Heartbeat Wave Research Articles

Extreme learning machine approach on heart abnormalities identification in ECG images

Heart abnormalities are atypical heart conditions that can lead to chronic heart disease. Heart abnormalities can be severe if not treated directly due to the crucial function of the heart as the blood circulation center. Heart abnormalities cannot be seen with the naked eye so it requires the recording of a heartbeat wave or electrocardiogram (EKG) for the disease to be detected. Therefore, a strategy that uses image processing and artificial neural networks to detect anomalies in the heart is strongly advocated. The proposed methods for feature extraction and identification are Invariant Moments and Extreme Learning Machine respectively. The testing procedure for this research employed a total of 386 ECG images as training data. and 44 ECG images for test data, and the heart condition was classified into 4 classes, namely Atrial Fibrillation, T-Wave, ST-Segment, and normal heart conditions. The test was carried out using 3 choices of extreme learning machine activation functions, namely sigmoidal, sine and hard-lim. The test also applied the parameter of hidden neurons in which amounting to 10, 30, 50, 100 and 500. The system accuracy in identifying heart abnormalities achieved 95.45% by the application of the sigmoid function with the total number of hidden neurons equal to 500.

Right main pulmonary artery distensibility on dynamic ventilation CT and its association with respiratory function

BackgroundHeartbeat-based cross-sectional area (CSA) changes in the right main pulmonary artery (MPA), which reflects its distensibility associated with pulmonary hypertension, can be measured using dynamic ventilation computed tomography (DVCT) in patients with and without chronic obstructive pulmonary disease (COPD) during respiratory dynamics. We investigated the relationship between MPA distensibility (MPAD) and respiratory function and how heartbeat-based CSA is related to spirometry, mean lung density (MLD), and patient characteristics.MethodsWe retrospectively analyzed DVCT performed preoperatively in 37 patients (20 female and 17 males) with lung cancer aged 70.6 ± 7.9 years (mean ± standard deviation), 18 with COPD and 19 without. MPA-CSA was separated into respiratory and heartbeat waves by discrete Fourier transformation. For the cardiac pulse-derived waves, CSA change (CSAC) and CSA change ratio (CSACR) were calculated separately during inhalation and exhalation. Spearman rank correlation was computed.ResultIn the group without COPD as well as all cases, CSACR exhalation was inversely correlated with percent residual lung volume (%RV) and RV/total lung capacity (r = -0.68, p = 0.003 and r = -0.58, p = 0.014). In contrast, in the group with COPD, CSAC inhalation was correlated with MLDmax and MLD change rate (MLDmax/MLDmin) (r = 0.54, p = 0.020 and r = 0.64, p = 0.004) as well as CSAC exhalation and CSACR exhalation.ConclusionIn patients with insufficient exhalation, right MPAD during exhalation was decreased. Also, in COPD patients with insufficient exhalation, right MPAD was reduced during inhalation as well as exhalation, which implied that exhalation impairment is a contributing factor to pulmonary hypertension complicated with COPD.Relevance statementAssessment of MPAD in different respiratory phases on DVCT has the potential to be utilized as a non-invasive assessment for pulmonary hypertension due to lung disease and/or hypoxia and elucidation of its pathogenesis.Key points• There are no previous studies analyzing all respiratory phases of right main pulmonary artery distensibility (MPAD).• Patients with exhalation impairment decreased their right MPAD.• Analysis of MPAD on dynamic ventilation computed tomography contributes to understanding the pathogenesis of pulmonary hypertension due to lung disease and/or hypoxia in patients with expiratory impairment.Graphical

Highly Stretchable, Self-Healing, and Low Temperature Resistant Double Network Hydrogel Ionic Conductor as Flexible Sensor and Quasi-Solid Electrolyte.

With the rapid development of flexible energy storage and wearable strain sensing, conductive hydrogels are attracting attention as electrolyte materials for flexible strain sensors and flexible supercapacitors due to their excellent flexibility and wetting properties. In this work, antifreezing hydrogels with high stretchability, adhesion, and conductivity are designed and prepared by introducing phosphoric acid solutions into polyacrylamide and chitosan systems. The multifunctional hydrogel samples prepared by this method can be used as both quasi-solid electrolytes and wearable strain sensors. The hydrogel-based supercapacitor shows a charge/discharge efficiency of 99.67% and a capacitance retention of 98.85% after 10000 cycles charge/discharge tests at -30°C. The tiny characteristic heartbeat wave forms are detected by the hydrogel as a flexible strain sensor. It is foreseeable that PCP multifunctional hydrogel can be a promising flexible material for a new generation of flexible sensors and flexible energy storage devices in a certain range of temperatures.

Untact Abnormal Heartbeat Wave Detection Using Non-Contact Sensor through Transfer Learning

This paper presents an important advancement in heart activity monitoring, focusing on non-contact sensor data, which tend to be noisy due to interference, and the limitations of non-contact (untact) technology. A preprocessing filter and optimal classification model are proposed to improve the accuracy and reliability of heart rate data measured by a non-contact Doppler radar sensor, and the results are compared to those of a contact heart rate sensor (Holter monitor). The MIT-BIH Arrhythmia Database of PhysioNet are used for learning, and the results from the non-contact sensor and Holter monitor are compared for verification. To train the abnormal heartbeat waveform classification model, (1) an optimal heart rate data separation window size is selected through iterative model comparison and used for data separation, and (2) meaningful indicators of heart rate variability are selected; the data are transformed and applied as model characteristics. The non-contact sensor data are then applied to three filter algorithms, and the accuracy is assessed by comparison with the contact sensor data using the trained abnormal heartbeat waveform classification model. Learning is performed using 12 classification models, and the accuracies of the models are compared. This study demonstrates an effective new method of transfer learning for contact data abnormality detection.

An Integrated Approach for Fetal Heart Rate Estimation from Abdominal Electrocardiogram Signal

This paper introduces an integrated approach to estimate the fetal heart rate from the abdominal Electrocardiogram (ECG) signal. Empirical mode decomposition (EMD) can decompose the fetal ECG signal into a set of intrinsic mode functions, which can be used as the indicator of the occurrence for the fetal heartbeats. The decomposition basis functions are directly derived from the fetal signal under test, which make the detection process robust and adaptive. Multiple signal classification (MUSIC) is a high resolution algorithm for frequency estimation, which can be applied to the fetal heartbeats indicator sequence output from the preceding EMD, estimating the fetal heart rate in frequency domain without the heartbeat wave detection. Compared with the popular Independent component analysis (ICA) method, the proposed method has shown improved robustness and fidelity in estimation of the fetal heart rate during testing with real fetal ECG database from DaISy and PhysioNet.

무선 압력센서를 이용한 실시간 맥박수 측정기 개발

Department of Electronics and Control Engineering, Hanbat National University, Daejeon 34158, Korea(Received March 14, 2016; Revised April 19, 2016; Accepted April 22, 2016)Abstract: Among the various physiological information that could be obtained from human body, heartbeat rate is a commonly used vital sign in the clinical milieu. Photoplethysography (PPG) sensor is incorporated into many wearable healthcare devices because of its advantages such as simplicity of hardware structure and low-cost. However, healthcare device employing PPG sensor has been issued in susceptibility of light and motion artifact. In this paper, to develop the real-time heart rate measurement device that is less sensitive to the external noises, we have fabricated an ultra-small wireless LC resonant pressure sensor by MEMS process. After performance evaluation in linearity and repeatability of the MEMS pressure sensor, heartbeat waveform and rate on radial artery were obtained by using resonant frequency-pressure conversion method. The measured data using the proposed heartbeat rate measurement system was validated by comparing it with the data of an commercialized heart rate measurement device. Result of the proposed device was agreed well to that of the commercialized device. The obtained real time heartbeat wave and rate were displayed on personal mobile system by bluetooth communication.Keywords: Heartbeat, Wearable, Wireless power transmission, Pressure sensor, LC resonance !

Creating a Library of Complex Metallic Nanostructures via Harnessing Pattern Transformation of a Single PDMS Membrane

By harnessing the elastic instability in a single PDMS membrane consisting of a square lattice array of circular pores, we fabricated a library of complex nanostructures in Au with variable feature size, connectivity, and geometry, including arrays of diamond-plate patterns (or elliptic herringbones), compound structures of circular dots and elliptical lines, heartbeat waves, aligned ovals, and a rhombus lattice of holes and lines. This was achieved first by swelling the PDMS membrane, followed by convective assembly of nanoparticles on the membrane. By taking advantage of the unique 3-D topography of the nanoparticle film and its photoresist replica, we could gradually etch the photoresist film to vary the feature size and connectivity of the underlying Au patterns. Further, through a combination of mechanical stretching (at different strain levels and stretching angles) and solvent swelling of the same PDMS membrane, we created a richer library of complex patterns in Au without application of new masters.