CN113440144A - Method and device for detecting early heart failure by using convolutional neural network DenseNet - Google Patents

Method and device for detecting early heart failure by using convolutional neural network DenseNet Download PDF

Info

Publication number
CN113440144A
CN113440144A CN202010225985.3A CN202010225985A CN113440144A CN 113440144 A CN113440144 A CN 113440144A CN 202010225985 A CN202010225985 A CN 202010225985A CN 113440144 A CN113440144 A CN 113440144A
Authority
CN
China
Prior art keywords
neural network
convolutional neural
heart failure
densenet
electrocardiosignals
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
Application number
CN202010225985.3A
Other languages
Chinese (zh)
Other versions
CN113440144B (en
Inventor
李灯熬
赵菊敏
麻惠婷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Taiyuan University of Technology
Original Assignee
Taiyuan University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Taiyuan University of Technology filed Critical Taiyuan University of Technology
Priority to CN202010225985.3A priority Critical patent/CN113440144B/en
Publication of CN113440144A publication Critical patent/CN113440144A/en
Application granted granted Critical
Publication of CN113440144B publication Critical patent/CN113440144B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • 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
    • A61B5/7253—Details of waveform analysis characterised by using transforms
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising
    • G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
    • 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
    • G06F2218/16—Classification; Matching by matching signal segments
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Theoretical Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Medical Informatics (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Pathology (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Physiology (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Fuzzy Systems (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

The application provides a method for detecting early heart failure by using a convolutional neural network DenseNet, which comprises the following steps: collecting electrocardiosignals; preprocessing the electrocardiosignals; classifying the preprocessed electrocardiosignals by adopting a maximum entropy model to obtain classification information; inputting the classification information into a convolutional neural network DenseNet for training; and outputting the result of the convolutional neural network DenseNet training. The method comprises the steps of firstly preprocessing the acquired electrocardiosignals, then analyzing a physiological time sequence by using a maximum entropy model, and finally training the convolutional neural network by using the acquired data set so as to automatically diagnose the electrocardiosignals, thereby providing a new effective method for early detection of heart failure.

Description

Method and device for detecting early heart failure by using convolutional neural network DenseNet
Technical Field
The present invention relates to the field of early heart failure detection, and in particular, to a method and apparatus for detecting early heart failure using a convolutional neural network DenseNet.
Background
Heart Failure (HF), commonly referred to simply as heart failure, refers to a complex set of clinical syndromes that arise as a result of an impairment of the systolic and diastolic function of the heart. In recent years, heart failure has become an important disease that gradually leads to global morbidity and mortality. Therefore, in the face of heart failure, a fatal disease, there is a need for early and accurate detection of the condition, evaluation of the condition, and timely and appropriate treatment.
The deep learning takes an artificial neural network as a framework, is an algorithm for performing characterization learning on data, and the deep learning raises a wave in various industries from 2006, namely the deep learning is widely applied to various fields by people. The convolutional neural network is a feedforward neural network which comprises convolutional calculation and has a deep structure, and is a very representative network in deep learning. In recent years, deep learning is more and more widely used in medical research, and the diagnosis of early heart failure by computer-aided detection has important significance and value for medical research.
Disclosure of Invention
The method and the device for detecting early heart failure by using the convolutional neural network DenseNet comprise the steps of firstly preprocessing the acquired electrocardiosignals, then analyzing physiological time sequences by using a maximum entropy model, and finally training the convolutional neural network by using the acquired data set so as to automatically diagnose the electrocardiosignals, thereby providing a new effective method for detecting early heart failure.
The application provides a method for detecting early heart failure by using a convolutional neural network DenseNet, which comprises the following steps: collecting electrocardiosignals; preprocessing the electrocardiosignals; classifying the preprocessed electrocardiosignals by adopting a maximum entropy model to obtain classification information; inputting the classification information into a convolutional neural network DenseNet for training; and outputting the result of the convolutional neural network DenseNet training.
Further, the preprocessing the cardiac signal comprises: performing noise reduction processing on the electrocardiosignals by using wavelet transformation; removing clutter in the P wave, the T wave and the QRS wave by using a filter; the maximum R wave in each part of the electrocardiogram is found, and the electrocardiosignals are divided into a plurality of RR intervals to obtain preprocessed signals.
Further, the maximum entropy model formula is as follows:
Figure BDA0002427652340000021
Figure BDA0002427652340000022
wherein, Pw(y|x)Representing the maximum entropy model, Zw(x)Represents a normalization factor, wiWeight of the representation feature, fi(x，y)Representing the feature function, w is the parameter vector in the maximum entropy model.
Further, in the convolutional neural network densnet, the output of all previous layer networks is included in the input of the next layer network.
Further, the DenseNet includes 3 density blocks.
Further, the Dense blocks are connected by a transition layer.
Further, the transition layer includes a convolutional layer and a pooling layer.
The present application provides a detection apparatus for early heart failure using a convolutional neural network DenseNet, comprising: a memory; and a processor configured to perform the aforementioned method.
A non-transitory storage medium having stored thereon instructions that, when executed by a processor, cause the processor to perform the foregoing method is provided.
The method for detecting early heart failure by using the convolutional neural network DenseNet comprises the steps of preprocessing acquired electrocardiosignal data, removing abnormal heartbeat parts and useless parts, finding out the maximum R wave in the electrocardiosignals, dividing the electrocardiosignals into a plurality of RR intervals, analyzing the physiological time sequence acquired in the last step by using a maximum entropy model, and training the convolutional neural network by using a data set, so that the aim of automatically detecting the electrocardiosignals is fulfilled.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 illustrates a method of detecting early heart failure using a convolutional neural network DenseNet according to an exemplary embodiment of the present application.
Fig. 2 shows a network structure of DenseNet.
Fig. 3 shows the structure of DenseNet.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the application, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present application unless specifically stated otherwise. Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description. Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate. In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Referring to fig. 1, a method of detecting early heart failure using a convolutional neural network DenseNet according to an exemplary embodiment of the present application is described below.
As shown in fig. 1, according to an exemplary embodiment of the present application, there is provided a method of detecting early heart failure using a convolutional neural network DenseNet, including:
s110: collecting electrocardiosignals;
s120: preprocessing the electrocardiosignals;
s130: classifying the preprocessed electrocardiosignals by adopting a maximum entropy model to obtain classification information;
s140: inputting the classification information into a convolutional neural network DenseNet for training;
s150: and outputting the result of the convolutional neural network DenseNet training.
The method for detecting early heart failure by using the convolutional neural network DenseNet comprises the steps of preprocessing acquired electrocardiosignal data, removing abnormal heartbeat parts and useless parts, finding out the maximum R wave in the electrocardiosignals, dividing the electrocardiosignals into a plurality of RR intervals, analyzing the physiological time sequence acquired in the last step by using a maximum entropy model, and training the convolutional neural network by using a data set, so that the aim of automatically detecting the electrocardiosignals is fulfilled.
In step S120, the acquired electrocardiographic signal is preprocessed. Generally, because an electrocardiographic signal acquired from a hospital is relatively complicated, it is necessary to remove unnecessary bands, i.e., P-waves, T-waves, and the like, but it is necessary to retain the peak value of the electrocardiographic signal to obtain physiological information having effective detection information. In one embodiment, preprocessing the cardiac electrical signal comprises:
s121: performing noise reduction processing on the electrocardiosignals by using wavelet transformation;
s122: removing clutter in the P wave, the T wave and the QRS wave by using a filter;
s123: the maximum R wave in each part of the electrocardiogram is found, and the electrocardiosignals are divided into a plurality of RR intervals to obtain preprocessed signals.
In step S130, the preprocessed electrocardiographic signals are classified by using the maximum entropy model, so as to obtain classification information. Specifically, the present application adopts a maximum entropy model to analyze the physiological time series obtained in step S120.
The maximum entropy model is a very classical algorithm that deals with classification, and usually assumes that the classification model is a conditional probability distribution P (Y | X), where X represents the features and Y represents the output.
Given a dataset (X1, Y1), (X2, Y2), … … (Xn, Yn), where X is an n-dimensional feature vector and Y is a class output. Thereby using the maximum entropy model to select a best classification model.
The maximum entropy model formula is as follows:
Figure BDA0002427652340000051
Figure BDA0002427652340000052
wherein, Pw(y|x)Representing the maximum entropy model, Zw(x)Represents a normalization factor, wiWeight of the representation feature, fi(x，y)Representing the feature function, w is the parameter vector in the maximum entropy model.
The application has the following advantages by adopting the maximum entropy model for classification processing:
1) the accuracy of the maximum entropy model is high compared to other models because the maximum entropy model, as a classical process classification model, satisfies the condition that the entropy is maximum in all constraint models.
2) In the maximum entropy model, the adaptability of the model to unknown data and the fitting capability of the model to known data can be adequately adjusted by the number of the constraints, and in the maximum entropy model, the constraints can be flexibly set.
In step S140, the classification information obtained in step S130 is trained using a convolutional neural network densnet. The DenseNet is actually a process of splicing channels, that is, the output of all previous layer networks is included in the input of the next layer network, that is, if there are N layers in the DenseNet, N (N +1)/2 connections will occur. To give an example here, for example, in the input to layer N, it is equal to KX (N-1) + K0, where K in the equation is used to represent the number of channels included in each layer network. The DenseNet can improve the transmission efficiency of information and gradient in the network, the gradient amount can be directly obtained from the loss function in each layer of the network, and the input signal of each layer can be directly obtained, so that the network with a deeper structure can be trained.
The network structure of DenseNet is shown in fig. 2. 3 DenseBlock are included in a complete DenseNet, and the DenseNet has the characteristics of narrow network, few parameters and the like due to the DenseBlock. As can be seen from the following figures, there are connections without transitions between the transition blocks, and they are connected by transitions (transition layers), which in turn include conv (convolutional layer) and pooling (pooling layer) parts. The convolutional layer is mainly used for extracting local features. The role of the pooling layer is mainly to retain main characteristics and reduce parameters, so that the function of reducing the dimension is achieved, and the calculated amount is reduced. The structure can not only slow down the phenomenon of gradient disappearance, but also simplify a great deal of calculation, and the feature reuse in DenseNet plays a role in resisting overfitting. The structure of DenseNet is shown in fig. 3.
Table 1 shows the specific structure of DenseNet.
Figure BDA0002427652340000061
Figure BDA0002427652340000071
From table 1, it can be seen that in DenseNet, the design of each layer network is very narrow, and in Dense Block, the feature size is required to be the same, where each unit is equivalent to a botteleeck layer (the dimension difference between input and output is relatively large), and in the botteleeck layer, it can be seen through the figure that it contains a conv (convolutional layer) of 1X1 and a conv of 3X 3. There is also a transition layer between blocks, which includes a conv of 1X1 and an average pool of 2X2, and m feature maps in a Block, usually the number of feature maps is limited by a parameter between 0-1.
The convolutional neural network DenseNet adopted by the invention has the following advantages:
1) DenseNet has a smaller number of parameters than ResNet.
2) The reuse of features is increased in the structure, namely, the feature map acquired by each layer network can be directly used by all the following layer networks.
3) The DenseNet network is easier to train and is somewhat regularizing.
According to an embodiment of the present application, there is provided an apparatus for detecting early heart failure using convolutional neural network DenseNet, including:
a memory; and
a processor configured to perform the aforementioned method of detecting early heart failure using a convolutional neural network DenseNet.
According to an embodiment of the present application, there is provided a non-transitory storage medium having stored thereon instructions that, when executed by a processor, cause the processor to perform the aforementioned method of detecting early heart failure using a convolutional neural network DenseNet.
In the description of the present application, it is to be understood that the orientation or positional relationship indicated by the directional terms such as "front, rear, upper, lower, left, right", "lateral, vertical, horizontal" and "top, bottom", etc., are generally based on the orientation or positional relationship shown in the drawings, and are used for convenience of description and simplicity of description only, and in the case of not making a reverse description, these directional terms do not indicate and imply that the device or element being referred to must have a particular orientation or be constructed and operated in a particular orientation, and therefore, should not be considered as limiting the scope of the present application; the terms "inner and outer" refer to the inner and outer relative to the profile of the respective component itself.
Spatially relative terms, such as "above … …," "above … …," "above … …," "above," and the like, may be used herein for ease of description to describe one device or feature's spatial relationship to another device or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if a device in the figures is turned over, devices described as "above" or "on" other devices or configurations would then be oriented "below" or "under" the other devices or configurations. Thus, the exemplary term "above … …" can include both an orientation of "above … …" and "below … …". The device may be otherwise variously oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
It should be noted that the terms "first", "second", and the like are used to define the components, and are only used for convenience of distinguishing the corresponding components, and the terms have no special meanings unless otherwise stated, and therefore, the scope of protection of the present application is not to be construed as being limited.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims (9)

1. A method for detecting early stage heart failure using a convolutional neural network DenseNet, comprising:
collecting electrocardiosignals;
preprocessing the electrocardiosignals;
classifying the preprocessed electrocardiosignals by adopting a maximum entropy model to obtain classification information;
inputting the classification information into a convolutional neural network DenseNet for training;
and outputting the result of the convolutional neural network DenseNet training.
2. The method of detecting early heart failure using a convolutional neural network DenseNet as claimed in claim 1, wherein preprocessing the cardiac electrical signal comprises:
performing noise reduction processing on the electrocardiosignals by using wavelet transformation;
removing clutter in the P wave, the T wave and the QRS wave by using a filter;
the maximum R wave in each part of the electrocardiogram is found, and the electrocardiosignals are divided into a plurality of RR intervals to obtain preprocessed signals.
3. The method for detecting early heart failure using the convolutional neural network DenseNet as claimed in claim 1, wherein the maximum entropy model formula is as follows:
Figure FDA0002427652330000011
Figure FDA0002427652330000012
wherein, Pw(y|x)Representing the maximum entropy model, Zw(x)Represents a normalization factor, wiWeight of the representation feature, fi(x，y)Representing the feature function, w is the parameter vector in the maximum entropy model.
4. The method for detecting early heart failure using a convolutional neural network densnet according to claim 1, wherein in the convolutional neural network densnet, the output of all previous layers of the network is included in the input of the next layer of the network.
5. The method for detecting early heart failure using a convolutional neural network densnet according to claim 1, wherein the densnet comprises 3 Dense blocks.
6. The method for early heart failure detection using a convolutional neural network DenseNet as claimed in claim 5, wherein said Dense blocks are connected by a transition layer.
7. The method for early heart failure detection using a convolutional neural network DenseNet as claimed in claim 6, wherein the transition layer comprises a convolutional layer and a pooling layer.
8. An apparatus for detecting early heart failure using a convolutional neural network DenseNet, comprising:
a memory; and
a processor configured to perform the method of any of the preceding claims 1-7.
9. A non-transitory storage medium having stored thereon instructions that, when executed by a processor, cause the processor to perform the method of any of the preceding claims 1-7.
CN202010225985.3A 2020-03-26 2020-03-26 Method and device for detecting early heart failure by using convolutional neural network DenseNet Active CN113440144B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010225985.3A CN113440144B (en) 2020-03-26 2020-03-26 Method and device for detecting early heart failure by using convolutional neural network DenseNet

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010225985.3A CN113440144B (en) 2020-03-26 2020-03-26 Method and device for detecting early heart failure by using convolutional neural network DenseNet

Publications (2)

Publication Number Publication Date
CN113440144A true CN113440144A (en) 2021-09-28
CN113440144B CN113440144B (en) 2022-12-27

Family

ID=77807360

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010225985.3A Active CN113440144B (en) 2020-03-26 2020-03-26 Method and device for detecting early heart failure by using convolutional neural network DenseNet

Country Status (1)

Country Link
CN (1) CN113440144B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06149863A (en) * 1992-11-05 1994-05-31 Yukio Tanaka Time series data analyzer
DE102006053728A1 (en) * 2006-08-28 2008-03-06 Biotronik Crm Patent Ag Electrocardiogram signal evaluation i.e. premature extra-systole detection, method, for e.g. implant, involves determining partial section of temporal difference, which corresponds to maximum entropy-value, as irregular RR-interval range
US20150141859A1 (en) * 2012-11-19 2015-05-21 Alex Sandler Systems and methods for cardiac rhythm variability analysis
US20180177415A1 (en) * 2016-12-23 2018-06-28 Tamas Madl Cardiovascular disease detection
WO2019046854A1 (en) * 2017-09-01 2019-03-07 University Of Cincinnati System, method, computer program product and apparatus for dynamic predictive monitoring in the critical health assessment and outcomes study/score/(chaos)
CN109620152A (en) * 2018-12-16 2019-04-16 北京工业大学 A kind of electrocardiosignal classification method based on MutiFacolLoss-Densenet
CN110299205A (en) * 2019-07-23 2019-10-01 上海图灵医疗科技有限公司 Biomedicine signals characteristic processing and evaluating method, device and application based on artificial intelligence
CN110811591A (en) * 2019-10-31 2020-02-21 太原理工大学 Heart failure grading method based on heart rate variability

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06149863A (en) * 1992-11-05 1994-05-31 Yukio Tanaka Time series data analyzer
DE102006053728A1 (en) * 2006-08-28 2008-03-06 Biotronik Crm Patent Ag Electrocardiogram signal evaluation i.e. premature extra-systole detection, method, for e.g. implant, involves determining partial section of temporal difference, which corresponds to maximum entropy-value, as irregular RR-interval range
US20150141859A1 (en) * 2012-11-19 2015-05-21 Alex Sandler Systems and methods for cardiac rhythm variability analysis
US20180177415A1 (en) * 2016-12-23 2018-06-28 Tamas Madl Cardiovascular disease detection
WO2019046854A1 (en) * 2017-09-01 2019-03-07 University Of Cincinnati System, method, computer program product and apparatus for dynamic predictive monitoring in the critical health assessment and outcomes study/score/(chaos)
CN109620152A (en) * 2018-12-16 2019-04-16 北京工业大学 A kind of electrocardiosignal classification method based on MutiFacolLoss-Densenet
CN110299205A (en) * 2019-07-23 2019-10-01 上海图灵医疗科技有限公司 Biomedicine signals characteristic processing and evaluating method, device and application based on artificial intelligence
CN110811591A (en) * 2019-10-31 2020-02-21 太原理工大学 Heart failure grading method based on heart rate variability

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
KYUNG-TAE PARK,SANG-HOON YI: "Quantification of the complexity in heart rate variability by using maximal entropy principle", 《SAE MULLI(THE KOREAN PHYSICAL SOCIETY)》 *
周婕: "基于心电信号的心衰自动诊断技术研究", 《中国优秀硕士学位论文全文数据库 (医药卫生科技辑)》 *
陈宇飞: "基于深度学习技术的ECG自动分类算法研究", 《中国优秀硕士学位论文全文数据库 (医药卫生科技辑)》 *
饶静: "心率变异性分析方法的研究和应用", 《中国优秀硕士学位论文全文数据库 (医药卫生科技辑)》 *
高扬: "《智能摘要与深度学习》", 31 July 2019, 北京理工大学出版社 *

Also Published As

Publication number Publication date
CN113440144B (en) 2022-12-27

Similar Documents

Publication Publication Date Title
CN109394205B (en) Electrocardiosignal analysis method based on deep neural network
US20070225932A1 (en) Methods, systems and computer program products for extracting paroxysmal events from signal data using multitaper blind signal source separation analysis
Jatmiko et al. Heart beat classification using wavelet feature based on neural network
CN111772619A (en) Electrocardiogram heart beat identification method, terminal device and storage medium
CN111956208B (en) ECG signal classification method based on ultra-lightweight convolutional neural network
CN112070067B (en) Scatter diagram classification method and device for photoplethysmograph signals
CN111481192A (en) Electrocardiosignal R wave detection method based on improved U-Net
US20230225663A1 (en) Method for predicting multi-type electrocardiogram heart rhythms based on graph convolution
KR100883185B1 (en) System and Method for Detecting Abnormality of Biosignal using Neural Network with Weighted Fuzzy Membership Funtions
CN115281688A (en) Cardiac hypertrophy multi-label detection system based on multi-mode deep learning
CN115221926A (en) Heart beat signal classification method based on CNN-GRU network model
CN115530788A (en) Arrhythmia classification method based on self-attention mechanism
CN113855037A (en) Atrial fibrillation identification method and device based on Transformer
CN107256408B (en) Method for searching key path of brain function network
CN113469218A (en) Electrocardiosignal critical value processing method, system and medium based on deep learning
Lee et al. Adaptive ecg signal compression method based on look-ahead linear approximation for ultra long-term operating of healthcare iot devices (sci)
CN113440144B (en) Method and device for detecting early heart failure by using convolutional neural network DenseNet
CN116269426A (en) Twelve-lead ECG-assisted heart disease multi-mode fusion screening method
Ren et al. A contrastive predictive coding-based classification framework for healthcare sensor data
WO2019115432A1 (en) Determining whether a hypothesis concerning a signal is true
CN112842342B (en) Electrocardiogram and magnetic signal classification method combining Hilbert curve and integrated learning
Sachnev An efficient classification scheme for ADHD problem based on Binary Coded Genetic Algorithm and McFIS
CN111345815B (en) Method, device, equipment and storage medium for detecting QRS wave in electrocardiosignal
CN114224354A (en) Arrhythmia classification method, device and readable storage medium
Wen et al. ECG beat classification using GreyART 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