• International Journal of Contents
• /
• 제18권2호
• /
• pp.68-80
• /
• 2022

The health of the human heart is commonly measured using ECG (Electrocardiography) signals. To identify any anomaly in the human heart, the time-sequence of ECG signals is examined manually by a cardiologist or cardiac electrophysiologist. Lightweight anomaly detection on ECG signals in an embedded system is expected to be popular in the near future, because of the increasing number of heart disease symptoms. Some previous research uses deep learning networks such as LSTM and BiLSTM to detect anomaly signals without any handcrafted feature. Unfortunately, lightweight LSTMs show low precision and heavy LSTMs require heavy computing powers and volumes of labeled dataset for symptom classification. This paper proposes an ECG anomaly detection system based on two level BiLSTM for acceptable precision with lightweight networks, which is lightweight and usable at home. Also, this paper presents a new threshold technique which considers statistics of the current ECG pattern. This paper's proposed model with BiLSTM detects ECG signal anomaly in 0.467 ~ 1.0 F₁ score, compared to 0.426 ~ 0.978 F₁ score of the similar model with LSTM except one highly noisy dataset.

• 대한전기학회논문지
• /
• 제41권4호
• /
• pp.433-441
• /
• 1992

This paper describes an algorithm that can efficiently analyze the ECG signal using frame knowledge representation technique. Input to the analysis process is a set of significant points which have been extracted from an original sampled signal(lead II) by the syntactic peak recognition algorithm. The hierarchical property of ECG signal is represented by hierarchical AND/OR graph. The semantic information and constraints of the ECG signal are desctibed by frame. As the control mechanism for labeling points, the search mechanism with the mixed paradigms of data-driven and model driven hypothesis formation, scoring function, hypothesis modification network and instance inheritance are used. We used the CSE database in order to evaluate the performance of the proposed algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.575-579
• /
• 1990

This paper describes an algorithm that can efficiently analyze the multichannel ECG signal using the frame. The input is a set of significant features (points) which have been extracted from an original sampled signal by using the split-and-merge algorithm. A signal from each channel can be hierarchical ADN/OR graph on the basis of the priori knowledge for ECG signal. The search mechanisms with some heuristics and the mixed paradigms of data-driven hypothesis formation are used as the major control mechanisms. The mutual relations among features are also considered by evaluating a score based on the relational spectrum. For recognition of morphologies corresponding to OR nodes, an hypothesis modification strategy is used. Other techniques such as instance, priority update of prototypes, and template matching facility are also used. This algorithm exactly recognized the primary points and supporting points from the multichannel ECG signals.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1989년도 춘계학술대회
• /
• pp.19-22
• /
• 1989

This paper represents a syntactic peak detection algorithm which detects peaks in the ECG signal. In the algorithm, the input waveform is linearly approximated by "split-and-merge" method, and then each line segment is symbolized with primitive set. The peeks in the symbolized input waveform are recognized by the finite-state automata, which the deterministic finite-state language is parsed by. This proposed algorithm correctly detects peaks in a normal ECG signal as well as in the abnormal ECG signal such as tachycardia and the contaminated signal with noise.

• 디지털산업정보학회논문지
• /
• 제17권1호
• /
• pp.7-14
• /
• 2021

With the increased attention about healthcare and management of heart diseases, smart healthcare services and related devices have been actively developed recently. R wave is the largest representative signal among ECG signals. R wave detection is very important because it detects QRS pattern and classifies arrhythmia. Several R wave detection algorithms have been proposed with different features, but the remaining problem is their implementation in low-cost portable platforms for real-time applications. In this paper, we propose R wave detection based on optimal threshold and arrhythmia classification through QRS pattern considering complexity in smart healthcare environments. For this purpose, we detected R wave from noise-free ECG signal through the preprocessing method. Also, we classify premature ventricular contraction arrhythmia in realtime through QRS pattern. The performance of R wave detection and premature ventricular contraction arrhythmia classification is evaluated by using 9 record of MIT-BIH arrhythmia database that included over 30 premature ventricular contraction. The achieved scores indicate the average of 98.72% in R wave detection and the rate of 94.28% in PVC classification.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1284-1287
• /
• 1987

A method of quantitative electrocardiogram analysis, based on concepts drawn from syntactic pattern recognition theories, is described. The algorithm can be used for removing the Interference noises and base line drift as a filter function, and for reducing the number of points representing the digitized ECG waveform. The Parsing is performed with simple finite state automata inferred by experiments and suitable to be updated during experiment execution. Two parameters are utilized for defining the noise and these make the algorithm flexible. The examples for testing the algorithm is real ECG waveforms with noise. Some experimental results lire presented.

• 융합신호처리학회논문지
• /
• 제5권3호
• /
• pp.190-197
• /
• 2004

본 연구는 신경망에 근거한 패턴매칭 방법을 사용하여 일시적 허혈 에피소드의 자동예측을 다루고 있다. 다층 신경망을 학습하기 위한 알고리즘은 수정된 역전파 알고리즘으로서 이 알고리즘은 학습속도를 향상시키기 위해 뉴런간의 연결계수 뿐만 아니라 뉴런내 비선형 함수의 변수들도 갱신한다. 제안된 방법의 성능은 MIT/BIH long-term 데이터베이스의 심전도(ECG) 신호를 사용하여 평가하였다. 총 15 레코드(237 허혈 에피소드)에 대한 실험결과에 의하면 허혈 에피소드 예측의 평균 sensitivity와 specificity 각각 85.71%와 71.11%이다. 또한 제안된 방법은 실제 허혈 에피소드로부터 평균 45.53초 이전에 예측하였다. 이러한 결과는 패턴매칭 분류기로서의 신경망 접근방법이 일시적 허혈 에피소드예측에 유용한 도구로 사용될 수 있음을 의미한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.77.3-77
• /
• 2002

In this paper, the algorithm for detecting the transient change of ST-segment and the device for measuring ECG from patient without restriction of activity are introduced. ST-segment elevation and depression is considered as the main characteristic in diagnosis of myocardial ischemia, but the change of pattern is also important. To consider all of the former and the latter, we used polynomial approximation for diagnosis of ECG. The feature points(R, S and T are detected through the signal processing processes including wavelet transform, and then R-S and S-T are approximated to polynomial. This method allows comparison of two signals that have different sampling time or different numbers of...

• 전자공학회논문지CI
• /
• 제49권1호
• /
• pp.1-7
• /
• 2012

최근 새롭게 연구되는 심전도기반 바이오인식은 통상 고가의 심전도 측정 장비를 필요로 하고 측정방법에도 제한이 많아 실제 인식시스템으로 사용하기 위해서는 극복해야할 문제들이 많은 실정이다. 이에 본 논문에서는 심전도 바이오인식용 심전도 측정 하드웨어를 제작해 심전도 리드 I 파형을 이용한 바이오인식 시스템을 개발했다. 제작된 하드웨어는 측정자의 동적인 측정환경 및 파형왜곡 최소화를 고려해 설계된 필터가 적용되었고, 기준접점을 제거해 두 개의 전극만으로도 심전도 측정이 가능하도록 설계되어 측정자의 거부감을 줄일 수 있다. 제작된 하드웨어를 기반으로 17명의 측정자로부터 심전도 리드 I 파형을 수집했으며, 파형 추출 알고리즘을 개발해 각각의 단일 심전도 파형으로 분리했다. SVM(support vector machine) 분류기를 이용한 심전도 바이오인식 실험결과 민감도(sensitivity, SN) 98.59% 및 정확도(accuracy, ACC) 97.21% 의 성능을 보였다. 개발된 심전도 바이오인식 기술은 기존 심전도 바이오인식 대비 사용 편의성을 높였으며 저가의 하드웨어로 구현 가능하다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.868-871
• /
• 2006

Mortality of domestic people from cardiovascular disease ranked second, which followed that of from cancer last year. Therefore, it is very important and urgent to enhance the reliability of medical examination and treatment for cardiovascular disease. Heart Rate Variability (HRV) is the most commonly used noninvasive methods to evaluate autonomic regulation of heart rate and conditions of a human heart. In this paper, our aim is to extract a quantitative measure for HRV to enhance the reliability of medical examination for cardiovascular disease, and then develop a prediction method for extracting multi-parametric features by analyzing HRV from ECG. In this study, we propose a hybrid Bayesian classifier called FP-based Bayesian. The proposed classifier use frequent patterns for building Bayesian model. Since the volume of patterns produced can be large, we offer a rule cohesion measure that allows a strong push of pruning patterns in the pattern-generating process. We conduct an experiment for the FP-based Bayesian classifier, which utilizes multiple rules and pruning, and biased confidence (or cohesion measure) and dataset consisting of 670 participants distributed into two groups, namely normal and patients with coronary artery disease.