Hz, the total number of observation time points per minute is 25 × 60, that is, 1500 points. If the filtering is performed by down-sampling, and in particular down-sampling is performed at a frequency of 1/60Hz, one remaining point may be selected from 1500 points per minute. Of course, the point may be specifically the 751 st point per minute, the first point, the 100 th point, or the 1500 th point, and the like, and the person skilled in the art may select and set the point at will, which is not limited in the embodiment of the present application.
Optionally, the method further comprises:
after filtering the sleep data and before inputting the sleep data into the sleep state pre-recognizer, respectively calculating statistical characteristic values of the sleep data of an observation object in a preset time period before and after an observation time point;
inputting sleep data into a sleep state pre-recognizer, and acquiring a pre-recognition result of the sleep state of an observation object at an observation time point comprises the following steps:
and inputting the sleep data and the statistical characteristic value into a sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of the observation object at the observation time point.
Specifically, in order to further improve the accuracy of the recognition result, the input data type of the sleep state pre-recognizer may be further increased, that is, not only the sleep data but also the statistical characteristic value of the sleep data is required. The common statistical characteristic values include variance, standard deviation, average value, and the like, wherein the standard deviation is preferred, and the standard deviation is a statistical characteristic value for measuring the dispersion degree of a group of data, and can well reflect the dispersion degree of the sleep data before and after the current observation time point. The preset time period can be selected and set by a person skilled in the art, and is recommended to be, but not limited to, 2-4 minutes.
For example, when the sleep data is triaxial acceleration data, and the preset duration is selected to be 3 minutes for the current observation time point T, the data to be input into the sleep state pre-recognizer includes the triaxial acceleration a corresponding to the observation time point T x 、a y And a z And all sleep data modulo lengths within 3 minutes before observation time point T
Standard deviation of (STD) pre And all sleep data model lengths within 3 minutes after observation time point T
Standard deviation of (2)STD pos .
Referring to fig. 3, fig. 3 is a comparison diagram of pre-recognition results of a sleep state recognition method according to an embodiment of the present application.
In fig. 3, from top to bottom, column 1 is a timing chart of the pre-recognition result of the sleep state pre-recognizer using the random forest algorithm, and column 2 is the acquired x-axis acceleration a x Column 3 is the acquired y-axis acceleration a y In column 4, the acquired z-axis acceleration a z Column 5 of the timing chart of (1), the standard deviation STD calculated within 3 minutes before the observation time point pre Column 6 of the time chart of (1) is the standard deviation STD calculated within 3 minutes after the observation time point pos Column 7 is the recorded real sleep state profile of the subject, which can be determined based on the subject's personal memory or other person's observations.
As can be seen from fig. 3, the pre-recognition result output by the sleep state pre-recognizer has a small number of isolated points, i.e., misjudged points, compared with the true sleep state of the subject.
Referring to fig. 4, fig. 4 is a comparison diagram of a final recognition result of the sleep state recognition method provided in the embodiment of the present application.
In fig. 4, from top to bottom, column 1 is a timing chart of the recorded true sleep state of the subject, column 2 is a timing chart of the pre-recognition result of the sleep state pre-recognizer adopting the random forest algorithm, and column 3 is a timing chart of the final recognition result of the output sleep state.
As can be seen from fig. 4, compared with the pre-recognition result output by the sleep state pre-recognizer, the final recognition result of the sleep state output in step 3 is very close to the real sleep state of the subject, and has better accuracy, so that the error judgment in the pre-recognition process can be effectively corrected.
Optionally, the pre-generation of the sleep state pre-recognizer according to the training of the sleep data with known sleep state in advance includes:
the sleep state pre-recognizer is generated by training in advance according to known sleep data of a sleep state by adopting a random forest algorithm or a radial basis function kernel support vector machine algorithm.
Specifically, the random forest algorithm is not easy to over-fit due to the introduction of randomness, and has good anti-noise capability and data set adaptation capability, so that a good identification result is obtained. In addition, the radial basis function kernel support vector machine algorithm is an algorithm which is commonly used for pattern recognition, and the support vector machine taking the radial basis function as the kernel function has better global property and better recognition effect.
Optionally, the method further comprises:
and after the pre-recognition result with the repetition rate exceeding a preset threshold value is taken as the sleep state of the observation time point, carrying out fine tuning training on the sleep state recognizer according to the sleep data and the sleep state.
Specifically, the sleep state recognizer may further improve accuracy by fine-tuning the training after recognition is completed. After the recognition is finished, considering that the obtained sleep state has higher confidence, a part of the data of the recognition result of the sleep state is selected as training data, and the sleep state pre-recognizer is retrained according to the training data so as to improve the accuracy of the sleep state pre-recognizer in time. In the training process, a grid search method is preferably adopted to select the optimal parameters.
Alternatively, the same number of samples may be selected as training data from the sleep data whose recognition results are "sleep" and "awake", respectively. It is recommended, but not limited to, to select 80% of the total sample size as training data, and the other 20% of the samples can also be used as test data to test the fine-tuned trained sleep state pre-recognizer. Also, training and testing may be repeated multiple times, for example, if 20% of the samples are selected as test data each time, it is recommended but not limited to repeat 5 times, so as to ensure the fine training accuracy of the sleep state pre-recognizer. In addition, it is easily understood that in order to guarantee that sleep data for fine-tuning training and a sleep state corresponding to the sleep data are representative, sleep data for a period of continuous 12 hours may be selected as a total sample size from the sleep data for which a sleep state recognition result is obtained, and training data and test data may be selected from the total sample size.
Referring to fig. 5, fig. 5 is a diagram of a ROC Curve (sensitivity Curve) of a sleep state pre-recognizer adopting a random forest algorithm according to an embodiment of the present application.
The ROC curve is used for representing the classification effect of the binary classification model, and is a curve with true positive rate (sensitivity) as a vertical coordinate and false positive rate (1-specificity) as a horizontal coordinate, and the range of vertical and horizontal coordinates is 0-1; the closer the ROC curve is to the upper left corner, i.e., the larger the area under the curve, the higher the accuracy of the classification model under test. As can be seen from fig. 5, the area under the ROC curve of the sleep state pre-recognizer adopting the random forest algorithm provided in the embodiment of the present application is close to 1, and a relatively accurate recognition effect is achieved.
The following describes a sleep state recognition apparatus provided in an embodiment of the present application.
Referring to fig. 2, fig. 2 is a block diagram illustrating a sleep state recognition apparatus according to the present application; the system comprises an acquisition module 1, a pre-recognition module 2 and a confirmation module 3;
the acquisition module 1 is used for acquiring sleep data of an observation object at an observation time point;
the pre-recognition module 2 is used for inputting sleep data into the sleep state pre-recognizer to obtain the pre-recognition result of the sleep state of the observation object at the observation time point; the sleep state pre-recognizer is generated by training according to known sleep data of a sleep state in advance;
the confirming module 3 is configured to take a pre-recognition result with a repetition rate exceeding a preset threshold as a sleep state of an observation time point from a plurality of pre-recognition results of a plurality of observation time points continuously adjacent to the observation time point.
Therefore, the sleep state recognition device provided by the application can obtain an effective sleep state recognition result according to the sleep data through the sleep state pre-recognizer generated by training according to the known sleep data of the sleep state in advance. Because the training process of the sleep state pre-recognizer does not depend on experience rules, the accuracy can be guaranteed. Meanwhile, according to the method, different sleep state pre-recognizers can be established for different user groups, so that the adaptability to individual differences of users can be improved.
The sleep state identification device provided by the application is based on the embodiment as follows:
as a preferred embodiment, further comprising:
a preprocessing module: is configured to perform filtering processing on the sleep data acquired by the acquisition module 1.
As a preferred embodiment, further comprising:
a calculation module: the statistical characteristic value is used for calculating the statistical characteristic value of the sleep data of the observation object in the preset time period before and after the observation time point;
the pre-recognition module 2 is specifically configured to:
and inputting the sleep data and the statistical characteristic value into a sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of the observation object at the observation time point.
The specific implementation of the sleep state identification apparatus provided in the present application and the above-described sleep state identification method may be referred to correspondingly, and are not described herein again.
The embodiments in the present application are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The technical solutions provided by the present application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, without departing from the principle of the present application, the present application can also make several improvements and modifications, and those improvements and modifications also fall into the protection scope of the claims of the present application.
Claims (8)
1. A sleep state recognition method, comprising:
acquiring sleep data of an observation object at an observation time point, and respectively calculating statistical characteristic values of the sleep data of the observation object in a preset time period before and after the observation time point;
inputting the sleep data and the statistical characteristic value into a sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of the observation object at the observation time point; the sleep state pre-recognizer is generated according to the training of the sleep data with known sleep state in advance;
and taking a pre-recognition result with the repetition rate exceeding a preset threshold value as the sleep state of the observation time point from a plurality of pre-recognition results of a plurality of observation time points continuously adjacent to the observation time point.
2. The sleep state recognition method of claim 1, wherein the sleep data is acceleration data.
3. The sleep state recognition method according to claim 1, further comprising:
after the sleep data of the observation object at the observation time point are acquired and before the sleep data are input into a sleep state pre-recognizer, filtering processing is carried out on the sleep data.
4. The sleep state recognition method of claim 1, wherein the statistical characteristic value is a standard deviation.
5. The sleep state recognition method according to any one of claims 1 to 4, wherein the pre-generation of the sleep state pre-recognizer is trained in advance according to sleep data of which the sleep state is known comprises:
the sleep state pre-recognizer is generated by adopting a random forest algorithm or a radial basis function kernel support vector machine algorithm according to the known sleep data of the sleep state in advance.
6. The sleep state recognition method according to claim 5, further comprising:
and after the pre-recognition result with the repetition rate exceeding a preset threshold value is taken as the sleep state of the observation time point, carrying out fine tuning training on the sleep state pre-recognizer according to the sleep data and the sleep state.
7. A sleep state recognition apparatus, comprising:
an acquisition module: the sleep data acquisition unit is used for acquiring the sleep data of an observation object at an observation time point and respectively calculating the statistical characteristic values of the sleep data of the observation object in the preset time period before and after the observation time point;
a pre-recognition module: the sleep state pre-recognizer is used for inputting the sleep data and the statistical characteristic value into a sleep state pre-recognizer to obtain a pre-recognition result of the sleep state of the observation object at the observation time point; the sleep state pre-recognizer is generated according to the training of the sleep data with known sleep state in advance;
a confirmation module: and the sleep state judging module is used for judging whether the sleep state of the observation time point is a sleep state of the observation time point according to the pre-recognition result of the observation time point, wherein the pre-recognition result of the observation time point is continuously adjacent to the observation time point.
8. The sleep state recognition apparatus according to claim 7, further comprising:
a preprocessing module: the sleep data acquisition module is used for acquiring the sleep data of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711146375.9A CN109793497B (en) | 2017-11-17 | 2017-11-17 | Sleep state identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711146375.9A CN109793497B (en) | 2017-11-17 | 2017-11-17 | Sleep state identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109793497A CN109793497A (en) | 2019-05-24 |
| CN109793497B true CN109793497B (en) | 2022-08-19 |
Family
ID=66554795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711146375.9A Active CN109793497B (en) | 2017-11-17 | 2017-11-17 | Sleep state identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109793497B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110742580A (en) * | 2019-09-18 | 2020-02-04 | 华为技术有限公司 | Sleep state identification method and device |
| CN111012132A (en) * | 2019-12-17 | 2020-04-17 | 珠海格力电器股份有限公司 | Sleep state adjusting method and device based on pillow and intelligent pillow |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103961109A (en) * | 2014-05-05 | 2014-08-06 | 北京航空航天大学 | Human body posture detection device based on acceleration signals and angular speed signals |
| CN104138260A (en) * | 2014-07-02 | 2014-11-12 | 中山大学 | Sleeping posture multi-classifying identifying method utilizing SVM classifier |
| CN104905795A (en) * | 2015-06-15 | 2015-09-16 | 深圳市奋达科技股份有限公司 | Method for monitoring Bluetooth low energy (BLE) networking sleeping |
| 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 |
| CN105678300A (en) * | 2015-12-30 | 2016-06-15 | 成都数联铭品科技有限公司 | Complex image and text sequence identification method |
| CN106419893A (en) * | 2016-09-18 | 2017-02-22 | 广州视源电子科技股份有限公司 | Method and device for detecting sleep state |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8192376B2 (en) * | 2003-08-18 | 2012-06-05 | Cardiac Pacemakers, Inc. | Sleep state classification |
-
2017
- 2017-11-17 CN CN201711146375.9A patent/CN109793497B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103961109A (en) * | 2014-05-05 | 2014-08-06 | 北京航空航天大学 | Human body posture detection device based on acceleration signals and angular speed signals |
| CN104138260A (en) * | 2014-07-02 | 2014-11-12 | 中山大学 | Sleeping posture multi-classifying identifying method utilizing SVM classifier |
| CN104905795A (en) * | 2015-06-15 | 2015-09-16 | 深圳市奋达科技股份有限公司 | Method for monitoring Bluetooth low energy (BLE) networking sleeping |
| 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 |
| CN105678300A (en) * | 2015-12-30 | 2016-06-15 | 成都数联铭品科技有限公司 | Complex image and text sequence identification method |
| CN106419893A (en) * | 2016-09-18 | 2017-02-22 | 广州视源电子科技股份有限公司 | Method and device for detecting sleep state |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109793497A (en) | 2019-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105242779B (en) | A kind of method and mobile intelligent terminal of identification user action | |
| JP6064280B2 (en) | System and method for recognizing gestures | |
| CN106228200B (en) | Action identification method independent of action information acquisition equipment | |
| Kamboh et al. | Computationally efficient neural feature extraction for spike sorting in implantable high-density recording systems | |
| CN109886068B (en) | Motion data-based action behavior identification method | |
| CN106897658A (en) | The discrimination method and device of face live body | |
| CN111288986B (en) | Motion recognition method and motion recognition device | |
| CN109793497B (en) | Sleep state identification method and device | |
| CN108510011B (en) | User travel mode analysis method based on mobile phone multi-sensor | |
| CN112690761B (en) | Sleep state detection method, device, equipment and computer readable medium | |
| CN107277222A (en) | User behavior state judging method based on mobile phone built-in sensors | |
| CN116226691A (en) | Intelligent finger ring data processing method for gesture sensing | |
| CN107169334B (en) | The user authen method based on straight punch motion detection for hand wearable device | |
| US10496877B2 (en) | Device and method of characterizing motion | |
| CN109758154B (en) | Motion state determination method, device, equipment and storage medium | |
| US10578640B2 (en) | Determination of a mobility context for a user carrying a device fitted with inertial sensors | |
| CN111803902B (en) | Swimming stroke identification method and device, wearable device and storage medium | |
| CN110414196B (en) | Smart watch identity verification method based on vibration signal | |
| CN109620241B (en) | Wearable device and motion monitoring method based on same | |
| Yang et al. | Extraction and denoising of human signature on radio frequency spectrums | |
| CN112130675A (en) | Wrist-lifting identification method and wearable terminal | |
| Banos et al. | Evaluating the effects of signal segmentation on activity recognition. | |
| CN116226727A (en) | Motion recognition system based on AI | |
| Al-Naffakh | A comprehensive evaluation of feature selection for gait recognition using smartwatches | |
| Ciabattoni et al. | Complex activity recognition system based on cascade classifiers and wearable device data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |