ECG signal classification and arrhythmia detection using ELM-RNN

Arrhythmia is a unique type of heart disease which produces inefficient and irregular heartbeat. This is a cardiac disease which is diagnosed through electrocardiogram (ECG) procedure. Several studies have been focused on the speed and accuracy on the learning algorithm by applying pattern recognition, artificial intelligence in the classification algorithm. In this work a novel classification algorithm is planned based on ELM (Extreme Learning Machine) with Recurrent Neural Network (RNN) by using morphological filtering. The popular publicly available ECG arrhythmia database (MIT-BIH arrhythmia DB) is used to express the performance of the proposed algorithm where the level of accuracy is compared with the existing similar types of work. The comparative study shows that performance of our proposed model is much faster than the models working with RBFN (radial basis function network), BPBB(back propagation neural network) and Support Vector Machine. The experimental result with the MIT BIH database with hidden neurons of ELM with RNN, the accuracy is 96.41%, sensitivity 93.62% and specificity 92.66%. The classification methodology follows main four steps the heart beat detection, the ECG feature extraction, feature selection and the construction of the proposed classifier.

     

Supplementary Networking of Interpenetrating Polymer System (SNIPSy) Strategy to Develop Strong & High Water Content Ionic Hydrogels for Solid Electrolyte Applications

To synthesize hydrogels that possess tensile strength and modulus together in MPas along with extensibility at high equilibrium water content (≥90 wt%) is challenging but important from the application perspective. Especially, such hydrogel compositions are useful for fabricating flexible electronics devices for subsea applications, where underwater risk-free implementation and optimum device performance at low temperature (≈0 °C) and high hydrostatic pressure (≤20 bar) conditions is desirable. The high water content of hydrogel is necessary to facilitate ion transportation, and mechanical strength is desirable to maintain a stable electrode–electrolyte interface under load. In this study, supplementary networking of an interpenetrating polymer system strategy is utilized to develop ionic hydrogels with tensile strength and Young's modulus values up to 2 and 1.67 MPa, respectively, at high equilibrium water content value up to 96%. Cost-effective, durable, rechargeable, and flexible batteries are fabricated using the Zn & Li ion soaked hydrogel as solid electrolyte without barrier. These batteries display minimal loss in capacity when immersed in water, deformed, exposed to flame, put under high load, and operated under low-temperature conditions suggesting the viability for subsea application.     

Influence of graphene oxide concentration and dipping cycles on electrical conductivity of coated cotton textiles

The electrical conductivity of cotton fabrics is enhanced by coating with graphene in aqueous phase by a suitable process. Two different types of fabrics viz. woven and knitted structures of same GSM are used as substrate. The fabrics are dipped in dispersed graphene oxide (GO) solution and then GO-enriched fabric samples are subjected to a reduction process for in-situ conversion of the added GO to electro-conductive graphene. The concentration of GO solution and number of dipping cycles influence the graphene add-on and electrical resistivity of the fabrics. The change in surface resistivity, thickness, air permeability, porosity and water vapour permeability of the fabrics after the treatment has been evaluated. Comparisons have been made between the woven and knitted fabrics for all these properties to understand the effect of fabric structure.     

Deep neural network to detect COVID-19: one architecture for both CT Scans and Chest X-rays

Applied Intelligence - Since December 2019, the novel COVID-19’s spread rate is exponential, and AI-driven tools are used to prevent further spreading [1]. They can help predict, screen, and...