• The Journal of the Acoustical Society of Korea
• /
• v.26 no.4
• /
• pp.144-152
• /
• 2007

Conventional research works on the classification of the heart sound signal have been done mainly with the artificial neural networks. But the analysis results on the statistical characteristic of the heart sound signal have shown that the HMM is suitable for modeling the heart sound signal. In this paper, we model the various heart sound signals representing different heart diseases with the HMM and find that the classification rate is much affected by the clustering of the heart sound signal. Also, the heart sound signal acquired in real environments is a continuous signal without any specified starting and ending points of time. Hence, for the classification based on the HMM, the continuous cyclic heart sound signal needs to be manually segmented to obtain isolated cycles of the signal. As the manual segmentation will incur the errors in the segmentation and will not be adequate for real time processing, we propose a variant of the ergodic HMM which does not need segmentation procedures. Simulation results show that the proposed method successfully classifies continuous heart sounds with high accuracy.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.277-283
• /
• 2023

Vital signals provide essential information regarding the health status of individuals, thereby contributing to health management and medical research. Present monitoring methods, such as ECGs (Electrocardiograms) and smartwatches, demand proximity and fixed postures, which limit their applicability. To address this, Non-contact vital signal measurement methods, such as CW (Continuous-Wave) radar, have emerged as a solution. However, unwanted signal components and a stepwise processing approach lead to errors and limitations in heart rate detection. To overcome these issues, this study introduces an integrated neural network approach that combines noise removal, demodulation, and dominant-frequency detection into a unified process. The neural network employed for signal processing in this research adopts a MLP (Multi-Layer Perceptron) architecture, which analyzes the in-phase and quadrature signals collected within a specified time window, using two distinct input layers. The training of the neural network utilizes CW radar signals and reference heart rates obtained from the ECG. In the experimental evaluation, networks trained on different datasets were compared, and their performance was assessed based on loss and frequency accuracy. The proposed methodology exhibits substantial potential for achieving precise vital signals through non-contact measurements, effectively mitigating the limitations of existing methodologies.

• Journal of the Society of Disaster Information
• /
• v.16 no.1
• /
• pp.87-95
• /
• 2020

Purpose: In this paper, we propose an algorithm for detecting respiratory rate and heart beat of a driver of car by exploiting Doppler radar, and verifying the feasibility of the study through experiments. Method: In this paper, we propose a weighted peak detection technique using peak frequency values. The tests are performed in stop-state and driving-state, and the experiment result is analyzed by two proposed algorithms. Result: The results showed more than 95% and 96% accuracy of respiratory and heart rate, respectively. It also showed more than 72% and 84% accuracy of those even for driving experiments. Conclusion: The proposed detection scheme for vital signs can be used for the safety of the driver as well as for prevention of a large size of car accidents.

• Journal of Biomedical Engineering Research
• /
• v.31 no.4
• /
• pp.316-320
• /
• 2010

HRV(Heart rate variability) analysis parameter is widely used as an index to evaluate the autonomic nervous system and cardiac function. For reliable HRV analysis, we need to acquire the accurate ECG signals. Most of commercially available portable ECG devices have low sampling rate because of low power consumption and small size issues, which make it difficult to measure RR-interval accurately. This study is to improve the accuracy of RR-interval by developing R-wave interpolation technique, based on the morphological characteristics of the QRS complex. When the developed method was applied to ECG obtained at 200 Hz and the results were compared with 1000 Hz reference device, the error range decreased by 1.33 times in sitting and by 2.38 times in cycling exercise. Therefore, the proposed interpolation technique is thought to be useful to improve the accuracy of R-R interval in the portable ECG device with low sampling rate.

• Journal of Korea Game Society
• /
• v.17 no.2
• /
• pp.17-26
• /
• 2017

Excessive use of the internet and smart phones have become a social issue. The level of engagement has both positive and negative effects such as good performance or indulgence phenomenon, respectively. This study was to develop an algorithm to determine the engagement state based on cardiovascular response. The participants were asked to play a pattern matching game and the experimental design was divided into cooperation and competition task to provide the level of engagement. The correlation between heart rate and amplitude was analyzed according to each task. The regression equation and accuracy were verified by polynomial regression analysis. The results showed that heart rate and amplitude were positively correlated when the task was a game, and negatively correlated when there was a reference task. The accuracy of classifying between game and reference task was 89%. The accuracy between tasks was confirmed to be 76.5%. This study is expected to be used to quantitatively evaluate the level of engagement in real time.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1395-1405
• /
• 2017

In this paper, we analyses heart beat data to identify subjects stress state (binary) using heart rate variability (HRV) features extracted from heart beat data of the subjects and implement supervised machine learning techniques to create the mental stress classifier. There are four steps need to be done: data acquisition, data processing (HRV analysis), features selection, and machine learning, before doing performance measurement. There are 56 features generated from the HRV Analysis module with several of them are selected (using own algorithm) after computing the Pearson Correlation Matrix (p-values). The results of the list of selected features compared with all features data are compared by its model error after training using several machine learning techniques: support vector machine, decision tree, and discriminant analysis. SVM model and decision tree model with using selected features shows close results compared to using all recording by only 1% difference. Meanwhile, the discriminant analysis differs about 5%. All the machine learning method used in this works have 90% maximum average accuracy.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.328-330
• /
• 2004

In this paper, ECG based cardiac disease diagnosis models are developed. Conventionally, ECG monitoring equipments can only measure and store ECG signals and they always require medical doctor's diagnosis actions which are not desirable for continuous ambulatory monitoring and diagnosis healthcare systems. In this paper, two kinds of neural based self cardiac disease diagnosis engines are developed and tested for four kinds of diseases, sinus bradycardia, sinus tachycardia, left bundle branch block and right bundle branch block. For diagnosis engines, error backpropagation neural network (BP) and probabilistic neural network (PNN) were applied. Five signal features including heart rate, QRS interval, PR interval, QT interval, and T wave types were selected for diagnosis characteristics. To show the validity of proposed diagnosis engine, MIT-BIH database were used to test. Test results showed that BP based diagnosis engine has 71% of diagnosis accuracy which is superior to accuracy of PNN based diagnosis engine. However, PNN based diagnosis engine showed superior diagnosis accuracy for complex-disease diagnoses than BP based diagnosis engine.

• Journal of Digital Convergence
• /
• v.19 no.9
• /
• pp.257-269
• /
• 2021

The purpose of this study is to collect biosignal data in a non-invasive and non-restrictive manner using a BCG (Ballistocardiogram) sensor, and utilize artificial intelligence machine learning algorithms in ICT and high-performance computing environments. And it is to present and study a method for developing and validating a data-based blood glucose prediction model. In the blood glucose level prediction model, the input nodes in the MLP architecture are data of heart rate, respiration rate, stroke volume, heart rate variability, SDNN, RMSSD, PNN50, age, and gender, and the hidden layer 7 were used. As a result of the experiment, the average MSE, MAE, and RMSE values of the learning data tested 5 times were 0.5226, 0.6328, and 0.7692, respectively, and the average values of the validation data were 0.5408, 0.6776, and 0.7968, respectively, and the coefficient of determination (R²) was 0.9997. If research to standardize a model for predicting blood sugar levels based on data and to verify data set collection and prediction accuracy continues, it is expected that it can be used for non-invasive blood sugar level management.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2159-2164
• /
• 2008

Ubiquitous healthcare system is system that monitors and manages user's health information, and most important in the healthcare system is accuracy of the measured health data. But, the accuracy changes remarkably according to user's motion artifacts in real life. To elevate accuracy of health data, we proposed new algorithm to detect maximum point of pulse wave for heart rate extraction. and the proposed algorithm is to detect maximum points detect of pulse wave in photo-plethysmography signal included motion artifacts by fuzzy inference and multi sub-band filters. In results of experiment to evaluate the performance of the proposed algorithm, we could verify the proposed algorithm extracted maximum point of pulse wave in complex motion artifacts.

• Journal of Preventive Medicine and Public Health
• /
• v.17 no.1
• /
• pp.289-294
• /
• 1984

The energy expended while playing tennis was determined from the players heart rate and from the amount of oxygen they consumed. This study was made using eight healthy but unathletic male college students. Expired air was collected for 2 minute periods during each game by the Douglas bag method. Samples were collected when serving and receiving. The air collected was measured using a wet test gas meter. The amount of air collected was expressed in STPD. Oxygen consumption was determined by measuring the oxygen content of the expired air with a Orzat gas analyzer. The energy expended during the tennis games was calculated indirectly. The caloric coefficient of oxygen was multiplied by the volume of oxygen consumed. The caloric coefficient of oxygen varied from 4.6 to 5.1 kcal/liter of oxygen. In this study the value of 5 kcal/liter of oxygen was used in the calculations. The accuracy of the measurements of energy expended was tested using regression analysis of the measured volume of oxygen. The mean values of heart rate, oxygen consumed and energy expended did not vary when the activity of serving and receiving was compared. The mean value of oxygen consumed during play was $1.4329{\pm}282ml/min$ or $21.6{\pm}4.0ml/kg/min$. The energy expended was $7.15{\pm}1.46kcal/min$ or $6.45{\pm}1.23kcal/kg/min$. The values were equivalent to 5.5 mets. When the levels of oxygen consumed were estimated using the formulas, they were found to be higher than the measured levels. The estimated amounts, however, were within 25% of the measured amounts.