• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.103-112
• /
• 2018

In this paper, we propose a method of recognizing emotions using PPG sensor which measures blood flow according to emotion. From the existing PPG signal, we use a method of determining positive emotions and negative emotions in the frequency domain through PSD (Power Spectrum Density). Based on James R. Russell's two-dimensional prototype model, we classify emotions as joy, sadness, irritability, and calmness and examine their association with the magnitude of energy in the frequency domain. It is significant that this study used the same PPG sensor used in wearable devices to measure the top four kinds of emotions in the frequency domain through image experiments. Through the questionnaire, the accuracy, the immersion level according to the individual, the emotional change, and the biofeedback for the image were collected. The proposed method is expected to be various development such as commercial application service using PPG and mobile application prediction service by merging with context information of existing smart phone.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.234-243
• /
• 2017

With the development of smartphone technologies enable photoplethysmogram (PPG) acquisition by camera and heart rate (HR) measurement. This papers presents improved algorithm to extract HR from PPG signal recorded by smartphone camera and to develop real-time PPG signal processing Android application. 400 video samples recorded by Samsung smartphone camera are imported as input data for further processing and evaluating algorithm on MATLAB. An optimized algorithm is developed and tested on Android platform with different kind of Samsung smartphones. To assess algorithm's performance, medical device Beurer BC08 is used as reference. According to related works, accuracy parameters includes 90% number of samples that has relative errors less than 5%, Person correlation (r) more than 0.9, and standard estimated error (SEE) less than 5 beats-per-minutes (bpm).

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.233-234
• /
• 2012

본 논문에서는 광전용적맥파(photoplethysmography:PPG)를 이용한 맥파 측정에 있어서 움직이는 상태에서의 파장에 따른 노이즈의 영향을 비교 연구하였다. 광전용적맥파는 광을 이용한 맥파 측정방식으로 움직임에 의한 잡음에 매우 취약하다. 이러한 노이즈로 인하여 측정 시 오차가 발생하게 되는데 특히 스마트폰 등을 이용한 상시 측정 시스템의 경우 이러한 노이즈의 발생이 큰 문제로 부각되게 된다. 따라서 본 연구에서는 움직이는 상태에서적외선광과 녹색광원의 노이즈영향을 측정하여 파장에 따른 움직임노이즈를 비교검토 하였다. 결과적으로 녹색광이 적외선광에 비해 움직임의 영향을 덜 받으며 이동 중에서의 측정이 용이하다는 결론을 얻었다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.7
• /
• pp.1020-1026
• /
• 2013

Multirate filtering process on the biological signals like Electrocardiogram (ECG) and Photoplethysmogram (PPG) can be defined as the digital signal processing algorithm in which the sampling rate varies to omit or interpolate the intermediate values between the sampled data. With this aim, we suggest a new multirate filtering algorithm by deleting the extraneous data to eliminate the unwanted degradations such as granular noise due to the usage of high sampling frequency and simultaneously to detect the fiducial features of ECG and PPG with reducing the complexity of resolving fiducial points such as R-peak, Pulse peak and Pulse Transit Time (PTT). After the experimental simulations performed, we can conclude the fact that we can detect the fiducial features of ECG and PPG signal in terms of R-peak, Pulse peak and PTT without the loss of accuracy even if we do not maintain the original sampling frequency.

• 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.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.6
• /
• pp.1194-1199
• /
• 2009

Heart rate may be a very important parameter in human health. To extract heart rate, the electrocardiogram(ECG) is commonly used. But the ECG acquisition procedure is very complex. On the other hand, the acquisition of pulse wave or photoplethysmogram(PPG) is very easy. However, the peak of PPG is not so sharp as ECG. This study tries to enhance the performance of peak detection in PPG signal. The method uses the average slopes around the main peak. The crossing point of the increasing and the decreasing slopes is selected as the peak point of heart rate period. The proposed method showed smoothed heart rate graph and reduced irregularity in heart rate values.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1101-1102
• /
• 2008

In this paper, we have developed PPG pillow system for unconstrained respiration monitoring during sleep. The system employs a pillow containing a PPG sensor and a simple respiration extraction algorithm. The results showed that the extracted respiratory rhythm was found to have close relations with the reference signal. The system has an advantage of processing simplicity. A follow-up study should be performed to evaluate the system in terms of breath intake.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.627-629
• /
• 2023

생체 신호를 분석하여 사용자의 건강과 정신 상태를 예측하고, 관련 질병에 관해 예방하는 연구가 늘어나고 있다. 생체 신호 중 심박은 사람의 육체, 정신적인 상태를 반영하는 대표적인 신호이지만 기존의 접촉 패드를 통한 ECG나 광학 센서를 통한 PPG로 심박을 예측할 때는 구속적인 환경이 필요하여 일상적인 상황 속에 적용하기 어려웠다. 이러한 단점을 해결하고자 본 논문은 UBFC-RPPG 데이터셋의 동영상 프레임을 RGB 채널마다 다른 가중치를 적용하는 전처리를 하여 학습 데이터의 크기를 줄이면서 정확도를 높이고, 3D-CNN을 활용한 딥러닝으로 순간적인 영상에서도 PPG 신호를 예측할 수 있도록 1초 전처리 영상을 학습한 후, 신호를 예측하는 것을 목표로 한다. 이렇게 비접촉식으로 취득된 신호는 더 다양한 환경에서의 감정분류, 우울증 진단, 질병 감지 등 다양한 분야에 활용될 수 있다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.4
• /
• pp.197-202
• /
• 2016

In this paper, a danger signal to tell caregivers when a dangerous situation occurs, the bio-signal analysis in infants to prevent sudden infant death sudden infant death propose a monitoring system. The Sudden infant death (SID) refers to a healthy baby is unexplained deaths between birth year in the month. Sudden infant death proposed monitoring system is composed of a processor unit and the monitoring and alarm part for processing part and the biological signal sensing biological signals. Using the PPG sensor to sense the bio-signal and the processor unit the signal obtained through the sensor by removing the motion artifact was able to alarm and monitoring the parent.The proposed system will send the alarm to monitoring and alerting caregivers if the risk situation by analyzing the heart rate of the infant. With the actual implementation of the system to evaluate the performance of the monitoring system.

• Journal of Biomedical Engineering Research
• /
• v.32 no.2
• /
• pp.109-117
• /
• 2011

Assuming that photons absorbed by a vessel do not have acute variations, DC component reflect the basal blood volume (or diameter) before blood pulsation. Vascular stiffness and reflection is influenced by changes in basal blood volume (or diameter). This paper describes analysis of the characteristic variations of vascular stiffness, according to relative variations in DC components of the PPG signal (25-75%). For quantitative analysis, we have used parameters that were proposed previously, reflection and stiffness index, and the second derivative of PPG waveform, b/a and d/a. Significantly, the vascular stiffness and reflections were increased according to increase in DC component of the PPG signal for more than about 3% of baseline values. The systolic blood pressure were increased from $113.1{\times}13.18$ to $116.2{\times}13.319$ mmHg, about 2.76% (r = 0.991, P < 0.001) and the AC component of the PPG signal were decreased from $2.073{\times}2.287$ to $1.973{\times}2.2038$ arbitrary unit, about 5.09% (r = -0.993, P < 0.001). It is separated by DC median and correlation analysis was performed for analyzing vascular characteristics according to instantaneous DC variations. There are significant differences between two correlation coefficients in separated data.