• Journal of Biomedical Engineering Research
• /
• v.20 no.4
• /
• pp.435-442
• /
• 1999

A fuzzy-ART(adaptive resonance theory) network for the PVC(premature ventricular contraction) classification using wavelet coefficient is designed. This network consists of the feature extraction and learning of the fuzzy-ART network. In the first step, we have detected the QRS from the ECG signal in order to set the threshold range for feature extraction and the detected QRS was divided into several frequency bands by wavelet transformation using Haar wavelet. Among the low-frequency bands, only the 6th coefficient(D6) are selected as the input feature. After that, the fuzzy-ART network for classification of the PVC is learned by using input feature which comprises of binary data converted by applying threshold to D6. The MIT/BIH database including the PVC is used for the evaluation. The designed fuzzy-ART network showed the PVC classification ratio of 96.52%.

• The Journal of the Acoustical Society of Korea
• /
• v.8 no.4
• /
• pp.53-59
• /
• 1989

A new proposed method can separate heart sounds and lung sounds by the realization of adaptive noise canceler using adaptive lattice Wiener filter in contrast to adaptive transversal LMS filter and high pass filter as before. Lung sounds and ECG signal are detected for this purpose, and especially the second heart sounds are reduced by finding T wave location with a T wave seeking algorithm. As a result, for heart sounds reduction It was found that adaptive transversal LMS filter required 100-200's orders, 75-100's orders In adaptive transversal MLMS filter, and only 10-20's orders in adaptive lattice Wiener filter. Adaptive filtering technique has shown greater accuracy than high pass filtering without loss of low frequency component.

• Investigative Magnetic Resonance Imaging
• /
• v.11 no.1
• /
• pp.1-9
• /
• 2007

The obstacles for cardiac imaging are motion artifacts due to cardiac motion, respiration, and blood flow, and low signal due to small tissue volume of heart. To overcome these obstacles, fast imaging technique with ECG gating is utilized. Cardiac exam using MRI comprises of morphology, ventricular function, myocardial perfusion, metabolism, and coronary artery morphology. During cardiac morphology evaluation, double and triple inversion recovery techniques are used to depict myocardial fluidity and soft tissue structure such as fat tissue, respectively. By checking the first-pass enhancement of myocardium using contrast-enhanced fast gradient echo technique, myocardial blood flow can be evaluated. In addition, delayed imaging in 10 - 15 minutes can inform myocardial destruction such as chronic myocardial infarction. Ventricular function including regional and global wall motion can be checked by fast gradient echo cine imaging in quantitative way. MRI is acknowledged to be practical for integrated cardiac evaluation technique except coronary angiography. Especially delay imaging is the greatest merit of MRI in myocardial viability evaluation.

• Journal of Biomedical Engineering Research
• /
• v.25 no.2
• /
• pp.129-135
• /
• 2004

In the home health management system, we often face the situation to handle biological signals that are frequently measured from normal subjects. In such a case, it is necessary to decide whether the signal at a certain moment is normal or abnormal. Since ECC is one of the most frequently measured biological signals, we describe algorithms that detect QRS-complex and decide whether it is normal or abnormal. The developed QRS detection algorithm is a simplified version of the conventional algorithm providing enough performance for the proposed application. The developed classification algorithm that detects abnormal from mostly normal beats is based on QRS width, R-R interval and QRS shape parameter using Karhunen-Loeve transformation. The simplified QRS detector correctly detected about 99% of all beats in the MTT/BIH ECG database. The classification algorithm correctly classified about 96% of beats as normal or abnormal. The QRS detection and classification algorithm described in this paper could be used in home health management system.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1997.11a
• /
• pp.75-79
• /
• 1997

The present study was designed to investigate whether there is a consistint changes in the signals from the central and autonomic nervous systim due to olfactory stimulation. The olfactory stimuli were 0.6% orange and 2.5% valeric acid and the stimuli through the olfactory stimulator soth controlled consistint flow, controlled concentration, and saturated with vapour to prevent drying the nasal mucosa. A room air blunk served as the control stimulus, EEG was recorede from 4channels according to the international 10-20 systim. Additionally, ECG, EOG, heart rate, skin conductance and resputation were recorded comtinuously. The fast Fourier transform analysis of EEG waves was analysed with the power spectra. Averaged power spectra were computed for the following frequency bands ; delta(0-4.5Hz), theta (4.5-7Hz), alphal(7-9.5Hz), alpha2 (9.5-12.5Hz) and beta(12.5-30Hz). Withthe results of the subjective sensibility test for the ordor, the orange was related to pleasant and familiar and the valeric acid was realted to snpleasant and bothersome. There is the difference between orange and valeric acid in alphal at PG2-A2 channel. While the unpleasant stimuli seem to be increased in alphal, alpha2 and beta waves at all channels. Also, the heart rate, galvaric skin resistance seem to be decreased by pleasant stimuli and thd unpleasant stimuli shdwed the opposite. In respiration, respiration rate had been declinig tendency, and input/output ampoitued and duration showed an upward trend by olfactory stimulation with orange, while opposite by valeric acid. In conclusion, the consistent EEG changes and the autonomic responses suggests the possibilities of the subjective signal of human sensibility.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.9
• /
• pp.2021-2030
• /
• 2012

Premature ventricular contraction(PVC) is the most common disease among arrhythmia and it may cause serious situations such as ventricular fibrillation and ventricular tachycardia. Particularly, in the healthcare system that must continuously monitor patient's situation, it is necessary to process ECG (Electrocardiography) signal in realtime. In other words, the design of algorithm that exactly detects R wave using minimal computation and classifies PVC by analyzing the persons's physical condition and/or environment is needed. Thus, the patient adaptive pattern matching algorithm for the classification of PVC is presented in this paper. For this purpose, we detected R wave through the preprocessing method, adaptive threshold and window. Also, we applied pattern matching method to classify each patient's normal cardiac behavior through the Hash function. The performance of R wave detection and abnormal beat classification is evaluated by using MIT-BIH arrhythmia database. The achieved scores indicate the average of 99.33% in R wave detection and the rate of 0.32% in abnormal beat classification error.

• Journal of Digital Contents Society
• /
• v.8 no.3
• /
• pp.355-363
• /
• 2007

One of major factors for learning achievement is the student's learning preference according to his character type. In course of learning, if a student studies e-learning contents opposed to his preference, then he would be under stress and his blood pressure and heart beat be changed. For measuring unwillingness, we used spectral components in frequency domain known as stress measure. For 13 children attending kindergarten we examined S(sensing)/ N(intuition) of MBTI and presented same learning contents during 10 minutes. During learning we gathered ECG signals, changed into HRV(heart rate variability), transformed time-varying HRV signal into spectral density in frequency domain. And then, we divided it into three areas of low(LF), middle(MF), and high-frequency(HF) and calculated stress measures by rates of those frequency area. We compared estimated stress measures of S group with them of N group whether students in different group preferred different contents or not. Experimental shows that students according to MBTI type prefer different contents.

• Journal of the Ergonomics Society of Korea
• /
• v.30 no.6
• /
• pp.705-713
• /
• 2011

Objective: The aim of this study is to compare results of emotion recognition by several algorithms which classify three different emotional states(happiness, neutral, and surprise) using physiological features. Background: Recent emotion recognition studies have tried to detect human emotion by using physiological signals. It is important for emotion recognition to apply on human-computer interaction system for emotion detection. Method: 217 students participated in this experiment. While three kinds of emotional stimuli were presented to participants, ANS responses(EDA, SKT, ECG, RESP, and PPG) as physiological signals were measured in twice first one for 60 seconds as the baseline and 60 to 90 seconds during emotional states. The obtained signals from the session of the baseline and of the emotional states were equally analyzed for 30 seconds. Participants rated their own feelings to emotional stimuli on emotional assessment scale after presentation of emotional stimuli. The emotion classification was analyzed by Linear Discriminant Analysis(LDA, SPSS 15.0), Support Vector Machine (SVM), and Multilayer perceptron(MLP) using difference value which subtracts baseline from emotional state. Results: The emotional stimuli had 96% validity and 5.8 point efficiency on average. There were significant differences of ANS responses among three emotions by statistical analysis. The result of LDA showed that an accuracy of classification in three different emotions was 83.4%. And an accuracy of three emotions classification by SVM was 75.5% and 55.6% by MLP. Conclusion: This study confirmed that the three emotions can be better classified by LDA using various physiological features than SVM and MLP. Further study may need to get this result to get more stability and reliability, as comparing with the accuracy of emotions classification by using other algorithms. Application: This could help get better chances to recognize various human emotions by using physiological signals as well as be applied on human-computer interaction system for recognizing human emotions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.5
• /
• pp.1047-1054
• /
• 2012

Atrial fibrillation (AF) is the most common arrhythmia encountered in clinical practice, and its risk increases with age. Conventionally, the way of detecting AF was the time·frequency domain analysis of RR variability. However, the detection of ECG signal is difficult because of the low amplitude of the P wave and the corruption by the noise. Also, the time·frequency domain analysis of RR variability has disadvantage to get the details of irregular RR interval rhythm. In this study, we describe an atrial fibrillation pattern analysis based on symbolization and information entropy. We transformed RR interval data into symbolic sequence through differential partition, analyzed RR interval pattern, quantified the complexity through Shannon entropy and detected atrial fibrillation. The detection algorithm was tested using the threshold between 10ms and 100ms on two databases, namely the MIT-BIH Atrial Fibrillation Database.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.450-460
• /
• 2017

T wave is cardiac parameters that represent ventricular repolarization, it is very important to diagnose arrhythmia. Several methods for detecting T wave have been proposed, such as frequency analysis and non-linear approach. However, detection accuracy is at the lower level. This is because of the overlap of the P wave and T wave depending on the heart condition. We propose T wave detection algorithm based on target area extraction through QRS cancellation and moving average. For this purpose, we detected Q, R, S wave from noise-free ECG(electrocardiogram) signal through the preprocessing method. And then we extracted P, T target area by applying decision rule for four PAC(premature atrial contraction) pattern another arrhythmia through moving average and detected T wave using RT interval and threshold of RR interval. The performance of T wave detection is evaluated by using 48 record of MIT-BIH arrhythmia database. The achieved scores indicate the average detection rate of 95.32%.