• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.05
• /
• pp.293-297
• /
• 1996

For the representative beat calculation and efficient rhythm analysis new method, that is, QRS typification were proposed. A problem that were resulted from pattern classification based on binary logic could be solved out by the fuzzy clustering and classification nodes could be reduced by using the proposed new feature vector. The accurate representative beat could be obtained by excluding the ST-T segment that happened outlier through ST-T segment typification procedure.

• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.657-665
• /
• 1991

Although orthogonal function is introduced in control theory in early 1970's, it is not perfect. Since the concept of integral operator by Chen and Hsiao in mid 1970's, orthogonal function (for example Walsh, Block-pulse, Haar, Laguerre, Legendre, Chebychev etc) has been widely applied In system's analysis and identification, model reduction, state estimation, optimal control, signal processing, image processing, EEG, and ECG etc. The reason why Walsh Functions introduces in control theory is that as integral of Walsh function is also developed in Walsh orthogonal function, if we transfer give system into integral equation and introduce Walsh function. We can know that system's characteristic by algebraical expression. This approach is based on least square error and that result is expressed as computer calculation and partly continuous constant value which is easy to apply. Such a Walsh function has been actively studied in USA, TAIWAN, INDO, CHINA, EUROPE etc and in domestic, author has studied it for 10 years since it was is introduced in 1982. This paper is consider the that author has studied for 10 years and Walsh function's efficiency.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.233-236
• /
• 2010

This paper describes the packet traffic management of the Ubiquitous Healthcare System. In this system, ECG signal and accelerometer signal is transmitted from a wearable health shirt (WHS) to the base station. However, with the increment of users in this system, traffic over-load issue occurs. The main aim of this paper is to reduce the traffic over-load issue between sensor nodes by only transmitting the required signals to the base station when irregular activities are observed. In order to achieve this, in-network processing is adapted where the process of observation is conducted inside the sensor node of WHS. Results shows that irregular activities such as fall can be detected on real-time inside the sensor node and thus resolves traffic over-load issue.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.21 no.8
• /
• pp.770-775
• /
• 2008

Autonomic nervous system of the anesthetized patients can be influenced by the many kinds of stimulations such as intubation, surgical incision and so on. The changes of the heart rates and blood pressures are surrogates of responses of the autonomic system to the external stimulations. Recently, the power spectral analysis of the heart rate variability (HRV) made it easy to know the fractions and changes of sympathetic and parasympathetic autonomic systems. In this study, the changes of pulse transit time, one of the response of vessels to stimulations, was investigated in relation to the HRV. Ten patients were examined and average age is 22.5 $\pm$ 11.04, average weight is 63 $\pm$ 14.4 kg. The patients were anesthetized only by sevoflurane inhalation. Pulse transit time is determined by calculating the difference of the time between the R peak of ECG and the characteristic point of the plethysmography. Power spectral density (PSD) of the HRV was achieved in the frequency of 0.04-0.15 (LF) and 0.15-0.4 (HF). Compared to preanesthetic period the values of LF and LF/HF ratio of HRV were decreased (p<0.05). HF and PTT was increased in anesthetic state with sevoflurane. Otherwise, after intubation, the HF was decreased and LF, LF/HF ratio and PTT were increased. PSD of the HRV is well-known for the index of the autonomic nervous activity. Not only HRV but PTT analysis also is a useful index reflecting the autonomic responses to various stimulations. And this analysis is useful in bed side monitoring because the calculating method is simple and it takes shorter processing time compared to the HRV analysis.

• Journal of the Ergonomics Society of Korea
• /
• v.31 no.2
• /
• pp.271-279
• /
• 2012

Objective: This study classified three different emotional states(boredom, pain, and surprise) using physiological signals. Background: Emotion recognition studies have tried to recognize human emotion by using physiological signals. It is important for emotion recognition to apply on human-computer interaction system for emotion detection. Method: 122 college students participated in this experiment. Three different emotional stimuli were presented to participants and physiological signals, i.e., EDA(Electrodermal Activity), SKT(Skin Temperature), PPG(Photoplethysmogram), and ECG (Electrocardiogram) were measured for 1 minute as baseline and for 1~1.5 minutes during emotional state. The obtained signals were analyzed for 30 seconds from the baseline and the emotional state and 27 features were extracted from these signals. Statistical analysis for emotion classification were done by DFA(discriminant function analysis) (SPSS 15.0) by using the difference values subtracting baseline values from the emotional state. Results: The result showed that physiological responses during emotional states were significantly differed as compared to during baseline. Also, an accuracy rate of emotion classification was 84.7%. Conclusion: Our study have identified that emotions were classified by various physiological signals. However, future study is needed to obtain additional signals from other modalities such as facial expression, face temperature, or voice to improve classification rate and to examine the stability and reliability of this result compare with accuracy of emotion classification using other algorithms. Application: This could help emotion recognition studies lead to better chance to recognize various human emotions by using physiological signals as well as is able to be applied on human-computer interaction system for emotion recognition. Also, it can be useful in developing an emotion theory, or profiling emotion-specific physiological responses as well as establishing the basis for emotion recognition system in human-computer interaction.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.535-536
• /
• 2021

현대의 스트레스 케어는 대부분 비디오 시청, 상담, 취미 활동 등을 통해 진행된다. 시각, 청각을 스트레스 케어에 활용한 사례는 이미 일상에서 쉽게 접할 수 있음으로 다른 새로운 감각을 요구하고 있다. 본 논문에서는 스트레스 케어를 목적으로, 생체정보를 대상으로 딥러닝 기술 기반의 '사용자 스트레스 및 효과적인 스트레스 해소 요소 판단 알고리즘 모델'을 사용하는 서비스 제공 시스템을 설계한다. 생체정보는 손목시계형 웨어러블을 통해 수집된 심박수, 혈압, 체온, 산소포화도, ECG 등 생체데이터를 사용한다. 제시하는 방법은 실시간으로 수집된 생체정보를 알고리즘, 모델을 통해 스트레스 수치를 예측하여 사용자에게 적절한 음악과 조명을 이용한 시청각적 요소와 아로마 요법을 이용한 후각적 요소를 제공한다.

• Journal of Biomedical Engineering Research
• /
• v.18 no.3
• /
• pp.285-290
• /
• 1997

In this paper, the power spectral analysis and the fractal analysis of heart rate variability(HRV) were performed to evaluate the effects of brain lesion on cardiovascular system and autonomic function for 24 normal subjects and 22 hemiplegic patients. The ECG and respiration signals were recorded at tilt angles of $0^{\circ}$ and $70^{\circ}$ for 5 and 6 minutes successively under the condition of frequency controlled respiration (0.25Hz). For normal subjects, HR, LF component, HF component and fractral dimension of HRV were distinctly changed after orthostatic stress, whereas, for hemiplegic patients, those were little changed. Complexity and variability of heart rate of patients were smaller than those of normal subjects. Sympathetic tone of patients was higher than that in normal subjects. All of these results support that autonomic disorder and cardiovascular disturbance accompanied by brain lesion could be assessed by the power spectral analysis and fractal analysis of HRV.

• Journal of Digital Convergence
• /
• v.12 no.4
• /
• pp.335-342
• /
• 2014

According to the recent trends in the growing elderly population, the chronically ill have increased. Thus the importance of the health care issues for them has emerged. In this paper, we want to implement a chronic disease management system using smart mobile devices. Proposed chronic disease management system is consisted of the biometric sensor, smart mobile devices, the patient management server, patient management DB, and patient symptoms analysis agent. The biometric sensor detects a biological information. Smart mobile devices receive the patient information from the sensor and transmit the information to the patient management server. The patient management server, patient management DB, and patient symptoms agent analysis agent analyze to process data delivered through a wireless communication network. Bio-signals includes modules of ECG, blood pressure, blood sugar and PPG. We are able to determine the current health status by monitoring measured biometric data through chronically ill health management system. We will focus on the individual service to be appropriate for a patient group in a mobile environment.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.406-409
• /
• 1997

In this paper, the power spectral analysis and fractral dimension analysis of heart rate variability(HRV) were performed to evaluate effects of orthostatic stress with head-up tilt on autonomic nervous system(ANS) for 24 young and healthy subjects(age: $24{\pm}5yr$.). The ECG and respiration signals were recorded at the tilt angle of $0^{\circ},\;15^{\circ},\;30^{\circ},\;45^{\circ},\;70^{\circ}$ and $90^{\circ}$ successively for 5 minutes per each stage under the condition of frequency controlled respiration (0.25Hz). Heart rate(HR) gradually increased as the angle increased. Similarly, according to the increment of angle, normalized low frequency(LF) component(0.05-0.15Hz) gradually increased, whereas normalized high frequency(HF) component (0.20-0.30Hz) was reduced. From these results it is speculated that orthostatic stress, head-up tilt, results in the prevalence of sympathetic tone in autonomic balance with the increment of sympathetic tone and the decrement of parasympathetic tone, which seems to mean that autonomic nervous system plays a major role in compensating for disturbances of cardiovascular system due to it.

• Journal of the Ergonomics Society of Korea
• /
• v.30 no.6
• /
• pp.705-713
• /
• 2011

Objective: The aim of this study is to compare results of emotion recognition by several algorithms which classify three different emotional states(happiness, neutral, and surprise) using physiological features. Background: Recent emotion recognition studies have tried to detect human emotion by using physiological signals. It is important for emotion recognition to apply on human-computer interaction system for emotion detection. Method: 217 students participated in this experiment. While three kinds of emotional stimuli were presented to participants, ANS responses(EDA, SKT, ECG, RESP, and PPG) as physiological signals were measured in twice first one for 60 seconds as the baseline and 60 to 90 seconds during emotional states. The obtained signals from the session of the baseline and of the emotional states were equally analyzed for 30 seconds. Participants rated their own feelings to emotional stimuli on emotional assessment scale after presentation of emotional stimuli. The emotion classification was analyzed by Linear Discriminant Analysis(LDA, SPSS 15.0), Support Vector Machine (SVM), and Multilayer perceptron(MLP) using difference value which subtracts baseline from emotional state. Results: The emotional stimuli had 96% validity and 5.8 point efficiency on average. There were significant differences of ANS responses among three emotions by statistical analysis. The result of LDA showed that an accuracy of classification in three different emotions was 83.4%. And an accuracy of three emotions classification by SVM was 75.5% and 55.6% by MLP. Conclusion: This study confirmed that the three emotions can be better classified by LDA using various physiological features than SVM and MLP. Further study may need to get this result to get more stability and reliability, as comparing with the accuracy of emotions classification by using other algorithms. Application: This could help get better chances to recognize various human emotions by using physiological signals as well as be applied on human-computer interaction system for recognizing human emotions.