• 전기학회논문지
• /
• 제60권3호
• /
• pp.654-661
• /
• 2011

This paper is about a personal identification algorithm using an ECG that has been studied by a few researchers recently. Previously published algorithm can be classified as two methods. One is the method that analyzes of ECG features and the other is the morphological analysis of ECG. The main characteristic of proposed algorithm can be classified the method of analysis ECG features. Proposed algorithm adopts DSTW(Down Slope Trace Wave) for extracting ECG features, and applies SVM(Support Vector Machine) to training and testing as a classifier algorithm. We choose 18 ECG files from MIT-BIH Normal Sinus Rhythm Database for estimating of algorithm performance. The algorithm extracts 100 heartbeats from each ECG file, and use 40 heartbeats for training and 60 heartbeats for testing. The proposed algorithm shows clearly superior performance in all ECG data, amounting to 93.89% heartbeat recognition rate and 100% ECG recognition rate.

• 대한의용생체공학회:의공학회지
• /
• 제29권3호
• /
• pp.249-253
• /
• 2008

The indirect-contact ECG (IDC-ECG) was introduced by a prior study for daily non-intrusive measurements. To improve the signal quality and to extend the application area of IDC-ECG, close study of the frequency characteristics of the IDC-ECG is necessary. In this study, the frequency response of the active electrode for several sample clothes was measured under conditions of actual IDC-ECG measurement with human body. Higher gain in low frequency range than expected by prior study was observed. In addition to it, wide variation in gain according to the cloth type in the low frequency range was observed. Variation in gain caused by moisture variation in the clothes was also observed. This study shows that the parallel R-C connection is proper for electrode model and the resistive factor is influenced by moisture in the clothes. This study is the first that provides the frequency response of the electrode in the actual indirect-contact ECG measurement and it is expected that the results will be helpful to improve the indirect-contact ECG method.

• 반도체디스플레이기술학회지
• /
• 제20권2호
• /
• pp.77-81
• /
• 2021

In this paper, a low-csst ECG system using a digital filter was implemented. After amplifying the analog ECG signal, it is converted into a digital signal and filtered. The developed ECG module is miniaturized by removing the analog filter element that occupies the existing volume and replacing it with a digital filter using a 3-stage Butterworth filter which is one of IIR filters. It uses a serial monitoring program with C# to check and save the ECG waveform measured on a computer screen. The ECG system using a developed digital filter in this paper uses a low-cost processor instead of an expensive, high-end processor, and its size and price are reduced by converting the analog filter to a digital filter. In addition, since the waveform of the developed ECG system is similar to the actual ECG waveform of MIT-BIU, it is considered that the existing analog filter can be replaced with the developed digital filter.

• 대한의용생체공학회:의공학회지
• /
• 제31권5호
• /
• pp.365-374
• /
• 2010

This paper is about the personal identification algorithm using an ECG that has been studied by a few researchers recently. Previously published algorithm can be classified as two methods. One is the method that analyzes ECG features and the other is the morphological analysis of ECG. The main characteristic of proposed algorithm uses together two methods. The algorithm consists of training and testing procedures. In training procedure, the features of all recognition objects' ECG were extracted and the PCA was performed for morphological analysis of ECG. In testing procedure, 6 candidate ECG's were chosen by morphological analysis and then the analysis of features among candidate ECG's was performed for final recognition. We choose 18 ECG files from MIT-BIH Normal Sinus Rhythm Database for estimating algorithm performance. The algorithm extracts 100 heartbeats from each ECG file, and use 40 heartbeats for training and 60 heartbeats for testing. The proposed algorithm shows clearly superior performance in all ECG data, amounting to 90.96% heartbeat recognition rate and 100% ECG recognition rate.

• 전자공학회논문지S
• /
• 제35S권8호
• /
• pp.39-46
• /
• 1998

ECG신호가 임상적으로 환자의 심장활동에 관련된 여러 정보를 의사에게 제공한다는 점에서 ECG 신호의 검출은 중요한 환자 진단방법의 하나이다. 특히 QRS복합 파형, P파, T파 등의 위치와 각 파 간의 간격에 의미 있는 정보가 담겨져 있어 정확한 환자진단을 위해 의공학 분야에서 ECG신호의 잡음제거에 관련된 여러 연구들이 있어 왔다. 기존의 ECG신호의 잡음제거 방법은 특정한 단일 잡음이 혼입된 경우에는 만족할 만한 성능을 보여 주는데 반해 여러 형태의 복합잡음이 혼입된 ECG신호로부터 정상 ECG신호를 분리해 내는데는 성능의 한계를 가진다. 본 논문에서는 최근 공학분야에서 그 활용 영역이 확대되고 있는 웨이브렛 변환 기법을 ECG신호의 잡음제거에 적용하여, 잡음이 혼입된 ECG신호의 잡음제거를 통한 정상 파형 복원을 수행하였다.

• 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.

• 정보처리학회논문지C
• /
• 제18C권3호
• /
• pp.195-198
• /
• 2011

본 연구에서는 ECG 신호를 측정하는 시스템에서 센서들과 기기 사이의 연결을 Zigbee 네트워크를 사용하여 무선화하고, 이를 통하여 이동성과 편리성을 제공하면서도, 병원용 ECG 기기에 준하는 데이터 정밀도를 가지는 U-healthcare용 ECG 시스템을 설계, 구현하였다. 대부분의 의료용 기기에서 이동성에 가장 문제가 되는 것은 센서와 기기를 연결하는 케이블로, 본 연구에서는 이를 줄이거나 없애는 방법으로 Zigbee를 기반으로 데이터를 송수신하는 센서 모듈과 컬렉터 모듈을 설계, 구현하여 근거리에서 동작하는 무선 네트워크를 구성하고, 이를 통하여 각 송신 모듈로부터 전송되는 데이터들을 수신하는 Zigbee-SD 전송 시스템을 설계, 구현하였다. 또한 ECG 신호의 분석과 처리에 스마트폰을 사용하여 데이터 분석과 심박수 표시를 수행하는 앱 응용 프로그램으로 구현함으로써 유비쿼터스 환경에서 이동성과 편리성을 최대한으로 제공할 수 있는 효과적인 U-healthcare 시스템을 구현하였다.

• 문화기술의 융합
• /
• 제9권4호
• /
• pp.611-616
• /
• 2023

심전도(electrocardiogram, ECG)는 심박동의 속도와 규칙성, 심실의 크기와 위치, 심장 손상 여부를 측정하는데 사용되며, 모든 심장질환의 원인을 찾아낼 수 있다. ECG-KIT를 이용하여 획득한 ECG 신호는 ECG 신호에 잡음을 포함하기 때문에 딥러닝에 적용하기 위해서는 ECG 신호에서 잡음을 제거해야만 한다. 본 논문에서는, ECG 신호에서 잡음은 Digital IIR Butterworth의 저역 통과 필터를 이용하여 제거하였다. LSTM의 딥러닝 모델을 사용하여 3가지 활성화 함수인 sigmoid(), ReLU(), tanh() 함수에 대한 성능 평가를 비교했을 때, 오차가 가장 작은 활성화 함수는 tanh() 함수 임을 확인하였으며, 또한 LSTM과 GRU 모델에 대한 성능 평가와 경과 시간을 비교한 결과 GRU 모델이 LSTM 모델보다 우수한 것을 확인하였다.

• 정보통신설비학회논문지
• /
• 제11권2호
• /
• pp.29-33
• /
• 2012

ECG widely used in cardiac function test is a graph that is recorded by measuring the electrical impulses occurred in the heart. Normal ECG has the form of similar sections that are repeated, and each section has the information occurred in a heart beat. Thus, In order to make the correct diagnosis, correct grasp of the sections and formed analysis must be done. In this research, a system that detects the sections of ECG is proposed. The system is based on ECG stored in the form of files. The ECG can easily have a noise caused by an outside factor. The noise of ECG is easily caused by external factors. Through a band-pass filter, it can be removed. and then, to get this ECG without a noise, interval detection algorithm using R-peak is applied. The clean, intuitive interface will help the above functions to be used without any difficulties.

• 제어로봇시스템학회논문지
• /
• 제15권4호
• /
• pp.406-412
• /
• 2009

ECG is used on purpose to keep good health or monitor cardiac function of aged person as well as on purpose to diagnose the disease of heart patients. The ambulatory ECG monitoring system under guarantee of safety and accuracy is very efficient to prevent the progress of heart disease and sudden death. These systems can detect the temporary change of ECG that is very significant to diagnose heart disease such as myocardial ischemia, arrhyamia and cardiac infarction. In this paper, we describe the ECG signal analysis algorithm and measurement device for ECG monitoring. The authors designed a small-size portable ECG device that consisted of instrumentation amplifier, micro-controller, filter and RF module. The device measures ECG with four electrodes on the body and detects QRS complex and ST level change in realtime. Also it transmits the measured signals to the personal computer. The developed software for ECG analysis in personal computer has the function to detect the feature points and ST level changes.