• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.10
• /
• pp.202-208
• /
• 2012

Fetal heart rate monitoring is important information to assess fetal well-being. Non-invasive fetal ECG (electrocardiography) can be derived from maternal abdominal signal. And various promising signal processing methods have been introduced to extract fetal ECG from mother's composite abdominal signal. However, non-invasive fetal ECG monitoring still has not been widely used in clinical practice due to insufficient reliable measurement and difficulty of signal processing. In application of signal processing method to extract fetal ECG, it might be lower signal to noise ratio due to time varying white Gaussian noise. In this paper, time varying Kalman smoother is proposed to remove white noise in fetal ECG and its feasibility is confirmed. Wiener process was set as Kalman system model and covariance matrix was modified according to white Gaussian noise level. Modified error covariance matrix changed Kalman gain and degree of smoothness. Optimal covariance matrix according to various amplitude in Gaussian white noise was extracted by 5 channel fetal ECG model, and feasibility of proposed method could be confirmed.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1072-1077
• /
• 2017

Mean-reverting analysis refers to a way of estimating the underlining tendency after new data has evoked the variation in the equilibrium state. In this paper, we propose a new method to interpret the specular portraits of Premature Ventricular Contraction(PVC) arrhythmia by applying K-means unsupervised learning algorithm on electrocardiogram(ECG) data. Aiming at this purpose, we applied a mean-reverting model to analyse Heart Rate Variability(HRV) in terms of the modified poincare plot by considering PVC rhythm as the component of disrupting the homeostasis state. Based on our experimental tests on MIT-BIH ECG database, we can find the fact that the specular patterns portraited by K-means clustering on mean-reverting HRV data can be more clearly visible and the Euclidean metric can be used to identify the discrepancy between the normal sinus rhythm and PVC beats by the relative distance among cluster-centroids.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.186-191
• /
• 2023

Neural Networks are widely used for huge variety of tasks solution. Machine Learning methods are used also for signal and time series analysis, including electrocardiograms. Contemporary wearable devices, both medical and non-medical type like smart watch, allow to gather the data in real time uninterruptedly. This allows us to transfer these data for analysis or make an analysis on the device, and thus provide preliminary diagnosis, or at least fix some serious deviations. Different methods are being used for this kind of analysis, ranging from medical-oriented using distinctive features of the signal to machine learning and deep learning approaches. Here we will demonstrate a neural network-based approach to this task by building an ensemble of 1D CNN classifiers and a final classifier of selection using logistic regression, random forest or support vector machine, and make the conclusions of the comparison with other approaches.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.65-74
• /
• 2010

We propose a system that automatically recognizes the tense or relaxed condition of scrolling-shooting game subject that plays. Existing study compares the changed values of source of stimulation to the player by suggesting the source, and thus involves limitation in automatic classification. This study applies SOM of unsupervised learning for automatic classification and recognition of player's condition change. Application of SOM for automatic recognition of tense and relaxed condition is composed of two steps. First, ECG measurement and analysis, is to extract characteristic vector through HRV analysis by measuring ECG after having the player play the game. Secondly, SOM learning and recognition, is to classify and recognize the tense and relaxed conditions of player through SOM learning of the input vectors of heart beat signals that the characteristic extracted. Experiment results are divided into three groups. The first is HRV frequency change and the second the SOM learning results of heart beat signal. The third is the analysis of match rate to identify SOM learning performance. As a result of matching the LF/HF ratio of HRV frequency analysis to the distance of winner neuron of SOM based on 1.5, a match rate of 72% performance in average was shown.

• Journal of the Korean Society of Safety
• /
• v.30 no.2
• /
• pp.56-62
• /
• 2015

The purpose of this study was to identify the relationship between the index of Electrocardiography(LF/HF) and the occurrence of drowsiness driving while driving in a simulated situation. Participants were 31 undergraduate students with an experience in driving and they participated 30 minutes driving under enough sleep condition and 1 hour under the sleep deprivation condition. The Euro Truck Simulator II was used for driving simulation task and ECG and perceived drowsiness of each participants were measured during two driving conditions. Perceived sleepiness recorded by the checklist every 10 minutes and ECG data extracted before and after 15 seconds of every 10 minutes to verify the relationship between two variables. The results showed that the level of perceived sleepiness under sleep deprivation condition was higher than that under the enough sleep condition, and the level of LF/HF under sleep deprivation condition was lower than that under the enough sleep condition. In addition, the result of analysis of repeated measure ANOVA for ECG indicated that authentic sleepiness revealed in 20 minutes after the start of driving under the sleep deprivation condition. However, the result of perceived drowsiness indicated that authentic sleepiness revealed in 30 minutes after the start of driving. These result suggest that the time difference between biological and perceived response on drowsiness may be exist. Finally, the significant negative correlation between the LF/HF level and perceived drowsiness was observed. These findings suggest that ECG(LF/HF) can be an possible index to measure drowsiness driving.

• Science of Emotion and Sensibility
• /
• v.14 no.2
• /
• pp.197-206
• /
• 2011

The purpose of the study was to suggest automatic recognition of the subject's level of arousal into high arousal and low arousal with neural network SOM learning. The automatic recognition in the level of arousal is composed of three stages. First, it is a stage of ECG measurement and analysis. It measures the subject playing a shooting game with ECG and extracts characteristics for SOM learning. Second, it is a stage of SOM learning. It learns input vectors extracting characteristics. Finally, it is a stage of arousal recognition which recognize the subject's level of arousal when new vectors are input after SOM learning is completed. The study expresses recognition results in the level of arousal and the level of arousal in numerical value and graph when SOM learning results in the level of arousal and new vectors are input. Finally, SOM evaluation was analyzed average 86% by comparing emotion evaluation results of the existing research with automatic recognition results of SOM in order. The study could experience automatic recognition with other levels of arousal by each subject with SOM.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.2
• /
• pp.244-253
• /
• 2016

The QRS complex of ECG signal represents the depolarization and repolarization activities in the cells of ventricle. Accurate informations of $QRS_{onset}$ and $QRS_{offset}$ are needed for automatic analysis of ECG waves. In this study, using the amount of change in the QRS complex voltage values and the distance from the $R_{peak}$, we determined the junction point from Q-wave to R-wave and the junction point from R-wave to S-wave. In the next step, using the integral calculation based on the connection point, we detected $QRS_{onset}$ and $QRS_{offset}$. We use the PhysioNet QT database to evaluate the performances of the algorithm, and calculate the mean and standard deviation of the differences between onsets or offsets manually marked by cardiologists and those detected by the proposed algorithm. The experiment results show that standard deviations are under the tolerances accepted by expert physicians, and outperform the results obtained by the other algorithms.

• Journal of People, Plants, and Environment
• /
• v.21 no.6
• /
• pp.575-589
• /
• 2018

This study analyzed the changes in Electroencephalogram(EEG) and Electrocardiogram(ECG) depending on the healing environment in order to find a way to improve the forest healing program based on the healing environment in response to the demand for qualitative improvement of the program since the program is a charged service. This study selected eight sites running forest healing programs at four national healing forests (i.e., Saneum, Cheongtaesan, Daegwanryeng, and Jangseong) - two routes per national healing forest - considering forest environments. This study chose NUMBER standard sampling plots ($20{\times}20m$) and measured three atmospheric environment items, seven physical environment items, two soil environment items, and eight vegetation environment items including forest sound and anion at each plot to evaluate physiological changes in it. EEG and ECG, which have been widely used in forest healing evaluation, were utilized as criteria. Seventy three subjects were selected with taking the age, drug, caffeine, smoking, and the time of last meal into consideration. As a result, EEG changes were correlated with three atmospheric environment items, six physical environment items, one soil environment item, and two vegetation environment items. ECG changes were significantly correlated with two atmospheric environment items, six physical environment items, two soil environment items, and two vegetation environment items (p<.05). It is expected that 11 environmental factors such as temperature, density, and altitude affecting EEG (e.g., alpha balance and gamma balance) and ECG (e.g., HRV mean) could be used as effective tools in developing more differentiated programs for improving healing effects.

• Science of Emotion and Sensibility
• /
• v.13 no.3
• /
• pp.467-474
• /
• 2010

Recently, Study of functional clothing for Vital sensing is focused on reducing artifact by human motions, in order to enhance the electrocardiogram(ECG) sensing accuracy. In this study, considering the factors for each element found from the analysis, a 3-lead electrode inside textile embroidered with silver yarn was developed, and draft designs off our types of vital-signal sensing garments, which are 'chest-belt typed' garment, 'cross-typed' garment 'x-typed' garment and 'curved x-typed' garment, were prepared. The draft designs were implemented on a sleeveless male shirt made of an elastic material so that the garment and the electrodes can remain closely attached along the contour of the human body, and the acquired data was sent to the main computer over a wireless network. In order to evaluate the effects caused by body movements and the ECG-sensing capability for each type in static and dynamic states, displacements were measured from one and two dimensional perspectives. ECG measurement evaluation was also performed for Signal-to-noise ratio(SNR) analysis. Applying the experimental results, the draft garment designs were modified and complemented to produce two types of modular approaches 'continuous-attached' and 'insertion-detached' for the ECG-sensing smart clothing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.313-316
• /
• 2009

A novel approach for electrocardiogram (ECG) analysis within a functional sensor node has been developed and evaluated. The main aim is to reduce data collision, traffic over loads and power consumption in healthcare applications of wireless sensor networks (WSN). The sensor node attached on the patient's bodysurface around the heart can perform ECG analysis based on a QRS detection algorithm to detect abnormal condition of the patient. Data transfer is activated only after detected abnormality in the ECG. This system can reduce packet loss during transmission by reducing traffic overload. In addition, it saves power supply energy leading to more reliable, cheap and user-friendly operation in the WSN based ubiquitous health monitoring.