CN109998495A - A kind of electrocardiosignal classification method based on particle group optimizing BP neural network - Google Patents
A kind of electrocardiosignal classification method based on particle group optimizing BP neural network Download PDFInfo
- Publication number
- CN109998495A CN109998495A CN201910436832.0A CN201910436832A CN109998495A CN 109998495 A CN109998495 A CN 109998495A CN 201910436832 A CN201910436832 A CN 201910436832A CN 109998495 A CN109998495 A CN 109998495A
- Authority
- CN
- China
- Prior art keywords
- particle
- neural network
- electrocardiosignal
- optimal location
- value
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 60
- 239000002245 particle Substances 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 25
- 210000002569 neuron Anatomy 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 10
- 230000016507 interphase Effects 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 8
- 208000019622 heart disease Diseases 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 210000004218 nerve net Anatomy 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 206010006578 Bundle-Branch Block Diseases 0.000 description 2
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 241000271566 Aves Species 0.000 description 1
- 206010006580 Bundle branch block left Diseases 0.000 description 1
- 206010006582 Bundle branch block right Diseases 0.000 description 1
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 241000544061 Cuculus canorus Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 210000004413 cardiac myocyte Anatomy 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000004064 dysfunction Effects 0.000 description 1
- 244000144992 flock Species 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 201000001715 left bundle branch hemiblock Diseases 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 239000002207 metabolite Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000001766 physiological effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000003716 rejuvenation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 201000007916 right bundle branch block Diseases 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
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
-
- 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
-
- 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
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Fuzzy Systems (AREA)
- Neurology (AREA)
- Cardiology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The electrocardio classification method for the BP neural network (PSO-BP) based on particle group optimizing that the invention discloses a kind of, first building BP neural network and initialization network parameter, then initialization example population and setup parameter, then the fitness value of each particle is calculated, the optimal location individual extreme value of the fitness value of particle and particle is compared, the optimal location individual extreme value of more new particle, then the fitness value of particle is compared with the global extremum of the optimal location of particle, the global extremum of the optimal location of more new particle, then the speed of more new particle and position, meet and obtains the global extremum of optimal location after condition as the weight and threshold value of BO neural network and be trained identification electrocardiosignal classification.The present invention solves the problems, such as that BP neural network study convergence rate is slow and learning process is easy to fall into local minimization, optimizes to introduce particle swarm algorithm, the results showed that more preferable by the BP neural network classifying quality of particle group optimizing, precision is higher.
Description
Technical field
The present invention relates to technical field of biological information, belong to Modulation recognition field, and in particular to one kind is excellent based on population
Change the electrocardiosignal classification method of BP neural network.
Background technique
Heart is the most important organ of human body, is the maincenter of human recycle system, it passes through periodically contraction and diastole
The function to human body each tissue and organ blood supply is completed, oxygen and other nutriments that cellular activity needs are carried in blood
And take away carbon dioxide and other metabolites.Therefore, when lesion or dysfunction occurs in heart, human body cannot be completed
Normal physiological activity.Heart disease is a kind of common chronic disease, seriously endangers people's lives health, often jeopardizes when serious
Life.The morbidity and mortality of heart disease were in rise year by year trend, and lead to three serious diseases of old man's death in recent years
One of because.At the same time, as the rhythm of modern society's work and life is constantly accelerated, young man's life stress is big, and diet is not
Rule, heart disease have the tendency that rejuvenation.
Electrocardiogram is as caused by the biological Electrical change of cardiac muscle cell, and electrocardiogram acquisition is to acquire the heart using electrocardiograph
The variation of body surface potential caused by dirty beat process, has reacted cardiomotility situation, has facilitated to the research of electrocardiosignal more acurrate
Discrimination heart disease, patient can get timely medical treatment.Electrocardiosignal is clinically to judge heart disease all the time
Important evidence, and electrocardiograph is all to acquire signal in vitro, does not have wound and detection and diagnosis heart disease to human body
Important evidence.
The essence of electrocardiosignal classification is pattern-recognition, and the widest classification method used under study for action is nerve net
Network.BP neural network is a kind of feedforward neural network of multilayer, and main feature is divided into two stages, and the first stage is signal
Propagated forward, second stage is the backpropagation of error.BP neural network has adaptive, self-organizing, self study ability,
Principle is simple, is easily achieved, and is one of the neural network model being most widely used at present.But there is study in BP neural network
Process convergence rate is slow, learning efficiency is low and learning process is easy to the problems such as falling into local minimization.Especially BP neural network
The selection of hidden layer neuron number has large effect to the learning ability and generalization ability of neural network.
For the defect of BP neural network, many scholars propose the learning algorithm of Optimized BP Neural Network, common are
Genetic algorithm, cuckoo algorithm, particle swarm algorithm etc..
Particle swarm algorithm is the evolution algorithm new by one kind of J.Kennedy and R.C Eberhart et al. exploitation.Particle
Group's algorithm belongs to one kind of evolution algorithm, derived from the behavioral study preyed on to flock of birds.The essence of particle swarm algorithm is a kind of random
Searching algorithm finds optimal solution by cooperating with information sharing between individual in population.Particle swarm algorithm can with compared with
Big convergence in probability compares in globally optimal solution with traditional algorithm, and particle swarm algorithm is with faster calculating speed and more
Good ability of searching optimum, and particle swarm algorithm have the characteristics that easily to realize, restrain it is fast, with high accuracy.
Summary of the invention
That the present invention is that there are learning process convergence rates in order to solve BP neural network is slow, learning efficiency is low and study is easy to
The limitations such as local minimization are fallen into influence BP neural network and carry out the relatively low problem of electrocardiosignal classification accuracy, this hair
It is bright in view of the deficiencies of the prior art, solve BP neural network Shortcomings by the way that particle swarm algorithm is merged BP neural network
Problem, so the present invention devises a kind of electrocardiosignal classification method based on particle group optimizing BP neural network.
The present invention devises a kind of electrocardiosignal classification method based on particle group optimizing BP neural network, it is characterised in that
The following steps are included:
Step 1: obtaining the electrocardiosignal of human body, using wavelet multi_resolution analysis principle, believes in wavelet field electrocardio
Number removal baseline drift interference, then using Min-max zero crossing principle detect R crest value, positioned using plane geometry method
QRS wave peak value is positioned about QRS wave start-stop point in zero base line, and RR interphase, QRS wave interphase and R are extracted in specimen sample point
5 wave, Q wave, S wave-amplitude characteristic parameters are as feature vector.
Step 2: determining the topological structure of BP neural network, and every layer of neuron number of BP neural network is arranged.BP nerve net
Network is three layers of BP neural network of single hidden layer, and the s group characteristic value that electrocardiosignal is extracted is as input, i.e., network input layer has
S neuron；Hidden layer neuron is according to formulaIt is set as k neuron, wherein m is output node layer
Number, n are input layer number, constant of a between [1,10]；Output layer is the classification results of three kinds of electrocardio types, so defeated
Layer is set as t neuron out.The topological structure of PSOS-BP neural network is s-k-t；
Step 3: initialization particle populations are randomly provided the speed v of each particleiWith position xi, population size N；
Step 4: setting operating parameter, Studying factors c1, c2, inertia weight w, maximum number of iterations M, population size m；
Step 5: the fitness value Fit [i] of each particle is calculated；
Step 6: the individual extreme value p of the fitness value Fit [i] of more each particle and i-th of optimal locationbest(i),
If Fit [i] > pbest(i), then p is replaced with Fit [i]best(i)；
Step 7: the overall situation for the optimal location that the fitness value Fit [i] of more each particle and entire population search
Extreme value gbest(i), if Fit [i] > gbest(i), then g is replaced with Fit [i]best(i)；
Step 8: optimal location individual extreme value p is being foundbest(i) and optimal location global extremum gbest(i) when, particle will
According to formula come the speed v of more new particleiWith position xi；
Formula are as follows: vid=vid*ω+c1r1(pid-xid)+c2r2(pgd-xid)
xid=xid+vid；
Step 9: it if it is good enough or one of reach any condition of both maximum cycles to meet error, exits；
Otherwise return step five；
Step 10: the optimal location global extremum g that will be obtainedbest(i) as the weight of BP neural network and threshold value, with instruction
Practice sample and carries out neural metwork training；
Step 11: being emulated with test sample, obtains electrocardiosignal classification of type result；
The beneficial effects of the present invention are: that there is learning process convergence rates is slow, learning efficiency is low due to BP neural network,
Learning time length, learning process are easy to the problems such as falling into local minimization, not high for the accuracy rate of electrocardiosignal identification classification,
So carry out Optimized BP Neural Network invention introduces particle swarm algorithm, the present invention establish PSO-BP neural network model come into
The Classification and Identification of row electrocardiosignal.Particle swarm algorithm has the characteristics that fast convergence rate, precision are high, learning efficiency is high, the present invention
Using the weight and threshold value of particle swarm algorithm amendment BP neural network, overcomes BP neural network and be easy to fall into local minimization
Limitation.The result shows that realizing the optimization to BP neural network weight and threshold value based on PSO-BP neural network model, overcome
The problem of BP neural network easily falls into local minimization.By comparison BP neural network and PSO-BP neural network for electrocardio
Signal characteristic abstraction classification results, the results showed that the electrocardiosignal classification method ratio based on PSO-BP neural network is based on BP nerve
Faster, nicety of grading is higher for the method convergence rate of network, is particularly suited for electrocardiosignal classification.
Detailed description of the invention
Fig. 1 is the flow chart of the electrocardiosignal classification method based on particle group optimizing BP neural network；
Fig. 2 is the fitness change curve of population；
Fig. 3 is BP neural network training error figure；
Fig. 4 is the PSP-BP training error figure based on particle group optimizing.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings.
As shown in Figure 1, the present invention proposes the electrocardio classification method based on particle group optimizing BP neural network, including following step
It is rapid:
Step 1: obtaining the electrocardiosignal of human body, using wavelet multi_resolution analysis principle, believes in wavelet field electrocardio
Number removal baseline drift interference, then using Min-max zero crossing principle detect R crest value, positioned using plane geometry method
QRS wave peak value is positioned about QRS wave start-stop point in zero base line, this invention experiment in specimen sample point extract RR interphase,
QRS wave interphase and 5 R wave, Q wave, S wave-amplitude characteristic parameters are as feature vector.
Step 2: determining the topological structure of BP neural network, and every layer of neuron number of BP neural network is arranged.BP nerve net
Network is three layers of BP neural network of single hidden layer, and 5 groups of characteristic values for extracting electrocardiosignal in present invention experiment are as input, i.e.,
Network input layer has 5 neurons；Hidden layer neuron is set as 10 neurons according to formula, and wherein m is output node layer
Number, n are input layer number, constant of a between [1,10]；Output layer is the classification results of three kinds of electrocardio types, so defeated
Layer is set as 3 neurons out.The topological structure of PSOS-BP neural network is 5-10-3；
Step 3: initialization particle populations are randomly provided speed and the position of each particle, population size N；
Step 4: setting operating parameter, Studying factors c1,c2, inertia weight w；Maximum number of iterations M；Population size m；
Step 5: the fitness value Fit [i] of each particle is calculated；
Step 6: the individual extreme value p of the fitness value Fit [i] of more each particle and i-th of optimal locationbest(i),
If Fit [i] > pbest(i), then p is replaced with Fit [i]best(i)；
Step 7: the overall situation for the optimal location that the fitness value Fit [i] of more each particle and entire population search
Extreme value gbest(i), if Fit [i] > gbest(i), then g is replaced with Fit [i]best(i)；
Step 8: optimal location individual extreme value p is being foundbest(i) and optimal location global extremum gbest(i) when, particle will
According to formula come the speed v of more new particleiWith position xi；
Formula are as follows: vid=vid*ω+c1r1(pid-xid)+c2r2(pgd-xid)
xid=xid+vid；
Step 9: it if it is good enough or one of reach any condition of both maximum cycles to meet error, exits；
Otherwise return step five；
Step 10: the optimal location global extremum g that will be obtainedbest(i) as the weight of BP neural network and threshold value, with instruction
Practice sample and carries out neural metwork training；
Step 11: being emulated with test sample, obtains electrocardiosignal classification of type result；
The parameter in network is initialized, chooses normal, left bundle branch block, right bundle branch block amounts to 350 groups of samples
This optionally takes 150 groups of samples as test sample as training sample.
To sampling feature vectors normalized, respectively with BP neural network and the nerve of the PSO-BP based on particle group optimizing
Training sample simultaneously emulates.
Fig. 2 is population fitness change curve, has reacted the superiority and inferiority degree of particle current location.As can be seen that with
The number of iterations increases, and fitness value is smaller and smaller, and individual fitness can be higher and higher,
Fig. 3 and Fig. 4 is respectively to verify sample in BP neural network and particle group optimizing PSO-BP neural network training process
The error curve of middle training sample and test sample, it can be seen that BP neural network and PSO-BP neural network can be preferable
Classify to different electrocardiosignals, but the mean square error of the PSO-BP neural network based on particle group optimizing is smaller, point
Class precision is higher.
Since particle swarm algorithm has faster calculating speed and better ability of searching optimum, can be effectively avoided sunken
Enter local extremum.Therefore the PSO-BP algorithm iteration number based on particle group optimizing is less, and convergence rate is faster.
Table 1 is the result of two kinds of algorithm identification classification
Table 1
As can be seen from Table 1 compared to traditional BP neural network algorithm, the BP neural network based on particle group optimizing is calculated
Method classifying quality is more preferable, and nicety of grading is higher, for the application value with higher of diagnosis automatically of ECG signal sampling.
Claims (3)
1. a kind of electrocardiosignal classification method based on particle group optimizing BP neural network, it is characterised in that the following steps are included:
Step 1: obtaining the electrocardiosignal of human body, to electrocardiosignal removal baseline drift interference, extracts in specimen sample point special
Levy vector；
Step 2: determining the topological structure of BP neural network, and every layer of neuron number of BP neural network is arranged, and BP neural network is
Three layers of BP neural network of single hidden layer, the s group characteristic value that electrocardiosignal is extracted have s as input, i.e. network input layer
Neuron；Hidden layer neuron is according to formulaIt is set as k neuron, wherein m is output layer number of nodes, n
For input layer number, constant of a between [1,10]；Output layer is the classification results of t kind electrocardio type, so output layer is set
It is set to t neuron, the topological structure of PSO-BP neural network is s-k-t；
Step 3: initialization particle populations are randomly provided the speed v of each particleiWith position xi, population size N；
Step 4: setting operating parameter, Studying factors c1, c2, inertia weight w, maximum number of iterations M, population size m；
Step 5: the fitness value Fit [i] of each particle is calculated；
Step 6: the individual extreme value p of the fitness value Fit [i] of more each particle and i-th of optimal locationbest(i), if
Fit[i]>pbest(i), then p is replaced with Fit [i]best(i)；
Step 7: the global extremum for the optimal location that the fitness value Fit [i] of more each particle and entire population search
gbest(i), if Fit [i] > gbest(i), then g is replaced with Fit [i]best(i)；
Step 8: optimal location individual extreme value p is being foundbest(i) and optimal location global extremum gbest(i) when, particle is by basis
Formula carrys out the speed v of more new particleiWith position xi；
Formula are as follows: vid=vid*ω+c1r1(pid-xid)+c2r2(pgd-xid)
xid=xid+vid；
Step 9: it if it is good enough or reach the condition of maximum cycle to meet error, exits, otherwise by return step
Five；
Step 10: the optimal location global extremum g that will be obtainedbest(i) as the weight of BP neural network and threshold value, with training sample
This training neural network；
Step 11: being emulated with test sample, obtains electrocardiosignal classification of type result.
2. electrocardiosignal removal baseline drift interference according to claim 1, is to utilize wavelet multi_resolution analysis principle
To electrocardiosignal removal baseline drift interference.
3. extracting feature vector according to claim 1, R crest value is detected using Min-max zero crossing principle, is used
Plane geometry method position QRS wave peak value, be positioned about QRS wave starting point in zero base line, in specimen sample point extract RR interphase,
QRS wave interphase and 5 R wave, Q wave, S wave-amplitude parameters are as feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910436832.0A CN109998495A (en) | 2019-05-23 | 2019-05-23 | A kind of electrocardiosignal classification method based on particle group optimizing BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910436832.0A CN109998495A (en) | 2019-05-23 | 2019-05-23 | A kind of electrocardiosignal classification method based on particle group optimizing BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109998495A true CN109998495A (en) | 2019-07-12 |
Family
ID=67177807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910436832.0A Pending CN109998495A (en) | 2019-05-23 | 2019-05-23 | A kind of electrocardiosignal classification method based on particle group optimizing BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109998495A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110988673A (en) * | 2019-11-05 | 2020-04-10 | 国网河北省电力有限公司电力科学研究院 | Motor rotor fault detection method and device and terminal equipment |
| CN111351668A (en) * | 2020-01-14 | 2020-06-30 | 江苏科技大学 | Diesel engine fault diagnosis method based on optimized particle swarm algorithm and neural network |
| CN115299955A (en) * | 2022-08-04 | 2022-11-08 | 浙江大学嘉兴研究院 | Noninvasive myocardium transmembrane potential reconstruction method based on global feature fast iterative soft threshold contraction algorithm network |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101919695A (en) * | 2010-08-06 | 2010-12-22 | 李楚雅 | Electrocardiosignal QRS complex detection method based on wavelet transform |
| CN102240208A (en) * | 2010-05-11 | 2011-11-16 | 南京医科大学第一附属医院 | Electrocardiosignal denoising wavelet algorithm implementable in single chip microcomputer |
| CN103927556A (en) * | 2014-05-07 | 2014-07-16 | 天津工业大学 | ECG signal classifying method based on wavelet packet and approximate entropy |
| CN104398252A (en) * | 2014-11-05 | 2015-03-11 | 深圳先进技术研究院 | Electrocardiogram signal processing method and device |
| CN107316099A (en) * | 2017-05-22 | 2017-11-03 | 沈阳理工大学 | Ammunition Storage Reliability Forecasting Methodology based on particle group optimizing BP neural network |
| US20180225993A1 (en) * | 2017-01-24 | 2018-08-09 | Tietronix Software, Inc. | System and method for three-dimensional augmented reality guidance for use of medical equipment |
-
2019
- 2019-05-23 CN CN201910436832.0A patent/CN109998495A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102240208A (en) * | 2010-05-11 | 2011-11-16 | 南京医科大学第一附属医院 | Electrocardiosignal denoising wavelet algorithm implementable in single chip microcomputer |
| CN101919695A (en) * | 2010-08-06 | 2010-12-22 | 李楚雅 | Electrocardiosignal QRS complex detection method based on wavelet transform |
| CN103927556A (en) * | 2014-05-07 | 2014-07-16 | 天津工业大学 | ECG signal classifying method based on wavelet packet and approximate entropy |
| CN104398252A (en) * | 2014-11-05 | 2015-03-11 | 深圳先进技术研究院 | Electrocardiogram signal processing method and device |
| US20180225993A1 (en) * | 2017-01-24 | 2018-08-09 | Tietronix Software, Inc. | System and method for three-dimensional augmented reality guidance for use of medical equipment |
| CN107316099A (en) * | 2017-05-22 | 2017-11-03 | 沈阳理工大学 | Ammunition Storage Reliability Forecasting Methodology based on particle group optimizing BP neural network |
Non-Patent Citations (3)
| Title |
|---|
| 柳炳祥，汤可宗: "《智能优化方法及应用》", 31 August 2017, 江苏凤凰美术出版社 第1版 * |
| 王莉，郭晓东，惠延波，何宇宸: "基于小波变换的 QRS 波特征提取算法研究与实现", 《自动化与仪表》 * |
| 袁丹阳: "基于小波包和神经网络的心电信号分类方法研究", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110988673A (en) * | 2019-11-05 | 2020-04-10 | 国网河北省电力有限公司电力科学研究院 | Motor rotor fault detection method and device and terminal equipment |
| CN111351668A (en) * | 2020-01-14 | 2020-06-30 | 江苏科技大学 | Diesel engine fault diagnosis method based on optimized particle swarm algorithm and neural network |
| CN115299955A (en) * | 2022-08-04 | 2022-11-08 | 浙江大学嘉兴研究院 | Noninvasive myocardium transmembrane potential reconstruction method based on global feature fast iterative soft threshold contraction algorithm network |
| CN115299955B (en) * | 2022-08-04 | 2024-12-10 | 浙江大学嘉兴研究院 | Non-invasive myocardial transmembrane potential reconstruction method based on global feature-based fast iterative soft threshold contraction algorithm network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Classification of ECG signals based on 1D convolution neural network | |
| Xia et al. | A novel wearable electrocardiogram classification system using convolutional neural networks and active learning | |
| CN107822622B (en) | Electrocardiogram diagnosis method and system based on deep convolutional neural network | |
| Houssein et al. | A hybrid heartbeats classification approach based on marine predators algorithm and convolution neural networks | |
| CN111626114B (en) | Electrocardiosignal arrhythmia classification system based on convolutional neural network | |
| Zhang et al. | ECG signal classification with deep learning for heart disease identification | |
| CN109998525A (en) | A kind of arrhythmia cordis automatic classification method based on discriminate depth confidence network | |
| CN110020636B (en) | An intelligent analysis method for premature ventricular contractions based on abnormal eigenvalues | |
| CN109998495A (en) | A kind of electrocardiosignal classification method based on particle group optimizing BP neural network | |
| CN109222963A (en) | A kind of anomalous ecg method for identifying and classifying based on convolutional neural networks | |
| CN108309284A (en) | Electrocardiogram T wave end point detection method and device | |
| CN110313894A (en) | Arrhythmia cordis sorting algorithm based on convolutional neural networks | |
| CN110638430A (en) | Multi-task cascade neural network ECG signal arrhythmia disease classification model and method | |
| Refahi et al. | Ecg arrhythmia classification using least squares twin support vector machines | |
| Han et al. | Optimal DNN architecture search using Bayesian Optimization Hyperband for arrhythmia detection | |
| Yeh et al. | Heartbeat Case Determination Using Fuzzy Logic Method on ECG Signals. | |
| Toma et al. | A comparative analysis of 2D deep CNN models for arrhythmia detection using STFT-based long duration ECG spectrogram | |
| Shukri et al. | Investigation on Elman neural network for detection of cardiomyopathy | |
| Chen et al. | Multi-channel lightweight convolution neural network for anterior myocardial infarction detection | |
| CN114692698A (en) | A one-dimensional ECG data classification method based on residual network | |
| Abo-Zahhad et al. | Classification of ECG Signals for Detecting Coronary Heart Diseases Using Deep Transfer Learning Techniques | |
| CN117100276B (en) | Cardiac function detection system, computer storage medium and terminal | |
| Patra et al. | ECG Signal Classification Using a CNN-LSTM Hybrid Network | |
| Ingole et al. | Electrocardiogram (ECG) signals feature extraction and classification using various signal analysis techniques | |
| Dilmaç et al. | Evaluation of a new heart beat classification method based on ABC algorithm, comparison with GA, PSO and ACO classifiers |
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: 20190712 |