CN110151138B - Sleep apnea fragment detection method and device based on convolutional neural network - Google Patents
Sleep apnea fragment detection method and device based on convolutional neural network Download PDFInfo
- Publication number
- CN110151138B CN110151138B CN201910460074.6A CN201910460074A CN110151138B CN 110151138 B CN110151138 B CN 110151138B CN 201910460074 A CN201910460074 A CN 201910460074A CN 110151138 B CN110151138 B CN 110151138B
- Authority
- CN
- China
- Prior art keywords
- channel
- neural network
- convolutional neural
- signal
- sequence
- 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
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 47
- 201000002859 sleep apnea Diseases 0.000 title claims abstract description 46
- 239000012634 fragment Substances 0.000 title claims abstract description 28
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 14
- 230000007958 sleep Effects 0.000 claims abstract description 5
- 238000013528 artificial neural network Methods 0.000 claims abstract description 4
- 238000006243 chemical reaction Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 36
- 238000004519 manufacturing process Methods 0.000 claims description 19
- 238000012360 testing method Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000016507 interphase Effects 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 3
- 208000008784 apnea Diseases 0.000 abstract description 2
- 238000003860 storage Methods 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 5
- 230000000747 cardiac effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000241 respiratory effect Effects 0.000 description 3
- 206010041235 Snoring Diseases 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 206010008132 Cerebral thrombosis Diseases 0.000 description 1
- 208000007590 Disorders of Excessive Somnolence Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 201000001429 Intracranial Thrombosis Diseases 0.000 description 1
- 206010041349 Somnolence Diseases 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- 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
- A61B5/4818—Sleep apnoea
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The invention discloses a sleep apnea fragment detection method and equipment based on a convolutional neural network, wherein the method comprises the following steps: collecting electrocardiosignals of a subject during night sleep; carrying out analog-to-digital conversion on the acquired electrocardiosignals to obtain electrocardio digital signals of the testee; dividing the electrocardiosignals into one-minute segments according to minutes; extracting RR interval signals and RR amplitude signals according to the obtained per-minute electrocardiosignals; the signals are classified by utilizing the one-dimensional convolution neural network provided by the invention. The sleep apnea fragment detection method based on the convolutional neural network is simple and easy to implement, has good accuracy, and can quickly and accurately measure the apnea fragments of a subject so as to realize early detection of sleep apnea diseases.
Description
Technical Field
The invention relates to the technical field of medical monitoring, in particular to a sleep apnea fragment detection method and device based on a convolutional neural network.
Background
At present, about 9.36 hundred million people worldwide suffer from sleep apnea (OSA), about 6000 million people in China suffer from the diseases, the sleep apnea patients are easy to have the symptoms of daytime sleepiness, inattention and the like, and the long-term sleep apnea is easy to cause the diseases of hypertension, coronary heart disease, cerebral thrombosis and the like. Therefore, the timely diagnosis of sleep apnea has great significance.
Currently, the gold standard for sleep apnea diagnosis is Polysomnography (PSG), which continuously records physiological signals such as Electrocardiogram (ECG), electroencephalogram (EEG), Electrooculogram (EOG), Electromyogram (EMG), respiratory airflow, blood oxygen saturation, thoracoabdominal respiratory motion, snoring, etc., and manually verifies the recorded signals item by item. 6000 million sleep apnea patients in China have less than 1 percent of confirmed diagnosis and less than 0.1 percent of treatment, and the diagnosis rate and the treatment rate in China are too low, wherein the main reasons are that people do not fully recognize the harm of sleep apnea, the sleep apnea diagnosis is troublesome, the cost is high, recorded signals need a doctor to perform a large amount of analysis, and the workload of the doctor is large. In order to complete the preliminary screening of the sleep apnea more conveniently and rapidly, a large number of researchers explore that the preliminary screening of the sleep apnea is completed only by adopting one signal or a plurality of signals of electrocardiogram, oral-nasal airflow and snore. In 1984, Guilleminaultd et al observed electrocardiogram and PSG graphs for 400 patients with sleep apnea syndrome for 24 consecutive hours, and found that when the patients had onset of apnea symptoms, the heart rate slowed down, and when normal recovery occurred, the heart rate was accelerated, suggesting that heart rate variability can be used to detect sleep apnea syndrome. In addition to detecting sleep apnea syndrome using RR interval sequences extracted from the cardiac electrical signal, it is also possible to detect from changes in the amplitude of the cardiac electrical signal, the electrical impedance of the chest as the person breathes changing due to changes in lung volume and, secondly, the cardiac vector changing due to changes in the displacement and orientation of the heart relative to the EEG electrodes.
In the existing sleep apnea detection method by using single lead data, most methods only use RR interval signals extracted from electrocardiosignals for analysis, but the information of electrocardio amplitude is lost when the RR interval signals are extracted from the electrocardiosignals, and the information contained in the electrocardiosignals is not fully utilized.
Disclosure of Invention
The invention aims to provide a sleep apnea fragment detection method and device based on a convolutional neural network, which are simple and feasible in technology, accurate in measurement and robust and based on an RR interval and RR amplitude dual-channel sequence.
The embodiment of the invention provides a sleep apnea fragment detection method based on a convolutional neural network, which comprises the following steps:
s1, collecting electrocardiosignals of a subject during sleep at night;
s2, carrying out analog-to-digital conversion on the acquired electrocardiosignals to obtain electrocardio digital signals of the testee;
s3, segmenting the obtained electrocardio digital signals according to minutes to obtain electrocardio signal segments per minute;
s4, extracting electrocardio RR interphase signals and RR amplitude signals according to the obtained electrocardio signal fragments per minute, labeling the electrocardio signal fragments by using the monitoring result of the polysomnography, and forming a dual-channel signal by using the extracted RR interphase signals and RR amplitude signals to manufacture a training set;
s5, building a one-dimensional convolutional neural network, and training the one-dimensional convolutional neural network by using the manufactured two-channel signal manufacturing training set:
and S6, classifying the test signal segments by using the trained one-dimensional convolutional neural network.
Preferably, step S4 specifically includes:
s41, recording the electrocardio digital signal as Q, segmenting the electrocardio signal according to minutes, recording the segment of the electrocardio signal at the nth minute as Qn, namely Q ═ Q1，Q2，…，Qn}；
S42, filtering the electrocardiosignal segments per minute, extracting the R wave position by adopting a Pan-Tompki algorithm, correcting the extracted R wave, and subtracting the former R wave from the next adjacent R wave to obtain an RR interval sequence as a first channel; meanwhile, an RR amplitude sequence obtained according to the R wave position is used as a second channel;
s43, filtering the RR interval sequence of the first channel and the RR amplitude sequence of the second channel respectively to remove the value interfered by noise and discard the segment of the signal difference;
s44, respectively carrying out mean value removing processing on the RR interval sequence of the first channel and the RR amplitude sequence of the second channel;
s45, filling the RR interval sequence of the first channel and the RR amplitude sequence of the second channel every minute until the length k is uniform;
s46, marking the electrocardiosignal segments per minute by using the monitoring result of the polysomnography, marking the normal segments as 0, marking the pause segments as 1, and forming a dual-channel signal manufacturing training set by using the extracted RR interval sequence and RR amplitude sequence.
Preferably, in step S45, the filling method is as follows:
the RR sequence of the first channel of the nth minute is Rn＝{r1，r2，…，rmGet the nth scoreThe RR amplitude sequence of the second channel of the clock is Qn＝{q1，q2，…，qmFill the data in front of the original sequence to the back, fill to a uniform length k, and the result after filling is
Wherein R'nAnd Q'nAll are K.
Preferably, the step S5 specifically includes:
s51, building a one-dimensional convolution neural network;
s52, making a training set of the dual-channel signals to carry out zero equalization and normalization processing, converting the data into data with an average value of 0 and a standard deviation of 1, and converting the data into a function of
Wherein mu is the mean value of all training sample data, sigma is the standard deviation of all dual-channel signal production training sets, mu and sigma obtained by the dual-channel signal production training sets are used for the test set, and zero equalization and normalization are carried out on the test set;
and S53, building a one-dimensional convolutional neural network, and training the one-dimensional convolutional neural network by utilizing a two-channel signal to manufacture a training set.
The embodiment of the invention also provides sleep apnea fragment detection equipment based on the convolutional neural network, which is characterized by comprising a memory and a processor, wherein executable codes are stored in the memory, and the executable codes can be executed by the processor to realize the sleep apnea fragment detection method based on the convolutional neural network.
Compared with the prior art, the invention has the following beneficial effects:
when the electrocardiosignals are processed, the RR interphase signals are extracted, and the amplitude information corresponding to the R wave is extracted, so that the sleep apnea information contained in the electrocardiosignals is more fully utilized, and the accuracy rate of sleep apnea fragment identification is improved;
the sleep apnea detecting method adopts a one-dimensional convolutional neural network method to identify and detect the sleep apnea fragments, compared with the traditional machine learning method, the convolutional neural network has stronger learning capacity, and the performance of the convolutional neural network is continuously increased along with the increase of the data scale.
Meanwhile, after the network is trained, extra signals such as respiratory signals, blood oxygen signals, electroencephalogram signals and the like do not need to be acquired, and only electrocardiosignals need to be acquired. Meanwhile, because the network adopted by the invention has strong functions, the accuracy can be further improved along with the amplification of the training set, so that the method is feasible in the aspect of implementation.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method for identifying segments of sleep apnea by a one-dimensional convolutional neural network according to an embodiment of the present invention.
Fig. 2 is a dual-channel signal waveform diagram of an RR interval sequence and an RR amplitude sequence according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a one-dimensional convolutional neural network model provided in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
Referring to fig. 1, an embodiment of the present invention provides a sleep apnea fragment detection method based on a convolutional neural network, which includes the following steps:
s1, collecting electrocardiosignals of the testee when the testee sleeps at night.
And S2, carrying out analog-to-digital conversion on the acquired electrocardiosignals to obtain electrocardio digital signals of the testee.
And S3, segmenting the obtained electrocardio digital signals according to minutes to obtain electrocardio signal segments per minute.
S4, extracting an electrocardiosignal RR interval sequence and an RR amplitude sequence according to the obtained electrocardiosignal fragments per minute, labeling the electrocardiosignal fragments by using a monitoring result of a Polysomnography (PSG), and forming a dual-channel signal manufacturing training set by using the extracted RR interval sequence and RR amplitude sequence.
Wherein, step S4 specifically includes:
s41, recording the electrocardio digital signal as Q, segmenting the electrocardio signal according to minutes, recording the segment of the electrocardio signal at the nth minute as Qn, namely Q ═ Q1，Q2，…，Qn}。
S42, filtering the electrocardiosignal segments per minute, extracting the R wave position by adopting a Pan-Tompki algorithm, correcting the extracted R wave, and subtracting the former R wave from the next adjacent R wave to obtain an RR interval sequence as a first channel; and the RR amplitude sequence obtained according to the R wave position is used as a second channel (shown in figure 2).
And S43, respectively filtering the RR interval sequence of the first channel and the RR amplitude sequence of the second channel to remove values interfered by noise and discard segments of the signal difference.
And S44, respectively carrying out mean value removing processing on the RR interval sequence of the first channel and the RR amplitude sequence of the second channel.
And S45, filling the RR interval sequence of the first channel and the RR amplitude sequence of the second channel every minute until the length k is uniform.
The specific filling method comprises the following steps:
the RR sequence of the first channel of the nth minute is Rn＝{r1，r2，…，rmAnd recording the RR amplitude sequence of the second channel at the nth minute as Qn＝{q1，q2，…，qmFill the data in front of the original sequence to the back, fill to a uniform length k, and the result after filling is
Wherein R'nAnd Q'nAll are K.
S46, marking the electrocardiosignal segments per minute by using the monitoring result of the polysomnography, marking the normal segments as 0, marking the pause segments as 1, and forming a dual-channel signal manufacturing training set by using the extracted RR interval sequence and RR amplitude sequence.
That is to say, in the embodiment of the invention, the electrocardio digital signal of the subject is obtained, the RR interval signal and RR amplitude signal of the electrocardio digital signal are extracted, and the RR interval signal and RR amplitude signal are combined into a double-channel signal to train the built one-dimensional convolution neural network.
And S5, building a one-dimensional convolutional neural network, and training the one-dimensional convolutional neural network by using the manufactured training set.
Wherein, step S5 specifically includes:
and S51, building a one-dimensional convolutional neural network.
The structure of the one-dimensional convolutional neural network is shown in fig. 3.
S52, making a training set of the dual-channel signals to carry out zero equalization and normalization processing, converting the data into data with an average value of 0 and a standard deviation of 1, and converting the data into a function of
And mu is the mean value of all training sample data, sigma is the standard deviation of all the two-channel signal production training sets, mu and sigma obtained by the two-channel signal production training sets are used for the test set, and zero equalization and normalization are carried out on the test set.
And S53, building a one-dimensional convolutional neural network, and training the one-dimensional convolutional neural network by utilizing a two-channel signal to manufacture a training set.
And S6, classifying the test signal segments by using the trained one-dimensional convolutional neural network.
In specific implementation, the electrocardiosignals used for manufacturing the training set and the testing set are electrocardiosignals acquired by a Polysomnography (PSG), the obtained electrocardio-digital signals are segmented according to minutes, a doctor marks electrocardiosignal segments per minute according to other channel signals of the PSG, then extracts RR interval signals and RR amplitude signals from the electrocardiosignals to manufacture the training set and the testing set, trains the built one-dimensional convolutional neural network through the training set, and finally tests the performance of the network through the testing set.
In summary, according to the sleep apnea fragment detection method based on the convolutional neural network provided by the embodiment of the present invention, the RR interval and RR amplitude dual-channel sequence extracted from the electrocardiographic signal is used as the feature of the training network and the recognition, and by adopting the method and the device, most of noise in the electrocardiographic signal can be eliminated, and the sleep apnea information contained in the electrocardiographic signal can be further retained. After the convolutional neural network training is finished, only electrocardiosignals need to be collected, and then the sleep apnea can be quickly identified. The method provided by the invention is simple and easy to implement, good in anti-interference effect and simple to operate, and can be used for rapidly and accurately measuring the sleep condition of the testee per minute, thereby realizing the early detection of sleep apnea.
The embodiment of the present invention further provides a sleep apnea fragment detection apparatus of a one-dimensional convolutional neural network, which includes a memory and a processor, where an executable code is stored in the processor, and the executable code can be executed by the processor to implement the method according to the above embodiment.
Illustratively, the executable code may be divided into one or more units, which are stored in the memory and executed by the processor to accomplish the present invention. The one or more units may be a series of executable code instruction segments capable of performing specific functions, and the instruction segments are used for describing the execution process of the executable code in the sleep apnea fragment detection device of the one-dimensional convolutional neural network.
The sleep apnea fragment detection device of the one-dimensional convolutional neural network may include, but is not limited to, a processor, and a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the sleep apnea segment detection apparatus of the one-dimensional convolutional neural network, and does not constitute a limitation of the sleep apnea segment detection apparatus of the one-dimensional convolutional neural network, and may include more or less components than those shown, or combine some components, or different components, for example, the sleep apnea segment detection apparatus of the one-dimensional convolutional neural network may further include an input-output device, a network access device, a bus, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the control center of the sleep apnea fragment detection apparatus of the one-dimensional convolutional neural network connects the various parts of the sleep apnea fragment detection apparatus of the whole one-dimensional convolutional neural network by using various interfaces and lines.
The memory may be configured to store the executable code and/or modules, and the processor may implement various functions of the sleep apnea fragment detection apparatus of the one-dimensional convolutional neural network by executing or executing the executable code and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The unit integrated with the sleep apnea fragment detection device of the one-dimensional convolutional neural network can be stored in a computer readable storage medium if the unit is realized in the form of a software functional unit and sold or used as an independent product. Based on such understanding, all or part of the flow of the method according to the above embodiments may be implemented by executable code, which may be stored in a computer-readable storage medium and may implement the steps of the above embodiments when executed by a processor. Where the executable code includes executable code that may be in source code form, object code form, an executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying said executable code, recording media, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (2)
1. A convolutional neural network based sleep apnea segment detection apparatus comprising a memory and a processor, the memory having stored therein executable code executable by the processor to implement the steps of:
s1, collecting electrocardiosignals of a subject during sleep at night;
s2, carrying out analog-to-digital conversion on the acquired electrocardiosignals to obtain electrocardio digital signals of the testee;
s3, segmenting the obtained electrocardio digital signals according to minutes to obtain electrocardio signal segments per minute;
s4, extracting electrocardio RR interphase signals and RR amplitude signals according to the obtained electrocardio signal fragments per minute, labeling the electrocardio signal fragments by using the monitoring result of the polysomnography, and forming a dual-channel signal by using the extracted RR interphase signals and RR amplitude signals to manufacture a training set;
s5, building a one-dimensional convolutional neural network, and training the one-dimensional convolutional neural network by using the manufactured two-channel signal to manufacture a training set;
s6, classifying the test signal segments by using the trained one-dimensional convolutional neural network; wherein, step S4 specifically includes:
s41, recording the electrocardio digital signal as Q, segmenting the electrocardio signal according to minutes, recording the segment of the electrocardio signal at the nth minute as Qn, namely Q ═ Q1，Q2，…，Qn}；
S42, filtering the electrocardiosignal segments per minute, extracting the R wave position by adopting a Pan-Tompki algorithm, correcting the extracted R wave, and subtracting the former R wave from the next adjacent R wave to obtain an RR interval sequence as a first channel; meanwhile, an RR amplitude sequence obtained according to the R wave position is used as a second channel;
s43, filtering the RR interval sequence of the first channel and the RR amplitude sequence of the second channel respectively to remove the value interfered by noise and discard the segment of the signal difference;
s44, respectively carrying out mean value removing processing on the RR interval sequence of the first channel and the RR amplitude sequence of the second channel;
s45, filling the RR interval sequence of the first channel and the RR amplitude sequence of the second channel every minute until the length k is uniform;
s46, marking the electrocardiosignal segments per minute by using the monitoring result of the polysomnography monitor, marking the normal segments as 0, marking the pause segments as 1, and forming a dual-channel signal manufacturing training set by using the extracted RR interval sequence and RR amplitude sequence; in step S45, the filling method is as follows:
the RR sequence of the first channel of the nth minute is Rn＝{r1，r2，…，rmAnd recording the RR amplitude sequence of the second channel at the nth minute as Qn＝{q1，q2，…，qmFill the data in front of the original sequence to the back, fill to a uniform length k, and the result after filling is
Wherein R'nAnd Q'nAll are K.
2. The sleep apnea fragment detection apparatus based on convolutional neural network as set forth in claim 1, wherein the step S5 specifically includes:
s51, building a one-dimensional convolution neural network;
s52, making a training set of the dual-channel signals to carry out zero equalization and normalization processing, converting the data into data with an average value of 0 and a standard deviation of 1, and converting the data into a function of
Wherein mu is the mean value of all training sample data, sigma is the standard deviation of all dual-channel signal production training sets, mu and sigma obtained by the dual-channel signal production training sets are used for the test set, and zero equalization and normalization are carried out on the test set;
and S53, building a one-dimensional convolutional neural network, and training the one-dimensional convolutional neural network by utilizing a two-channel signal to manufacture a training set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910460074.6A CN110151138B (en) | 2019-05-29 | 2019-05-29 | Sleep apnea fragment detection method and device based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910460074.6A CN110151138B (en) | 2019-05-29 | 2019-05-29 | Sleep apnea fragment detection method and device based on convolutional neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110151138A CN110151138A (en) | 2019-08-23 |
| CN110151138B true CN110151138B (en) | 2021-08-24 |
Family
ID=67629857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910460074.6A Active CN110151138B (en) | 2019-05-29 | 2019-05-29 | Sleep apnea fragment detection method and device based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110151138B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110811591A (en) * | 2019-10-31 | 2020-02-21 | 太原理工大学 | Heart failure grading method based on heart rate variability |
| CN110801221B (en) * | 2019-12-09 | 2021-04-27 | 中山大学 | Sleep apnea fragment detection equipment based on unsupervised feature learning |
| CN111166294B (en) * | 2020-01-29 | 2021-09-14 | 北京交通大学 | Automatic sleep apnea detection method and device based on inter-heartbeat period |
| CN111297327B (en) * | 2020-02-20 | 2023-12-01 | 京东方科技集团股份有限公司 | Sleep analysis method, system, electronic equipment and storage medium |
| CN113243890B (en) * | 2021-05-10 | 2023-01-13 | 清华大学深圳国际研究生院 | Sleep apnea syndrome recognition device |
| CN113273992B (en) * | 2021-05-11 | 2023-04-18 | 清华大学深圳国际研究生院 | Signal processing method and device |
| TWI784513B (en) * | 2021-05-11 | 2022-11-21 | 國立勤益科技大學 | Method of monitoring apnea events based on electrocardiogram delayed reactions |
| CN113397556A (en) * | 2021-07-22 | 2021-09-17 | 福州大学至诚学院 | Method for classifying sleep disordered breathing events based on sleep data |
| CN113693608A (en) * | 2021-08-04 | 2021-11-26 | 福州大学至诚学院 | Detection method for diagnosing sleep disorder based on cloud platform |
| CN114073495B (en) * | 2021-12-03 | 2024-03-22 | 中山大学·深圳 | Sleep apnea detection method and device based on information similarity |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103479349A (en) * | 2013-09-25 | 2014-01-01 | 深圳市理邦精密仪器股份有限公司 | Electrocardiosignal data acquisition and processing method and system |
| CN106361277A (en) * | 2016-08-26 | 2017-02-01 | 中山大学 | Sleep apnea syndrome assessment method based on electrocardiogram signals |
| CN109350014A (en) * | 2018-12-10 | 2019-02-19 | 苏州小蓝医疗科技有限公司 | A kind of sound of snoring recognition methods and system |
| CN109620208A (en) * | 2018-12-29 | 2019-04-16 | 南京茂森电子技术有限公司 | Sleep Apnea-hypopnea Syndrome detection system and method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9545227B2 (en) * | 2013-12-13 | 2017-01-17 | Vital Connect, Inc. | Sleep apnea syndrome (SAS) screening using wearable devices |
| US10159421B2 (en) * | 2015-03-30 | 2018-12-25 | Resmed Sensor Technologies Limited | Detection of periodic breathing |
-
2019
- 2019-05-29 CN CN201910460074.6A patent/CN110151138B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103479349A (en) * | 2013-09-25 | 2014-01-01 | 深圳市理邦精密仪器股份有限公司 | Electrocardiosignal data acquisition and processing method and system |
| CN106361277A (en) * | 2016-08-26 | 2017-02-01 | 中山大学 | Sleep apnea syndrome assessment method based on electrocardiogram signals |
| CN109350014A (en) * | 2018-12-10 | 2019-02-19 | 苏州小蓝医疗科技有限公司 | A kind of sound of snoring recognition methods and system |
| CN109620208A (en) * | 2018-12-29 | 2019-04-16 | 南京茂森电子技术有限公司 | Sleep Apnea-hypopnea Syndrome detection system and method |
Non-Patent Citations (1)
| Title |
|---|
| Support Vector Machines for Automated Recognition of Obstructive Sleep Apnea Syndrome From ECG Recordings;Ahsan H.Khandoker等;《IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE》;20090131;第13卷(第1期);第37-48页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110151138A (en) | 2019-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110151138B (en) | Sleep apnea fragment detection method and device based on convolutional neural network | |
| CN108388912B (en) | Sleep staging method based on multi-sensor feature optimization algorithm | |
| CN108670200B (en) | Sleep snore classification detection method and system based on deep learning | |
| CN110801221B (en) | Sleep apnea fragment detection equipment based on unsupervised feature learning | |
| US7578793B2 (en) | Sleep staging based on cardio-respiratory signals | |
| US20080243017A1 (en) | Breathing sound analysis for estimation of airlow rate | |
| EP3637432B1 (en) | System and method for non-apnea sleep arousal detection | |
| CN1736324A (en) | Detection/disposal method and apparatus for obtaining respiratory disturbance index information | |
| CN113095302B (en) | Depth model for arrhythmia classification, method and device using same | |
| CN109044280B (en) | Sleep staging method and related equipment | |
| CA2799094A1 (en) | System and methods of acoustical screening for obstructive sleep apnea during wakefulness | |
| CN113520343A (en) | Sleep risk prediction method and device and terminal equipment | |
| Sloboda et al. | A simple sleep stage identification technique for incorporation in inexpensive electronic sleep screening devices | |
| CN115630290B (en) | Cardiopulmonary coupling feature extraction method and system based on synchronous extrusion transformation | |
| Bhattacharjee et al. | SleepTight: identifying sleep arousals using inter and intra-relation of multimodal signals | |
| Bai et al. | Detection of sleep apnea syndrome by CNN based on ECG | |
| Kao et al. | Using Bootstrap AdaBoost with KNN for ECG-based automated obstructive sleep apnea detection | |
| Aboofazeli et al. | Analysis and classification of swallowing sounds using reconstructed phase space features | |
| CN115040074A (en) | Obstructive sleep apnea detection method and device | |
| Rezaei et al. | Diagnosis of sleep apnea by evaluating points distribution in poincare plot of RR intervals | |
| KR102345884B1 (en) | Method for making prediction model for sleep apnea syndrome by using numerical data and method for predicting sleep apnea syndrome by using the same prediction model | |
| Sisodia et al. | Sleep order detection model using support vector machines and features extracted from brain ECG signals | |
| CN115804581A (en) | Heart rate characteristic measuring method, symptom detection method and related equipment | |
| CA2584258A1 (en) | Breathing sound analysis for estimation of airflow rate | |
| Antonakakis et al. | A New Multi-Feature Classification Scheme for Normal and Abnormal Respiratory Sounds Discrimination |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231121 Address after: No. 66, Gongchang Road, Xinhu Street, Guangming District, Shenzhen, Guangdong 518000 Patentee after: Shenzhen, Zhongshan University Patentee after: SUN YAT-SEN University Address before: 510275 No. 135 West Xingang Road, Guangdong, Guangzhou Patentee before: SUN YAT-SEN University |
|
| TR01 | Transfer of patent right |