DTW 최소누적거리를 이용한 심전도 이상 검출 알고리즘 구현 및 평가

노윤홍 ( Yun Hong Noh ),이영동 ( Young Dong Lee ),정도운 ( Do Un Jeong ) 한국센서학회 2012 센서학회지 Vol.21 No.1

Recently the convergence of healthcare technology is used for daily life healthcare monitoring. Cardiac arrhythmia is presented by the state of the heart irregularity. Abnormal heart`s electrical signal pathway or heart`s tissue disorder could be the cause of cardiac arrhythmia. Fatal arrhythmia could put patient`s life at risk. Therefore arrhythmia detection is very important. Previous studies on the detection of arrhythmia in various ECG analysis and classification methods had been carried out. In this paper, an ECG signal processing techniques to detect abnormal ECG based on DTW minimum accumulation distance through the template matching for normalized data and variable threshold method for ECG R-peak detection. Signal processing techniques able to determine the occurrence of normal ECG and abnormal ECG. Abnormal ECG detection algorithm using DTW minimum accumulation distance method is performed using MITBIH database for performance evaluation. Experiment result shows the average percentage accuracy of using the propose method for Rpeak detection is 99.63 % and abnormal detection is 99.60 %.

A New Method of ECG Feature Detection Based on Combined Wavelet Transform for u-health Service

김윤년,김민수,서석태,조영창,손창식 대한의용생체공학회 2011 Biomedical Engineering Letters (BMEL) Vol.1 No.2

Purpose The analysis of the ECG is required of accuracy for diagnosing many cardiac diseases. In this work, we propose an algorithm using wavelet transform to analyze and classify ECG (electrocardiogram) signal obtained from the developed patch type electrode. This paper presents a new combined wavelet transform artificial neural network (CWTANN) based system for classification and detection of QRS complex, P and T waves. CWTANN provided useful information for detection of cardiac disease or abnormality. Methods In this paper, we proposed a method to detect characteristic waves, such as P, QRS and T wave from abnormal ECG signal. Daubechies, Coiflets and Symlets order 5 wavelet transform were applied to the ECG. The methods have been proven out for detection of normal signal,ventricular tachycardia (VT) and PVC (premature ventricular contraction) in the ECG through subband decomposition and combined wavelet transform. Results From the results, the detection rate achieved was 96.2% for off-line classification, which is indeed a good rate of accuracy for data recognition. Using the simple proposed wavelet scheme, the developed methodology achieves higher detection rates. Conclusions The proposed ECG detection method can be used P, QRS, T wave detection by sum of combined scale using DWT. Thus the clinical use of the methodology is to be beneficial in the analysis of various heart diseases. The new CWTANN method is expected used in monitoring of ECG for mobile home healthcare applications.

랜덤 포레스트를 이용한 감정인식 결과를 바탕으로 스마트폰 중독군 검출

이진규,강현우,강행봉,Lee, Jin-Kyu,Kang, Hyeon-Woo,Kang, Hang-Bong 한국전기전자학회 2015 전기전자학회논문지 Vol.19 No.2

최근 기술의 발달로 국내에 10명 중 8명은 스마트폰을 사용하고 있다. 또한, 스마트폰을 이용한 다양한 어플리케이션들이 개발되었다. 이로 인해, 스마트폰 중독현상이 사회적인 문제로 대두되고 있다. 특히, 스마트폰 중독은 스스로가 조절하기 어렵고, 자각하기 힘들다. 주로 설문지를 중심으로한 연구들에서, 스마트폰 중독을 진단하기 위해 예를 들면 S-척도와 같은 연구를 수행해왔다. 본 연구에서는 ECG(심전도)와 Eye Gaze 신호를 이용한 검출 방법을 제안하고자 한다. 피험자가 감정 영상을 시청했을 때, 피험자의 ECG 신호와 Eye Gaze 신호를 각각 Shimmer와 스마트아이를 이용하여 측정한다. 더불어, ECG 신호의 S-transform 결과를 특징으로 추출한다. 또한 동공의 직경, 시선과의 거리, 눈 깜빡임으로 구성된 Eye Gaze 신호로부터 12개의 특징을 추출한다. 분류기는 랜덤 포레스트를 이용하여 학습시키고 피험자의 데이터를 이용하여 스마트폰 중독군을 검출한다. 검출한 결과와 실험 전 진행한 S-척도 결과와 비교한 결과 ECG는 87.89%의 정확도, Eye Gaze는 60.25%의 정확도를 보여주는 것을 알 수 있었다. Recently, eight out of ten people have smartphone in Korea. Also, many applications of smartphone have increased. So, smartphone addiction has become a social issue. Especially, many people in smartphone addiction can't control themselves. Sometimes they don't realize that they are smartphone addiction. Many studies, mostly surveys, have been conducted to diagnose smartphone addiction, e.g. S-measure. In this paper, we suggest how to detect smartphone addiction based on ECG and Eye Gaze. We measure the signals of ECG from the Shimmer and the signals of Eye Gaze from the smart eye when the subjects see the emotional video. In addition, we extract features from the S-transform of ECG. Using Eye Gaze signals(pupil diameter, Gaze distance, Eye blinking), we extract 12 features. The classifier is trained using Random Forest. The classifiers detect the smartphone addiction using the ECG and Eye Gaze signals. We compared the detection results with S-measure results that surveyed before test. It showed 87.89% accuracy in ECG and 60.25% accuracy in Eye Gaze.

PPG와 ECG의 상관 관계에 기반한 심박 시계열 데이터 이상 상황 탐지 최적 모델 비교 연구

김진수,이강윤 한국인터넷정보학회 2019 인터넷정보학회논문지 Vol.20 No.6

This paper Various services exist to detect and monitor abnormal event. However, most services focus on fires and gas leaks. so It is impossible to prevent and respond to emergency situations for the elderly and severely disabled people living alone. In this study, AI model is designed and compared to detect abnormal event of heart rate signal which is considered to be the most important among various bio signals. Specifically, electrocardiogram (ECG) data is collected using Physionet's MIT-BIH Arrhythmia Database, an open medical data. The collected data is transformed in different ways. We then compare the trained AI model with the modified and ECG data. 본 논문은 이상 상황을 탐지하고 모니터링하는 다양한 서비스가 존재한다. 하지만 대부분의 서비스는 화재, 가스누출에 초점을 맞추어 진행되고 있으며, 독거노인과 중증장애인들의 사망 혹은 심정지 등 위급상황에 대하여 사전 예방 및 위급상황 대응이 불가능하다. 본 연구에서는 여러 생체신호 중 가장 위중하다고 판단되는 심박 신호의 이상 상태를 탐지하기 위하여 인공지능 모델을 설계하는 과정에서 적합한 데이터 변형과 모델을 비교한다. 세부적으로는 오픈 의료 데이터 PhysioNet의 MIT-BIH Arrhythmia Database를 이용하여 심전도(ECG) 데이터를 수집하고, 수집한 데이터를 각각 다른 방법으로 데이터를 변형한 후 학습하여 기본 심전도 데이터를 이용해 학습한 인공지능 모델과 비교한다.

비특이적인 증상을 나타내는 허혈성(虛血性) 심질환(心疾患) 진단 2례

백종우,정기용,하유군,박종형,전찬용,최유경,Baik, Jong-Woo,Jung, Ki-Yong,Hsia, Yu-Chun,Park, Jong-Hyeong,Jeon, Chan-Yong,Choi, You-Kyung 대한한방내과학회 2008 大韓韓方內科學會誌 Vol.29 No.4

Objectives : Oriental medical doctors usually use the three-finger pulse diagnosis method to observe disease. Since it is difficult to diagnose ischemic heart disease (IHD) objectively by this diagnostic method, we performed the study to diagnose it as soon as possible by using Yuk Bu Jung Wee Jin Mac(六部定位診脈) and electrocardiogram(ECG). Methods : Patients who had abdominal discomfort were observed by Yuk Bu Jung Wee Jin Mac(六部定位診脈) and we presumed they had heart disease and checked them with electrocardiogram(ECG). Results : We diagnosed it early by using Yuk Bu Jung Wee Jin Mac(六部定位診脈) and electrocardiogram (ECG). Conclusions : The study suggests that it is easy to diagnose IHD early using Yuk Bu Jung Wee Jin Mac(六部定位診脈) and ECG. More data related to IHD is needed.

A Wearable Electrocardiogram (ECG) Measurement Device for Using a Daily Life

ChanYoung Hahm,SeungYun Nam,SeokHee Lee,HyunSoon Shin 중소기업융합학회 2015 중소기업융합학회 국제학술대회논문집 Vol.2 No.1

There is a need to be small and low power for wearable healthcare system for using a daily life. In this paper, we present the PCB minimized while a user wearing the device carries out our daily activities. Although the device consists of a wireless communication, microcontroller for controlling and analog to digital converting, and analog front end (AFE), we report the only results of AFE for amplifying and filtering of the electrocardiogram. To confirm the quality of the AFE, we use the ECG source signal, electrocardiogram emulator, MiniSim 1000 by Netech Corp., and the function generator for measuring the each function.

감성을 평가하기 위한 생체신호 분석 시스템에 관한 연구

이지형(Ji-Hyeoung Lee),김경호(Kyung-Ho Kim) 한국컴퓨터정보학회 2010 韓國컴퓨터情報學會論文誌 Vol.15 No.12

본 논문에서는 일상생활 속에서 무자각적으로 생체신호를 측정하고 분석하여 감성을 평가할 수 있는 임베디드 시스템에 관하여 연구하였다. 지속적으로 변화하는 감성을 일관적이며 신뢰성이 높은 생리적인 방법으로 평가하기 위해 심전도(ECG:Electrocardiogram), 맥파(PPG:Photoplethysmography)의 두 가지 생체신호를 측정하고, 무선전송(Bluetooth) 장치를 이용하여 측정한 생체신호를 실시간으로 노트북PC로 전송하여 분석하였다. 생체신호의 분석방법은 고속 퓨리에 변환(FFT:Fast Fourier Transform)과 전력 스펙트럼 밀도(PSD:Power Spectrum Density)를 이용한 주파수 분석방법으로 두 생체신호의 특정 주파수 대역이 가지는 자율신경계의 활성도의 비율을 분석하여 비교 연구하였다. 또한 보다 빠르고 정확한 감성을 평가하기 위하여 분석 알고리즘의 연산을 최소화 하였으며 그래프를 이용한 분석결과의 시각화를 하였다. 본 논문에서는 무자각적인 생체 신호 측정 시스템을 이용하여 다양한 상황에서 생체신호를 측정하고, 개발한 분석 알고리즘으로 분석한 결과의 차이를 연구하여 정확도 및 신뢰도를 기준으로 감성을 평가하기 위한 분석 시스템을 평가하였다. In this paper, we studied about the Embedded System of the biosignal measurement and analysis to sensibility evaluation in daily life for non-intrusive. This system is two kinds of measuring biosiganls(Electrocardiogram:ECG, Photoplethysmography:PPG) and analyzed by real-time wireless transmission to notebook PC using bluetooth for consistent and reliability of physiological way to assess continuously changing sensibility. Comparative studied of an autonomic nerve system activity ratio on characteristics frequency band of two kinds of biosignal analyzed frequency way using the Fast Fourier Transform(FFT) and Power Spectrum Density(PSD). Also the key idea of this system is to minimize computing of analysis algorithm for faster and more accurate to assess the sensibility, and the result of the visualization using graph. In this paper, we evaluated the analysis system to assess sensibility that measuring various situation in daily life using a non-intrusive biosignal measurement system, and the accuracy and reliability in comparison with difference of result by development analysis system.

말하기 불안의 분석 모형 연구

김평원 ( Pyoung Won Kim ) 국어교육학회 2011 國語敎育學硏究 Vol.40 No.-

말하기 불안 현상을 이해하고 이를 극복하는 전략이 말하기 교육의 중요한 내용임은 주지의 사실이다. 하지만 현행 말하기 교육에서는 말하기 불안의 원인을 소개하고 이를 극복하기 위한 상식적인 수준의 내용을 소개하는데 그치고 있다. 이는 말하기 수행 과정을 말하기 불안 측면에서 구체적으로 분석하고 논의할 수 있는 이론적 모형이 없었기 때문이다. 본 연구의 목적은 말하기 불안과 관련된 교육 내용을 구안하는 것으로 구체적으로 말하기 불안 현상을 가시적으로 확인하고 교육할 수 있는 이론적 모형을 확립하는 것이다. 본 연구에서는 말하기 불안을 분석할 수 있는 방안으로 심전도룰 활용한 말하기 불안 분석 모형을 제안하였다. 말하기 불안의 측정은 의학적 개념이 개입됨으로 인해 그 동안 많은 사람들이 논의 자체를 기피해 왔다는 점에 주목하여, 이를 쉽게 이해하고 분석할 수 있는 방법과 모형을 구안하는 데 중점을 두었다. 말하기 불안을 가시적으로 이해하고 분석하는데 필요한 심전도 분석은 차후 말하기 불안과 관련된 교육 내용에 반영할 수 있음을 염두에 두고, 3단계에 걸쳐 설명하였다. 첫째 단계는 말하기 불안이 자율신경계에 반영되는 것임을 이해하는 것이고, 둘째 단계는 심전도 파형의 R-R간격 분석을 토대로 말하기 불안 양상을 분석하는 방법을 이해하는 것이며, 마지막 단계는 대표적인 유형으로 정리한 교육적 모형을 이해하는 것이다. 본 연구의 의의는 자율신경계의 반응을 말하기 불안의 지표로서 분석할 수 있는 이론적 모형을 제시하여 말하기 불안을 가시적이고 과학적으로 이해하고 분석하기 위한 전략을 구안했다는 데 있다. It is very important to understand what speech anxiety is and to overcome it in a speaking education. However, current speaking education only shows the cause of speech anxiety and how to get over it at a low level. That is because there has been no specific theory to analyze and discuss the speaking process with regard to anxiety. This study is for framing a draft of the education related to speech anxiety, which establishes a theoretical model to give a perceptible indication of speech anxiety. This study suggests the analysis model of speech anxiety by means of ECG(electrocardiogram)to examine speech anxiety. There have been few people who has tried to measure speech anxiety because it is associated with medical examination. This research puts emphasis on setting up a simple and comprehensible model to analyze. Speech anxiety is explained by three steps, considering that the ECG result will be adapted to the education related to speech anxiety in the future. The first step is to understand that there is a link between speech anxiety and the autonomic nervous system. The second step is to comprehend the process of analyzing speech anxiety on the basis of ECG. The third step is to understand the education model which is comprehended through the representative types. This study has significance because it suggests a theoretical model that serves as an index in which the response in the autonomic nervous system is analyzed and a comprehensible strategy for analyzing speech anxiety is built.

Neural Networks-Based Method for Electrocardiogram Classification

Maksym Kovalchuk,Viktoriia Kharchenko,Andrii Yavorskyi,Igor Bieda,Taras Panchenko International Journal of Computer ScienceNetwork S 2023 International journal of computer science and netw Vol.23 No.9

Neural Networks are widely used for huge variety of tasks solution. Machine Learning methods are used also for signal and time series analysis, including electrocardiograms. Contemporary wearable devices, both medical and non-medical type like smart watch, allow to gather the data in real time uninterruptedly. This allows us to transfer these data for analysis or make an analysis on the device, and thus provide preliminary diagnosis, or at least fix some serious deviations. Different methods are being used for this kind of analysis, ranging from medical-oriented using distinctive features of the signal to machine learning and deep learning approaches. Here we will demonstrate a neural network-based approach to this task by building an ensemble of 1D CNN classifiers and a final classifier of selection using logistic regression, random forest or support vector machine, and make the conclusions of the comparison with other approaches.

웨어러블 심전도 측정과 임상 심전도 측정과의 상관관계에 대한 연구

이강휘(Kang-Hwi Lee),이성수(Seong-Su Lee),김상민(Sang-Min Kim),이혁재(Hyeok-Jae Lee),민경진(Kyoung-Jin Min),강현규(Hyun-Kyu Kang),이주현(Joo-Hyeon Lee),곽휘권(Hwy-Kuen Kwak),고윤수(Yun-Soo Ko),이정환(Jeong-Whan Lee) 대한전기학회 2018 전기학회논문지 Vol.67 No.12

Recent advances in ICT technology have transformed many of our daily lives and attracted a lot of attention to personal health. Heart beat measurement that reflects cardiac activities has been used in various fields such as exercise evaluation and psychological state evaluation for a long time, but its utilization method is limited due to its differentiation from clinical electrocardiogram. Therefore, in this study, we could observe the change of the measured signal according to the change of the distance and the position of the measuring electrodes which are non-standard electrode configuration. Based on the electric dipole model of the heart, correlation with clinical electrocardiogram could be confirmed by synthesizing multiple surface potentials measured with a shorter electrode distance than standard one. From the electromagnetic point of view, the distance between the measuring electrodes corresponds to the distance that the electric potential by the cardiac electric dipole moves, and the electric potential measured at the body surface is proportional to the moving distance of the electric potential. Therefore, it is preferable to make the distance between electrodes as long as possible, and to position the measuring electrode close to the ventricle rather than the atrium. In addition, it was found that standard electrocardiographic waveforms could be synthesized by using arithmetic sum of multiple measuring electrodes due to the relationship of electrical dipole vectors, which is obtained by dividing and positioning a plurality of measuring electrodes on a reference electrode line, such as Lead-I, Lead-II direction. Also, we obtained a significant Pearson correlation coefficient (r = 0.9113 ± 0.0169) as a result of synthetic experiments on four subjects.