• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.550-552
• /
• 2022

최근 사물인터넷(IoT) 기기가 활성화됨에 따라 웨어러블 장치 환경에서 장기간 모니터링 및 수집이 가능해짐에 따라 생체 신호 처리 및 ECG 분석 연구가 활성화되고 있다. 그러나, ECG 데이터는 부정맥 비트의 불규칙적인 발생으로 인한 클래스 불균형 문제와 근육의 떨림 및 신호의 미약등과 같은 잡음으로 인해 낮은 신호 품질이 발생할 수 있으며 훈련용 공개데이터 세트가 작다는 특징을 갖는다. 이 논문에서는 ECG 1D 신호를 2D 스펙트로그램 이미지로 변환하여 잡음의 영향을 최소화하고 전이학습과 메타학습의 장점을 결합하여 클래스 불균형 문제와 소수의 데이터에서도 빠른 학습이 가능하다는 특징을 갖는다. 따라서, 이 논문에서는 ECG 스펙트럼 이미지를 사용하여 2D-CNN 메타-전이 학습 기반 부정맥 분류 기법을 제안한다.

• Smart Media Journal
• /
• v.8 no.4
• /
• pp.33-37
• /
• 2019

Because the ECG signals are time-series data acquired as time elapses, it is important to obtain comparative data the same in size as the enrolled data every time. This paper suggests a network model of GAN (Generative Adversarial Networks) based on an auxiliary classifier to generate synthetic ECG signals which may address the different data size issues. The Cosine similarity and Cross-correlation are used to examine the similarity of synthetic ECG signals. The analysis shows that the Average Cosine similarity was 0.991 and the Average Euclidean distance similarity based on cross-correlation was 0.25: such results indicate that data size difference issue can be resolved while the generated synthetic ECG signals, similar to real ECG signals, can create synthetic data even when the registered data are not the same as the comparative data in size.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.199-201
• /
• 2002

본 논문에서는 심장질환의 진단 알고리즘의 개발에 있어서 필수적으로 요구되는 심장질환별 ECG 데이터의 수집에 관하여 기술한다. 또한, 진단 알고리즘을 개발하기 위한 전단계로서 심전도 신호에서 각 특징들을 검출하는 알고리즘에 관하여 설명하고, 이를 MITDB와 수집한 ECG 신호에 적용한 결과를 보인다. QRS-complex의 검출은 99% 이상의 정확도를 보이나, P-wave와 T-wave의 검출에서는 아직까지 보완할 점이 많은 것으로 나타난다. 심장질환별 12-채널 ECG 데이터베이스의 구축은 보다 정확하고 현실적인 진단 알고리즘을 개발하는 데 크게 기여할 것으로 기대한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.649-652
• /
• 2016

빅데이터 시대와 다양한 웨어러블 디바이스의 등장으로 사용자로부터 다양한 비정형 데이터를 수집할 수 있고 분석을 통해 정보를 제공하는 연구가 증가하고 있다. 본 논문에서 사용한 nymi 밴드를 통해 사용자의 ECG 신호에 대한 수집이 가능해졌고 수집된 데이터를 이용하여 부정맥과 관련된 데이터 분석이 가능해 졌다. 지도 학습의 방법중 하나인 분류 기법을 사용하여 수집 되는 ECG 신호 데이터에 대한 부정맥 질병을 판단할 수 있는 시스템을 제안한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.4C
• /
• pp.313-320
• /
• 2012

An ECG(Electrocardiogram) compression can increase the processing speed of system as well as reduce amount of signal transmission and data storage of long-term records. Whereas conventional performance evaluations of loss or lossless compression algorithms measure PRD(Percent RMS Difference) and CR(Compression Ratio) in the viewpoint of engineers, this paper focused on the performance evaluations of compression algorithms in the viewpoint of diagnostician who diagnosis ECG. Generally, for not effecting the diagnosis in the ECG compression, the position, length, amplitude and waveform of the restored signal of PQRST wave should not be damaged. AZTEC, a typical ECG compression algorithm, is validated its effectiveness in conventional performance evaluation. In this paper, we propose novel performance evaluation of AZTEC in the viewpoint of diagnostician.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1279-1286
• /
• 2021

The electrocardiogram (ECG) signal is a good indicator for early diagnosis of heart abnormalities. The ECG signal has a different reference normal signal for each person. And it requires lots of data to diagnosis. In this paper, we propose an adaptive OpenCL-based FPGA-GPU hybrid-layer platform to efficiently accelerate ECG signal diagnosis. As a result of diagnosing 19870 number of ECG signals of MIT-BIH arrhythmia database on the platform, the FPGA accelerator takes 1.15s, that the execution time was reduced by 89.94% and the power consumption was reduced by 84.0% compared to the software execution. The GPU accelerator takes 1.87s, that the execution time was reduced by 83.56% and the power consumption was reduced by 62.3% compared to the software execution. Although the proposed FPGA-GPU hybrid platform has a slower diagnostic speed than the FPGA accelerator, it can operate a flexible algorithm according to the situation by using the GPU.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2009.11a
• /
• pp.154-157
• /
• 2009

본 논문은 ECG의 긴장과 이완상태를 자동으로 인식하기 위해서 SOM 학습을 이용한다. 기존의 ECG 연구는 자극원의 유무에 따라서 정상상태와 변화상태를 비교하여 데이터를 분석하였다. 본 연구에서는 피험자를 ECG로 측정하여 분석한 후 SOM학습을 이용해서 자동으로 긴장과 이완상태를 분석한다. 실험은 피험자에게 슈팅게임을 하게 한 후 ECG로 측정한다. SOM 입력벡터는 측정된 ECG의 HRV분석으로 시간분석과 주파수분석의 특징벡터들을 추출한다. 특징이 추출된 입력벡터들은 SOM으로 학습하여 자동으로 피험자의 긴장과 이완상태를 분류하여 인식할 수 있었다. ECG와 SOM학습의 매칭도 결과는 71%의 정확도를 보였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.3 no.1
• /
• pp.13-18
• /
• 2010

In this study, heart rate through ECG R-R intervals using the methods about how to automatically extract studied. Heart rate as measured by the naked eye, using the 2-order differential equations to extract heart rate, using self-correlation function to extract the heart rate was compared contemplate. To verify its efficacy and validity in practical applications, these method has been applied to MIT/BIH database. Based on this, making a ECG meter automatic heart rate measurements, and our ECG meter was compared with the existing ICU.

• Journal of Digital Convergence
• /
• v.12 no.1
• /
• pp.397-403
• /
• 2014

In u-Healthcare environment, large amounts of important medical information is processed through wireless communication. Therefore there is a need to increase the efficiency of the network system of sending ECG data. This paper presents a compression solution for efficient ECG data transmission(ECGLZW) in u-Healthcare environment. The results showed that the average compression ratio of ECGLZW was 4.6, which got 200% better than existing methods(Huffman and LZW compression). ECGLZW's high compression ratio can increase the efficiency of wireless channels. As a result, reliable communication and security of u-Healthcare information could be achieved by applying these remaining channels to retransmission and encryption.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.62-69
• /
• 2019

Electrocardiogram (ECG) signals cannot be counterfeited and can easily acquire signals from both wrists. In this paper, we propose a method of generating a coupling image using direction information of ECG signals as well as its usage in a personal recognition method. The proposed coupling image is generated by using forward ECG signal and rotated inverse ECG signal based on R-peak, and the generated coupling image shows a unique pattern and brightness. In addition, R-peak data is increased through the ECG signal calculation of the same beat, and it is thus possible to improve the recognition performance of the individual. The generated coupling image extracts characteristics of pattern and brightness by using the proposed convolutional neural network and reduces data size by using multiple pooling layers to improve network speed. The experiment uses public ECG data of 47 people and conducts comparative experiments using five networks with top 5 performance data among the public and the proposed networks. Experimental results show that the recognition performance of the proposed network is the highest with 99.28%, confirming potential of the personal recognition.