• Journal of Biomedical Engineering Research
• /
• v.19 no.1
• /
• pp.39-46
• /
• 1998

In this paper, we present a neural network identification and a control of highly complicated nonlinear left ventricular assist device(LVAD) system with a pneumatically driven mock circulation system. Generally, the LVAD system needs to compensate for nonlinearities. It is necessary to apply high performance control techniques. Fortunately, the neural network can be applied to control of a nonlinear dynamic system by learning capability. In this study, we identify the LVAD system with neural network identification(NNI). Once the NNI has learned the dynamic model of the LVAD system, the other network, called neural network controller(NNC), is designed for a control of the LVAD system. The ability and effectiveness of identifying and controlling the LVAD system using the proposed algorithm will be demonstrated by computer simulation.

• Journal of Biomedical Engineering Research
• /
• v.27 no.2
• /
• pp.47-52
• /
• 2006

The purpose of this study was to predict successful defibrillation in ventricular fibrillation using parameters extracted by wave analysis method and neuro-fuzzy. Total 15 dogs were tested for predicting successful defibrillation. Feature parameters were extracted for return of spontaneous circulation (ROSC) and non-ROSC by wave analysis method, and these parameters are an irregularity factor, spectral moments, mean power of level-crossing spectrum, and mean of alpha-significant value. Additionally, two parameters by analyzing method of frequency were extracted into a mean of power spectrum and a mean frequency. Then extracted parameters were analyzed in which parameters result to have high performance of discriminating ROSC and non-ROSC by a statistical method of t-test. The average of sensitivity and specificity were 62.5% and 75.0%, respectively. The average of positive predictive factor and negative predictive factor were 61.2% and 75.8%, respectively.

• 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 Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.233-242
• /
• 2018

Previous works for detecting arrhythmia have mostly used nonlinear method such as artificial neural network, fuzzy theory, support vector machine to increase classification accuracy. Most methods require higher computational cost and larger processing time. Therefore it is necessary to design efficient algorithm that classifies PVC(premature ventricular contraction) and decreases computational cost by accurately detecting feature point based on only R peak through optimal R wave. For this purpose, we detected R wave through optimal threshold value and extracted RR interval and R peak pattern from noise-free ECG signal through the preprocessing method. Also, we classified PVC in realtime through RR interval and R peak pattern. The performance of R wave detection and PVC classification is evaluated by using 9 record of MIT-BIH arrhythmia database that included over 30. The achieved scores indicate the average of 99.02% in R wave detection and the rate of 94.85% in PVC classification.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.11B
• /
• pp.1289-1295
• /
• 2009

Premature ventricular contractions are the most common of all arrhythmias and may cause more serious situation like ventricular fibrillation and ventricular tachycardia in some patients. Therefore, the detection of this arrhythmia becomes crucial in the early diagnosis and prevention of possible life threatening cardiac diseases. Particularly, in the healthcare system that must continuously monitor people's situation, it is necessary to process ECG signal in realtime. In other words, design of algorithm that exactly detects R wave using minimal computation and classifies PVC is needed. So, R wave detection algorithm based adaptive threshold and window for the classification of PVC is presented in this paper. For this purpose, ECG signals are first processed by the usual preprocessing method and R wave was detected and adaptive window through R-R interval is used for efficiency of the detection. The performance of R wave detection and PVC classification is evaluated by using MIT-BIH arrhythmia database. The achieved scores indicate 99.33%, 88.86% accuracy respectively for R wave detection and PVC classification.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.761-766
• /
• 2023

In this paper, TI was measured to classify the presence or absence of mild left ventricular diastolic dysfunction. Of the total 306 data, 206 were used as training data and 100 were used as test data, and the machine learning models used for classification used SVM and KNN. As a result, it was confirmed that SVM showed relatively higher accuracy than KNN and was more useful in diagnosing the presence of left ventricular diastolic dysfunction. In future research, it is expected that classification performance can be further improved by adding various indicators that evaluate not only TI but also cardiac function and securing more data. Furthermore, it is expected to be used as basic data to predict and classify other diseases and solve the problem of insufficient medical manpower compared to the increasing number of tests.

• Journal of Korea Multimedia Society
• /
• v.12 no.3
• /
• pp.451-459
• /
• 2009

This paper presents an approach to detect premature ventricular contraction(PVC) using discrete wavelet transform and fuzzy neural network. As the input of the algorithm, we use 14 coefficients of d3, d4, and d5, which are transformed by a discrete wavelet transform(DWT). This paper uses a neural network with weighted fuzzy membership functions(NEWFM) to diagnose PVC. The NEWFM discussed in this paper classifies a normal beat and a PVC beat. The size of the window of DWT is $-31/360{\sim}+32/360$ second(64 samples) whose center is the R wave. Using the seven records of the MIT-BIH arrhythmia database used in Shyu's paper, the classification performance of the proposed algorithm is 99.91%, which outperforms the 97.04% of Shyu's analysis. Using the forty records of the M1T-BIH arrhythmia database used in Inan's paper, the classification performance of the proposed algorithm is 98.01%, which outperforms 96.85% of Inan's one. The SE and SP of the proposed algorithm are 84.67% and 99.39%, which outperforms the 82.57% and 98.33%, respectively, of Inan's study.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1531-1539
• /
• 2014

Premature ventricular contraction(PVC) is the most common disease among arrhythmia and it may cause serious situations such as ventricular fibrillation and ventricular tachycardia. Nevertheless personalized difference of ECG signal exist, performance degradation occurs because of carrying out diagnosis by general classification rule. In other words, the design of algorithm that exactly detects abnormal signal and classifies PVC by analyzing the persons's physical condition and/or environment and variable QRS pattern is needed. Thus, PVC classification by personalized abnormal signal detection and QRS pattern variability is presented in this paper. For this purpose, we detected R wave through the preprocessing method and subtractive operation method and selected abnormal signal sets. Also, we classified PVC in realtime through QS interval and R wave amplitude. The performance of abnormal beat detection and PVC classification is evaluated by using MIT-BIH arrhythmia database. The achieved scores indicate the average of 98.33% in abnormal beat classification error and 94.46% in PVC classification.

• Clinical and Experimental Pediatrics
• /
• v.61 no.12
• /
• pp.392-396
• /
• 2018

Purpose: Adenotonsillar hypertrophy (ATH) that causes upper airway obstruction might lead to chronic hypoxemic pulmonary vasoconstriction and right ventricular (RV) dysfunction. We aimed to evaluate whether adenotonsillectomy (T&A) in children suffering from obstructive sleep apnea (OSA) due to severe ATH could improve RV function. Methods: Thirty-seven children (boy:girl=21:16; mean age, $9.52{\pm}2.20years$), who underwent T&A forsleep apnea due to ATH, were included. We analyzedthe mean pulmonary artery pressure (mPAP), the presence and the maximal velocity of tricuspid regurgitation (TR), the tricuspid annular plane systolic excursion (TAPSE), and the right ventricular myocardial performance index (RVMPI) with tissue Doppler echocardiography (TDE) by transthoracic echocardiography pre- and post-T&A. The follow-up period was $1.78{\pm}0.27years$. Results: Only the RVMPI using TDE improved after T&A ($42.18{\pm}2.03$ vs. $40{\pm}1.86$, P=0.001). The absolute value of TAPSE increased ($21.45{\pm}0.90mm$ vs. $22.30{\pm}1.10mm$, P=0.001) but there was no change in the z score of TAPSE pre- and post-T&A ($1.19{\pm}0.34$ vs. $1.24{\pm}0.30$, P=0.194). The mPAP was within normal range in children with ATH, and there was no significant difference between pre- and post-T&A ($19.6{\pm}3.40$ vs. $18.7{\pm}2.68$, P=0.052). There was no difference in the presence and the maximal velocity of TR (P=0.058). Conclusion: RVMPI using TDE could be an early parameter of RV function in children with OSA due to ATH.

• Journal of Chest Surgery
• /
• v.35 no.7
• /
• pp.511-516
• /
• 2002

Background: This study was undertaken in infant patients with isolated ventricular septal defect(VSD) to determine the effect of surgical closure on ventricular systolic time interval, as a parameter for ventricular performance, by echocardiography. Material and Method: Thirty patients were enrolled. Mean age of patients at operation was 6.5$\pm$3.2 months and all patients had non-restrictive VSD. We checked the left atrium/aorta(LA/Ao) ratio, left ventricle ejection fraction(EF), left ventricular systolic time interval(LVSTI), and right ventricular systolic time interval(RVSTI). Echocardiographic studies were done before surgical correction and postoperative periods(postopl: within 2 weeks, postop2: between 4 and 6 months, postop3: between 1 and 2 years). Result: LA/Ao ratio decreased significantly at immediate postoperative period compared to preoperative period and sustained during further follow-up period(from 1.74$\pm$0.37 to 1.36$\pm$0.24＊, 1.32$\pm$0.22＊, and 1.27$\pm$0.19＊, p<0.01). LV EF had not changed during follow-up periods(from 65.1$\pm$7.0 to 62.3$\pm$9.5, 62.8$\pm$5.7, and 64.1$\pm$6.9). LVSTI decreased significantly at postop2 and sustained during further follow-up period (from 0.46$\pm$0.13 to 0.46$\pm$0.11, 0.37$\pm$0.08＊, and 0.34$\pm$0.07＊, p<0.01). RVSTI decreased significantly at postop3(0.33$\pm$0.08 to 0.32$\pm$0.08, 0.31$\pm$0.07, and 0.27$\pm$0.05＊, p<0.01). Conclusion: We found that right and left ventricular systolic time intervals had decreased over the period of 1 year after surgical correction of VSD. Therefore, it is necessary to observe the change of ventricular function during that period.