• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.2
• /
• pp.117-126
• /
• 2019

Legacy study for detecting arrhythmia have mostly used nonlinear method to increase classification accuracy. Most methods are complex to process and manipulate data and have difficulties in classifying various arrhythmias. Therefore it is necessary to classify various arrhythmia based on short-term data. In this study, we propose a feature extraction based on auto regressive modeling and an premature contraction arrhythmia classification method using SVM., For this purpose, the R-wave is detected in the ECG signal from which noise has been removed, QRS and RR interval segment is modelled. Also, we classified Normal, PVC, PAC through SVM in realtime by extracting four optimal segment length and AR order. The detection and classification rate of R wave and PVC is evaluated through MIT-BIH arrhythmia database. The performance results indicate the average of 99.77% in R wave detection and 99.23%, 97.28%, 96.62% in Normal, PVC, PAC classification.

• Clinical and Experimental Pediatrics
• /
• v.53 no.5
• /
• pp.644-647
• /
• 2010

Purpose: To evaluate myocardial conductivity to understand cardiac involvement in patients with mitochondrial disease. Methods: We performed retrospective study on fifty-seven nonspecific mitochondrial encephalopathy patients with no clinical cardiac manifestations. The patients were diagnosed with mitochondrial respiratory chain complex defects through biochemical enzyme assays of muscle tissue. We performed standard 12-lead electrocardiography (ECG) on all patients. Results: ECG abnormalities were observed in 30 patients (52.6%). Prolongation of the QTc interval (>440 ms) was seen in 19 patients (33.3%), widening of the corrected QRS interval in 15 (26.3%), and bundle branch block in four (7.0%). Atrioventricular block, premature atrial contraction and premature ventricular contraction were seen in two patients each (3.5%) and Wolff-Parkinson-White syndrome in one patient (1.8%). Conclusion: Given this finding, we recommend active screening with ECG in patients with mitochondrial disease even in patients without obvious cardiac manifestation.

• Journal of Sensor Science and Technology
• /
• v.29 no.1
• /
• pp.19-26
• /
• 2020

Electrocardiogram (ECG) classification has become an essential task of modern day wearable devices, and can be used to detect cardiovascular diseases. State-of-the-art Artificial Intelligence (AI)-based ECG classifiers have been designed using various artificial neural networks (ANNs). Despite their high accuracy, ANNs require significant computational resources and power. Herein, three different ANNs have been compared: multilayer perceptron (MLP), convolutional neural network (CNN), and spiking neural network (SNN) only for the ECG classification. The ANN model has been developed in Python and Theano, trained on a central processing unit (CPU) platform, and deployed on a PYNQ-Z2 FPGA board to validate the model using a Jupyter notebook. Meanwhile, the hardware accelerator is designed with Overlay, which is a hardware library on PYNQ. For classification, the MIT-BIH dataset obtained from the Physionet library is used. The resulting ANN system can accurately classify four ECG types: normal, atrial premature contraction, left bundle branch block, and premature ventricular contraction. The performance of the ECG classifier models is evaluated based on accuracy and power. Among the three AI algorithms, the SNN requires the lowest power consumption of 0.226 W on-chip, followed by MLP (1.677 W), and CNN (2.266 W). However, the highest accuracy is achieved by the CNN (95%), followed by MLP (76%) and SNN (90%).

• Journal of Biomedical Engineering Research
• /
• v.30 no.4
• /
• pp.294-305
• /
• 2009

The bio signals essentially have different characteristics in each person. And the main purpose of automatic diagnosis algorithm based on bio signals focuses on discriminating differences of abnormal state from personal differences. In this paper, we propose automatic ECG diagnosis algorithm which discriminates normal heart beats from premature ventricular contraction using optimization of wavelet parameterization to solve that problem. The proposed algorithm optimizes wavelet parameter to let energy of signal be concentrated on specific scale band. We can reduce the personal differences and consequently highlight the differences coming from arrhythmia via this process. The proposed algorithm using ELM as a classifier show high discrimination performance between normal beat and PVC. From the experimental results on MIT-BIH arrhythmia database the performances of the proposed algorithm are 98.1% in accuracy, 93.0% in sensitivity, 96.4% in positive predictivity, and 0.8% in false positive rate. This results are similar or higher then results of existing researches in spite of small human intervention.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.378-382
• /
• 2006

This paper presents an approach to detect premature ventricular contractions(PVC) using the neural network with weighted fuzzy membership functions(NEWFM). NEWFM classifies normal and PVC beats by the trained weighted fuzzy membership functions using wavelet transformed coefficients extracted from the MIT-BIH PVC database. The two most important coefficients are selected by the non-overlap area distribution measurement method to minimize the classification rules that show PVC classification rate of 99.90%. By Presenting locations of the extracted two coefficients based on the R wave location, it is shown that PVC can be detected using only information of the two portions.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1924-1925
• /
• 2007

본 논문에서는 부정맥 판별을 위한 전처리 과정으로 PCA, LDA, ICA를 바탕으로 하여 정확도를 비교하여 보았다. 각각의 전처리는 고유의 특성을 가지고 있으며 본 논문의 목적은 부정맥 판별상 어떤 전처리가 더욱 정확성의 면에서 효과적인지를 알아보는 것이다. 본 논문의 데이터는 MIT-BIH에 기반하고 있으며, Beat의 분류는 정상(Normal), 좌각차단(Left Bundle Branch Block, LBBB), 우각차단(Right Bundle Branch Block, RBBB), 조기심실수축(Premature Ventricular Contraction, PVC), 조기심방수축(Atrial Premature Beat, APB), paced Beat, 심실보충수축(Ventricular Escape Beat)로 나누었다. 실험적 결과는 PCA-BPNN의 경우 95.53%, ICA-BPNN의 경우 93.95%, LDA-BPNN의 경우 96.42%로 LDA가 가장 ECG 부정맥 판별 응용에 있어 가장 효율적인 방법으로 나타났다.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• pp.571-579
• /
• 2005

In this paper, we proposed an algorithm for arrhythmia classification, which is associated with the reduction of feature dimensions by linear discriminant analysis (LDA) and a support vector machine (SVM) based classifier. Seventeen original input features were extracted from preprocessed signals by wavelet transform, and attempts were then made to reduce these to 4 features, the linear combination of original features, by LDA. The performance of the SVM classifier with reduced features by LDA showed higher than with that by principal component analysis (PCA) and even with original features. For a cross-validation procedure, this SVM classifier was compared with Multilayer Perceptrons (MLP) and Fuzzy Inference System (FIS) classifiers. When all classifiers used the same reduced features, the overall performance of the SVM classifier was comprehensively superior to all others. Especially, the accuracy of discrimination of normal sinus rhythm (NSR), arterial premature contraction (APC), supraventricular tachycardia (SVT), premature ventricular contraction (PVC), ventricular tachycardia (VT) and ventricular fibrillation (VF) were $99.307\%,\;99.274\%,\;99.854\%,\;98.344\%,\;99.441\%\;and\;99.883\%$, respectively. And, even with smaller learning data, the SVM classifier offered better performance than the MLP classifier.

• Clinical and Experimental Pediatrics
• /
• v.61 no.11
• /
• pp.362-365
• /
• 2018

Purpose: This study aimed to analyze changes in QRS duration and cardiothoracic ratio (CTR) following pulmonary valve replacement (PVR) in patients with tetralogy of Fallot (TOF). Methods: Children and adolescents who had previously undergone total repair for TOF (n=67; median age, 16 years) who required elective PVR for pulmonary regurgitation and/or right ventricular out tract obstruction were included in this study. The QRS duration and CTR were measured pre- and postoperatively and postoperative changes were evaluated. Results: Following PVR, the CTR significantly decreased (pre-PVR $57.2%{\pm}6.2%$, post-PVR $53.8%{\pm}5.5%$, P=0.002). The postoperative QRS duration showed a tendency to decrease (pre-PVR $162.7{\pm}26.4$ msec, post-PVR $156.4{\pm}24.4$ msec, P=0.124). QRS duration was greater than 180 msec in 6 patients prior to PVR. Of these, 5 patients showed a decrease in QRS duration following PVR; QRS duration was less than 180 msec in 2 patients, and QRS duration remained greater than 180 msec in 3 patients, including 2 patients with diffuse postoperative right ventricular outflow tract hypokinesis. Six patients had coexisting arrhythmias before PVR; 2 patients, atrial tachycardia; 3 patients, premature ventricular contraction; and 1 patient, premature atrial contraction. None of the patients presented with arrhythmia following PVR. Conclusion: The CTR and QRS duration reduced following PVR. However, QRS duration may not decrease below 180 msec after PVR, particularly in patients with right ventricular outflow tract hypokinesis. The CTR and ECG may provide additional clinical information on changes in right ventricular volume and/or pressure in these patients.

• Women's Health Nursing
• /
• v.26 no.3
• /
• pp.205-212
• /
• 2020

Purpose: This study aimed to identify the components of preterm birth (PTB) through women's personal narratives and to visualize clinical symptom expressions (CSEs). Methods: The participants were 11 women who gave birth before 37 weeks of gestational age. Personal narratives were collected by interactive unstructured storytelling via individual interviews, from August 8 to December 4, 2019 after receiving approval of the Institutional Review Board. The textual data were converted to PDF and analyzed using the MAXQDA program (VERBI Software). Results: The participants' mean age was 34.6 (±2.98) years, and five participants had a spontaneous vaginal birth. The following nine components of PTB were identified: obstetric condition, emotional condition, physical condition, medical condition, hospital environment, life-related stress, pregnancy-related stress, spousal support, and informational support. The top three codes were preterm labor, personal characteristics, and premature rupture of membrane, and the codes found for more than half of the participants were short cervix, fear of PTB, concern about fetal well-being, sleep difficulty, insufficient spousal and informational support, and physical difficulties. The top six CSEs were stress, hydramnios, false labor, concern about fetal wellbeing, true labor pain, and uterine contraction. "Stress" was ranked first in terms of frequency and "uterine contraction" had individual attributes. Conclusion: The text network analysis of narratives from women who gave birth preterm yielded nine PTB components and six CSEs. These nine components should be included for developing a reliable and valid scale for PTB risk and stress. The CSEs can be applied for assessing preterm labor, as well as considered as strategies for students in women's health nursing practicum.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.16-22
• /
• 2010

Electrocardiogram(ECG) analysis and arrhythmia recognition are critical for diagnosis and treatment of ill patients. Cardiac arrhythmia is a condition in which heart beat may be irregular and presents a serious threat to the patient recovering from ventricular tachycardia (VT) and ventricular fibrillation (VF). Other arrhythmias like atrial premature contraction (APC), Premature ventricular contraction (PVC) and superventricular tachycardia (SVT) are important in diagnosing the heart diseases. This paper presented new method to classify various arrhythmias contrary to other techniques which are limited to only two or three arrhythmias. ECG is decomposed into Intrinsic Mode Functions (IMFs) by Empirical Mode Decomposition (EMD). Burg algorithm was performed on IMFs to obtain AR coefficients which can reduce the dimension of feature vector and utilized as Multi-class SVM inputs which is basically extended from binary SVM. We chose optimal parameters for SVM classifier, applied to arrhythmias classification and achieved the accuracies of detecting NSR, APC, PVC, SVT, VT and VP were 96.8% to 99.5%. The results showed that EMD was useful for the preprocessing and feature extraction and multi-class SVM for classification of cardiac arrhythmias, with high usefulness.