CN108814580A - A kind of method and relevant device of non-contact type heart rate test - Google Patents
A kind of method and relevant device of non-contact type heart rate test Download PDFInfo
- Publication number
- CN108814580A CN108814580A CN201810351744.6A CN201810351744A CN108814580A CN 108814580 A CN108814580 A CN 108814580A CN 201810351744 A CN201810351744 A CN 201810351744A CN 108814580 A CN108814580 A CN 108814580A
- Authority
- CN
- China
- Prior art keywords
- heart rate
- sample data
- heart
- training sample
- cnn model
- 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.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/0245—Detecting, measuring or recording pulse rate or heart rate by using sensing means generating electric signals, i.e. ECG signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
- A61B5/6892—Mats
-
- 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
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
Abstract
The embodiment of the present application provides a kind of non-contact type heart rate test method and relevant device, for significantly promoting the accuracy and reliability of heart rate identification.This method includes：By presetting heart rate data of the sensor acquisition to heart rate measuring personnel；Determine that heart rate predicts convolutional neural networks CNN model；The heart rate data is inputted into the heart rate and predicts CNN model, to export cyclic curve；The cyclic curve is converted into target heart by Fourier transform, the target heart is the heart rate to heart rate measuring personnel.
Description
Technical field
This application involves field of medicaments more particularly to a kind of methods and relevant device of non-contact type heart rate test.
Background technique
Heart rate (heart rate) has considerable meaning to human heart health degree is measured, it refers to the unit time
The number of interior heartbeat is the physiological parameter of clinical routine diagnostics.Changes in heart rate is closely related with heart disease, thus in time
The Heart Rate States for understanding oneself are very important.
Existing heart rate measurement is that high sensitive pressure inductor is placed on mattress or pillow mostly to acquire due to body
Pressure change caused by body movement, breathing, heartbeat, is then filtered the data of acquisition under different frequency range, passes through frequency
Analysis obtains heart rate.Some methods then by placing piezoelectric cable on mattress, choose most by the pulse signal that acquisition human body generates
The half of the mean value of several peak value of pulses of nearly a period of time carries out threshold value mirror as threshold value, to filtered signal is amplified
Not, it is determined as heartbeat pulse more than threshold value person.But due to external vibration interference, the continuous variation of position of human body, inductor sheet
Noise of body etc. factor, the data of acquisition often include a large amount of noise, while pressure change caused by heartbeat is again very
Faint, this brings difficulty to accurately identifying for heart rate.
Summary of the invention
The embodiment of the present application provides the method and relevant device of a kind of non-contact type heart rate test, knows for promoting heart rate
Other accuracy and reliability.
The embodiment of the present application first aspect provides a kind of non-contact type heart rate test method, specifically includes：
By presetting heart rate data of the sensor acquisition to heart rate measuring personnel；
Determine that heart rate predicts convolutional neural networks CNN model；
The heart rate data is inputted into the heart rate and predicts CNN model, to export cyclic curve；
The cyclic curve is converted into target heart by Fourier transform, the target heart is described to heart rate measuring
The heart rate of personnel.
Optionally, the determining heart rate prediction convolutional neural networks CNN model includes：
Training sample data are obtained, the training sample data include that M different testers lie in different-thickness and material
The beats of preset time on the mattress of matter；
Heartbeat sample data is extracted according to preset rules from the training sample data；
The heartbeat sample data corresponding target heart time is obtained by heart rate measuring instrument；
The method of the layer-by-layer backpropagation of standard is used based on the heartbeat sample data and the target heart time
Determine the heart rate prediction convolutional neural networks CNN model.
Optionally, the acquisition training sample data include：
The M different testers are monitored by mattress sensor lie in preset described in different-thickness and the mattress of material
The beats of time obtain the training sample data.
Optionally, it is described the cyclic curve is converted to by target heart by Fourier transform after, by the target
Heart rate is shown or is exported.
The embodiment of the present application second aspect provides a kind of non-contact type heart rate test device, specifically includes：
Acquisition unit, for by presetting heart rate data of the sensor acquisition to heart rate measuring personnel；
Determination unit, for determining that heart rate predicts convolutional neural networks CNN model；
Predicting unit predicts CNN model for the heart rate data to be inputted the heart rate, to export cyclic curve；
Converting unit, for the cyclic curve to be converted to target heart, the target heart by Fourier transform
For the heart rate to heart rate measuring personnel.
Optionally, the determination unit is specifically used for：
Training sample data are obtained, the training sample data include that M different testers lie in different-thickness and material
The beats of preset time on the mattress of matter；
Heartbeat sample data is extracted according to preset rules from the training sample data；
The heartbeat sample data corresponding target heart time is obtained by heart rate measuring instrument；
The method of the layer-by-layer backpropagation of standard is used based on the heartbeat sample data and the target heart time
Determine the heart rate prediction convolutional neural networks CNN model.
Optionally, the determination unit also particularly useful for：
The M different testers are monitored by mattress sensor lie in preset described in different-thickness and the mattress of material
The beats of time obtain the training sample data.
Optionally, described device includes：
Output unit, for being shown or being exported the target heart.
The embodiment of the present application third aspect provides a kind of processor, and the processor is for running computer program, institute
Non-contact type heart rate test method described in above-mentioned any one is executed when stating computer program operation.
The embodiment of the present application fourth aspect provides a kind of computer readable storage medium, is stored thereon with computer journey
Sequence, it is characterised in that：The side as described in any one of claim 1 to 7 is realized when the computer program is executed by processor
The step of method.
In conclusion heart rate data of the acquisition to heart rate measuring personnel within a preset time, which is inputted and is trained
Good heart rate predicts CNN model, exports cyclic curve, is converted into target heart by cyclic curve between Fourier transformation.Thus
As can be seen that CNN model is predicted by heart rate, analyzes the relationship between the data of acquisition and practical heart rate data in the application,
And then significantly promote the accuracy and reliability of heart rate identification.
Detailed description of the invention
Fig. 1 is one embodiment schematic diagram of non-contact type heart rate test method provided by the embodiments of the present application；
Fig. 2 is the process schematic provided by the embodiments of the present application that heartbeat sample data is extracted from training sample data；
Fig. 3 is the schematic diagram of heartbeat data sample provided by the embodiments of the present application mark；
Fig. 4 is the trained schematic diagram with test frame of convolutional neural networks provided by the embodiments of the present application；
Fig. 5 is one embodiment schematic diagram of non-contact type heart rate test device provided by the embodiments of the present application；
Fig. 6 is the structural schematic diagram of non-contact type heart rate test device provided by the embodiments of the present application.
Specific embodiment
The embodiment of the present application provides a kind of non-contact type heart rate test method and non-contact type heart rate test device, is used for
Significantly promote the accuracy and reliability of heart rate identification.
The description and claims of this application and term " first ", " second ", " third ", " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so that the embodiments described herein can be in addition to illustrating herein
Or the sequence other than the content of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that
Cover it is non-exclusive include, for example, containing the process, method, system, product or equipment of a series of steps or units need not limit
In step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, produce
The other step or units of product or equipment inherently.
The five contacts heart rate test method is illustrated from the angle of non-contact type heart rate test device below, it is described
Non-contact type heart rate test device can be server, or the functional unit in server does not limit specifically.
Referring to Fig. 1, one embodiment of non-contact type heart rate test method includes in the embodiment of the present application：
101, by presetting heart rate data of the sensor acquisition to heart rate measuring personnel.
In the present embodiment, non-contact type heart rate test device can acquire the heart rate to heart rate measuring personnel within a preset time
Data do not limit acquisition mode specifically.For example, setting mattress sensor, by allowing mattress sensor to acquire, in the present embodiment,
The sample frequency of mattress sensor is 100Hz, i.e., the 100 pressure Value Datas of output in 1 second intercepted sense in 5 seconds every 0.5 second
Device data (i.e. heart rate data Sn) is answered, totally 500 data.It can certainly be acquired using other means, the present embodiment is only
It is illustrated as example, specifically without limitation.
102, the convolutional neural networks CNN model of heart rate prediction is determined.
In the present embodiment, non-contact type heart rate test device can determine the convolution mind of heart rate prediction in the following way
Through network C NN model：
Step 1：Obtain training sample data, training sample data include M different testers lie in different-thickness and
The beats of preset time on the mattress of material, specifically, mattress sensor is placed on bed during obtaining training sample
Pad is in the following, allow M different testers lain on different-thickness and the mattress of material during sleep naturally, continuous acquisition is pre-
If the sensor data of time.Tester can naturally overturn body and breathing.Herein, it is equal to 10 with M, chooses 8 differences
The mattress of material and thickness, preset time are to be illustrated for 20 minutes：
Training sample data include 10 different testers, 5 male 5 female, different ages and weight, choose 8 differences
Mattress, include the mattress of common different-thickness and material, amount to 80 different data acquisitions, 1600 minutes beats
According to about 1600 × 70=112000 times beats.
Step 2：Heartbeat sample data is extracted according to preset rules from training sample data, specifically, referring to Fig.2, Fig. 2
For the process schematic provided by the embodiments of the present application for extracting heartbeat sample data from training sample data, wherein institute in Fig. 2
The two frame S [n] shown and S [n+L] are sampling window schematic diagram, use the method for sliding window from training sample in this implementation
Sample data is extracted in data, the time interval of two neighboring sample is 0.5 second.That is, the heartbeat sample data chosen
{ S [n] ..., S [n+L] }, wherein L be sample time length, this sentence 5 seconds totally 500 data instances be illustrated, n is
The initial time of sample.
Step 3：The heartbeat sample data corresponding target heart time is obtained by heart rate measuring instrument, specifically, using doctor
Accurate heart rate time is obtained with heart rate monitor, referring to Fig. 3, Fig. 3 is heartbeat data sample provided by the embodiments of the present application
The schematic diagram of mark is mapped in time with the heartbeat of training sample data as shown in the stain below Fig. 3, is known that
The accurate location that heartbeat occurs, determines the target heart time.The output of the corresponding target heart of heartbeat sample is one 500 dimension
Vector, if corresponding position is heartbeat, P [n+m]=1, wherein m is the numerical value in 0 to 500, is otherwise set as 0.Pn is the heart
Jump probability graph.On the position both sides of heartbeat, we are set as the numerical value between 0 and 1.Referring to Fig. 3, in the present embodiment, warp
Overtesting certification, when heartbeat probability graph is smoothed curve, the accuracy of non-contact type heart rate test is more preferable, in order to enable without connecing
The accuracy of touch heart rate test is more preferable, the method that the present embodiment uses linear interpolation, and width is 0.2 second, i.e. 20 data.
Step 4：The side of the layer-by-layer backpropagation of standard is used based on heartbeat sample data and the target heart time
Method determines that heart rate predicts convolutional neural networks CNN model, specifically, referring to Fig. 4, Fig. 4 is volume provided by the embodiments of the present application
The schematic diagram of product neural metwork training and test frame, in the present embodiment, CNN is by multiple convolutional layer (convolution
Layer it) is formed with pond layer (pooling layer), adds multiple full-mesh layers (fully connected layer), CNN
Input be heartbeat sample data Sn, vector length 500, output is the prediction Pn of heartbeat position, and vector length is
50.In this application, 5 convolutional layers, 5 pond layers, in addition two full-mesh layers are chosen.In the training process, standard is taken
Layer-by-layer backpropagation method complete heart rate predict convolutional neural networks CNN model.
It should be noted that above-mentioned only a kind of mode has determined convolutional neural networks CNN model, naturally it is also possible to there is it
His mode, specifically without limitation, in addition, above-mentioned described heart rate presets convolutional neural networks CNN model by 5 convolutional layers, 5
A pond layer, two full-mesh layers, is merely illustrative, naturally it is also possible to convolutional layer, pond layer including other numbers and
Full-mesh layer, as long as being able to achieve the purpose of the application, specifically without limitation.
It should be noted that the heart rate data to heart rate measuring personnel can be acquired by default sensor by step 101,
Preset convolutional neural networks CNN model can be determined by step 102, however there is no successively execute between the two steps
The limitation of sequence can first carry out step 101, can also first carry out step 102, or be performed simultaneously, specifically without limitation.
103, heart rate data input heart rate is predicted into CNN model, to export cyclic curve.
In the present embodiment, when non-contact type heart rate test device, which collects heart rate data, to be predicted, the non-contact type heart
Heart rate data can be inputted heart rate and predict that CNN model, heart rate predict that CNN model can be defeated according to heart rate data by rate test device
Cyclic curve out.
104, cyclic curve is converted to by target heart by Fourier transform.
In the present embodiment, after cyclic curve has been determined, non-contact type heart rate test device can be become by Fourier
The cyclic curve of changing commanders is converted to target heart, which is the heart rate to heart rate measuring personnel.
105, target heart is shown or is exported.
In the present embodiment, after determining target heart to heart rate measuring personnel, non-contact type heart rate test device can be with
Target heart is shown or exported according to demand the target heart, such as the target heart is printed.
In conclusion heart rate data of the acquisition to heart rate measuring personnel within a preset time, which is inputted and is trained
Good heart rate predicts CNN model, exports cyclic curve, is converted into target heart by cyclic curve between Fourier transformation.Thus
As can be seen that in the application, the CNN model predicted by heart rate analyzes the pass between the data of acquisition and practical heart rate data
System, and then significantly promote the accuracy and reliability of heart rate identification.
The embodiment of the present application is illustrated from the angle of non-contact type heart rate test method above, below from non-contact type
The angle of heart rate test device is illustrated the embodiment of the present application.
Referring to Fig. 5, one embodiment of non-contact type heart rate test device includes in the embodiment of the present application：
Acquisition unit 501, for by presetting heart rate data of the sensor acquisition to heart rate measuring personnel；
Determination unit 502, for determining that heart rate predicts convolutional neural networks CNN model；
Predicting unit 503 predicts CNN model for the heart rate data to be inputted the heart rate, to export cyclic curve；
Converting unit 504, for the cyclic curve to be converted to target heart, the target heart by Fourier transform
Rate is the heart rate to heart rate measuring personnel；
Output unit 505, for being shown or being exported the target heart.
Wherein, the determination unit 502 is specifically used for：
Training sample data are obtained, the training sample data include that M different testers lie in different-thickness and material
The beats of preset time on the mattress of matter；
Heartbeat sample data is extracted according to preset rules from the training sample data；
The heartbeat sample data corresponding target heart time is obtained by heart rate measuring instrument；
The method of the layer-by-layer backpropagation of standard is used based on the heartbeat sample data and the target heart time
Determine the heart rate prediction convolutional neural networks CNN model.
The determination unit 502 also particularly useful for：
The M different testers are monitored by mattress sensor lie in preset described in different-thickness and the mattress of material
The beats of time obtain the training sample data.
Interactive mode such as earlier figures 1 between each module and unit of non-contact type heart rate test device in the present embodiment
Description in illustrated embodiment, specific details are not described herein again.
In conclusion heart rate data of the acquisition to heart rate measuring personnel within a preset time, which is inputted and is trained
Good heart rate predicts CNN model, exports cyclic curve, is converted into target heart by cyclic curve between Fourier transformation.Thus
As can be seen that CNN model is predicted by heart rate, analyzes the relationship between the data of acquisition and practical heart rate data in the application,
And then significantly promote the accuracy and reliability of heart rate identification.
Referring to Fig. 6, the embodiment of the invention also provides a kind of non-contact type heart rate test device, the non-contact type heart
Rate test device includes processor 601 and memory 602, and above-mentioned acquiring unit, converting unit and processing unit etc. are used as journey
Sequence unit stores in memory, executes above procedure unit stored in memory by processor to realize corresponding function
Energy.
Include kernel in processor 601, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set one
It is a or more, user data is updated by adjusting kernel parameter.
Memory 602 may include the non-volatile memory in computer-readable medium, random access memory (RAM)
And/or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM), memory includes at least one
Storage chip.
The embodiment of the invention provides a kind of storage mediums, are stored thereon with program, real when which is executed by processor
The existing non-contact type heart rate test method.
The embodiment of the invention provides a kind of processor, the processor is for running program, wherein described program operation
Non-contact type heart rate test method described in Shi Zhihang.
The embodiment of the invention provides a kind of equipment, equipment include processor, memory and storage on a memory and can
The program run on a processor, processor realize following steps when executing program：
By presetting heart rate data of the sensor acquisition to heart rate measuring personnel；
Determine that heart rate predicts convolutional neural networks CNN model；
The heart rate data is inputted into the heart rate and predicts CNN model, to export cyclic curve；
The cyclic curve is converted into target heart by Fourier transform, the target heart is described to heart rate measuring
The heart rate of personnel.
Optionally, the determining heart rate prediction convolutional neural networks CNN model includes：
Training sample data are obtained, the training sample data include that M different testers lie in different-thickness and material
The beats of preset time on the mattress of matter；
Heartbeat sample data is extracted according to preset rules from the training sample data；
The heartbeat sample data corresponding target heart time is obtained by heart rate measuring instrument；
The method of the layer-by-layer backpropagation of standard is used based on the heartbeat sample data and the target heart time
Determine the heart rate prediction convolutional neural networks CNN model.
Optionally, the acquisition training sample data include：
The M different testers are monitored by mattress sensor lie in preset described in different-thickness and the mattress of material
The beats of time obtain the training sample data.
Optionally, it is described the cyclic curve is converted to by target heart by Fourier transform after, by the target
Heart rate is shown or is exported.
Equipment herein can be server, PC, PAD, mobile phone etc..
Present invention also provides a kind of computer program products, when executing on data processing equipment, are adapted for carrying out just
The program of beginningization there are as below methods step：
By presetting heart rate data of the sensor acquisition to heart rate measuring personnel；
Determine that heart rate predicts convolutional neural networks CNN model；
The heart rate data is inputted into the heart rate and predicts CNN model, to export cyclic curve；
The cyclic curve is converted into target heart by Fourier transform, the target heart is described to heart rate measuring
The heart rate of personnel.
Optionally, the determining heart rate prediction convolutional neural networks CNN model includes：
Training sample data are obtained, the training sample data include that M different testers lie in different-thickness and material
The beats of preset time on the mattress of matter；
Heartbeat sample data is extracted according to preset rules from the training sample data；
The heartbeat sample data corresponding target heart time is obtained by heart rate measuring instrument；
The method of the layer-by-layer backpropagation of standard is used based on the heartbeat sample data and the target heart time
Determine the heart rate prediction convolutional neural networks CNN model.
Optionally, the acquisition training sample data include：
The M different testers are monitored by mattress sensor lie in preset described in different-thickness and the mattress of material
The beats of time obtain the training sample data.
Optionally, it is described the cyclic curve is converted to by target heart by Fourier transform after, by the target
Heart rate is shown or is exported.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application be referring to the method for the embodiment of the present application, equipment (system) and computer program product flow chart and/
Or block diagram describes.It should be understood that each process that can be realized by computer program instructions in flowchart and/or the block diagram and/
Or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer program instructions
To general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices processor to generate one
A machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing
The device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (10)
1. a kind of method of non-contact type heart rate test, which is characterized in that including：
By presetting heart rate data of the sensor acquisition to heart rate measuring personnel；
Determine that heart rate predicts convolutional neural networks CNN model；
The heart rate data is inputted into the heart rate and predicts CNN model, to export cyclic curve；
The cyclic curve is converted into target heart by Fourier transform, the target heart is described to heart rate measuring personnel
Heart rate.
2. the method according to claim 1, wherein the determining heart rate predicts convolutional neural networks CNN model
Including：
Training sample data are obtained, the training sample data include that M different testers lie in different-thickness and material
The beats of preset time on mattress；
Heartbeat sample data is extracted according to preset rules from the training sample data；
The heartbeat sample data corresponding target heart time is obtained by heart rate measuring instrument；
It is determined based on the heartbeat sample data and the target heart time using the method for the layer-by-layer backpropagation of standard
The heart rate predicts convolutional neural networks CNN model.
3. according to the method described in claim 2, it is characterized in that, the acquisition training sample data include：
The M different testers, which are monitored, by mattress sensor lies in preset time described in different-thickness and the mattress of material
Beats, obtain the training sample data.
4. method according to claim 1 or 2, which is characterized in that it is described by Fourier transform by the cyclic curve
After being converted to target heart, the method includes：
The target heart is shown or exported.
5. a kind of non-contact type heart rate test device, which is characterized in that including：
Acquisition unit, for by presetting heart rate data of the sensor acquisition to heart rate measuring personnel；
Determination unit, for determining that heart rate predicts convolutional neural networks CNN model；
Predicting unit predicts CNN model for the heart rate data to be inputted the heart rate, to export cyclic curve；
Converting unit, for the cyclic curve to be converted to target heart by Fourier transform, the target heart is institute
State the heart rate to heart rate measuring personnel.
6. device according to claim 5, which is characterized in that the determination unit is specifically used for：
Training sample data are obtained, the training sample data include that M different testers lie in different-thickness and material
The beats of preset time on mattress；
Heartbeat sample data is extracted according to preset rules from the training sample data；
The heartbeat sample data corresponding target heart time is obtained by heart rate measuring instrument；
It is determined based on the heartbeat sample data and the target heart time using the method for the layer-by-layer backpropagation of standard
The heart rate predicts convolutional neural networks CNN model.
7. device according to claim 6, which is characterized in that the determination unit also particularly useful for：
The M different testers, which are monitored, by mattress sensor lies in preset time described in different-thickness and the mattress of material
Beats, obtain the training sample data.
8. device according to claim 5 or 6, which is characterized in that described device includes：
Output unit, for being shown or being exported the target heart.
9. a kind of processor, which is characterized in that the processor is for running computer program, when the computer program is run
It executes such as any one of Claims 1-4 the method.
10. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that：The computer program
It is realized when being executed by processor such as the step of any one of Claims 1-4 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810351744.6A CN108814580A (en) | 2018-04-18 | 2018-04-18 | A kind of method and relevant device of non-contact type heart rate test |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810351744.6A CN108814580A (en) | 2018-04-18 | 2018-04-18 | A kind of method and relevant device of non-contact type heart rate test |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108814580A true CN108814580A (en) | 2018-11-16 |
Family
ID=64154955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810351744.6A Pending CN108814580A (en) | 2018-04-18 | 2018-04-18 | A kind of method and relevant device of non-contact type heart rate test |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108814580A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109965858A (en) * | 2019-03-28 | 2019-07-05 | 北京邮电大学 | Based on ULTRA-WIDEBAND RADAR human body vital sign detection method and device |
| CN110464326A (en) * | 2019-08-19 | 2019-11-19 | 上海联影医疗科技有限公司 | A kind of sweep parameter recommended method, system, device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05245148A (en) * | 1992-03-09 | 1993-09-24 | Matsushita Electric Ind Co Ltd | Sleeping sense inferring device and alarm device |
| CN101095612A (en) * | 2006-06-28 | 2008-01-02 | 株式会社东芝 | Apparatus and method for monitoring biological information |
| CN103622671A (en) * | 2013-11-05 | 2014-03-12 | 深圳市视聆科技开发有限公司 | Non-contact physiological signal or periodicity acting force signal collecting device and cushion |
| CN105212918A (en) * | 2015-11-19 | 2016-01-06 | 中科院微电子研究所昆山分所 | A kind of method for measuring heart rate based on piezoelectric signal and system |
| CN106344005A (en) * | 2016-10-28 | 2017-01-25 | 张珈绮 | Mobile ECG (electrocardiogram) monitoring system and monitoring method |
| CN107811626A (en) * | 2017-09-10 | 2018-03-20 | 天津大学 | A kind of arrhythmia classification method based on one-dimensional convolutional neural networks and S-transformation |
| CN107822622A (en) * | 2017-09-22 | 2018-03-23 | 成都比特律动科技有限责任公司 | Electrocardiographic diagnosis method and system based on depth convolutional neural networks |
-
2018
- 2018-04-18 CN CN201810351744.6A patent/CN108814580A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05245148A (en) * | 1992-03-09 | 1993-09-24 | Matsushita Electric Ind Co Ltd | Sleeping sense inferring device and alarm device |
| CN101095612A (en) * | 2006-06-28 | 2008-01-02 | 株式会社东芝 | Apparatus and method for monitoring biological information |
| CN103622671A (en) * | 2013-11-05 | 2014-03-12 | 深圳市视聆科技开发有限公司 | Non-contact physiological signal or periodicity acting force signal collecting device and cushion |
| CN105212918A (en) * | 2015-11-19 | 2016-01-06 | 中科院微电子研究所昆山分所 | A kind of method for measuring heart rate based on piezoelectric signal and system |
| CN106344005A (en) * | 2016-10-28 | 2017-01-25 | 张珈绮 | Mobile ECG (electrocardiogram) monitoring system and monitoring method |
| CN107811626A (en) * | 2017-09-10 | 2018-03-20 | 天津大学 | A kind of arrhythmia classification method based on one-dimensional convolutional neural networks and S-transformation |
| CN107822622A (en) * | 2017-09-22 | 2018-03-23 | 成都比特律动科技有限责任公司 | Electrocardiographic diagnosis method and system based on depth convolutional neural networks |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109965858A (en) * | 2019-03-28 | 2019-07-05 | 北京邮电大学 | Based on ULTRA-WIDEBAND RADAR human body vital sign detection method and device |
| CN110464326A (en) * | 2019-08-19 | 2019-11-19 | 上海联影医疗科技有限公司 | A kind of sweep parameter recommended method, system, device and storage medium |
| CN110464326B (en) * | 2019-08-19 | 2022-05-10 | 上海联影医疗科技股份有限公司 | Scanning parameter recommendation method, system, device and storage medium |
| US11967429B2 (en) | 2019-08-19 | 2024-04-23 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for scan preparation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mert et al. | Evaluation of bagging ensemble method with time-domain feature extraction for diagnosing of arrhythmia beats | |
| CN101467881B (en) | Sleep evaluation device and sleep evaluation method therefor | |
| Föll et al. | FLIRT: A feature generation toolkit for wearable data | |
| US20120184862A1 (en) | System and method for patient monitoring | |
| Phanphaisarn et al. | Heart detection and diagnosis based on ECG and EPCG relationships | |
| CN105637502B (en) | For determining the method and apparatus for being smoothed data point in data point stream | |
| CN105167742B (en) | A kind of fetal weight adaptive estimation method and system | |
| CN107110743A (en) | Check data processing equipment and check data processing method | |
| JP6943287B2 (en) | Biometric information processing equipment, biometric information processing systems, biometric information processing methods, and programs | |
| WO2020187987A1 (en) | Population-level gaussian processes for clinical time series forecasting | |
| CN108814580A (en) | A kind of method and relevant device of non-contact type heart rate test | |
| US20170127960A1 (en) | Method and apparatus for estimating heart rate based on movement information | |
| Umematsu et al. | Forecasting stress, mood, and health from daytime physiology in office workers and students | |
| CN109166626B (en) | Method for supplementing medical index missing data of peptic ulcer patient | |
| Roy et al. | BePCon: A photoplethysmography-based quality-aware continuous beat-to-beat blood pressure measurement technique using deep learning | |
| CN114052693A (en) | Heart rate analysis method, device and equipment | |
| CN103784118B (en) | Method and apparatus for calculating amount of exercise performed | |
| CN113456033A (en) | Physiological index characteristic value data processing method and system and computer equipment | |
| CN109864731B (en) | Pulse measuring method and device, terminal equipment and readable storage medium | |
| US20130275154A1 (en) | Apparatus and method for predicting potential degree of coronary artery calcification (cac) risk | |
| CN107221128B (en) | A kind of evaluation of portable body fall risk and early warning system and its method | |
| CN114469040A (en) | Heart rate detection method and device, storage medium and electronic equipment | |
| CN113288133A (en) | Method, apparatus, storage medium, and processor for predicting blood glucose level | |
| CN110276044A (en) | Body temperature prediction technique and the clinical thermometer that body temperature is predicted using the body temperature prediction technique | |
| US20210117782A1 (en) | Interpretable neural networks for cuffless blood pressure estimation |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181116 |