CN108875575A - The automatic arrhythmia analysis method of deep neural network is merged based on multi channel signals - Google Patents
The automatic arrhythmia analysis method of deep neural network is merged based on multi channel signals Download PDFInfo
- Publication number
- CN108875575A CN108875575A CN201810451710.4A CN201810451710A CN108875575A CN 108875575 A CN108875575 A CN 108875575A CN 201810451710 A CN201810451710 A CN 201810451710A CN 108875575 A CN108875575 A CN 108875575A
- Authority
- CN
- China
- Prior art keywords
- neural network
- dimension
- deep neural
- lead
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- 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
- A61B5/72—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Veterinary Medicine (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Signal Processing (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Data Mining & Analysis (AREA)
- Cardiology (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Fuzzy Systems (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses one kind to merge the automatic arrhythmia analysis method of deep neural network based on multi channel signals, it includes:Three kinds of sample modes generate multichannel ecg samples;The 600 dimension electrocardiosignal amplifications respectively obtained are 3*(600*1)Dimension, when original electro-cardiologic signals are two leads, equivalent formation 2*3* (600*1) ties up electrocardiosignal sample, by every lead input signal by merging laminated and being input in lead channel all the way.Lead channel is made of concatenated convolution layer unit, and the merging layer of output end merges characteristic pattern, there is attention layers between convolution layer unit and LSTM layer unit;Convolution layer unit includes that the exciting unit for being extracted the convolutional layer of one-dimensional electrocardiosignal feature using one-dimensional convolution and being sequentially connected in series is operated and a pond layer operation;The full articulamentum that LSTM layer unit one exciting unit of series connection is softmax;Output;The parameter for learning deep neural network carries out automatic identification to sample;Solve the problems, such as that existing arrhythmia analysis system is still insufficient for the accuracy rate demand of clinical application.
Description
Technical field
The present invention relates to medical signals processing technology fields, it more particularly relates to which a kind of believed based on multichannel
Number fusion the automatic arrhythmia analysis method of deep neural network.
Background technique
In recent years, rapid for the auxiliary diagnosis equipment development of electrocardiogram, with the scientific and technological progress of message area, especially
With the progress of mode identification technology, the function of ecg equipment be no longer only obtain electrocardiosignal, printing electrocardiogram, but
Direction message development is clapped towards valid data and automatic identification, the statistics heart excavated in electrocardiogram.The band automatic identification heart claps function
The analytical equipment of energy can provide more intuitive effective ECG information for doctor, effectively saving Diagnostic Time, improve doctor's
Diagnosis efficiency is important one of auxiliary medical equipment.
The automatic arrhythmia analysis system of work on the computing device is the core of such equipment, and technological approaches has two
Kind, first is that characterizing the feature vector of electrocardiogram effective information by extracting, it is input to classifier algorithm and obtains the classification of heart bat;
Second is that passing through the automatic learning characteristic of depth learning technology and being identified, the classification of heart bat is obtained.
Arrhythmia analysis system based on depth learning technology can use data bonus, effectively improve accuracy of identification,
However current arrhythmia analysis system is still insufficient for the accuracy rate demand of clinical application.
Summary of the invention
The purpose of the present invention is the accuracy rate of clinical application is still insufficient for for the existing arrhythmia analysis system of solution
The problem of demand, one kind merging the automatic arrhythmia analysis method of deep neural network based on multi channel signals.
One kind merging the automatic arrhythmia analysis method of deep neural network based on multi channel signals, it includes:
1)Compound sampling is carried out using three kinds of sample modes, generates multichannel ecg samples;
A. to the electrocardiosignal of each lead, front and back respectively take 100 points again resampling to fixed dimension 600;
B. to the electrocardiosignal of each lead, the preceding R-R wave section for taking 2 periods, after take the R-R wave section in 1 period, then weigh
Sample fixed dimension 600;
C. to the electrocardiosignal of each lead, the preceding R-R wave section for taking 2 periods, which is laid equal stress on, samples 300 dimensions, after take 1 period
R-R wave section lay equal stress on and sample 300 dimensions, the signal of front and back resampling is finally spliced to form 600 dimensional signals;
Thus the resulting 600 dimension electrocardiosignal of three kinds of sample modes is respectively Input k1, and Input k2 and Input k3, k are
It I, is II, III ..., the lead number of original electro-cardiologic signals, the size of each Input is that 600*1 is tieed up, at this time every lead electrocardio
Signal increases to 600*3 dimension by 600*1 dimensional expansion, and 3 at this time indicate that the electrocardiosignal of each lead possesses 3 sub- leads.It uses
Data set in original electro-cardiologic signals when possessing 2 leads, the electrocardiogram (ECG) data of original each lead is passed through into the compound sampling
Mode forms the electrocardiosignal sample X, the input Input as deep neural network model of above-mentioned 2*3*600 dimension;
2) deep neural network is built
Deep neural network includes the lead channel of multiple successively parallel connections, each lead channel is by concatenated convolution layer unit group
At the output end in every lead channel all the way has a merging layer, by the characteristic pattern per lead channel all the way along the last one dimension
Degree merges, i.e., dimension where the depth of characteristic pattern.Have between the merging layer and LSTM layer unit of every lead channel output end
Attention layers are used as connection unit;Each convolution layer unit include a convolutional layer and the convolutional layer output end according to
Secondary concatenated exciting unit operation and a pond layer operation;The convolution layer unit uses one-dimensional convolution, for extracting
The feature of one-dimensional electrocardiosignal;
The full articulamentum that output one exciting unit of series connection of LSTM layer unit is softmax;Output;
3)Learn the parameter of deep neural network;
4)Automatic identification is carried out to sample;
Described builds deep neural network, and when electrocardio data set possesses two lead signals, input signal dimension is 2*3*
600*1.By the input signal of each lead by being input in lead channel all the way after merging laminated and the last one dimension, then
The input signal size in each lead channel is 600*3, totally 2 lead channels, wherein 3 refer to port number.It will be each
The sub- lead that lead expands is used as lead channel all the way after merging channel;Each layer of convolution layer unit in per lead channel all the way
Output end be sequentially connected in series an exciting unit operation and a pond layer operation;The convolution nucleus number of first convolution layer unit is 32
A, convolution kernel size is 4, and exciting unit thereafter is relu function, and the pond core size of pond layer unit is 6, pond step-length
It is 3;Characteristic pattern dimension after the unit of first layer pond is 200*32;The convolution nucleus number of second convolution layer unit is 64
A, convolution kernel size is 5, and exciting unit thereafter is relu function, and the pond core size of pond layer unit is 6, pond step-length
It is 3;Characteristic pattern dimension after the unit of second layer pond is 67*64;
The deep neural network is the two convolution layer units and LSTM layer unit being sequentially connected in series;
In per lead channel all the way it is special to merge output by merging laminated and the last one dimension for the output of two layers of convolution unit
Dimension where levying the depth of figure, the characteristic pattern size after merging are 67*128;
One attention unit of series connection, attention unit construct the power that a dimension is similarly 67*128 after merging layer
Characteristic pattern corresponding element dot product after weight matrix and convolution, the characteristic pattern output dimension after weighting is 67*128.This weight square
The element of battle array is got by neural metwork training, and matrix element initial value is random number of the range between 0-1.By the spy after weighting
Sign figure is input in LSTM layer unit, and taking the hiding number of plies of LSTM layer unit is that 128, LSTM layer unit output characteristic pattern dimension is
128.The full articulamentum that output one exciting unit of series connection of LSTM layer unit is softmax, the output dimension of full articulamentum are
4, i.e. classification number.The final deep neural network model exports predicted vector dimension;
The predicted vector dimension of the deep neural network output is 4;It is taken using keras Open Framework and python language
It builds, uses cross entropy as loss function, optimize loss function using Adam optimizer;
The parameter of the study deep neural network is:The training parameter for initializing the deep neural network will sample
Signal be divided into training set sample and test set sample;Randomly selected from population sample the sample of a part of number as
Training set is considered as test set for other unchecked samples.The multichannel electrocardiosignal X in training set is input to initially again
It in deep neural network after change, is iterated using minimizing cost function as target, to generate the deep neural network simultaneously
It preserves;Wherein, every iteration once then updates the primary training parameter, until the damage of the last deep neural network
Mistake value and accuracy rate are stablized near a certain numerical value, deconditioning and can save the training parameter and model structure of current network
Information;
Described is automatically recognized as sample:Ready-portioned test set sample is fully entered to the nerve saved
In network, running the deep neural network can be obtained the corresponding 4 dimension predicted value vector output of test set sample, by test set
The label of sample generates the label vector of 4 dimensions, then the predicted value by that will export and test set using the method for one-hot coding
The label of sample compares to check whether that classification is correct.
Detailed description of the invention
Fig. 1 is deep neural network structure chart.
Specific embodiment
Automatic arrhythmia analysis method of the embodiment 1 based on deep neural network
The invention will be further described with specific embodiment with reference to the accompanying drawing.
Specific example is current international practice ECG data library MIT-BIH Arrhythmia Database (mitdb), the number
The website physionet.org known in industry is disclosed according to the data and operation instruction in library;Database includes 47 patients two
The half an hour 360Hz electrocardiographic recorder of lead mode, and have passed through heart disease doctor and mark manually;It is selected from the data set
Four kinds of hearts divided according to AAMI standard clap category combinations as recruitment evaluation foundation, including N class out(The normal heart is clapped or bundle branch passes
The retardance heart is led to clap), S class(The supraventricular exception heart is clapped), V class(The ventricle exception heart is clapped), F class(The heart is merged to clap);These four classifications
Label and corresponding relationship such as table 1 with classification in mitdb data set;In this example, pass through on computers soft of working
Well known Matlab and python simulated environment is realized in part system and industry.
The detailed step of the present embodiment is as follows:
One, generates the realization of multichannel ecg samples using compound sampling mode
After the original signal denoising in the mitdb data set, using the channel of following three kinds of sample mode amplified signals
Number:
(1)Sample mode one is:To the electrocardiosignal of each lead, front and back respectively take 100 points again resampling to fixed dimension
600;Generate the Input I 1 and Input II 1 in Fig. 1;
(2)Sample mode two is:To the electrocardiosignal of each lead, the preceding R-R wave section for taking 2 periods, after take 1 period
R-R wave section, then resampling is to fixed dimension 600;Generate the Input I 2 and Input II 2 in Fig. 1;
(3)Sample mode three is:To the electrocardiosignal of each lead, the preceding R-R wave section for taking 2 periods, which is laid equal stress on, samples 300
Dimension, after take the R-R wave section in 1 period to lay equal stress on to sample 300 dimensions, the signal of front and back resampling is finally spliced to form 600 dimensions
Signal;Generate the Input I 3 and Input II 3 in Fig. 1;
Thus the resulting 600 dimension electrocardiosignal of three kinds of sample modes is respectively Input k1, and Input k2 and Input k3, k are
I, II, it is the lead number of original electro-cardiologic signals in mitdb data set, the size of each Input is 600*1 dimension, often at this time
Lead electrocardiosignal increases to 3* by 600*1 dimensional expansion(600*1)Dimension, 3 at this time indicate that the electrocardiosignal of each lead possesses 3
Sub- lead.Because original electro-cardiologic signals possess 2 leads in mitdb data set, by the electrocardiogram (ECG) data of original each lead
The sample X that above-mentioned 2*3* (600*1) dimension is formed by the compound sampling mode, the input as deep neural network model.
Two, build deep neural network
(1)The specific structure of the deep neural network
The depth model input is the electrocardiosignal X in each channel of each lead, when electrocardio data set possesses two lead signals
When, so input signal dimension is 2*3*600*1.By the input signal of each lead by merging layer(Merge layers)Merge most
Be input to after the latter dimension in lead channel all the way, then the input signal size in each lead channel be 600*3, totally 2
Lead channel, wherein 3 refer to port number.Will the sub- lead that expands of each lead merge channel after lead to as lead all the way
Road in corresponding diagram 1, is used as a lead channel after Iuput1, Input2, Input3 are merged, by Iuput4, Input5,
Input6 is used as another lead channel after merging.The output end of each layer of convolution layer unit is sequentially connected in series one and swashs in lead channel
Encourage unit operation and a pond layer operation;The convolution nucleus number of first convolution layer unit is 32, and convolution kernel size is 4, thereafter
Exciting unit be relu function, the pond core size of pond layer unit is 6, and pond step-length is 3;By first layer pond unit
Characteristic pattern dimension afterwards is 200*32;The convolution nucleus number of second convolution layer unit is 64, and convolution kernel size is 5, thereafter
Exciting unit is relu function, and the pond core size of pond layer unit is 6, and pond step-length is 3;After the unit of second layer pond
Characteristic pattern dimension be 67*64;
The output of two layers of convolution unit merges the last one dimension by merging layer (Merge layers) in per lead channel all the way, i.e.,
Dimension where merging the depth of output characteristic pattern, the characteristic pattern size after merging are 67*128.It connects one after merging layer
Attention unit, attention unit construct the weight matrix and the spy after convolution that a dimension is similarly 67*128
Figure corresponding element dot product is levied, the characteristic pattern output dimension after weighting is 67*128;Characteristic pattern after weighting is input to LSTM layers
In unit, it is 128 that the hiding number of plies for taking LSTM layer unit, which is 128, LSTM layer unit output characteristic pattern dimension,;LSTM layer unit
Output connects an exciting unit as the full articulamentum of softmax, and the number of plies of full articulamentum is 4, i.e. classification number.The final depth
The predicted vector y_pred dimension for spending neural network model output is 4.
(2)The specific implementation of the deep neural network
The model is built using keras Open Framework and python language, network configuration parameter such as table 3.The depth nerve
Functional expression model buildings in Web vector graphic keras frame import Model function, setting that is, from keras.models module
The input of Model is the multichannel electrocardiosignal X after compound sampling, exports the predicted vector y_ for being 4 for dimension
pred;By the one-dimensional convolutional layer of Convolution1D construction of function imported in keras.layers module, pass through importing
The one-dimensional maximization pond layer of MaxPool1D construction of function in keras.layers module, by importing keras.layers mould
LSTM construction of function LSTM layer unit in block, and the dropout parameter and recurrent_dropout being arranged in LSTM function
Parameter is 0.2.
The parameter of three, study deep neural network
The signal sampled is divided into training set sample and test by the training parameter for initializing the deep neural network first
Collect sample, the data set after division is as shown in table 2.It is defeated that training is concentrated use in the multichannel electrocardiosignal after complex method sampling
Enter in the deep neural network to after initialization, uses cross entropy as cost function in the deep neural network;In Keras
Using categorical_crossentropy function, pass through the functional expression model M odel of building in the deep neural network
Instantiate an object model, in model.compile function be arranged parameter loss be ' categorical_
crossentropy';And be iterated using minimizing cost function as target using Adam optimizer, by
It is that ' Adam ' is optimized that parameter optimizer is arranged in model.compile function, to generate the deep neural network
And save as the file model1.hd5 of hd5 suffix;Wherein, every iteration once then updates the primary training parameter;Until most
The penalty values of the deep neural network and accuracy rate are stablized near a certain numerical value afterwards, deconditioning and can save current
The training parameter and model structure information of network;The deep neural network has trained 3000 batches altogether, and each batch is 64
A sample.
Four, carry out automatic identification to sample
Ready-portioned test set sample is fully entered in the neural network model1.hd5 saved, the depth is run
Degree neural network can be obtained the corresponding 4 dimension predicted value vector output y_pred of test set sample, by the label of test set sample
The label vector y_label that 4 dimensions are generated using the method for one-hot coding, provides np_ in keras.utils module
Utils.to_categorical function carries out one-hot coding, then the prediction by will export to the test set label of input
The label of value and test set sample compares to check whether that classification is correct, i.e. statistics y_pred and y_label corresponding position value phase
With number of samples num, divided by test set total sample number be final accuracy rate with num.
According to table 1, the heart bat of four seed types under AAMI standard is marked.
According to quantity shown in table 2, classification based training collection of a part in intentionally clapping as embodiment is randomly selected;?
During the remaining heart is clapped, intentionally clapping as test set other than training set is removed.
According to network architecture parameters listed by table 3, the parameter value of corresponding position in channel type such as the Type column of every layer of network,
The parameter value of corresponding position, is sized to Kernel for every layer of network of core in every layer of channel type such as Output layer column
The moving step length of every layer of core of network is set as the parameter value of corresponding position in Strides by the parameter value of corresponding position in size.
Claims (5)
1. one kind merges the automatic arrhythmia analysis method of deep neural network based on multi channel signals, it includes:
1)Compound sampling is carried out using three kinds of sample modes, generates multichannel ecg samples;
A. to the electrocardiosignal of each lead, front and back respectively take 100 points again resampling to fixed dimension 600;
B. to the electrocardiosignal of each lead, the preceding R-R wave section for taking 2 periods, after take the R-R wave section in 1 period, then weigh
Sample fixed dimension 600;
C. to the electrocardiosignal of each lead, the preceding R-R wave section for taking 2 periods, which is laid equal stress on, samples 300 dimensions, after take 1 period
R-R wave section lay equal stress on and sample 300 dimensions, the signal of front and back resampling is finally spliced to form 600 dimensional signals;
Thus the resulting 600 dimension electrocardiosignal of three kinds of sample modes is respectively Input k1, and Input k2 and Input k3, k are
It I, is II, III ..., the lead number of original electro-cardiologic signals, the size of each Input is that 600*1 is tieed up, at this time every lead electrocardio
Signal increases to 600*3 dimension by 600*1 dimensional expansion, and 3 at this time indicate that the electrocardiosignal of each lead possesses 3 sub- leads;It uses
Data set in original electro-cardiologic signals when possessing 2 leads, the electrocardiogram (ECG) data of original each lead is passed through into the compound sampling
Mode forms the electrocardiosignal sample X, the input Input as deep neural network model of above-mentioned 2*3*600 dimension;
By the input signal of each lead by being input in lead channel all the way after merging laminated and the last one dimension, then often
The input signal size in one lead channel is 600*3, totally 2 lead channels, wherein 3 refer to port number;It will each lead
Join after the sub- lead expanded merges channel and is used as lead channel all the way;Each layer of convolution layer unit in per lead channel all the way
Output end is sequentially connected in series exciting unit operation and a pond layer operation;The convolution nucleus number of first convolution layer unit is 32,
Convolution kernel size is 4, and exciting unit thereafter is relu function, and the pond core size of pond layer unit is 6, and pond step-length is 3;
Characteristic pattern dimension after the unit of first layer pond is 200*32;The convolution nucleus number of second convolution layer unit is 64, volume
Product core size is 5, and exciting unit thereafter is relu function, and the pond core size of pond layer unit is 6, and pond step-length is 3;Through
Characteristic pattern dimension after crossing second layer pond unit is 67*64;
2) deep neural network is built
Deep neural network includes the lead channel of multiple successively parallel connections, each lead channel is by concatenated convolution layer unit group
At the output end in every lead channel all the way has a merging layer, by the characteristic pattern per lead channel all the way along the last one dimension
Degree merges, i.e., dimension where the depth of characteristic pattern;Have between the merging layer and LSTM layer unit of every lead channel output end
Attention layers are used as connection unit;Each convolution layer unit include a convolutional layer and the convolutional layer output end according to
Secondary concatenated exciting unit operation and a pond layer operation;The convolution layer unit uses one-dimensional convolution, for extracting
The feature of one-dimensional electrocardiosignal;
The full articulamentum that output one exciting unit of series connection of LSTM layer unit is softmax;Output;
3)Learn the parameter of deep neural network;
4)Automatic identification is carried out to sample.
2. according to claim 1 a kind of based on the multi channel signals fusion automatic arrhythmia analysis side of deep neural network
Method, it is characterised in that:The deep neural network is the two convolution layer units and LSTM layer unit being sequentially connected in series;
In per lead channel all the way it is special to merge output by merging laminated and the last one dimension for the output of two layers of convolution unit
Dimension where levying the depth of figure, the characteristic pattern size after merging are 67*128;
One attention unit of series connection, attention unit construct the power that a dimension is similarly 67*128 after merging layer
Characteristic pattern corresponding element dot product after weight matrix and convolution, the characteristic pattern output dimension after weighting is 67*128, this weight square
The element of battle array is got by neural metwork training, and matrix element initial value is random number of the range between 0-1;By the spy after weighting
Sign figure is input in LSTM layer unit, and taking the hiding number of plies of LSTM layer unit is that 128, LSTM layer unit output characteristic pattern dimension is
The full articulamentum that output one exciting unit of series connection of 128, LSTM layer units is softmax, the output dimension of full articulamentum are
4, i.e. classification number;The final deep neural network model exports predicted vector dimension.
3. according to claim 2 a kind of based on the multi channel signals fusion automatic arrhythmia analysis side of deep neural network
Method, it is characterised in that:The predicted vector dimension of the deep neural network output is 4;Using keras Open Framework and
Python language is built, and uses cross entropy as loss function, optimizes loss function using Adam optimizer.
4. according to claim 1,2 or 3 a kind of based on the multi channel signals fusion automatic arrhythmia cordis of deep neural network
Analysis method, it is characterised in that:The parameter of the study deep neural network is:Initialize the instruction of the deep neural network
Practice parameter, the signal sampled is divided into training set sample and test set sample;One is randomly selected from population sample
Score purpose sample is considered as test set as training set, for other unchecked samples;Again by the multichannel heart in training set
Electric signal X is input in the deep neural network after initialization, is iterated using minimizing cost function as target, to generate
It states deep neural network and preserves;Wherein, every iteration once then updates the primary training parameter, until described in last
The penalty values and accuracy rate of deep neural network are stablized near a certain numerical value, deconditioning and can save the instruction of current network
Practice parameter and model structure information.
5. according to claim 4 a kind of based on the multi channel signals fusion automatic arrhythmia analysis side of deep neural network
Method, it is characterised in that:Described is automatically recognized as sample:Ready-portioned test set sample is fully entered and has been saved
The neural network in, run the deep neural network can be obtained test set sample it is corresponding 4 dimension predicted value vector it is defeated
Out, the label of test set sample is generated to the label vector of 4 dimensions using the method for one-hot coding, then pre- by that will export
The label of measured value and test set sample compares to check whether that classification is correct.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810451710.4A CN108875575B (en) | 2018-05-12 | 2018-05-12 | Automatic arrhythmia analysis method based on multi-channel signal fusion deep neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810451710.4A CN108875575B (en) | 2018-05-12 | 2018-05-12 | Automatic arrhythmia analysis method based on multi-channel signal fusion deep neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108875575A true CN108875575A (en) | 2018-11-23 |
CN108875575B CN108875575B (en) | 2021-05-11 |
Family
ID=64333452
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810451710.4A Active CN108875575B (en) | 2018-05-12 | 2018-05-12 | Automatic arrhythmia analysis method based on multi-channel signal fusion deep neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108875575B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108764457A (en) * | 2018-05-12 | 2018-11-06 | 鲁东大学 | The automatic arrhythmia analysis method of deep neural network is merged based on sampling channel |
CN109480825A (en) * | 2018-12-13 | 2019-03-19 | 武汉中旗生物医疗电子有限公司 | The processing method and processing device of electrocardiogram (ECG) data |
CN109662707A (en) * | 2018-12-18 | 2019-04-23 | 深圳先进技术研究院 | Disease probability acquisition method, device, electronic equipment and computer-readable medium |
CN109846472A (en) * | 2019-01-30 | 2019-06-07 | 郑州大学 | Beat classification method based on BiLSTM-Attention deep neural network |
CN110141219A (en) * | 2019-06-20 | 2019-08-20 | 鲁东大学 | Myocardial infarction automatic testing method based on lead fusion deep neural network |
CN110141220A (en) * | 2019-06-20 | 2019-08-20 | 鲁东大学 | Myocardial infarction automatic testing method based on multi-modal fusion neural network |
CN110263684A (en) * | 2019-06-06 | 2019-09-20 | 山东省计算中心(国家超级计算济南中心) | Electrocardiogram classification method based on lightweight neural network |
CN110507318A (en) * | 2019-08-16 | 2019-11-29 | 武汉中旗生物医疗电子有限公司 | A kind of electrocardiosignal QRS wave group localization method and device |
CN111759302A (en) * | 2020-07-10 | 2020-10-13 | 齐鲁工业大学 | Wearable individual electrocardiogram detection method |
WO2021057328A1 (en) * | 2019-09-24 | 2021-04-01 | 上海数创医疗科技有限公司 | St segment classification convolutional neural network based on feature selection and method for using same |
CN112990025A (en) * | 2021-03-19 | 2021-06-18 | 北京京东拓先科技有限公司 | Method, apparatus, device and storage medium for processing data |
CN113168915A (en) * | 2018-11-30 | 2021-07-23 | 普瑞万蒂斯技术有限公司 | Multichannel and cardioversion learning |
RU2767157C2 (en) * | 2020-07-21 | 2022-03-16 | Общество с ограниченной ответственностью "СберМедИИ" (ООО "СберМедИИ") | Method and system for automatic ecg analysis |
CN116956174A (en) * | 2019-05-13 | 2023-10-27 | 北京绪水互联科技有限公司 | Classification model for cold head state classification detection and life prediction and generation method of prediction model |
WO2024089382A1 (en) * | 2022-10-26 | 2024-05-02 | Oxford University Innovation Limited | Method for extracting information from multi-channel measurement data, measurement system for obtaining multi-channel measurement data |
CN117958834A (en) * | 2023-11-20 | 2024-05-03 | 齐鲁工业大学(山东省科学院) | Electrocardiogram classification method based on random mask and generation type self-supervision learning |
RU2823433C1 (en) * | 2023-11-21 | 2024-07-23 | Общество С Ограниченной Ответственностью "Компания "Стрим Лабс" | Method of processing and analysing electrocardiogram (ecg) data |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104921722A (en) * | 2015-07-15 | 2015-09-23 | 西南民族大学 | Double-lead combined with electrocardiogram QRS wave detection method |
WO2016072940A1 (en) * | 2014-11-05 | 2016-05-12 | Agency For Science, Technology And Research | Multi-channel ballistocardiography with cepstrum smoothing and quality-based dynamic channel selection |
CN106108880A (en) * | 2016-06-28 | 2016-11-16 | 吉林大学 | A kind of heart claps automatic identifying method and system |
CN106485213A (en) * | 2016-09-27 | 2017-03-08 | 鲁东大学 | A kind of utilization electrocardiosignal carries out the feature extracting method of automatic identification |
US20180032691A1 (en) * | 2016-07-29 | 2018-02-01 | Nissim Zur | Health monitor and a method for monitoring health using an artificial intelligence engine pattern |
CN107693000A (en) * | 2017-10-23 | 2018-02-16 | 山东大学 | Heart rate method of estimation, the device and system merged based on electrocardio and pulse signal |
CN107837082A (en) * | 2017-11-27 | 2018-03-27 | 乐普(北京)医疗器械股份有限公司 | Electrocardiogram automatic analysis method and device based on artificial intelligence self study |
CN107945844A (en) * | 2017-11-27 | 2018-04-20 | 乐普(北京)医疗器械股份有限公司 | Examining report data creation method |
CN107951485A (en) * | 2017-11-27 | 2018-04-24 | 乐普(北京)医疗器械股份有限公司 | Ambulatory ECG analysis method and apparatus based on artificial intelligence self study |
-
2018
- 2018-05-12 CN CN201810451710.4A patent/CN108875575B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016072940A1 (en) * | 2014-11-05 | 2016-05-12 | Agency For Science, Technology And Research | Multi-channel ballistocardiography with cepstrum smoothing and quality-based dynamic channel selection |
CN104921722A (en) * | 2015-07-15 | 2015-09-23 | 西南民族大学 | Double-lead combined with electrocardiogram QRS wave detection method |
CN106108880A (en) * | 2016-06-28 | 2016-11-16 | 吉林大学 | A kind of heart claps automatic identifying method and system |
US20180032691A1 (en) * | 2016-07-29 | 2018-02-01 | Nissim Zur | Health monitor and a method for monitoring health using an artificial intelligence engine pattern |
CN106485213A (en) * | 2016-09-27 | 2017-03-08 | 鲁东大学 | A kind of utilization electrocardiosignal carries out the feature extracting method of automatic identification |
CN107693000A (en) * | 2017-10-23 | 2018-02-16 | 山东大学 | Heart rate method of estimation, the device and system merged based on electrocardio and pulse signal |
CN107837082A (en) * | 2017-11-27 | 2018-03-27 | 乐普(北京)医疗器械股份有限公司 | Electrocardiogram automatic analysis method and device based on artificial intelligence self study |
CN107945844A (en) * | 2017-11-27 | 2018-04-20 | 乐普(北京)医疗器械股份有限公司 | Examining report data creation method |
CN107951485A (en) * | 2017-11-27 | 2018-04-24 | 乐普(北京)医疗器械股份有限公司 | Ambulatory ECG analysis method and apparatus based on artificial intelligence self study |
Non-Patent Citations (4)
Title |
---|
MOHAMED LIMAM 等: ""Atrial fibrillation detection and ECG classification based on convolutional recurrent neural network"", 《2017 COMPUTING IN CARDIOLOGY (CINC)》 * |
SHING-HONG LIU 等: ""Arrhythmia Identification with Two-Lead Electrocardiograms Using Artificial Neural Networks and Support Vector Machines for a Portable ECG Monitor System"", 《SENSORS》 * |
刘通 等: ""基于核主元分析和支持向量机的心拍识别"", 《光学 精密工程》 * |
白洋: ""基于深度置信网络的心律失常分类算法研究"", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108764457A (en) * | 2018-05-12 | 2018-11-06 | 鲁东大学 | The automatic arrhythmia analysis method of deep neural network is merged based on sampling channel |
CN113168915A (en) * | 2018-11-30 | 2021-07-23 | 普瑞万蒂斯技术有限公司 | Multichannel and cardioversion learning |
CN109480825A (en) * | 2018-12-13 | 2019-03-19 | 武汉中旗生物医疗电子有限公司 | The processing method and processing device of electrocardiogram (ECG) data |
CN109480825B (en) * | 2018-12-13 | 2021-08-06 | 武汉中旗生物医疗电子有限公司 | Electrocardio data processing method and device |
CN109662707A (en) * | 2018-12-18 | 2019-04-23 | 深圳先进技术研究院 | Disease probability acquisition method, device, electronic equipment and computer-readable medium |
CN109846472A (en) * | 2019-01-30 | 2019-06-07 | 郑州大学 | Beat classification method based on BiLSTM-Attention deep neural network |
CN116956174A (en) * | 2019-05-13 | 2023-10-27 | 北京绪水互联科技有限公司 | Classification model for cold head state classification detection and life prediction and generation method of prediction model |
CN110263684B (en) * | 2019-06-06 | 2021-02-09 | 山东省计算中心(国家超级计算济南中心) | Electrocardiogram classification method based on lightweight neural network |
CN110263684A (en) * | 2019-06-06 | 2019-09-20 | 山东省计算中心(国家超级计算济南中心) | Electrocardiogram classification method based on lightweight neural network |
CN110141220A (en) * | 2019-06-20 | 2019-08-20 | 鲁东大学 | Myocardial infarction automatic testing method based on multi-modal fusion neural network |
CN110141219A (en) * | 2019-06-20 | 2019-08-20 | 鲁东大学 | Myocardial infarction automatic testing method based on lead fusion deep neural network |
CN110507318A (en) * | 2019-08-16 | 2019-11-29 | 武汉中旗生物医疗电子有限公司 | A kind of electrocardiosignal QRS wave group localization method and device |
WO2021057328A1 (en) * | 2019-09-24 | 2021-04-01 | 上海数创医疗科技有限公司 | St segment classification convolutional neural network based on feature selection and method for using same |
CN111759302A (en) * | 2020-07-10 | 2020-10-13 | 齐鲁工业大学 | Wearable individual electrocardiogram detection method |
RU2767157C2 (en) * | 2020-07-21 | 2022-03-16 | Общество с ограниченной ответственностью "СберМедИИ" (ООО "СберМедИИ") | Method and system for automatic ecg analysis |
CN112990025A (en) * | 2021-03-19 | 2021-06-18 | 北京京东拓先科技有限公司 | Method, apparatus, device and storage medium for processing data |
WO2024089382A1 (en) * | 2022-10-26 | 2024-05-02 | Oxford University Innovation Limited | Method for extracting information from multi-channel measurement data, measurement system for obtaining multi-channel measurement data |
CN117958834A (en) * | 2023-11-20 | 2024-05-03 | 齐鲁工业大学(山东省科学院) | Electrocardiogram classification method based on random mask and generation type self-supervision learning |
CN117958834B (en) * | 2023-11-20 | 2024-07-23 | 齐鲁工业大学(山东省科学院) | Electrocardiogram classification method based on random mask and generation type self-supervision learning |
RU2823433C1 (en) * | 2023-11-21 | 2024-07-23 | Общество С Ограниченной Ответственностью "Компания "Стрим Лабс" | Method of processing and analysing electrocardiogram (ecg) data |
Also Published As
Publication number | Publication date |
---|---|
CN108875575B (en) | 2021-05-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108875575A (en) | The automatic arrhythmia analysis method of deep neural network is merged based on multi channel signals | |
CN108764457B (en) | Automatic arrhythmia analysis method based on sampling channel fusion deep neural network | |
CN108962393B (en) | Automatic arrhythmia analysis method based on compression figure neural network | |
CN108720831A (en) | A kind of automatic arrhythmia analysis method based on lead deep neural network | |
CN108937912A (en) | A kind of automatic arrhythmia analysis method based on deep neural network | |
CN108766557A (en) | Automatic arrhythmia analysis method based on channel signal fused neural network | |
US10758139B2 (en) | Automatic method to delineate or categorize an electrocardiogram | |
Guan | A novel method of plant leaf disease detection based on deep learning and convolutional neural network | |
CN109620152B (en) | MutifacolLoss-densenert-based electrocardiosignal classification method | |
CN107203692A (en) | The implementation method of atrial fibrillation detection based on depth convolutional neural networks | |
CN109785928A (en) | Diagnosis and treatment proposal recommending method, device and storage medium | |
CN105105743B (en) | Electrocardiogram intelligent processing method based on deep neural network | |
CN111626114B (en) | Electrocardiosignal arrhythmia classification system based on convolutional neural network | |
CN110141220A (en) | Myocardial infarction automatic testing method based on multi-modal fusion neural network | |
CN107680676A (en) | A kind of gestational diabetes Forecasting Methodology based on electronic health record data-driven | |
CN110141219A (en) | Myocardial infarction automatic testing method based on lead fusion deep neural network | |
CN111785366B (en) | Patient treatment scheme determination method and device and computer equipment | |
CN110974214A (en) | Automatic electrocardiogram classification method, system and equipment based on deep learning | |
CN111956212A (en) | Inter-group atrial fibrillation identification method based on frequency domain filtering-multi-mode deep neural network | |
CN108304887A (en) | Naive Bayesian data processing system and method based on the synthesis of minority class sample | |
CN112270240B (en) | Signal processing method, device, electronic equipment and storage medium | |
CN111956208B (en) | ECG signal classification method based on ultra-lightweight convolutional neural network | |
CN109448703A (en) | In conjunction with the audio scene recognition method and system of deep neural network and topic model | |
CN109620203A (en) | A kind of electrocardiosignal characteristic automatic extraction method based on one-dimensional convolutional neural networks | |
CN110897634A (en) | Electrocardiosignal generation method based on generation countermeasure network |
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: 20211207 Address after: 264006 No. 1, No. 10, Hengshan Road, Yantai Development Zone, Yantai area, China (Shandong) pilot Free Trade Zone, Yantai City, Shandong Province Patentee after: YANTAI YIZHONG MEDICAL SCIENCE & TECHNOLOGY Co.,Ltd. Address before: 264025 No. 186 Hongqi Middle Road, Zhifu District, Shandong, Yantai Patentee before: LUDONG University |
|
TR01 | Transfer of patent right |