• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.11
• /
• pp.213-216
• /
• 1996

In this research we would like to develop an exercise ECG signal analysis algorithm using the wavelet transform, which is possible to analyze the time and the frequency simultaneously. Wavelet transform has an advantage of dividing the nonstationary signals into the high frequency and low frequency band successively. Thus, it can separates the unnecessary noises from the frequency band of QRS complex and then using the selected frequency band we could detect the QRS complex and ST segment.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.205-212
• /
• 2023

Among cardiac diseases, arrhythmias can lead to serious complications such as stroke, heart attack, and heart failure if left untreated, so continuous and accurate ECG monitoring is crucial for clinical care. However, the accurate interpretation of electrocardiogram (ECG) data is entirely dependent on medical doctors, which requires additional time and cost. Therefore, this paper proposes an arrhythmia recognition module for the purpose of developing a medical platform through the analysis of abnormal pulse waveforms based on Lifelogs. The proposed method is to convert ECG data into image format instead of time series data, apply visual pattern recognition technology, and then detect arrhythmia using CNN model. In order to validate the arrhythmia classification of the CNN model by image type conversion of ECG data proposed in this paper, the MIT-BIH arrhythmia dataset was used, and the result showed an accuracy of 97%.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.4
• /
• pp.181-188
• /
• 2006

The purpose of this study is to predict the defibrillation success of a ventricular Fibrillation ECG signal using time-frequency analysis. During CPR, coronary perfusion pressure and electrocardiogram were measured. Parameters extracted from time-frequency domain were served as predictor of resuscitation success. Time frequency distribution(TFD) of ECG signals was estimated from the smoothed pseudo Wigner-Ville distribution(SPWVD). Median frequency, peak frequency, 1/f slope, frequency band ratios$(2{\sim}4Hz,\;4{\sim}6Hz,\;6{\sim}8Hz,\;8{\sim}10Hz,\;10{\sim}12Hz,\;12{\sim}15Hz)$ were extracted from each TFD as function of time. Paired t-test was used to determine the differences in ROSC and non-ROSC groups. In the statistical results, we selected four significant parameters - median frequency, 1/f slope, $2{\sim}4Hz$ band ratio, $8{\sim}10Hz$ band ratio. We made an attempt to predict defibrillation success by combining features extracted from time frequency distribution. Independent t-test was used to determine the differences ROSC and non-ROSC groups. Consequently, we selected four significant parameters-median frequency, 1/f slope, $2{\sim}4Hz$ band ratio, $8{\sim}10Hz$ band ratio. The relationship between coronary perfusion pressure and ECG parameters was analyzed with linear regression analysis. R-square value was 55%. 1/f slope and $8{\sim}10Hz$ band ratio had the significant relationship with coronary perfusion pressure.

• Transactions on Electrical and Electronic Materials
• /
• v.14 no.6
• /
• pp.299-303
• /
• 2013

Anesthesia, which started being used to remove pain during surgery, has become itself one of the major concerns to be considered during surgery. While actual anesthesia is being performed, patients tend to have unpleasant experiences, due to wakening that accompanies pain, or wakening that does not accompany pain. Since this awakening during anesthesia is a most unpleasant experience in a patient's life, evaluating the depth of anesthesia during surgery is essential for patients to avoid this experience. Although there has been much effort on the understanding and measurement of the depth of anesthesia, while various researches were performed on the need of anesthesia, the development of an indicator that could objectively evaluate the depth of anesthesia, other than by using the patient's vital signs, is still inadequate. Therefore, this study was to develop an objective indicator by using EEG and ECG, which are essentially measured during the surgery, to evaluate the depth of anesthesia. The experiment was performed by taking patients who require a relatively short operation time, and general inhalation anesthetics among surgical patients in obstetrics and gynecology as the subjects of experiment, to measure the EEG and ECG signals of patients under anesthetics. The result showed that SEF using EEG and LF, HF using ECG signal and correlation dimension analysis parameter were valuable parameters that could measure the depth of anesthesia, by the stage of anesthesia.

• Journal of Digital Convergence
• /
• v.15 no.5
• /
• pp.217-223
• /
• 2017

With the development of sensor networks and Internet of Things (IoT) technology, personalized context information has been collected and customized services can be provided to related users. Currently, the context information system is at the level of analyzing and recognizing user specific behavioral characteristics and generating events.In the IoT environment, IoT products themselves should provide the required services with minimal user intervention, rather than acting for a specific purpose. In this paper, to minimize the user intervention in the IoT environment, we implemented an automatic attendance recognition system using context information from the ECG based on beacon. Environment of provided specific Context information, we compared and analyzed the degree of user intervention among the authentication method using ECG sensor in this paper and the existing authentication method. As a result of the analysis, we confirmed that the system implemented in this paper minimizes user intervention.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.1
• /
• pp.93-101
• /
• 2013

The accurate detection of R-wave is important for other feature extraction in ECG, and R-wave has a lot of medical information about heart. Numerous R-wave detection algorithms have been studied on the ECG signal shape analysis, but it was difficult to find accurate R-wave when the shape of R-wave is similar to the shape of P-wave. This paper presents an R-wave detection method based on the refractory period that is the period of depolarization and repolarization of the cell membrane after excitation. And we also use the shape of kurtosis in the refractory period. The proposed method is validated using the ECG records of the MIT-BIH arrhythmia database. Experimental results show that the proposed method significantly outperforms other method in case of 105 and 108 record that have R-wave similar to P-wave, as well as other records.

• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.4
• /
• pp.2217-2224
• /
• 2014

This paper deals with system development which measures 12 channel ECG using medical analog front end(AFE) and discriminates arrythmia through signal analysis. Recently, occurrences of cardiac arrest have been increased. So the need of system that diagnoses an arrythmia which results in cardiac arrest is increasing. There are some drawbacks of conventional 12 channel ECG system that it occupies bulk and consists of complicated circuit. To improve those, we made up the system composed of medical AFE, algorithm for discriminating arrythmia and DSP for signal processing. This system can be monitored 12 channel ECG waveforms and the discriminant analysis result of arrhythmia through 7" LCD and received the input through touch pannel. In this study, we conducted normal operation test about output signal of ECG simulator(normal/abnormal ECG signal) to verify the implemented system and performance evaluation of the optimization process for applying arrhythmia algorithm to an embedded environment.

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.11
• /
• pp.207-212
• /
• 1996

In this paper, we designed a Holter analysis system using the visual programming method. It differs from the existing analysis system in that the various signal processing algorithms represented by icons were designed by GUI concept which provide unskilled user with easy and convenient analysis environment. In order to analysis ECG signal, we only select the icon representing a algorithm to be applied by mouse and arrange the selected icons upon the order to be processed on screen. As a result it provides a convenient usage and flexibility of analysis. Finally, we can find the optimal algorithm for the ambulatory ECG analysis by comparing the several results obtained from the various analysis configuration.

• Journal of the Korea society of information convergence
• /
• v.6 no.2
• /
• pp.45-49
• /
• 2013

Electrocardiogram(ECG) signal noise as well as conducting other bio-signal measurement were generated. It was intened to enhance the accuracy of cadiac disease diagnosis with removing signal white-noise. Sampling signal was made with generating white-noise. The noise were removed using wavelet transforms and thresholding. Removed noise were compared numerical using SNR(signal to noise ratio). The results compared SNR showed that SURE method was 5.931, 4.9301 in 3, 5dB noise, uninversal was 3.6590, 1.9698 in 7, 9dB noise. De-noising by Thresholding removed noise effectively. ECG signal is expected to improve the accuracy of cadiac desease dianosis.