The occurrence of life-threatening ventricular arrhythmias (VAs) such as Ventricular tachycardia (VT) and Ventricular fibrillation (VF) leads to sudden cardiac death which requires detection at an early stage. The main aim of this work is to develop an automated system using machine learning tool for accurate prediction of VAs that may reduce the mortality rate. In this paper, a novel method using variational mode decomposition (VMD) based features and C4.5 classifier for detection of ventricular arrhythmias is presented. The VMD model was used to decompose the electrocardiography (ECG) signals to extract useful informative features. The method was tested for ECG signals obtained from PhysioNet database. Two standard databases i.e. CUDB (Creighton University Ventricular Tachyarrhythmia Database) and VFDB (MIT-BIH Malignant Ventricular Ectopy Database) were considered for this work. A set of time–frequency features were extracted and ranked by the gain ratio attribute evaluation method. The ranked features are subjected to support vector machine (SVM) and C4.5 classifier for classification of normal, VT and VF classes. The best detection was obtained with sensitivity of 97.97%, specificity of 99.15%, and accuracy of 99.18% for C4.5 classifier with a 5 s data analysis window. These results were better than SVM classifier result having an average accuracy of 86.87%. Hence, the proposed method demonstrates the efficiency in detecting the life-threatening VAs and can serve as an assistive tool to clinicians in the diagnosis process.
In this paper, a study has been done on the solid-state coating of SS316 over medium-carbon steel EN8. The objective is to determine the characterization of friction-surfaced joints with process parameters such as axial load, traverse speed and rotational speed. Coating thickness and coating width depend on the traverse and rotational speeds, which decrease with the increase in axial load. A maximum bending strength of 134 MPa was obtained for the sample with highest axial load of 9 kN, rotational speed of 1600 rpm and traverse speed of 2.2 mm/s. The XRD peaks of SS316-coated EN08 sample show a considerable shift, indicating martensite (α′) formation. It has been observed that strong bonding could be obtained under specific conditions, as the substrate bonding materials are metallurgically inconsistent and have a tendency to form brittle compounds. External degradation occurred when the specimen was exposed to elevated temperatures. The results were analyzed statistically. To access its potential application corrosion studies were carried out, which shows SS316 overlaid EN8 exhibits better corrosion resistance than the substrate EN8 sample. 相似文献
In this study, the use of PLA‐g‐MA is investigated as a potential method for improving interfacial adhesion between agricultural residues and PLA, with the goal of enhancing mechanical properties. Compatibilization was achieved by using PLA‐g‐MA prepared via reactive extrusion. Green renewable and compatibilized PLA/wheat straw composites were extruded and injection‐molded. Addition of 3 and 5 phr PLA‐g‐MA to the composites resulted in significant improvements in tensile strength (20%) and flexural strength (14%) of the composites, matching that of the neat polymer. The observed improvement in strength was attributed to the good interfacial adhesion between the fiber and matrix.
The effects of process engineering in the fabrication of PHBV, PLA and their blends prepared by melt blending are studied. The elongation of an optimized blend can be improved by 148 and 250% over the virgin PHBV and PLA polymers, respectively. DSC shows that the two polymers are immiscible in blends of any composition. The crystallinity of PHBV is hindered by the presence of PLA. UV‐Vis demonstrates the opacity of the blend with incorporation of PHBV to the PLA phase. The observed tensile modulus of the optimized sample is compared with theoretical values from the rule of mixtures. Gordon‐Taylor's equation is applied on the glass transition temperatures for theoretical modeling to explain the miscibility of the polymers.
In the current study, a combination of acrylic polyol (AP) and ester polyol (EP) were synthesized and reacted at variable ratios with hexamethylene diisocyanates and isophorone diisocyanates to prepare a transparent two-component polyurethane (PU) coating formulation. The formations of the polyol system, isocyanate system, and the PU systems were confirmed by 1H nuclear magnetic resonance and Fourier-transform infrared spectroscopy. Transparency of the coatings was examined using haze, and gloss measurement, which showed acrylic-ester-polyurethane (aePU-5 and aePU-6) have 91.5% and 91.8% transparency and gloss of 90.3 and 90.7 GU respectively. The thermal properties like Tg and the thermal stability of the coatings were verified using differential scanning calorimetry, and thermogravimetric analysis respectively which was found to increase with increasing EP content and decreasing AP content which may be ascribed to improved compatibility of copolymers, and homogeneity in PU along with enhanced crosslinking density. The degree of adhesion of coating with the substrate was validated from lap-shear, and cross-cut tape test which showed improved performance at AP:EP ratio of 60:40. The coatings were found to exhibit resistance toward pencil hardness with aePU-5 and aePU-6 having the optimum resistance of 9H. The surface morphology and topography were observed under scanning electron microscopy, and atomic force microscopy, respectively. The outcome confirms the higher smoothness of the surfaces subjected to the increase in EP content. The PU system with 40 wt% AP content and 60 wt% EP designated as aePU-5 was found to exhibit optimum performance. 相似文献