• 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%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2361-2376
• /
• 2023

The electrocardiogram (ECG) signal is commonly used to screen and diagnose cardiovascular diseases. In recent years, deep neural networks have been regarded as an effective way for automatic ECG disease diagnosis. The convolutional neural network is widely used for ECG signal extraction because it can obtain different levels of information. However, most previous studies adopt single scale convolution filters to extract ECG signal features, ignoring the complementarity between ECG signal features of different scales. In the paper, we propose a dual-scale network with convolution filters of different sizes for 12-lead ECG classification. Our model can extract and fuse ECG signal features of different scales. In addition, different spatial and time periods of the feature map obtained from the 12-lead ECG may have different contributions to ECG classification. Therefore, we add a spatial-temporal attention to each scale sub-network to emphasize the representative local spatial and temporal features. Our approach is evaluated on PTB-XL dataset and achieves 0.9307, 0.8152, and 89.11 on macro-averaged ROC-AUC score, a maximum F1 score, and mean accuracy, respectively. The experiment results have proven that our approach outperforms the baselines.

• 전자공학회논문지B
• /
• 제30B권6호
• /
• 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.

• 센서학회지
• /
• 제29권1호
• /
• pp.19-26
• /
• 2020

Electrocardiogram (ECG) classification has become an essential task of modern day wearable devices, and can be used to detect cardiovascular diseases. State-of-the-art Artificial Intelligence (AI)-based ECG classifiers have been designed using various artificial neural networks (ANNs). Despite their high accuracy, ANNs require significant computational resources and power. Herein, three different ANNs have been compared: multilayer perceptron (MLP), convolutional neural network (CNN), and spiking neural network (SNN) only for the ECG classification. The ANN model has been developed in Python and Theano, trained on a central processing unit (CPU) platform, and deployed on a PYNQ-Z2 FPGA board to validate the model using a Jupyter notebook. Meanwhile, the hardware accelerator is designed with Overlay, which is a hardware library on PYNQ. For classification, the MIT-BIH dataset obtained from the Physionet library is used. The resulting ANN system can accurately classify four ECG types: normal, atrial premature contraction, left bundle branch block, and premature ventricular contraction. The performance of the ECG classifier models is evaluated based on accuracy and power. Among the three AI algorithms, the SNN requires the lowest power consumption of 0.226 W on-chip, followed by MLP (1.677 W), and CNN (2.266 W). However, the highest accuracy is achieved by the CNN (95%), followed by MLP (76%) and SNN (90%).

• 한국정보통신학회논문지
• /
• 제19권7호
• /
• pp.1728-1736
• /
• 2015

부정맥 분류를 위한 기존 연구들은 개인별 ECG신호의 차이는 고려하지 않고 특정 ECG 데이터에 종속적으로 개발되었기 때문에 다른 환경에 적용할 경우 그 성능에 변화가 많아 임상 적용에 한계가 있다. 또한 기존의 방법들은 각 ECG 특징점의 정확한 측정을 필요로 하며, 연산이 매우 복잡하다. 복잡도를 줄이기 위한 여러 가지 방법들이 제안되었지만, 그에 따른 분류의 정확도가 떨어지는 문제점이 있었다. 따라서 이러한 문제점을 극복하기 위해서는 개인별 다양한 ECG 신호의 패턴에 따라 최소한의 특징점을 추출함으로써 연산의 복잡도를 줄이고 부정맥을 정확하게 분류 할 수 있는 방법이 필요하다. 본 연구에서는 대상 유형별 ECG 신호의 QRS 패턴을 이용한 부정맥 분류 방법을 제안한다. 이를 위해 전처리를 통해 잡음이 제거된 심전도 신호에서 R파를 검출하고 QRS 특징점을 통해 대상 유형별 ECG 신호의 QRS 패턴을 정의하였다. 이후 패턴분류에 따른 오류를 검출 및 수정하고, 중복된 QRS 패턴을 별도의 부정맥으로 분류하였다. 제안한 방법의 우수성을 입증하기 위해 MIT-BIH 부정맥 데이터베이스 43개의 레코드를 대상으로 PVC, PAC, Normal, LBBB, RBBB, Paced beat의 검출율을 비교하였다. 실험결과 Normal, PVC, PAC, LBBB, RBBB, Paced beat의 검출율은 각각 99.98, 97.22 95.14, 91.47, 94.85, 97.48%의 우수한 검출율을 나타내었다.

• 융합신호처리학회논문지
• /
• 제12권2호
• /
• pp.96-101
• /
• 2011

최근 들어 실시간 원격 ECG모니터링 시스템에 대한 수요가 늘어가고 있으며 가입자의 증가와 더불어 실시간 모니터링 시스템의 자동화에 대한 필요성이 대두되고 있다. 비정상적인 ECG 비트의 자동검출은 이러한 실시간 원격 ECG모니터링 시스템의 성공적인 상업화를 위해서는 반드시 필요한 요소기술이다. 본 논문에서는 이러한 점에 착안하여 QRS 폭(width)과 RR interval의 패턴을 이용한 효율적인 비정상적 ECG 비트 자동검출알고리듬을 제안하였다. 기존에는 주로 ECG 비트의 상세한 분류에 대해서 많은 연구가 이루어졌으나 이러한 방법들은 분류 오류가 많고 주변 환경이 변화함에 따라서 분류성능의 변동성이 심하다는 단점이 있었다. 또한 정확한 ECG 비트 분류를 위해서는 충분한 양의 훈련데이터를 필요로 하며 특히 분류시에 많은 계산량을 필요로 한다는 문제점도 있었다. 그러나 자동화된 원격 ECG모니터링 시스템을 위해서는 ECG 비트의 세세한 분류 보다는 비트의 정상여부판단이 더 중요하다. 이러한 점에 착안하여 본 논문에서는 ECG 신호의 비정상적인 비트중에서도 가장 빈번이 발생하는 VEBs(Ventricular ectopic beats) 비트의 검출을 시도하였고 제안된 알고리듬을 MIT-BIH 부정맥 데이터베이스에 적용한 결과 만족스러운 VEBs 바트 검출성능을 얻을 수 있었다.

• 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.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(5)
• /
• pp.273-276
• /
• 2002

This paper has design of ECG pattern classification system using decision of fuzzy IF-THEN rules and neural network. each fuzzy IF-THEN rule in our classification system has antecedent lingustic values and a single consequent class. we use a fuzzy reasoning method based on a single winner rule in the classification phase. this paper in, the MIT/BIH arrhythmia database for the source of input signal is used in order to evaluate the performance of the proposed system. From the simulation results, we can effectively pattern classification by application of learned from neural networks.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.28.5-28
• /
• 2001

This paper investigates a classification method of the electrocardiogram (ECG) into different disease categories. The features for the classification of the ECG are the coefficients of the discrete wavelet transform (DWT) of ECG signals. The coefficients are calculated with Haar wavelet, and after DWT we can get 64 coefficients. Each coefficient has morphological information and they may be good features when conventional time-domain features are not available. Since all of them are not meaningful, it is needed to reduce the size of meaningful coefficients set. The distributions of each coefficient can be the rules to classify ECG signal. The optimally reduced feature set is obtained by fuzzy c-means algorithm and rough set theory. First, the each coefficient is clustered by fuzzy c-means algorithm and the clustered ...

• 한국정보통신학회논문지
• /
• 제24권1호
• /
• pp.37-43
• /
• 2020

최근 심전도 (ECG) 신호를 사용하여 심장병을 진단하는 많은 연구가 이루어지고 있다. 이러한 심전도 신호는 비정상적인 심장 상태를 나타내는 부정맥을 모니터링하고 진단하는 데 유용하게 쓰인다. 본 논문에서는 1차원 합성곱 신경망을 사용하여 ECG 신호에 대하여 부정맥을 분류하는 시스템을 제안한다. 제안하는 신경망 알고리즘은 부정맥 신호의 특징을 세밀하게 추출하도록 4개의 합성곱 계층으로 구성하고 매개변수를 최적화하도록 설계되었다. MIT-BIH 부정맥 데이터베이스에 대해 학습한 신경망은 시뮬레이션을 통해 99% 이상의 정확도의 분류 성능을 가진다는 것을 보여준다. 비교적 합성곱 커널의 개수가 많을수록 ECG 신호의 특성을 더 잘 나타내기 때문에 좋은 성능을 나타내는 것으로 분석되었다. 또한 제안된 신경망을 활용한 실제 시스템을 구현하여 실시간으로 부정맥을 분류하는 결과를 검증하였다.