Best-First decision tree 기법을 적용한 심전도 데이터 분류기의 정확도 향상에 관한 연구

이현주 ( Hyunju Lee ),신동규 ( Dongkyoo Shin ),박희원 ( Heewon Park ),김수한 ( Soohan Kim ),신동일 ( Dongil Shin ) 한국인터넷정보학회 2011 인터넷정보학회논문지 Vol.12 No.6

심전도 질환 데이터는 일반적으로 분류기를 사용한 실험이 많다. 심전도 신호는 QRS-Complex와 R-R interval을 추출하는 경우가 많은데 본 실험에서는 R-R interval을 추출하여 실험하였다. 심전도 데이터의 분류기 실험은 일반적으로 SVM(Support Vector Machine)과 MLP(Multilayer Perceptron) 분류기로 수행되지만 본 실험은 정확도 향상을 위해 Random Forest 분류기 알고리즘 중 Decision Tree를 Best-First Decision Tree(B-F Tree)로 수정하여 실험하였다. 그리고 정확도 비교분석을 위해 SVM, MLP, RBF(Radial Basic Function) Network와 Decision Tree 분류기 실험을 같이 수행하였고, 동일한 데이터와 간격으로 실험한 타 논문의 결과와 비교해보았다. 수정한 Random Forest 분류기의 정확도를 다른 네 개의 분류기와 타 논문의 실험과 비교해보니 정확도 부분에서는 Random Forest가 가장 우수하였다. 본 실험의 전처리 과정은 대역통과 필터(Band-pass filter)를 사용하여 R-R interval을 추출하였는데 향후에는 정확한 간격을 추출하기 위한 필터의 연구가 사려된다. Cardiac disorder data are generally tested using the classifier and QRS-Complex and R-R interval which is used in this experiment are often extracted by ECG(Electrocardiogram) signals. The experimentation of ECG data with classifier is generally performed with SVM(Support Vector Machine) and MLP(Multilayer Perceptron) classifier, but this study experimented with Best-First Decision Tree(B-F Tree) derived from the Dicision Tree among Random Forest classifier algorithms to improve accuracy. To compare and analyze accuracy, experimentation of SVM, MLP, RBF(Radial Basic Function) Network and Decision Tree classifiers are performed and also compared the result of announced papers carried out under same interval and data. Comparing the accuracy of Random Forest classifier with above four ones, Random Forest is the best in accuracy. As though R-R interval was extracted using Band-pass filter in pre-processing of this experiment, in future, more filter study is needed to extract accurate interval.

심전도 R-R 간격 정보를 이용한 심실조기수축 부정맥 검출

윤태호(Yoon, Tae-Ho),이선주(Lee, Sun-Ju),김경섭(Kim, Kyeong-Seop),이정환(Lee, Jeong-Whan) 한국정보전자통신기술학회 2009 한국정보전자통신기술학회논문지 Vol.2 No.2

심실조기수축 (PVC: Premature Ventricular Contraction)은 성인에게서 가장 흔하게 발생되는 심장 부정맥 증상 중의 하나이다. 심실조기수축 부정맥이 자주 발현되는 사람의 경우 관상 동맥 질환, 고혈압 등의 심혈관계 질환이 진행되고 있을 가능성이 많고, 심실빈맥이나 심실세동으로 전이되는 경우에는 심정지 등을 유발하여 사망에 이르기 때문에 지속적으로 관찰이 필요한 증상이다. 따라서 본 연구에서는 심전도 신호의 R-R 간격 정보를 이용하여 심실조기수축 부정맥 증상을 실시간으로 검출할 수 있는 알고리즘을 구현하였으며, 또한 심전도 신호의 R-R 간격 정보와 R-peak의 진위성 여부를 판단하여 심실조기수축 및 심실조기수축 파형이 다발적으로 발생되는 PVC-RUNs를 효율적으로 검출할 수 있는 부정맥 진단 알고리즘을 제안하고자 하였다. This paper proposes a novel algorithm to assess the abnormal heart beats such as PVC (Premature Ventricular Contraction) and its subsequent RUNs. Our Arrhythmic detection scheme is based on only the R-R Interval features extracted from ECG waveforms and MIT-BIH arrhythmia database is evaluated to validate the efficiency of our algorithm in terms of sensitivity, specificity, FPR(%) and FNR(%).

심전도 신호에서 부정맥 환자의 R파 검출 알고리즘 연구

안세종(Ahn, Se-Jong),임창주(Lim, Chang-Joo),김용권(Kim, Yong-Gwon),정성택(Chung, Sung-Taek) 한국산학기술학회 2011 한국산학기술학회논문지 Vol.12 No.10

심전도는 다양한 형태의 전기적 신호로 이루어져 있으며, 이러한 신호들의 특징점을 분석함으로써 부정맥을 검출할 수 있다. 지금까지 부정맥 검출을 위한 특징점 추출 방법에 대하여 많은 연구가 이루어졌으나, 복잡한 연산과 정으로 실시간 연산 결과를 활용하는 휴대형 기기에는 부적합하다. 이와 같은 문제점을 해결하기 위하여 본 연구에서 는 환자의 R-R 간격과 QRS 너비의 정보를 이용하여 R파를 추출하였다. 우선 버터워스 필터를 이용하여 저주파 대역 의 잡음을 제거하였으며, R-R간격의 이동평균과 QRS 너비의 이동평균을 이용하여 R파를 추출하였다. 이에 대한 결 과 검증은 MIT-BIH 부정맥 데이터베이스의 데이터를 활용하여 실험하였으며, 제공된 데이터의 R파 위치와 제안한 알고리즘의 R파 위치를 비교하였다. 이에 대한 결과로는 제안한 알고리즘 방법이 우수한 검출 성능을 보였으며, 연산 과정에서도 효율적인 방법임을 확인 할 수 있었다. ECG consists of various types of electrical signal on the heart, and feature point of these signals can be detected by analyzing the arrhythmia. So far, feature points extraction method for the detection of arrhythmia done in the many studies. However, it is not suitable for portable device using real time operation due to complicated operation. In this paper, R-peak were extracted using R-R interval and QRS width informations on patients. First, noise of low frequency bands eliminated using butterworth filter, and the R-peak was extracted by R-R interval moving average and QRS width moving average. In order to verify, it was experimented to compare the R-peak of data in MIT-BIH arrhythmia database and the R-peak of suggested algorithm. As a results, it showed an excellent detection for feature point of R-peak, even during the process of operation could be efficient way to confirm.

IoT 환경에서 최적 R파 검출 및 최소 특징점 추출을 통한 향상된 PVC 분류방법

조익성,우동식 (사)디지털산업정보학회 2017 디지털산업정보학회논문지 Vol.13 No.4

Previous works for detecting arrhythmia have mostly used nonlinear method such as artificial neural network, fuzzy theory, support vector machine to increase classification accuracy. Most methods require higher computational cost and larger processing time. Therefore it is necessary to design efficient algorithm that classifies PVC(premature ventricular contraction) and decreases computational cost by accurately detecting minimal feature point based on only R peak through optimal R wave. We propose an optimal R wave detection and PVC classification method through extracting minimal feature point in IoT environment. For this purpose, we detected R wave through optimal threshold value and extracted RR interval and R peak pattern from noise-free ECG signal through the preprocessing method. Also, we classified PVC in realtime through RR interval and R peak pattern. The performance of R wave detection and PVC classification is evaluated by using record of MIT-BIH arrhythmia database. The achieved scores indicate the average of 99.758% in R wave detection and the rate of 93.94% in PVC classification.

$([r,s],[t,u])$-interval-valued intuitionistic fuzzy alpha generalized continuous mappings

박춘기 강원경기수학회 2017 한국수학논문집 Vol.25 No.2

In this paper, we introduce the concepts of $([r,s], [t,u])$-interval-valued intuitionistic fuzzy alpha generalized closed and open sets in the interval-valued intuitionistic smooth topological space and $([r,s], [t,u])$-interval-valued intuitionistic fuzzy alpha generalized continuous mappings and then investigate some of their properties.

심전도신호의 R-R 간격을 이용한 부정맥 구간 검출 알고리즘

김경호,이상운,김진영 통신위성ㆍ우주산업연구회 2014 한국위성정보통신학회논문지 Vol.9 No.1

심전도(electrocardiography, ECG)는 심장박동을 할 때, 발생하는 탈분극과 재분극으로 심장의 전위변화를 시간의 흐름에 따라 파형 으로 표현한 것이다. 의료기관에서는 심전도신호를 이용하여 환자의 심장질환을 진단한다. 일반적으로 사람의 정상적인 심장박동 수는 1분에 60-100회 이다. 만약 정상적인 심장박동 수보다 느리거나 빠르다면 부정맥이라고 한다. 본 논문에서는 심전도신호에서 R-peak를 검출하여, R-R 간격을 구하고 부정맥 중에 서맥(bradycardia)과 빈맥(tachycardia) 구간을 검출하는 알고리즘을 제안하고 모의실험을 하였다.

ECG 분석을 위한 R-R interval 탐지 시스템

김영섭,홍성호,지용석,이명석,노학엽 한국정보통신설비학회 2012 정보통신설비학회논문지 Vol.11 No.2

ECG 분석을 위한 R-R interval 탐지 시스템

김영섭,홍성호,지용석,이명석,노학엽 한국정보통신설비학회 2012 한국정보통신설비학회 학술대회 Vol.2012 No.1

UARS 수면장애자의 심전도 데이터에서 R-R 간격, R-R간격 변화량, 저주파대고주파전력비에 관한 고찰

정동규 대한의용생체공학회 2001 의공학회지 Vol.22 No.2

뇌졸중 환자의 자율신경계 기능의 전기생리학적 특성

김도성,심영주,전포성,이지형,정호중 대한재활의학회 2009 Annals of Rehabilitation Medicine Vol.33 No.6

Objective: To evaluate the autonomic nervous function in post-stroke patients. Method: A total of 58 subjects, 34 post-stroke patients (mean age of 61.35 years) and 24 healthy subjects (mean age of 34.42 years) were included. The sympathetic skin response (SSR), the R-R interval variation (RRIV) and orthostatic hypotension (OH) were evaluated. Bilateral sympathetic skin responses were recorded on the palm and sole with stimulation of both median and tibial nerves. The obtained SSRs were divided into normal response and abnormal response including no response. The R-R interval variations were estimated during rest, deep breathing and Valsalva maneuver respectively. Results: In all healthy subjects, obtained SSRs were of normal response. Although the rate of abnormal SSR was 75.4% (205 of 272 waves) in stroke patients, the rate of abnormal SSR on affected side (81.6%, 111 of 136 waves) was significantly higher than unaffected side (69.1%, 94 of 136 waves) (p<0.05). The rate of abnormal SSR according to OH was not significantly different (with OH 75.0%, without OH 75.6%) (p>0.05). The RRIV of stroke patients with OH (1.09±0.06) was significantly lower than in control (1.14±0.05) during rest (p<0.01), and in stroke patients without OH, the RRIV (1.13±0.06) was also significantly lower than in control (1.27±0.22) during Valsalva maneuver (p<0.01). Conclusion: Evaluation of SSR and RRIV could be helpful in detecting dysfunction of autonomic nervous system in post-stroke patients. Objective: To evaluate the autonomic nervous function in post-stroke patients. Method: A total of 58 subjects, 34 post-stroke patients (mean age of 61.35 years) and 24 healthy subjects (mean age of 34.42 years) were included. The sympathetic skin response (SSR), the R-R interval variation (RRIV) and orthostatic hypotension (OH) were evaluated. Bilateral sympathetic skin responses were recorded on the palm and sole with stimulation of both median and tibial nerves. The obtained SSRs were divided into normal response and abnormal response including no response. The R-R interval variations were estimated during rest, deep breathing and Valsalva maneuver respectively. Results: In all healthy subjects, obtained SSRs were of normal response. Although the rate of abnormal SSR was 75.4% (205 of 272 waves) in stroke patients, the rate of abnormal SSR on affected side (81.6%, 111 of 136 waves) was significantly higher than unaffected side (69.1%, 94 of 136 waves) (p<0.05). The rate of abnormal SSR according to OH was not significantly different (with OH 75.0%, without OH 75.6%) (p>0.05). The RRIV of stroke patients with OH (1.09±0.06) was significantly lower than in control (1.14±0.05) during rest (p<0.01), and in stroke patients without OH, the RRIV (1.13±0.06) was also significantly lower than in control (1.27±0.22) during Valsalva maneuver (p<0.01). Conclusion: Evaluation of SSR and RRIV could be helpful in detecting dysfunction of autonomic nervous system in post-stroke patients.