System and method for ventricular premature beat recognition based on classifier fusion and diagnosis rules
A premature ventricular contraction and identification system technology, applied in the field of medical electronics, can solve problems such as ignoring the doctor's diagnostic thinking process, and achieve the effect of improving the overall classification performance and accuracy
Active Publication Date: 2021-10-12
SUZHOU INST OF NANO TECH & NANO BIONICS CHINESE ACEDEMY OF SCI
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The former category usually ignores the doctor's diagnostic thinking process; while the latter category considers the doctor's diagnostic thinking process, but it needs to extract some feature points of PVC in advance, such as R wave, QRS wave boundary points, etc., and how to accurately extract these Feature points are also a problem that researchers need to focus on
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0074] The data used in this example comes from the China Cardiovascular Disease Database (CCDD database, http: / / 58.210.56.164 / ccdd / ).
[0075] (1) In order to perform denoising preprocessing, ECG records are firstly subjected to band-pass filtering at 0.5-40 Hz;
[0076] (2) 35840 (including 3112 PVC records) preprocessed ECG records are used as training samples; the other 141046 records (including 2148 PVC records) are used for testing. All training samples are input into 4 LCNNs and 6 RNNs for independent parallel training, among which the 4 LCNNs are selected from more LCNN models that have been trained. The results are better and the differences between the models are relatively large. Large LCNN model. Similarly, these six RNNs are also selected from more trained RNN models with better results and greater differences among the models. After learning, the test samples are independently tested by these 4 LCNNs and 6 RNNs to obtain 4 LCNN classification results and 6 RNN ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a premature ventricular beat recognition system and method based on classifier fusion and diagnostic rules. The system includes: a classification unit, including an LCNN classification module and an RNN classification module for independently processing electrocardiogram data, and the LCNN classification module includes m first classifiers with different structures are used to output at least m first classification results, and the RNN classification module includes n second classifiers with different structures, which are used to output at least n second classification results; the fusion unit is used to According to the fusion decision rule, the first classification result and the second classification result are fused and decided to obtain the fusion result; the discrimination unit is used to discriminate the non-PVC data and PVC data judged by the fusion unit according to the PVC pathological characteristics, and obtain the PVC recognition result . The invention fuses the classification results of the LCNN and RNN classifiers, incorporates PVC pathological features, and adopts a method of combining machine learning and disease diagnosis rules to improve the overall classification performance and accuracy of PVC recognition.
Description
technical field [0001] The invention relates to a ventricular premature beat recognition system, in particular to a ventricular premature beat recognition system and a recognition method based on classifier fusion and diagnosis rules, belonging to the technical field of medical electronics. Background technique [0002] The computer-aided diagnosis of premature ventricular contraction (PVC) has very important clinical significance. It can relieve doctors from massive ECG analysis, reduce the workload of doctors, and improve the efficiency of doctors' diagnosis. At present, there are mainly two types of computer-aided recognition systems for premature ventricular contractions: one is to use a certain classifier for recognition; the other is to use rule reasoning to distinguish based on the pathological characteristics of PVC. The former category usually ignores the doctor's diagnostic thinking process; while the latter category considers the doctor's diagnostic thinking proce...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G16H50/20G06N3/02
CPCG06N3/02
Inventor 周飞燕金林鹏董军
Owner SUZHOU INST OF NANO TECH & NANO BIONICS CHINESE ACEDEMY OF SCI