• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.37-43
• /
• 2020

Recently, many researches have been actively to diagnose symptoms of heart disease using ECG signal, which is an electrical signal measuring heart status. In particular, the electrocardiogram signal can be used to monitor and diagnose arrhythmias that indicates an abnormal heart status. In this paper, we proposed 1-D convolutional neural network for arrhythmias classification systems. The proposed model consists of deep 11 layers which can learn to extract features and classify 5 types of arrhythmias. The simulation results over MIT-BIH arrhythmia database show that the learned neural network has more than 99% classification accuracy. It is analyzed that the more the number of convolutional kernels the network has, the more detailed characteristics of ECG signal resulted in better performance. Moreover, we implemented a practical application based on the proposed one to classify arrythmias in real-time.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.328-330
• /
• 2004

In this paper, ECG based cardiac disease diagnosis models are developed. Conventionally, ECG monitoring equipments can only measure and store ECG signals and they always require medical doctor's diagnosis actions which are not desirable for continuous ambulatory monitoring and diagnosis healthcare systems. In this paper, two kinds of neural based self cardiac disease diagnosis engines are developed and tested for four kinds of diseases, sinus bradycardia, sinus tachycardia, left bundle branch block and right bundle branch block. For diagnosis engines, error backpropagation neural network (BP) and probabilistic neural network (PNN) were applied. Five signal features including heart rate, QRS interval, PR interval, QT interval, and T wave types were selected for diagnosis characteristics. To show the validity of proposed diagnosis engine, MIT-BIH database were used to test. Test results showed that BP based diagnosis engine has 71% of diagnosis accuracy which is superior to accuracy of PNN based diagnosis engine. However, PNN based diagnosis engine showed superior diagnosis accuracy for complex-disease diagnoses than BP based diagnosis engine.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.6
• /
• pp.67-75
• /
• 1993

ECG pattern was classified using a back-propagation neural network. An improved feature extractor of ECG is proposed for better classification capability. It is consisted of preprocessing ECG signal by an FIR filter faster than conventional one by a factor of 5. QRS complex recognition by moving-window integration, and peak extraction by quadratic approximation. Since the FIR filter had a periodic frequency spectrum, only one-fifth of usual processing time was required. Also, segmentation of ECG signal followed by quadratic approximation of each segment enabled accurate detection of both P and T waves. When improtant features were extracted and fed into back-propagation neural network for pattern classification, the required number of nodes in hidden and input layers was reduced compared to using raw data as an input, also reducing the necessary time for study. Accurate pattern classification was possible by an appropriate feature selection.

• Journal of Veterinary Clinics
• /
• v.30 no.6
• /
• pp.456-458
• /
• 2013

The aim of this study is to evaluate the reference value for electrocardiogram in healthy captive raccoon dogs. Forty-one free-ranging adult raccoon dogs rescued from Wildlife rescue centre, Kangwon National University were enrolled in this study. The 6-lead electrocardiogram was obtained in all raccoon dogs without any chemical restraints. The mean heart rate was $146.10{\pm}43.31$ beats/min (95% confidence interval 132.84~159.36 beats/min). The mean respiration rate was $35.73{\pm}11.56$ breaths/min (95% confidence interval 32.19~39.27 breaths/min). The mean systolic blood pressure was $136{\pm}29.26$ mmHg (95% confidence interval 127.99~145.91 mmHg). Electrocardiographical features were also evaluated in all raccoon dogs. The mean duration and amplitude of P-wave were $38.2{\pm}4.0$ ms (range 28-40 ms) and $0.128{\pm}0.039$ mV (range 0.09~0.20). The mean duration and amplitude of QRS complexes were $48.5{\pm}7.2ms$ (range 36-60 ms) and $1.330{\pm}0.650$ mV (range 0.15~2.30). The range of the mean electrical (QRS) axis was $-91^{\circ}{\sim}+96^{\circ}$ ($10^{\circ}{\sim}60^{\circ}$; 95% of confidence interval). The mean corrected QT (QTc) interval was $273.7{\pm}32.7ms$ (range 212-333 ms), while the mean PR interval was $76.1{\pm}10.0ms$ (range 50-82 ms). To the authors' knowledge, this is the first study to provide references in electrocardiogram (ECG) in healthy captive raccoon dogs.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.1
• /
• pp.31-38
• /
• 2013

Patients with heart disease need long-term monitoring of the electrocardiogram (ECG) signal using a portable electrocardiograph. This trend requires the miniaturization of data storage and faster transmission to medical doctors for diagnosis. The ECG signal needs to be utilized for efficient storage, processing and transmission, and its data must contain the important components for diagnosis, such as the P wave, QRS-complex, and T wave. In this study, we select the vertex which has a larger curvature value than the threshold value for compression. Then, we reconstruct the compressed signal using by radial basis function interpolation. This technique guarantees a lower percentage of root mean square difference with respect to the extracted sample points and preserves all the important features of the ECG signal. Its effectiveness has been demonstrated in the experiment using the Massachusetts Institute of Technology and Boston's Beth Israel Hospital arrhythmia database.

• Journal of Multimedia Information System
• /
• v.7 no.3
• /
• pp.231-238
• /
• 2020

This work presents a fully analog baseline wander tracking and removal circuitry using high-pass filter (HPF) based R-peak detection and quadratic interpolation that does not require digital post processing, thus suitable for compact and low power long-term ECG monitoring devices. The proposed method can effectively track and remove baseline wander in ECG waveforms corrupted by various motion artifacts, whereas minimizing the loss of essential features including the QRS-Complex. The key component for tracking the baseline wander is down sampling the moving average of the corrupted ECG waveform followed by quadratic interpolation, where the R-peak samples that distort the baseline tracking are excluded from the moving average by using a HPF based approach. The proposed circuit is designed using CMOS 0.18-㎛ technology (1.8V supply) with power consumption of 19.1 ㎼ and estimated area of 15.5 ㎟ using a 4^th order HPF and quadratic interpolation. Results show SNR improvement of 10 dB after removing the baseline wander from the corrupted ECG waveform.

• Journal of Biomedical Engineering Research
• /
• v.41 no.1
• /
• pp.42-47
• /
• 2020

A personal authentication system based on biosignals has received increasing attention due to its relatively high security as compared to traditional authentication systems based on a key and password. Electrocardiography (ECG) measured from the chest or wrist is one of the widely used biosignals to develop a personal authentication system. In this study, we investigated the feasibility of using similar ECG measured behind the ears to develop a personal authentication system. To this end, similar ECGs were measured from thirty subjects using a pair of three electrodes attached behind each of the ears during resting state during which the standard Lead-I ECG was also simultaneously measured from both wrists as baseline ECG. The three ECG components, Q, R, and S, were extracted for each subject as classification features, and authentication accuracy was estimated using support vector machine (SVM) based on a 5×5-fold cross-validation. The mean authentication accuracies of Lead I-ECG and similar ECG were 90.41 ± 8.26% and 81.15 ± 7.54%, respectively. Considering a chance level of 3.33% (=1/30), the mean authentication performance of similar ECG could demonstrate the feasibility of using similar ECG measured behind the ears on the development of a personal authentication system.

• Journal of Veterinary Clinics
• /
• v.31 no.4
• /
• pp.325-328
• /
• 2014

A 8-month-old female Maltese dog was presented with a history of heart murmur. In physical examination, grade 4/6 systolic murmur heard at the left heart base. Electrocardiography showed sinus arrhythmia, right axis deviation, deep S wave and splintered QRS complex. Thoracic radiography revealed enlarged right side heart and bulging of the main pulmonary artery. Echocardiography showed mild hypertrophy of right ventricle, a supravalvular stenosis, marked post-stenotic dilation of the main pulmonary artery and a moderately increased pulmonary arterial velocity through the stenotic area (4.4 m/s, pressure gradient of 78.7 mmHg). The dog was diagnosed with supravalvular pulmonic stenosis based on the diagnostic imaging findings. Medical management using ${\beta}1$-blocker and ACE inhibitor was started in this dog and this is first case report described diagnostic characteristic features of supravalvular pulmonic stenosis in korea.

• Tuberculosis and Respiratory Diseases
• /
• v.50 no.1
• /
• pp.106-116
• /
• 2001

Background : Pulmonary thromboembolism is relatively frequent and potentially fatal. However, it is commonly misdiagnosed. The incidence of pulmonary thromboembolism is not decreasing despite advances in diagnosis and effective prophylatic measures. Its potential for significant sequela necessitates a prompt diagnosis and treatment. Unfortunately, there are many difficulties and problems regarding accurate diagnosis. There is a low prevalence of deep vein thrombosis and pulmonary thromboembolism in Korea and only few reports on this subject are available. Method : The clinical features of 36 patients, who were diagnosed with pulmonary thromboembolism at the Korea University medical center, were reviewed. Results : 1) There was no significant difference in prevalence between men an women, and the mean age was 50.9 years in men 59.2 years in women. 2) The frequent causes of pulmonary thromboembolism were malignancies (22.2%), surgery (22.2%), and heart disease(8.2%). Specific causes were not identified in 33.3%. 3) The most common symptom was dyspnea(72.2%), and the most common sign was tachypnea(61.1%). 4) The EKG findings were normal in 28.6%, an S1Q3T3 pulmonale pattern in 25.7%, ST or QRS changes in others. 5) The chest X-ray findings indicated pulmonary infiltration in 37.5%, cardiomegaly in 15.6%, pleural effusion in 12.5%, and normal in 27.8%. The perfusion lung scan showed a high probability in 66.7%, and intermediate or low probability in 33.3%. 6) The pulmonary arterial pressure(PAP) in the high probability groups was 57.9mmHg with a higher mortality rate(35%). Conclusion : Pulmonary thromboembolism is not uncommon in Korea and its clinical features do not differ greatly from thase reported in the literature. When pulmonary thromboemblism of unknown causes are diagnosed, a search for an occult malignancy is recommended. Rapid diagnosis and treatment are achieved when thromboemblism is suspected.

• Journal of The Korean Society of Clinical Toxicology
• /
• v.9 no.1
• /
• pp.20-25
• /
• 2011

Purpose: This study was designed to analyze the contributing factors, as well as the incidence and nature of the cardiac toxicity, in patients presenting with diphenhydramine overdose. Methods: We retrospectively reviewed the medical records of the intoxicated patients who presented to the ED of Korea University Anam Hospital from January 2008 to December 2010. Those patients who visited due to a diphenhydramine overdose were selected and the following features were recorded for analysis: the general characteristics, vital signs, the amount of ingested diphenhydramine, the time interval from ingestion to presentation, the coingested drugs (if any), the toxicities and the ECG findings. Cardiac toxicity, while defined mainly in terms of the temporary ECG changes such as QTc prolongation, right axis deviation, QRS widening, high degree AV block and ischemic changes, also encompassed cardiogenic shock, which is a clinical finding. Results: A total of eighteen patients were enrolled. Of the eighteen patients, eight had ingested diphenhydramine only, while ten had ingested other drugs in addition to diphenhydramine. The most commonly observed toxicity following diphenhydramine overdose included cardiac toxicity (78%). Cardiac toxicity was observed in all the patients who presented to the emergency department 2 hours after ingestion. The patients with QTc prolongation turned out to have ingested significantly larger amounts of diphenhydramine. Conclusion: QTc prolongation and right axis deviation were common findings for the patients with a diphenhydramine overdose. QTc prolongation was more likely to occur with ingesting larger amounts of diphenhydramine. Close monitoring is mandatory for patients who have ingested large amounts of diphenhydramine to prevent such potentially lethal cardiac toxicity.