• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.209-215
• /
• 2019

The most important personal health care in digital health care is a very important issue mainly for chronic diseases. Therefore, it is important to develop a simple wearable device for real-time health management. Existing blood pressure estimation wearable devices use PPG characteristics to analyze PTT and propose blood pressure estimation algorithms. However, the influencing factors of the algorithm such as the reproducibility of PPG, whether to apply various PTTs, and variables generated from the physical differences of the measurers are actually very complex. Therefore, in this study, the correlation between PTT, SBP, and DBP was analyzed, and it was designed to use PPG sensors for device miniaturization. The blood pressure estimation algorithm took into account differences in PPG, heart rate, and personal variables.

• Journal of the Korean Magnetics Society
• /
• v.20 no.3
• /
• pp.106-113
• /
• 2010

In order to get the precise blood pressure and pulse number in the cuffless status, the wrist wearable pulsimeter with a portable and small size apparatus using by Hall device is developed. The regression analysis of the pulse wave measured by the testing product of pulsimeter is conducted two equations of the blood pressure algorithm. The estimated values of blood pressure obtained by the cuffless pulsimeter during 5 s are compared with the practical values measured by electronic or mercury liquid blood pressure meters. The standard deviation of the estimated value and the practical value for the high blood pressure and the low blood pressure were 12.1 and 5.9, respectively, which have the neighborhood values of BP International Standard. The detail analysis of a pulse wave measured by cuffless wrist wearable detecting the changes of the magnetic field can be used to develop a new diagnostic algorithm of blood pressure applying for oriental medical apparatus like as the wrist wearable pulsimeter.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.67-73
• /
• 2019

The blood pressure measurement is calculated as a value corresponding to the pressure of the blood vessel using the pressure from the outside for a long time. Due to the recent miniaturization of measurement equipment and the ICT combination of personal healthcare systems, a system that enables continuous and real-time measurement of blood pressure with a sensor is required. In this study, blood pressure was measured using pulse transit time using Photoplethysmography. In this study, blood pressure was estimated by using systolic blood pressure. And it is possible to make measurement only with PPG itself, which can contribute to making a micro blood pressure measuring device. As a result, systolic blood pressure and PPG's S1-P and P-S2 were used to analyze the possibility of blood pressure estimation.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.3
• /
• pp.1-10
• /
• 2020

In this paper, we propose an algorithm for estimating blood pressure using ECG (Electrocardiogram) and PPG (Photoplethysmography) signals. To estimate the BP (Blood pressure), we generate a periodic input signal, remove the noise according to the differential and threshold methods, and then estimate the systolic and diastolic blood pressures based on the convolutional neural network. We used 49 patient data of 3.1GB in the MIMIC database. As a result, it was found that the prediction error (RMSE) of systolic BP was 5.80mmHg, and the prediction error of diastolic BP was 2.78mmHg. This result confirms that the performance of class A is satisfied with the existing BP monitor evaluation method proposed by the British High Blood Pressure Association.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1796-1797
• /
• 2011

본 연구에서는 기존 오실로메트리(oscillomatry) 혈압측정에서 가압 커프의 영향을 최소화 하기위하여, 캐패시턴스 센서를 추가하여 혈압측정 동안의 혈압 및 혈류의 변화량을 측정하여 얻은 신호로 수축기 혈압 및 이완기 혈압을 추정하였다. 필터를 적용한 캐패시턴스 센서의 값을 피크의 크기에 따른 알고리즘을 적용하였으며 얻어진 혈압값과 기존의 혈압계의 값을 비교분석 하였다. 피험자의 연령은 $25{\pm}4$세의 15명을 기준으로 실험하였으며 알콜 및 운동 등 혈압에 영향을 미치는 요소들에 대해 제한 시켰으며 측정 전 15분의 안정을 취했다. 결과적으로 피험자 15명에 대해 수축기 혈압에서의 오차범위는 ${\pm}4$ mmHg이하로 나타났으며 평균 및 표준편차는 각각 2.13 mmHg 과 1.36 mmHg이었다. 이완기 혈압에서는 오차범위가 11명에 대해 수축기혈압과 같았으며 4명은 ${\pm}7mmHg$이상 이였고 평균과 표준편차는 4.20 mmHg와 2.24 mmHg 로 수축기 혈압에서 오차 및 분산 모두 이완기혈압 추정보다 비교적 정확한 값을 검출했다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.678-681
• /
• 2007

In this study, an implementation of a system for measuring more accurate blood pressure by non-invasive methods of oscillometric was performed. The system were composed of pressure control, signal measurement, blood pressure signal processing units and wireless sensor network parts. For verify the validity of the system, tests of characteristics evaluations for pressure measurement unit, extraction of characteristic ratios for blood pressure estimation, blood pressure tracking by oscillometric method were performed. A group of five adult male was selected for the clinical test of the implemented system. The results of the oscillometric method in comparison with auscultatory method are that the maximum ratios of PAD of average, systolic and diastolic arterial pressure are 1.38%, 1.63% and 2.97% with SEP of 5.00, 3.72 and 4.34.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.227-228
• /
• 2012

맥압증폭은 대동맥과 말초기관과의 혈압기능 평가 및 심혈관 질환을 예측하는 주요 매개변수로 나이와 관련이 높다. 그러나, 기존의 맥압증폭을 구하기 위해서는 관혈적인 방법으로 대동맥압을 측정하거나 혹은 전달함수와 같은 복잡한 대동맥압 추정 알고리즘을 구현하여 측정하여야 한다. 그러나, 유헬스를 활용한 스마트케어 환경에서 복잡한 알고리즘은 오히려, 계산량을 높이고, 시스템가격을 높일 수 있으므로, 최대한 단순화된 알고리즘이 필요하다. 본 논문에서는 맥압증폭을 주파수영역의 에너지 관점으로 맥압증폭을 접근하였고, 대동맥압 추정없이 추정할 수 있는 새로운 지수를 제안한다.

• Journal of the Korea Convergence Society
• /
• v.10 no.8
• /
• pp.53-58
• /
• 2019

Recently, product research has been continuously conducted to enhance accessibility to blood pressure measurement for the purpose of healthcare for the chronic patient. In previous studies, electrocardiogram (ECG) and photoelectric pulse wave (PPG) are analyzed to calculate systolic and diastolic blood pressure. The problem is the development of analysis algorithms for accuracy and reproducibility. In this study, in the development stage of a micro blood pressure measuring device, the size of the device was reduced and the measurement method was simplified, while the algorithm was to extract systolic blood pressure (SBP) using only two PPGs and obtain diastolic blood pressure (DBP). The difference value of PPG, DF_P, is inversely related to SBP, and has a proportional relationship with DBP, which can be leaked by algorithm, and DBP can be tracked through SBP.

• Journal of the Korea Convergence Society
• /
• v.11 no.7
• /
• pp.35-40
• /
• 2020

Recently, devices such as smart watches capable of measuring small biosignals have been released. Body composition, blood pressure, heart rate, and oxygen saturation can be easily obtained. However, the part that is not trusted by the user is accuracy. These biosignals are sensitive to the external environment and have large fluctuations depending on the conditions inside the subject's body. Blood pressure measurements, in particular, still give different results, depending on how the conditions in the body are handled. Therefore, in this study, PPG was analyzed to measure PTT at two points of 80% and 100%, the highest in PTT measurement. The effect of the measured value on SBP and DBP was analyzed and a method was proposed to increase the accuracy. As a result of the study, the measured value of PTT at 80% of the peak PPG is more effective in estimating blood pressure of SBP and DBP than the value measured at 100%. In the regression analysis of the rate of change blood pressure estimation, the coefficient of determination of SBP (80%) was 0.6946, and DBP (100%) was 0.547.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1469-1476
• /
• 2022

Recently, many researches have been conducted to estimate blood pressure using ECG(Electrocardiogram) and PPG(Photoplentysmography) signals. In this paper, we designed and implemented a mobile system to monitor blood pressure in real time by using 1-D convolutional neural networks. The proposed model consists of deep 11 layers which can learn to extract various features of ECG and PPG signals. The simulation results show that the more the number of convolutional kernels the learned neural network has, the more detailed characteristics of ECG and PPG signals resulted in better performance with reduced mean square error compared to linear regression model. With receiving measurement signals from wearable ECG and PPG sensor devices attached to the body, the developed system receives measurement data transmitted through Bluetooth communication from the devices, estimates systolic and diastolic blood pressure values using a learned model and displays its graph in real time.