CN112716504B - Electrocardiogram data processing method and device, storage medium and electronic equipment - Google Patents
Electrocardiogram data processing method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN112716504B CN112716504B CN202011529285.XA CN202011529285A CN112716504B CN 112716504 B CN112716504 B CN 112716504B CN 202011529285 A CN202011529285 A CN 202011529285A CN 112716504 B CN112716504 B CN 112716504B
- Authority
- CN
- China
- Prior art keywords
- data
- target
- self
- training
- electrocardio
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title description 2
- 238000012549 training Methods 0.000 claims abstract description 128
- 239000013598 vector Substances 0.000 claims abstract description 77
- 238000012545 processing Methods 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000007635 classification algorithm Methods 0.000 claims abstract description 21
- 230000009467 reduction Effects 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 abstract description 9
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000005070 sampling Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 206010006580 Bundle branch block left Diseases 0.000 description 6
- 206010006582 Bundle branch block right Diseases 0.000 description 5
- 206010006578 Bundle-Branch Block Diseases 0.000 description 5
- 206010042602 Supraventricular extrasystoles Diseases 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 5
- 206010003658 Atrial Fibrillation Diseases 0.000 description 4
- 206010003671 Atrioventricular Block Diseases 0.000 description 4
- 230000033764 rhythmic process Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 201000001715 left bundle branch hemiblock Diseases 0.000 description 3
- 208000002102 Atrial Premature Complexes Diseases 0.000 description 2
- 206010003674 Atrioventricular block first degree Diseases 0.000 description 2
- 208000009729 Ventricular Premature Complexes Diseases 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 230000000747 cardiac effect Effects 0.000 description 2
- 230000008602 contraction Effects 0.000 description 2
- 201000002934 first-degree atrioventricular block Diseases 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011946 reduction process Methods 0.000 description 2
- 201000007916 right bundle branch block Diseases 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000001508 eye Anatomy 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000003183 myoelectrical effect Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The disclosure relates to a method and a device for processing electrocardiographic data, a storage medium and electronic equipment, which are applied to the technical field of electronic information processing, wherein the method comprises the following steps: acquiring target electrocardio data to be processed, determining a target electrocardio feature vector capable of representing the target electrocardio data through a pre-trained self-encoder according to the target electrocardio data, determining a target sign type corresponding to the target electrocardio data through a pre-trained classification algorithm according to the target electrocardio feature vector and a pre-trained self-organizing map network, wherein the self-organizing map network is obtained through training according to a pre-set training data set. According to the method and the device, the target sign type corresponding to the target electrocardiograph data can be intelligently determined through the self-encoder and the self-organizing mapping network and by combining the classification algorithm, manual participation is not needed, and the processing efficiency and accuracy of the electrocardiograph data can be improved.
Description
Technical Field
The present disclosure relates to the field of electronic information processing technologies, and in particular, to a method and apparatus for processing electrocardiographic data, a storage medium, and an electronic device.
Background
Heart related diseases are one of the main diseases threatening human life, and research on heart related diseases has been an important topic in the medical community for a long time. An Electrocardiogram (ECG) is a simple continuous record of the electrical activity produced by the heart, and can reflect the physical state of each part of the heart to a certain extent, thereby effectively assisting a doctor in judging the heart state of a user. However, to determine the heart state of the user through the electrocardiographic data, the requirements on the ability and experience of the doctor are high, and erroneous determination or missed determination is easily caused.
Disclosure of Invention
In order to solve the problems in the related art, the present disclosure provides a method, an apparatus, a storage medium, and an electronic device for processing electrocardiographic data.
To achieve the above object, according to a first aspect of embodiments of the present disclosure, there is provided a method for processing electrocardiographic data, the method including:
acquiring target electrocardiographic data to be processed;
determining a target electrocardio characteristic vector capable of representing the target electrocardio data through a pre-trained self-encoder according to the target electrocardio data;
and determining a target sign type corresponding to the target electrocardiographic data through a preset classification algorithm according to the target electrocardiographic feature vector and a pre-trained self-organizing map network, wherein the self-organizing map network is obtained through training according to a preset training data set.
Optionally, the determining, by a pre-trained self-encoder, a target electrocardiographic feature vector capable of characterizing the target electrocardiographic data according to the target electrocardiographic data includes:
filtering the target electrocardio data, and carrying out peak detection on the filtered target electrocardio data to extract a second number of heartbeat data;
performing dimension reduction processing on a third number of heartbeat data in the second number of heartbeat data to obtain a heartbeat data sequence, wherein the third number is smaller than or equal to the second number;
and inputting the heartbeat data sequence into the self-encoder to obtain the target electrocardio characteristic vector.
Optionally, the inputting the heartbeat data sequence into the self-encoder to obtain the target electrocardiographic feature vector includes:
dividing the heartbeat data sequence into a plurality of heartbeat data segments according to a designated duration;
inputting each of the heartbeat data segments into the self-encoder to obtain a sub-feature vector capable of representing the heartbeat data segment;
and splicing the sub-feature vectors corresponding to each heartbeat data segment to obtain the target electrocardio feature vector.
Optionally, the determining, according to the target electrocardiographic feature vector and the pre-trained self-organizing map network, the target sign type corresponding to the target electrocardiographic data through a preset classification algorithm includes:
determining the distance from the target electrocardio feature vector to each region in a first number of regions corresponding to the self-organizing map network, wherein the first number is determined when the self-organizing map network is trained according to the training data set;
and taking the sign type corresponding to the target area as the target sign type, wherein the target area is the area with the minimum distance with the target electrocardio feature vector.
Optionally, the self-organizing map network is trained by:
acquiring the training data set, wherein the training data set comprises a plurality of training electrocardio data;
according to any training electrocardio data, determining the best matching node matched with the training electrocardio data in all nodes included in the network to be trained;
determining a neighborhood node in the topological neighborhood of the best matching node;
updating the weights of the neighborhood node and the best matching node according to the distance between the neighborhood node and the best matching node;
and repeatedly executing the steps of determining the best matching node matched with the training electrocardio data in all nodes included in the network to be trained according to any training electrocardio data, and updating the weights of the neighborhood nodes and the best matching node according to the distance between the neighborhood nodes and the best matching node until the network to be trained meets the preset training ending condition so as to obtain the self-organizing map network.
According to a second aspect of embodiments of the present disclosure, there is provided an apparatus for processing electrocardiographic data, the apparatus comprising:
the acquisition module is used for acquiring target electrocardiographic data to be processed;
the processing module is used for determining a target electrocardio characteristic vector capable of representing the target electrocardio data through a pre-trained self-encoder according to the target electrocardio data;
the determining module is used for determining the target sign type corresponding to the target electrocardiographic data through a preset classification algorithm according to the target electrocardiographic feature vector and a pre-trained self-organizing map network, wherein the self-organizing map network is obtained through training according to a preset training data set.
Optionally, the processing module includes:
the extraction sub-module is used for filtering the target electrocardiograph data and carrying out peak detection on the filtered target electrocardiograph data so as to extract a second number of heartbeat data;
the dimension reduction sub-module is used for carrying out dimension reduction processing on a third number of heartbeat data in the second number of heartbeat data so as to obtain a heartbeat data sequence, wherein the third number is smaller than or equal to the second number;
and the encoding submodule is used for inputting the heartbeat data sequence into the self-encoder so as to obtain the target electrocardio characteristic vector.
Optionally, the encoding submodule is configured to:
dividing the heartbeat data sequence into a plurality of heartbeat data segments according to a designated duration;
inputting each of the heartbeat data segments into the self-encoder to obtain a sub-feature vector capable of representing the heartbeat data segment;
and splicing the sub-feature vectors corresponding to each heartbeat data segment to obtain the target electrocardio feature vector.
Optionally, the determining module includes:
a first determining submodule, configured to determine a distance from the target electrocardiographic feature vector to each region in a first number of regions corresponding to the self-organizing map network, where the first number is determined when the self-organizing map network is trained according to the training data set;
and the second determining submodule is used for taking the sign type corresponding to the target area as the target sign type, and the target area is the area with the minimum distance with the target electrocardio feature vector.
Optionally, the self-organizing map network is trained by:
acquiring the training data set, wherein the training data set comprises a plurality of training electrocardio data;
according to any training electrocardio data, determining the best matching node matched with the training electrocardio data in all nodes included in the network to be trained;
determining a neighborhood node in the topological neighborhood of the best matching node;
updating the weights of the neighborhood node and the best matching node according to the distance between the neighborhood node and the best matching node;
and repeatedly executing the steps of determining the best matching node matched with the training electrocardio data in all nodes included in the network to be trained according to any training electrocardio data, and updating the weights of the neighborhood nodes and the best matching node according to the distance between the neighborhood nodes and the best matching node until the network to be trained meets the preset training ending condition so as to obtain the self-organizing map network.
According to the technical scheme, firstly, target electrocardio data to be processed are obtained, a target electrocardio feature vector capable of representing the target electrocardio data is determined through a pre-trained self-encoder according to the target electrocardio data, then, a target sign type corresponding to the target electrocardio data is determined through a preset classification algorithm according to the target electrocardio feature vector and a pre-trained self-organizing map network, wherein the self-organizing map network is obtained through training according to a preset training data set. According to the method and the device, the target sign type corresponding to the target electrocardiograph data can be intelligently determined through the self-encoder and the self-organizing mapping network and by combining the classification algorithm, manual participation is not needed, and the processing efficiency and accuracy of the electrocardiograph data can be improved.
Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification, illustrate the disclosure and together with the description serve to explain, but do not limit the disclosure. In the drawings:
FIG. 1 is a flow chart illustrating a method of processing electrocardiographic data according to an exemplary embodiment;
FIG. 2 is a flow chart of one step 102 shown in the embodiment of FIG. 1;
FIG. 3 is a flow chart illustrating a training manner of an ad hoc mapping network in accordance with an exemplary embodiment;
FIG. 4 is a block diagram illustrating an apparatus for processing electrocardiographic data according to an exemplary embodiment;
FIG. 5 is a block diagram of one processing module shown in the embodiment of FIG. 4;
FIG. 6 is a block diagram of one determination module shown in the embodiment of FIG. 4;
fig. 7 is a block diagram of an electronic device, according to an example embodiment.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
Fig. 1 is a flow chart illustrating a method of processing electrocardiographic data according to an exemplary embodiment. As shown in fig. 1, the method may include the steps of:
step 101, acquiring target electrocardiographic data to be processed.
For example, first, the ECG device may acquire the target electrocardiographic data to be processed by performing data acquisition on a specified location on the body surface of the target user by using a specified number of leads according to a specified sampling frequency and sampling duration. The target electrocardiographic data may be understood, among other things, as data of the time-dependent changes of the electrical potentials included in an electrocardiogram generated by the ECG device. For example, twelve leads (I, II, III, aVR, aVL, aVF, V, V2, V3, V4, V5 and V6) are adopted to collect data at the designated position of the body surface of the target user by ECG equipment according to the sampling frequency of 500Hz and the sampling time period of 1min so as to acquire the target electrocardiographic data. For another example, the ECG device may acquire the target electrocardiographic data by acquiring data from a designated location on the target user's body surface using a single lead at a sampling frequency of 300Hz and a sampling duration of 1 min. After the target electrocardiographic data is obtained, the target electrocardiographic data may be stored, for example, the target electrocardiographic data may be stored in a Matlab (english: matrix Laboratory, chinese: matrix laboratory) file.
Step 102, determining a target electrocardio characteristic vector capable of representing the target electrocardio data through a pre-trained self-encoder according to the target electrocardio data.
For example, to reduce the requirement for the ability and experience of a physician in determining the heart status of a target user from electrocardiographic data, the type of sign corresponding to electrocardiographic data may be automatically determined by classifying the electrocardiographic data. Specifically, the target electrocardiographic data may be first processed to extract main features contained in the target electrocardiographic data, and generate a target electrocardiographic feature vector capable of characterizing the target electrocardiographic data. For example, the target electrocardiographic data may be filtered first to remove interference in the target electrocardiographic data. And extracting heartbeat data corresponding to each heartbeat from the filtered target electrocardio data, and encoding the extracted heartbeat data through a pre-trained self encoder (English: autoencoder, abbreviated as AE) to obtain a target electrocardio feature vector.
And step 103, determining the target sign type corresponding to the target electrocardiographic data through a preset classification algorithm according to the target electrocardiographic feature vector and the pre-trained self-organizing mapping network.
The self-organizing map network is obtained through training according to a preset training data set.
Further, because of the high labor cost required for the massive labeling of the electrocardiographic data, there is a potential lack of available data when classifying the electrocardiographic data in a supervised learning manner. Thus, the electrocardiographic data may be classified in an unsupervised learning manner. For example, the self-organizing map network may be trained in advance from training data sets containing electrocardiographic data of different sign types. The self-organizing map network after training corresponds to a plurality of areas, and each area is formed by mapping electrocardiographic data with the same sign type, namely, each area corresponds to one sign type.
The training data set may be, for example, an ICBEB data set or a PhysioNet data set. The sign types may include a normal sign type for characterizing that there is no abnormality in the cardiac state corresponding to the electrocardiographic data and a plurality of abnormal sign types for characterizing that there is an abnormality in the cardiac state corresponding to the electrocardiographic data. For example, in the case where 8 types of abnormal signs are included, the 8 types of abnormal signs may be respectively: atrial fibrillation (English: atrial fibrillation, abbreviation: AF), primary atrioventricular block (English: first-degree atrioventricular block, abbreviation: I-AVB), left bundle branch block (English: left bundle branch block, abbreviation: LBBB), right bundle branch block (English: right bundle branch bloc, abbreviation: RBBB), extra-atrial contraction (English: premature atrial contraction, abbreviation: PAC), extra-ventricular contraction (English: premature ventricular contraction, abbreviation: PVC), ST segment depression (English: ST-segment depression, abbreviation: STD), and ST segment elevation (English: ST-segment elevation, abbreviation: STE).
Then, after the target electrocardio feature vector is determined, the target electrocardio feature vector is input as a preset classification algorithm, the classification algorithm determines a region corresponding to the target electrocardio feature vector from a plurality of regions corresponding to the trained self-organizing map network, and the sign type corresponding to the region is used as the target sign type corresponding to the target electrocardio data. The classification algorithm may be understood as a classifier, for example, when the classifier uses a KNN (k-nearest neighbor, chinese: k nearest neighbor) classifier, the KNN classifier may target a plurality of regions corresponding to the self-organizing map network, then determine a target electrocardiographic feature vector, a distance from each region in a first number of regions corresponding to the self-organizing map network, and use a sign type corresponding to the target region as a target sign type. The first number is determined when the self-organizing map network is trained according to the training data set (namely, the number of areas corresponding to the self-organizing map network after training is completed), and the target area is an area with the minimum distance from the target electrocardio feature vector.
It should be noted that the disclosure may be applied not only to determining a sign type corresponding to the thermoelectric data, but also to determining a sign type corresponding to any other kind of biological data. The biological data may include, among other things, bioelectric data (brain, muscle, eye, etc.) and bioelectric data (e.g., blood pressure, blood oxygen, tension, pressure, body temperature, etc.).
In summary, the disclosure first obtains target electrocardiographic data to be processed, determines a target electrocardiographic feature vector capable of representing the target electrocardiographic data through a pre-trained self-encoder according to the target electrocardiographic data, and then determines a target sign type corresponding to the target electrocardiographic data through a pre-trained classification algorithm according to the target electrocardiographic feature vector and a pre-trained self-organizing map network, wherein the self-organizing map network is obtained through training according to a pre-set training data set. According to the method and the device, the target sign type corresponding to the target electrocardiograph data can be intelligently determined through the self-encoder and the self-organizing mapping network and by combining the classification algorithm, manual participation is not needed, and the processing efficiency and accuracy of the electrocardiograph data can be improved.
FIG. 2 is a flow chart of one of the steps 102 shown in the embodiment of FIG. 1. As shown in fig. 2, step 102 may include the steps of:
step 1021, filtering the target electrocardiograph data, and performing peak detection on the filtered target electrocardiograph data to extract a second number of heartbeat data.
In one scenario, high frequency interference, myoelectric interference, power frequency interference, baseline drift, etc. may exist in the target electrocardiographic data, which may affect the determination of the target sign type. Thus, the target electrocardiographic data may be filtered first, for example, using a Butterworth band-pass filter (the bandwidth of the filter may be, for example, 0.25Hz-40 Hz). In order to enable the subsequent classification model to process data of equal length, peak detection may be performed on the filtered target electrocardiographic data to extract a second number of heartbeat data of equal time length. Specifically, the heartbeat may be extracted from the target electrocardiographic data using the biossppy toolkit of third party Python: all R-wave peaks in the target electrocardiographic data are first identified by the biossppy kit, and then cut in a specified time period before each R-wave peak and a specified time period after the R-wave peak to obtain a second number of continuous time periods containing complete P-QRS-T waves, wherein the data corresponding to each continuous time period can be understood as heartbeat data corresponding to one complete heartbeat. For example, a time period of 0.2 seconds before each R-peak and 0.6 seconds after the R-peak may be selected for cutting to obtain a second number of heartbeat data, i.e. one heartbeat data corresponds to a sampling period of 0.8 seconds.
Step 1022, performing dimension reduction processing on a third number of heartbeat data in the second number of heartbeat data to obtain a heartbeat data sequence, where the third number is less than or equal to the second number.
Step 1023, inputting the heartbeat data sequence into the self-encoder to obtain the target electrocardio characteristic vector.
In this step, a third number of heartbeat data may be selected from the second number of heartbeat data to determine the target sign type. For example, 1 heartbeat data may be arbitrarily selected from the second number of heartbeat data to determine the target sign type, 4 heartbeat data may be arbitrarily selected to determine the target sign type, and 3 consecutive heartbeat data may be selected to determine the target sign type, which is not specifically limited in this disclosure. By selecting the third number of heartbeat data from the second number of heartbeat data to determine the target sign type, the amount of data used to determine the target sign type can be reduced, thereby increasing the speed of determining the target sign type.
Then, in order to reduce the influence of redundant information and noise information contained in the data of the third number of heartbeats on the determination of the target sign type, the accuracy of the determination of the target sign type is improved. For example, the dimension reduction processing may be performed on each of the third number of heartbeat data by using a principal component analysis technique (english: principal Components Analysis, abbreviated: PCA), and the heartbeat data sequence may be formed from each of the dimension-reduced heartbeat data. And finally, inputting the heartbeat data sequence into a self-encoder, and encoding the heartbeat data sequence by the self-encoder to obtain the target electrocardio feature vector.
Alternatively, step 1023 may be implemented by:
and step A, dividing the heartbeat data sequence into a plurality of heartbeat data segments according to the appointed duration.
Step B, inputting each heartbeat data segment into the self-encoder to obtain a sub-feature vector capable of representing the heartbeat data segment.
And C, splicing the sub-feature vectors corresponding to each heartbeat data segment to obtain the target electrocardio feature vector.
For example, the accuracy of determining the target sign type may be further improved by generating a more resolvable target electrocardiographic feature vector. Specifically, first, the heartbeat data sequence may be divided into a plurality of heartbeat data segments according to a specified duration. For example, in the case where the heartbeat data sequence includes 300 sampling points, the heartbeat data sequence may be divided into 6 heartbeat data segments with 50 sampling periods as a specified duration (i.e., one heartbeat data segment with 50 sampling points). And then inputting each heartbeat data segment into a self-encoder, encoding each heartbeat data segment by the self-encoder to obtain a sub-feature vector of each heartbeat data segment, and splicing the sub-feature vectors corresponding to each heartbeat data segment to obtain the target electrocardio feature vector. The sub-feature vector of each heartbeat data segment can reflect the main feature corresponding to the heartbeat data segment, and the target electrocardio feature vector with better resolvable property can be obtained by splicing the sub-feature vectors of different heartbeat data segments. Meanwhile, by dividing the heartbeat data sequence, the dimension of data input to the self-encoder can be reduced, the encoding efficiency of the self-encoder is improved, and the speed of determining the target sign type is further improved.
Fig. 3 is a flow chart illustrating a training manner of an ad hoc mapping network according to an exemplary embodiment. As shown in fig. 3, the self-organizing map network may be trained by:
in step 201, a training data set is obtained, the training data set comprising a plurality of training electrocardiographic data.
For example, when training the self-organizing map network, a training data set including a plurality of training electrocardiographic data may be first obtained, where each training electrocardiographic data corresponds to a training sign type. The training data set may be an ICBEB 2018 data set or a PhysioNet Computing in Cardiology Challenge 2017 data set, among others.
In the case of the ICBEB 2018 dataset, the training dataset is obtained by data acquisition using twelve leads for 6 to 60 seconds at a sampling frequency of 500 Hz. The training dataset included 6877 training electrocardiographic data, the training dataset corresponding to 9 training sign types, the 9 training sign types including 1 Normal sign type (i.e., normal in table 1) and 8 abnormal sign types (i.e., AF, I-AVB, LBBB, RBBB, PAC, PVC, STD, and STE in table 1), the number of records for each training sign type being shown in table 1.
TABLE 1
| Training of sign type | Number of records |
| Normal | 918 |
| Atrial fibrillation(AF) | 1098 |
| First-degree atrioventricular block(I-AVB) | 704 |
| Left bundle branch block(LBBB) | 207 |
| Right bundle branch block(RBBB) | 1695 |
| Premature atrial contraction(PAC) | 556 |
| Premature ventricular contraction(PVC) | 672 |
| ST-segment depression(STD) | 825 |
| ST-segment elevated(STE) | 202 |
In the case of the training dataset using the PhysioNet Computing in Cardiology Challenge 2017 dataset, the training dataset is obtained by data acquisition using a single lead for 9 seconds to 60 seconds at a sampling frequency of 300 Hz. The training dataset included 8528 training electrocardiographic data, the training dataset corresponding to 4 training sign types, the 4 training sign types including 1 Normal sign type (i.e., normal in table 2) and 3 abnormal sign types (i.e., AF, other rhythm, and noise in table 2), the number of records for each training sign type being shown in table 2.
TABLE 2
| Training of sign type | Number of records |
| Normal | 5154 |
| Atrial fibrillation(AF) | 771 |
| Other rhythm | 2557 |
| Noisy | 46 |
Wherein Other rhythms are Other rhythms and noise is noise.
Step 202, determining the best matching node matched with the training electrocardio data in all nodes included in the network to be trained according to any training electrocardio data.
Specifically, before training an SOM (english: self-organization Maps, chinese: self-organizing map network), the training data set needs to be processed to process the training data set into a format required by the Self-organizing map network. For example, each training electrocardiographic data may first be extracted in advance from a file (e.g., matlab file) storing a training data set, and filtered using a butterworth band-pass filter. And secondly, converting each piece of filtered training electrocardio data into a Numpy array, and inserting all the training electrocardio data into a CSV (Comma-Separated Values, chinese: comma Separated Values) file. And then, carrying out peak detection on each piece of training electrocardio data in the CSV file to extract each piece of heartbeat data included in the training electrocardio data, taking all pieces of heartbeat data included in the training electrocardio data as a training sample, and inserting all training samples into the CSV file as independent lines. Then, the dimension reduction process can be performed on each training sample to obtain each training sample after the dimension reduction process.
When the SOM is trained, firstly, the weight of each node (namely a neuron) of the network to be trained can be initialized, then one training sample Xi is randomly selected from all training samples subjected to dimension reduction processing, and the Xi is input to an input layer of the network to be trained. Traversing each node of the output layer of the network to be trained by the network to be trained, calculating the Euclidean distance between Xi and each node, and selecting the node with the smallest distance as the best matching node (English: best Matching Unit, abbreviated: BMU) for matching the training electrocardio data corresponding to the training sample.
Step 203, determining a neighborhood node in the topological neighborhood of the best matching node.
And 204, updating the weights of the neighborhood nodes and the best matching nodes according to the distance between the neighborhood nodes and the best matching nodes.
And repeatedly executing the steps 202 to 204 until the network to be trained meets the preset training ending condition to obtain the self-organizing map network.
For example, after determining the best matching node, a neighborhood node included in a topological neighborhood of the best matching node may be determined according to a neighborhood radius σ of the best matching node. And then updating the weights of the neighborhood nodes and the best matching nodes by using a preset weight updating formula according to the distance between the neighborhood nodes and the best matching nodes so as to finish one training of the network to be trained. Then, a training sample can be reselected, and the steps are repeatedly executed to continuously train the network to be trained until the network to be trained meets the preset training ending condition, so as to obtain the SOM after training is completed. The training ending condition may be that after training the network to be trained by each training sample in all training samples, the network to be trained is determined to be trained.
The weight update formula includes:
wherein,
t is the number of times the network to be trained is trained, w_ij (t) is the weight vector of the node located at (i, j) in the network to be trained after the network to be trained is trained for the t th time, i is the row coordinate of the network to be trained, j is the column coordinate of the network to be trained, d is the distance between the neighborhood node and the best matching node, x (t) is the input vector corresponding to the training sample, sigma (t) is the neighborhood radius function, alpha (t) is the learning rate, n is the number of training samples, sigma 0 For an initial neighborhood radius, r 0 Is the initial radius.
Further, the self-encoder may be trained in the following manner: firstly, selecting a specified number of training samples, then taking each training sample in the specified number of training samples as the input of a self-encoder in sequence, taking the training sample as the output of the self-encoder, and training the self-encoder. And simultaneously, optimizing the trained self-encoder by using a preset loss function, and obtaining the self-encoder after training when the loss function reaches the minimum value. Furthermore, since a single self-encoder operates with the best architecture performance with a single hidden layer, the decoder portion of the self-encoder may be discarded after the self-encoder has been trained, leaving only the encoder portion to improve the performance of the self-encoder.
In summary, the disclosure first obtains target electrocardiographic data to be processed, determines a target electrocardiographic feature vector capable of representing the target electrocardiographic data through a pre-trained self-encoder according to the target electrocardiographic data, and then determines a target sign type corresponding to the target electrocardiographic data through a pre-trained classification algorithm according to the target electrocardiographic feature vector and a pre-trained self-organizing map network, wherein the self-organizing map network is obtained through training according to a pre-set training data set. According to the method and the device, the target sign type corresponding to the target electrocardiograph data can be intelligently determined through the self-encoder and the self-organizing mapping network and by combining the classification algorithm, manual participation is not needed, and the processing efficiency and accuracy of the electrocardiograph data can be improved.
Fig. 4 is a block diagram illustrating an apparatus for processing electrocardiographic data according to an exemplary embodiment. As shown in fig. 4, the apparatus 300 may include:
the acquiring module 301 is configured to acquire target electrocardiographic data to be processed.
A processing module 302 is configured to determine, from the target electrocardiographic data, a target electrocardiographic feature vector capable of characterizing the target electrocardiographic data through a pre-trained self-encoder.
The determining module 303 is configured to determine, according to the target electrocardiographic feature vector and a pre-trained self-organizing map network, a target sign type corresponding to the target electrocardiographic data through a preset classification algorithm, where the self-organizing map network is obtained by training according to a preset training data set.
FIG. 5 is a block diagram of one processing module shown in the embodiment of FIG. 4. As shown in fig. 5, the processing module 302 may include:
the extraction submodule 3021 is configured to filter the target electrocardiographic data, and perform peak detection on the filtered target electrocardiographic data to extract a second number of heartbeat data.
The dimension reduction submodule 3022 is configured to perform dimension reduction processing on a third number of heartbeat data in the second number of heartbeat data, so as to obtain a heartbeat data sequence, where the third number is smaller than or equal to the second number.
An encoding submodule 3023 for inputting the heartbeat data sequence from the encoder to obtain the target electrocardio feature vector.
Optionally, the encoding submodule 3023 is configured to:
the heartbeat data sequence is divided into a plurality of heartbeat data segments according to the designated duration.
Each beat data segment is input from an encoder to obtain a sub-feature vector that characterizes the beat data segment.
And splicing the sub-feature vectors corresponding to each heartbeat data segment to obtain the target electrocardio feature vector.
FIG. 6 is a block diagram of one determination module shown in the embodiment of FIG. 4. As shown in fig. 6, the determining module 303 includes:
the first determining submodule 3031 is configured to determine a distance from the target electrocardiographic feature vector to each of a first number of regions corresponding to the self-organizing map network, where the first number is determined when the self-organizing map network is trained according to the training data set.
The second determining submodule 3032 is configured to take the sign type corresponding to the target area as the target sign type, where the target area is an area with the minimum distance from the target electrocardiographic feature vector.
Optionally, the self-organizing map network is trained by:
a training data set is acquired, the training data set comprising a plurality of training electrocardiographic data.
And determining the best matching node matched with the training electrocardio data in all nodes included in the network to be trained according to any training electrocardio data.
A neighborhood node in the topological neighborhood of the best matching node is determined.
And updating the weights of the neighborhood nodes and the best matching nodes according to the distance between the neighborhood nodes and the best matching nodes.
And repeatedly executing the steps of determining the best matching node matched with the training electrocardio data in all nodes included in the network to be trained according to any training electrocardio data until the weights of the neighborhood nodes and the best matching node are updated according to the distance between the neighborhood nodes and the best matching node until the network to be trained meets the preset training ending condition, so as to obtain the self-organizing map network.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
In summary, the disclosure first obtains target electrocardiographic data to be processed, determines a target electrocardiographic feature vector capable of representing the target electrocardiographic data through a pre-trained self-encoder according to the target electrocardiographic data, and then determines a target sign type corresponding to the target electrocardiographic data through a pre-trained classification algorithm according to the target electrocardiographic feature vector and a pre-trained self-organizing map network, wherein the self-organizing map network is obtained through training according to a pre-set training data set. According to the method and the device, the target sign type corresponding to the target electrocardiograph data can be intelligently determined through the self-encoder and the self-organizing mapping network and by combining the classification algorithm, manual participation is not needed, and the processing efficiency and accuracy of the electrocardiograph data can be improved.
Fig. 7 is a block diagram of an electronic device 700, according to an example embodiment. As shown in fig. 7, the electronic device 700 may include: a processor 701, a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input/output (I/O) interface 704, and a communication component 705.
The processor 701 is configured to control the overall operation of the electronic device 700 to perform all or part of the steps in the method for processing electrocardiographic data. The memory 702 is used to store various types of data to support operation on the electronic device 700, which may include, for example, instructions for any application or method operating on the electronic device 700, as well as application-related data, such as contact data, messages sent and received, pictures, audio, video, and so forth. The Memory 702 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 703 can include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 702 or transmitted through the communication component 705. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the processor 701 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near Field Communication, NFC for short), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or a combination of more of them, is not limited herein. The corresponding communication component 705 may thus comprise: wi-Fi module, bluetooth module, NFC module, etc.
In an exemplary embodiment, the electronic device 700 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, abbreviated as ASIC), digital signal processor (Digital Signal Processor, abbreviated as DSP), digital signal processing device (Digital Signal Processing Device, abbreviated as DSPD), programmable logic device (Programmable Logic Device, abbreviated as PLD), field programmable gate array (Field Programmable Gate Array, abbreviated as FPGA), controller, microcontroller, microprocessor, or other electronic component for performing the above-described method of processing electrocardiographic data.
In another exemplary embodiment, a computer readable storage medium is also provided, comprising program instructions which, when executed by a processor, implement the steps of the method of processing electrocardiographic data described above. For example, the computer readable storage medium may be the memory 702 including program instructions described above, which are executable by the processor 701 of the electronic device 700 to perform the method of processing electrocardiographic data described above.
In another exemplary embodiment, a computer program product is also provided, which comprises a computer program executable by a programmable apparatus, the computer program having code portions for performing the above-mentioned method of processing electrocardiographic data when being executed by the programmable apparatus.
The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solutions of the present disclosure within the scope of the technical concept of the present disclosure, and all the simple modifications belong to the protection scope of the present disclosure.
In addition, the specific features described in the foregoing embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, the present disclosure does not further describe various possible combinations.
Moreover, any combination between the various embodiments of the present disclosure is possible as long as it does not depart from the spirit of the present disclosure, which should also be construed as the disclosure of the present disclosure.
Claims (8)
1. A method for processing electrocardiographic data, the method comprising:
acquiring target electrocardiographic data to be processed;
determining a target electrocardio characteristic vector capable of representing the target electrocardio data through a pre-trained self-encoder according to the target electrocardio data;
determining a target sign type corresponding to the target electrocardiographic data through a preset classification algorithm according to the target electrocardiographic feature vector and a pre-trained self-organizing map network, wherein the self-organizing map network is obtained through training according to a preset training data set;
determining, from the target electrocardiographic data, a target electrocardiographic feature vector capable of characterizing the target electrocardiographic data by a pre-trained self-encoder, including:
filtering the target electrocardio data, and carrying out peak detection on the filtered target electrocardio data to extract a second number of heartbeat data;
performing dimension reduction processing on a third number of heartbeat data in the second number of heartbeat data to obtain a heartbeat data sequence, wherein the third number is smaller than or equal to the second number;
and inputting the heartbeat data sequence into the self-encoder to obtain the target electrocardio characteristic vector.
2. The method of claim 1, wherein said inputting the sequence of heartbeat data into the self-encoder to obtain the target electrocardiographic feature vector comprises:
dividing the heartbeat data sequence into a plurality of heartbeat data segments according to a designated duration;
inputting each of the heartbeat data segments into the self-encoder to obtain a sub-feature vector capable of representing the heartbeat data segment;
and splicing the sub-feature vectors corresponding to each heartbeat data segment to obtain the target electrocardio feature vector.
3. The method according to claim 1, wherein the determining, according to the target electrocardiographic feature vector and a pre-trained self-organizing map network, the target sign type corresponding to the target electrocardiographic data through a preset classification algorithm includes:
determining the distance from the target electrocardio feature vector to each region in a first number of regions corresponding to the self-organizing map network, wherein the first number is determined when the self-organizing map network is trained according to the training data set;
and taking the sign type corresponding to a target area as the target sign type, wherein the target area is the area with the minimum distance with the target electrocardio feature vector.
4. A method according to claim 3, wherein the self-organizing map network is trained by:
acquiring the training data set, wherein the training data set comprises a plurality of training electrocardio data;
according to any training electrocardio data, determining the best matching node matched with the training electrocardio data in all nodes included in the network to be trained;
determining a neighborhood node in the topological neighborhood of the best matching node;
updating the weights of the neighborhood node and the best matching node according to the distance between the neighborhood node and the best matching node;
and repeatedly executing the steps of determining the best matching node matched with the training electrocardio data in all nodes included in the network to be trained according to any training electrocardio data, and updating the weights of the neighborhood nodes and the best matching node according to the distance between the neighborhood nodes and the best matching node until the network to be trained meets the preset training ending condition so as to obtain the self-organizing map network.
5. An apparatus for processing electrocardiographic data, the apparatus comprising:
the acquisition module is used for acquiring target electrocardiographic data to be processed;
the processing module is used for determining a target electrocardio characteristic vector capable of representing the target electrocardio data through a pre-trained self-encoder according to the target electrocardio data;
the determining module is used for determining a target sign type corresponding to the target electrocardiographic data through a preset classification algorithm according to the target electrocardiographic feature vector and a pre-trained self-organizing map network, wherein the self-organizing map network is obtained through training according to a preset training data set;
the processing module comprises:
the extraction sub-module is used for filtering the target electrocardiograph data and carrying out peak detection on the filtered target electrocardiograph data so as to extract a second number of heartbeat data;
the dimension reduction sub-module is used for carrying out dimension reduction processing on a third number of heartbeat data in the second number of heartbeat data so as to obtain a heartbeat data sequence, wherein the third number is smaller than or equal to the second number;
and the encoding submodule is used for inputting the heartbeat data sequence into the self-encoder so as to obtain the target electrocardio characteristic vector.
6. The apparatus of claim 5, wherein the encoding submodule is to:
dividing the heartbeat data sequence into a plurality of heartbeat data segments according to a designated duration;
inputting each of the heartbeat data segments into the self-encoder to obtain a sub-feature vector capable of representing the heartbeat data segment;
and splicing the sub-feature vectors corresponding to each heartbeat data segment to obtain the target electrocardio feature vector.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any one of claims 1-4.
8. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011529285.XA CN112716504B (en) | 2020-12-22 | 2020-12-22 | Electrocardiogram data processing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011529285.XA CN112716504B (en) | 2020-12-22 | 2020-12-22 | Electrocardiogram data processing method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112716504A CN112716504A (en) | 2021-04-30 |
| CN112716504B true CN112716504B (en) | 2023-12-15 |
Family
ID=75605435
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011529285.XA Active CN112716504B (en) | 2020-12-22 | 2020-12-22 | Electrocardiogram data processing method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112716504B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102281816A (en) * | 2008-11-20 | 2011-12-14 | 人体媒介公司 | Method and apparatus for determining critical care parameters |
| CN105902266A (en) * | 2016-04-22 | 2016-08-31 | 江苏物联网研究发展中心 | Electrocardiographic signal classification method based on self-organizing neural network |
| CN107710205A (en) * | 2015-04-14 | 2018-02-16 | 优比欧迈公司 | For the sign in the microorganism group source of cardiovascular disease condition, diagnosis and the method and system for the treatment of |
| CN107849599A (en) * | 2015-06-30 | 2018-03-27 | 优比欧迈公司 | method and system for diagnostic test |
| CN108398268A (en) * | 2018-03-15 | 2018-08-14 | 哈尔滨工业大学 | A kind of bearing performance degradation assessment method based on stacking denoising self-encoding encoder and Self-organizing Maps |
| CN108573227A (en) * | 2018-04-09 | 2018-09-25 | 深圳竹信科技有限公司 | ECG data quality evaluating method and device |
| 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 |
| WO2019071201A1 (en) * | 2017-10-06 | 2019-04-11 | Alivecor, Inc. | Continuous monitoring of a user's health with a mobile device |
| CN109688990A (en) * | 2016-09-06 | 2019-04-26 | 新感知公司 | For providing a user the method and system of attached sensory information |
| CN110141218A (en) * | 2019-06-17 | 2019-08-20 | 东软集团股份有限公司 | A kind of electrocardiosignal classification method, device and program product, storage medium |
| CN110811582A (en) * | 2019-12-09 | 2020-02-21 | 北京明略软件系统有限公司 | Heart rate detection method, device and equipment |
| CN111265210A (en) * | 2020-03-24 | 2020-06-12 | 华中科技大学 | Atrial fibrillation prediction device and equipment based on deep learning |
| CN111449645A (en) * | 2020-03-07 | 2020-07-28 | 河南大学 | Intelligent classification and identification method for electrocardiogram and heartbeat |
| US10743809B1 (en) * | 2019-09-20 | 2020-08-18 | CeriBell, Inc. | Systems and methods for seizure prediction and detection |
| CN112101162A (en) * | 2020-09-04 | 2020-12-18 | 沈阳东软智能医疗科技研究院有限公司 | Image recognition model generation method and device, storage medium and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10537463B2 (en) * | 2015-01-13 | 2020-01-21 | Align Technology, Inc. | Systems and methods for positioning a patient's mandible in response to sleep apnea status |
-
2020
- 2020-12-22 CN CN202011529285.XA patent/CN112716504B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102281816A (en) * | 2008-11-20 | 2011-12-14 | 人体媒介公司 | Method and apparatus for determining critical care parameters |
| CN107710205A (en) * | 2015-04-14 | 2018-02-16 | 优比欧迈公司 | For the sign in the microorganism group source of cardiovascular disease condition, diagnosis and the method and system for the treatment of |
| CN107849599A (en) * | 2015-06-30 | 2018-03-27 | 优比欧迈公司 | method and system for diagnostic test |
| CN105902266A (en) * | 2016-04-22 | 2016-08-31 | 江苏物联网研究发展中心 | Electrocardiographic signal classification method based on self-organizing neural network |
| CN109688990A (en) * | 2016-09-06 | 2019-04-26 | 新感知公司 | For providing a user the method and system of attached sensory information |
| WO2019071201A1 (en) * | 2017-10-06 | 2019-04-11 | Alivecor, Inc. | Continuous monitoring of a user's health with a mobile device |
| CN108398268A (en) * | 2018-03-15 | 2018-08-14 | 哈尔滨工业大学 | A kind of bearing performance degradation assessment method based on stacking denoising self-encoding encoder and Self-organizing Maps |
| CN108573227A (en) * | 2018-04-09 | 2018-09-25 | 深圳竹信科技有限公司 | ECG data quality evaluating method and device |
| 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 |
| CN110141218A (en) * | 2019-06-17 | 2019-08-20 | 东软集团股份有限公司 | A kind of electrocardiosignal classification method, device and program product, storage medium |
| US10743809B1 (en) * | 2019-09-20 | 2020-08-18 | CeriBell, Inc. | Systems and methods for seizure prediction and detection |
| CN110811582A (en) * | 2019-12-09 | 2020-02-21 | 北京明略软件系统有限公司 | Heart rate detection method, device and equipment |
| CN111449645A (en) * | 2020-03-07 | 2020-07-28 | 河南大学 | Intelligent classification and identification method for electrocardiogram and heartbeat |
| CN111265210A (en) * | 2020-03-24 | 2020-06-12 | 华中科技大学 | Atrial fibrillation prediction device and equipment based on deep learning |
| CN112101162A (en) * | 2020-09-04 | 2020-12-18 | 沈阳东软智能医疗科技研究院有限公司 | Image recognition model generation method and device, storage medium and electronic equipment |
Non-Patent Citations (15)
| Title |
|---|
| Deep Autoencoder Networks Optimized with Genetic Algorithms for Efficient ECG Clustering;Thinsungnoen, T.; Kerdprasop, K.; Kerdprasop, N.;《International Journal of Machine Learning and Computing》;第8卷(第2期);112-16 * |
| ECG波形分类算法研究;洪玮;《CNKI》;全文 * |
| Gogna, A (Gogna, Anupriya) [1] * |
| Li, MC (Li, Mingchun) [1] ; He, G (He, Gary) [1] ; Zhu, BF (Zhu, Baofeng) [1] .Atrial Fibrillation Detection Based on the Combination of Depth and Statistical Features of ECG.《assoc aomp machinery》.2019,全文. * |
| Majumdar, A (Majumdar, Angshul) [1] * |
| Semi-supervised Stacked Label Consistent Autoencoder for Reconstruction and Analysis of Biomedical Signals;Gogna, A (Gogna, Anupriya) [1] ; Majumdar, A (Majumdar, Angshul) [1] ; Ward, R (Ward, Rabab) [2];《IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 》;第64卷(第9期);2196-2205 * |
| 基于FCM算法的心电信号特征分类研究;郑淋文;《CNKI》;全文 * |
| 基于信息融合的薄壁机器人轴承状态评估;刘洋, 颉潭成, 徐彦伟, 等.;《机械强度》;第41卷(第5期);1042-1047 * |
| 基于小波变换的动态心电图波形特征聚类研究;郑刚, 黄亚楼, 王鹏涛;《光电子．激光》;第18卷(第4期);475-477 * |
| 基于数学形态学和SOM网络的心拍检测分类算法研究;郑唯琴;《CNKI》;全文 * |
| 基于深度学习和模糊C均值的心电信号分类方法;吴志勇, 丁香乾, 许晓伟等.;《自动化学报》;第44卷(第10期);全文 * |
| 基于移动窗FICA和SOM方法的心动异常诊断;杨青川, 杨青, 姚鑫等.;《南京理工大学学报》;第37卷(第04期);全文 * |
| 基于自组织特征映射网络的心电信号矢量量化;张浙亮, 吕维雪.;《中国生物医学工程学报》;第18卷(第1期);97-103 * |
| 杨荣峰,魏义祥.多级自组织映射用于心电信号QRS波群聚类.《清华大学学报(自然科学版)》.2007,全文. * |
| 模糊聚类技术在心电波形分类中的应用研究;李贵娟;《CNKI》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112716504A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Afkhami et al. | Cardiac arrhythmia classification using statistical and mixture modeling features of ECG signals | |
| CN108478209B (en) | Electrocardio information dynamic monitoring method and dynamic monitoring system | |
| CN111990989A (en) | Electrocardiosignal identification method based on generation countermeasure and convolution cyclic network | |
| CN112022144B (en) | Network training method for detecting electrocardio abnormality, electrocardio abnormality early warning method and device | |
| CN110522440B (en) | Electrocardiosignal recognition device based on grouping convolution neural network | |
| CN110226921B (en) | Electrocardiosignal detection and classification method and device, electronic equipment and storage medium | |
| CN110226920B (en) | Electrocardiosignal identification method and device, computer equipment and storage medium | |
| CN111631704B (en) | Diabetes early-stage detection system and method based on combination of electrocardio information and electroencephalogram information | |
| CN111345816A (en) | Multi-lead QRS complex detection method, device, equipment and storage medium | |
| CN110680278B (en) | Electrocardiosignal recognition device based on convolutional neural network | |
| Moses et al. | A survey of data mining algorithms used in cardiovascular disease diagnosis from multi-lead ECG data | |
| Agyeman et al. | Classification Techniques for Arrhythmia Patterns Using Convolutional Neural Networks and Internet of Things (IoT) Devices | |
| CN110720894A (en) | Atrial flutter detection method, device, equipment and storage medium | |
| CN115778403A (en) | Electrocardiogram analysis method, electrocardiogram analysis device, electronic equipment and storage medium | |
| CN113749656B (en) | Emotion recognition method and device based on multidimensional physiological signals | |
| Yang et al. | Multi-label classification of electrocardiogram with modified residual networks | |
| Zhang et al. | A signal quality assessment method for electrocardiography acquired by mobile device | |
| CN111528833B (en) | Rapid identification and processing method and system for electrocardiosignals | |
| CN112716504B (en) | Electrocardiogram data processing method and device, storage medium and electronic equipment | |
| CN110786847B (en) | Electrocardiogram signal library building method and analysis method | |
| Sathawane et al. | Prediction and analysis of ECG signal behaviour using soft computing | |
| Jothiramalingam et al. | Review of Computational Techniques for the Analysis of Abnormal Patterns of ECG Signal Provoked by Cardiac Disease. | |
| Anbarasi et al. | Detection and classification of arrhythmia type using hybrid model of LSTM with convolutional neural network | |
| CN113693610B (en) | Method and device for processing few-lead electrocardiogram data, storage medium and computer equipment | |
| CN111956207B (en) | Electrocardiogram recording labeling method, device, equipment and storage medium |
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 |