Hangsik Shin

Adaptive threshold method for the peak detection of photoplethysmographic waveform

Photoplethysmography (PPG)-based temporal analyses have been widely used as a useful analytical method in physiological and cardiovascular diagnosis. Most of temporal approaches of PPG are based on detected peak points, peak and foot of PPG. The aim of presented study is the development of improved peak detection algorithm of PPG waveform. The present study demonstrates a promising approach to overcome respiration effect and to detect PPG peak. More extensive investigation is necessary to adapt for the cardiovascular diseases, whose PPG morphology has different form.

Robust algorithm for arrhythmia classification in ECG using extreme learning machine.

BackgroundRecently, extensive studies have been carried out on arrhythmia classification algorithms using artificial intelligence pattern recognition methods such as neural network. To improve practicality, many studies have focused on learning speed and the accuracy of neural networks. However, algorithms based on neural networks still have some problems concerning practical application, such as slow learning speeds and unstable performance caused by local minima.MethodsIn this paper we propose a novel arrhythmia classification algorithm which has a fast learning speed and high accuracy, and uses Morphology Filtering, Principal Component Analysis and Extreme Learning Machine (ELM). The proposed algorithm can classify six beat types: normal beat, left bundle branch block, right bundle branch block, premature ventricular contraction, atrial premature beat, and paced beat.ResultsThe experimental results of the entire MIT-BIH arrhythmia database demonstrate that the performances of the proposed algorithm are 98.00% in terms of average sensitivity, 97.95% in terms of average specificity, and 98.72% in terms of average accuracy. These accuracy levels are higher than or comparable with those of existing methods. We make a comparative study of algorithm using an ELM, back propagation neural network (BPNN), radial basis function network (RBFN), or support vector machine (SVM). Concerning the aspect of learning time, the proposed algorithm using ELM is about 290, 70, and 3 times faster than an algorithm using a BPNN, RBFN, and SVM, respectively.ConclusionThe proposed algorithm shows effective accuracy performance with a short learning time. In addition we ascertained the robustness of the proposed algorithm by evaluating the entire MIT-BIH arrhythmia database.

Noncontact Respiration Rate Measurement System Using an Ultrasonic Proximity Sensor

This research presents the ultrasonic proximity sensor approach to respiration measurement. The ultrasonic proximity sensor measures respiration signatures and rates in real-time and for long-term monitoring, which is necessary for mobility from the end-user perspective. The study used a 240 kHz ultrasonic sensor to measure the time of flight of a sound wave between the transmitted signal and received signal during respiration in the abdominal wall-motion. Respiration rates measured with the ultrasonic proximity sensor were then compared with those measured with a thermocouple sensor on ten male subjects. Data from the measurement of respiration rates at 100 cm is provided. We have used this data from the method comparison study to confirm agreement with the reference signal to determine that the current version of respiratory rate detection system using ultrasonic can successfully measure respiration rates. The proposed respiratory measurement method could be used to monitor an unconscious person without the need to apply electrodes or other sensors in the correct position and to wire the subject to the system. Monitoring respiration using ultrasonic sensor offers a promising possibility of noncontact measurement of respiration rates. In particular, this technology offers a potentially inexpensive means to extend applications to consumer home-healthcare and mobile-healthcare products. Further advances in the sensor design, system design and signal processing can increase the range and quality of the measurement, broadening the potential application areas of this technology.

Simplified Structural Textile Respiration Sensor Based on Capacitive Pressure Sensing Method

We propose a simplified structural textile capacitive respiration sensor (TCRS) for respiration monitoring system. The TCRS is fabricated with conductive textile and Polyester, and it has a simple layered architecture. We derive the respiration by the distance changes between two textile plates in the TCRS, which measures the force from the abdominal diameter changes with the respiratory movement. To evaluate the reliability of TCRS, both linearity test and comparison test were carried out. Three times of tensile experiment were performed to confirm the linearity of change in capacitance by the distance change. The result shows that the coefficient of determination (R2) of proposed TCRS is 0.9933. For comparative study, 16 subjects were participating in the experiment. As a result, the proposed respiratory rate detection system using TCRS successfully measures respiration compared with nasal airflow detection (R = 0.9846, p <; 0.001). In Bland-Altman analysis, the upper limit agreement is 0.5018 respirations per minute and lower limit of the agreement is -0.5049 respirations per minute. From these results, we confirmed that the TCRS could be used for monitoring of unconscious persons, avoiding the uncomfortness of subjects. Monitoring respiration using TCRS offers a promising possibility of convenient measurement of respiration rates. In particular, this technology offers a potentially inexpensive implementation that could extend applications to consumer home-healthcare and mobile-healthcare products.

Algorithm for Classifying Arrhythmia using Extreme Learning Machine and Principal Component Analysis

In this paper, we developed the novel algorithm for cardiac arrhythmia classification. Until now, back propagation neural network (BPNN) was frequently used for these tasks. However, general gradient based learning method is far slower than what is required for their application. The proposed algorithm adapts extreme learning machine (ELM) that has the advantage of very fast learning speed and high accuracy. In this paper, we classify beats into normal beat, left bundle branch block beat, right bundle branch block beat, premature ventricular contraction, atrial premature beat, paced beat, and ventricular escape beat. Experimental results show that we can obtain 97.45 % in average accuracy, 97.44 % in average sensitivity, 98.46 % in average specificity, and 2.423 seconds in learning time.

Unconstrained snoring detection using a smartphone during ordinary sleep

BackgroundSnoring can be a representative symptom of a sleep disorder, and thus snoring detection is quite important to improving the quality of an individual’s daily life. The purpose of this research is to develop an unconstrained snoring detection technique that can be integrated into a smartphone application. In contrast with previous studies, we developed a practical technique for snoring detection during ordinary sleep by using the built-in sound recording system of a smartphone, and the recording was carried out in a standard private bedroom.MethodThe experimental protocol was designed to include a variety of actions that frequently produce noise (including coughing, playing music, talking, rining an alarm, opening/closing doors, running a fan, playing the radio, and walking) in order to accurately recreate the actual circumstances during sleep. The sound data were recorded for 10 individuals during actual sleep. In total, 44 snoring data sets and 75 noise datasets were acquired. The algorithm uses formant analysis to examine sound features according to the frequency and magnitude. Then, a quadratic classifier is used to distinguish snoring from non-snoring noises. Ten-fold cross validation was used to evaluate the developed snoring detection methods, and validation was repeated 100 times randomly to improve statistical effectiveness.ResultsThe overall results showed that the proposed method is competitive with those from previous research. The proposed method presented 95.07% accuracy, 98.58% sensitivity, 94.62% specificity, and 70.38% positive predictivity.ConclusionThough there was a relatively high false positive rate, the results show the possibility for ubiquitous personal snoring detection through a smartphone application that takes into account data from normally occurring noises without training using preexisting data.

Feasibility study for the non-invasive blood pressure estimation based on ppg morphology: normotensive subject study

BackgroundBlood pressure is a critical bio-signal and its importance has been increased with the aged society and the growth of cardiovascular disease population. However, most of hypertensive patients have been suffered the inconvenience in monitoring blood pressure in daily life because the measurement of the blood pressure depends on the cuff-based technique. Nowadays there are many trials to measure blood pressure without cuff, especially, photoplethysmography (PPG) based research is carried out in various ways.MethodsOur research is designed to hypothesis the relationship between vessel wall movement and pressure-flow relationship of PPG and to validate its appropriateness by experimental methods. PPG waveform is simplified by approximate model, and then it is analyzed as the velocity and the acceleration of blood flow using the derivatives of PPG. Finally, we develop pressure index (PI) as an estimation factor of blood pressure by combining of statistically significant segments of photoplethysmographic waveform.ResultsTwenty-five subjects were participated in the experiment. As a result of simulation, correlation coefficients between developed PI and blood pressure were represented with Rxa0=xa00.818, Rxa0=xa00.827 and Rxa0=xa00.615 in systolic blood pressure, pulse pressure and mean arterial pressure, respectively, and both of result showed the meaningful statistically significance (Pxa0<xa00.05).ConclusionsCurrent study can estimate only the relative variation of blood pressure but could not find the absolute pressure value. Moreover, proposed index has the limitation of diastolic pressure tracing. However, the result shows that the proposed PI is statistically significantly correlated with blood pressures, and it suggests that the proposed PI as a promising additional parameter for the cuff less blood pressure monitoring.

Simple and Robust Realtime QRS Detection Algorithm Based on Spatiotemporal Characteristic of the QRS Complex.

The purpose of this research is to develop an intuitive and robust realtime QRS detection algorithm based on the physiological characteristics of the electrocardiogram waveform. The proposed algorithm finds the QRS complex based on the dual criteria of the amplitude and duration of QRS complex. It consists of simple operations, such as a finite impulse response filter, differentiation or thresholding without complex and computational operations like a wavelet transformation. The QRS detection performance is evaluated by using both an MIT-BIH arrhythmia database and an AHA ECG database (a total of 435,700 beats). The sensitivity (SE) and positive predictivity value (PPV) were 99.85% and 99.86%, respectively. According to the database, the SE and PPV were 99.90% and 99.91% in the MIT-BIH database and 99.84% and 99.84% in the AHA database, respectively. The result of the noisy environment test using record 119 from the MIT-BIH database indicated that the proposed method was scarcely affected by noise above 5 dB SNR (SE = 100%, PPV > 98%) without the need for an additional de-noising or back searching process.

Feasibility Study of Sitting Posture Monitoring Based on Piezoresistive Conductive Film-Based Flexible Force Sensor

A study was conducted to develop a force sensor made of piezoresistive conductive film and to assess the feasibility of detecting inappropriate sitting postures using the force sensor platform. The force sensor was designed with multiple layers and includes a conductive foil and an insulation cover. The sensor delivers voltage output according to its power-law characteristics in response to a change in the applied force. The distribution of pressure was measured for three postures-upright, forward leaning, and backward leaning-using a three-by-three sensor array attached to a chair. The results indicate that the ratio of the average pressure distribution on the front row to that on the rear row of the sensor array exhibits a significant variation.

The Relationship among Complex Fractionated Electrograms, Wavebreak, Phase Singularity, and Local Dominant Frequency in Fibrillation Wave-Dynamics: a Modeling Comparison Study

Although complex fractionated electrogram (CFE) is known to be a target for catheter ablation of fibrillation, its physiological meaning in fibrillation wave-dynamics remains to be clarified. We evaluated the spatiotemporal relationships among the parameters of fibrillation wave-dynamics by simulation modeling. We generated maps of CFE-cycle length (CFE-CL), local dominant frequency (LDF), wave break (WB), and phase singularity (PS) of fibrillation in 2-dimensional homogeneous bidomain cardiac modeling (1,000 × 1,000 cells ten Tusscher model). We compared spatiotemporal correlations by dichotomizing each maps into 10 × 10 lattice zones. In spatial distribution, WB and PS showed excellent correlation (R = 0.963, P < 0.001). CFE-CL had weak correlations with WB (R = 0.288, P < 0.001), PS (R = 0.313, P < 0.001), and LDF (R = -0.411, P < 0.001). However, LDF did not show correlation with PS or WB. PSs were mostly distributed at the periphery of low CFE-CL area. Virtual ablation (5% of critical mass) of CFE-CL < 100 ms terminated fibrillation at 14.3 sec, and high LDF ablation (5% of critical mass) changed fibrillation to organized tachycardia, respectively. In homogeneous 2D fibrillation modeling, CFE-CL was weakly correlated with WB, PS, and LDF, spatiotemporally. PSs are mostly positioned at the periphery of low CFE-CL areas, and virtual ablation targeting low CFE-CL regions terminated fibrillation successfully. Graphical Abstract