• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권3호
• /
• pp.204-210
• /
• 2011

This paper proposes a fuzzy support vector machine ($FSVM_n$) pattern classifier to classify the arrhythmia patterns of an electrocardiograph (ECG). The $FSVM_n$ is a pattern classifier which combines n-dimensional fuzzy membership functions with a slack variable of SVM. To evaluate the performance of the proposed classifier, the MIT/BIH ECG database, which is a standard database for evaluating arrhythmia detection, was used. The pattern classification experiment showed that, when classifying ECG into four patterns - NSR, VT, VF, and NSR, VT, and VF classification rate resulted in 99.42%, 99.00%, and 99.79%, respectively. As a result, the $FSVM_n$ shows better pattern classification performance than the existing SVM and FSVM algorithms.

• 한국간호교육학회지
• /
• 제20권1호
• /
• pp.60-70
• /
• 2014

Purpose: Bedside electrocardiograph (ECG) monitoring is continuously used for assessing patients' cardiac status in intensive care units. However, it has not been explored whether it is used with proper knowledge and nursing practices; if not, its usage will be limited and the risk for compromised patient safety might be significant. This study, therefore, explored knowledge and nursing practices regarding bedside ECG monitoring in nurses working at intensive care units. Methods: Participants in this survey research were a convenience sample of 156 nurses from 25 intensive care units distributed in five hospitals with more than 1,000 beds each in Seoul, South Korea. Results: Participants showed limited and incorrect knowledge and nursing practices. Only 4 (2.6%) participants correctly answered to all electrode placement sites of RA, LA, LL, and V1. Lead II was the most frequently monitored unit regardless of the main purpose of ECG monitoring, and nursing practices to manage noisy signals did not include skin care at the top priorities. Conclusion: Educators and clinicians alike need to make an effort to ensure that a safe level of knowledge and practices for the monitoring is maintained in order to make sure that patient outcomes are not compromised.

• 한국산학기술학회논문지
• /
• 제9권5호
• /
• pp.1130-1133
• /
• 2008

본 논문에서는 일반 9V 알카라인 배터리로 동작하는 초소형 심전도계를 설계 및 구현하였다. 제작된 심전도계는 심장신호를 검출하고 증폭하기 위한 계측 증폭단, 고역통과필터, 저역통과필터, 미분회로 및 피크검출기로 구성하였다. 세 개의 전극을 통해 검출된 심장신호는 오실로스코프 상에 깨끗한 파형으로 표현되었으며, 이를 통해 완성된 심전도계가 정상적으로 잘 동작함을 알 수 있었다. 제작된 심전도계는 감지된 심장신호를 디지털 데이터화하여 소형 LCD에 디스플레이함으로써 측정의 간편성 및 휴대성을 크게 개선할 수 있으며, 따라서 누구나, 언제, 어디서든 본인의 심장 상태를 쉽고 간편하게 체크할 수 있을 것이다.

• 대한의용생체공학회:의공학회지
• /
• 제21권4호
• /
• pp.345-351
• /
• 2000

본 연구는 심전신호와 부가정보 신호의 다중신호를 주파수분할 다중방식과 주파수변조에 의해 무선전송하기 위함이다. 심전신호는 전극으로부터 유도되고 아날로그 증폭기에 의해 증폭된다. 전극 전착부실, 간호사 호출 및 저전압 배터리 신호의 부가정보 신호는 서로 주파수가 중복되지 않도록 발진되고 주파수분할 다중방식에 의해 합성되어 주파수 변조된다. 주파수 변조된 신호는 콜피츠회로에 의해 발진된 기본 반송파로 주파수 변조되고 체배되어 송신 반송주파수로 변환된다. 수신된 신호는 슈퍼헤테로다인 방식에 의해 중간주파수로 변환되고 쿼드래처 복조기에 의해 주파수 변조된 신호는 복조된다. 펄스카운터와 저역통과필터에 의해 심전신호와 부가정보 신호들은 복조된다.

• ETRI Journal
• /
• 제29권4호
• /
• pp.530-532
• /
• 2007

This paper presents a simple method to implement a complete on-line portable wireless holter including an electrocardiogram (ECG) monitoring, processing, and communication protocol. The proposed algorithm significantly reduces the hardware resources of threshold estimation for ECG compression, using the standard deviation updated with each new input signal sample. The new method achieves superior performance in terms of hardware complexity, channel occupation and memory requirements, while keeping the ECG quality at a clinically acceptable level.

• 반도체디스플레이기술학회지
• /
• 제12권2호
• /
• pp.73-78
• /
• 2013

This paper proposes a portable electrocardiograph and smart device-based heart health monitoring and risk notification system. The proposed system consists of a portable electrocardiograph and a smart device for a system user, and a web-based monitoring system for observers. This system can improve the convenience and efficiency of measurement by using a light-weight portable electrocardiograph and a smart device. In addition, any authorized person such as caregiver or family member who is not related to medical institution can monitor users'heart health in real-time using the web-based monitoring system. Therefore, a user and authorized remote observers can efficiently monitor and manage user's heart health in daily-life even without any medical institution's help, and can preemptively deal with any possible dangerous situations, such as degeneration of a cardiac disorder and sudden cardiac death.

• 대한의용생체공학회:의공학회지
• /
• 제35권5호
• /
• pp.111-118
• /
• 2014

As assessment of quantitative energy expenditure for effective exercise is becoming more important, many researches about the monitoring system for exercise status or result have been actively carried out. In this case, however, bicycle riders feel restrained and uncomfortable because the riders should wear a belt-type electrocardiograph or a watch-type accelerometer or GPS system during the assessment of bicycle exercise. In this study, therefore, an electrocardiograph based on textile electrode was developed for measuring ECG and calculating heart rate from the bicycle rider without feeling restraint, and smartphone application was also developed for monitoring the heart rate.

• 융합신호처리학회논문지
• /
• 제16권1호
• /
• pp.29-34
• /
• 2015

The ECG(Electrocardiograph) ambulatory test as called Holter is performed usually to diagnose several heart diseases causing different arrhythmias. This paper exposes the insights of the design of a 10-lead ambulatory ECG recorder. Reducing the size and minimizing the power consumption of the ECG recorder are crucial to allow long recording time without causing discomfort to the patient. This paper proposes lower hardware design and differential compression algorithm to extend the maximum 72 hours recording time in consideration of smaller and light-weighted recorder size. The performance results by newly introduced compression algorithm are shown and discussed.

• 한국통신학회논문지
• /
• 제35권9B호
• /
• pp.1322-1329
• /
• 2010

As body sensor network (BSN) research becomes mature, the need for managing power consumption of sensor nodes has become evident since most of the applications are designed for continuous monitoring. Real time Electrocardiograph (ECG) analysis on sensor nodes is proposed as an optimal choice for saving power consumption by reducing data transmission overhead. Smart sensor nodes with the ability to categorize lately detected ECG cycles communicate with base station only when ECG cycles are classified as abnormal. In this paper, ECG classification algorithms are described, which categorize detected ECG cycles as normal or abnormal, or even more specific cardiac diseases. Our Euclidean distance (ED) based classification method is validated to be most power efficient and very accurate in determining normal or abnormal ECG cycles. A close comparison of power efficiency and classification accuracy between our ED classification algorithm and generalized linear model (GLM) based classification algorithm is provided. Through experiments we show that, CPU cycle power consumption of ED based classification algorithm can be reduced by 31.21% and overall power consumption can be reduced by 13.63% at most when compared with GLM based method. The accuracy of detecting NSR, APC, PVC, SVT, VT, and VF using GLM based method range from 55% to 99% meanwhile, we show that the accuracy of detecting normal and abnormal ECG cycles using our ED based method is higher than 86%.

• Journal of Multimedia Information System
• /
• 제3권2호
• /
• pp.1-8
• /
• 2016

In this paper, we propose a method to automatically diagnose various diseases. The input data consists of electrocardiograph (ECG) recordings. We extract R-to-R interval (RRI) signals from ECG recordings, which are preprocessed to remove trends and ectopic beats, and to keep the signal stationary. After that, we perform some prospective analysis to extract time-domain parameters, frequency-domain parameters, and nonlinear parameters of the signal. Those parameters are unique for each disease and can be used as the statistical symptoms for each disease. Then, we perform feature selection to improve the performance of the diagnosis classifier. We utilize the selected features to diagnose various diseases using machine learning. We subsequently measure the performance of the machine learning classifier to make sure that it will not misdiagnose the diseases. The first two steps, which are R-to-R extraction and preprocessing, have been successfully implemented with satisfactory results.