Search

Atrial fibrillation (AF) is the most common type of cardiac arrhythmia and is characterized by the heart's beating in an uncoordinated manner. In clinical studies, patients often do not have visible symptoms during AF, and hence it is harder to detect this cardiac ailment. Therefore, automated detection of AF using the electrocardiogram (ECG) signals can reduce the risk of stroke, coronary artery disease, and other cardiovascular complications. In this paper, a novel time-frequency domain deep learning-based approach is proposed to detect AF and classify terminating and non-terminating AF episodes using ECG signals. This approach involves evaluating the time-frequency representation (TFR) of ECG signals using the chirplet transform. The two-dimensional (2D) deep convolutional bidirectional long short-term memory (BLSTM) neural network model is used to detect and classify AF episodes using the time-frequency images of ECG signals. The proposed TFR based 2D deep learning approach is evaluated using the ECG signals from three public databases. Our developed approach has obtained an accuracy, sensitivity, and specificity of 99.18% (Confidence interval (CI) as [98.86, 99.49]), 99.17% (CI as [98.85 99.49]), and 99.18% (CI as [98.86 99.49]), respectively, with 10-fold cross-validation (CV) technique to detect AF automatically. The proposed approach also classified terminating and non-terminating AF episodes with an average accuracy of 75.86%. The average accuracy value obtained using the proposed approach is higher than the short-time Fourier transform (STFT), discrete-time continuous wavelet transform (DT-CWT), and Stockwell transform (ST) based time-frequency analysis methods with deep convolutional BLSTM models to detect AF. The proposed approach has better AF detection performance than the existing deep learning-based techniques using ECG signals from the MIT-BIH database., (Copyright © 2021 Elsevier Ltd. All rights reserved.)

A synthetic procedure for the encapsulation of cadmium selenide (CdSe) nanoparticles in a sago starch matrix is introduced. The nanocomposite was investigated using structural, spectroscopic, and thermal methods. TEM micrographs of the nanocomposite showed spherical CdSe particles of 4-5 nm in size coated with a biopolymer layer. The absorption edges of both the aqueous solution and the thin film of the CdSe-starch nanocomposite were shifted toward lower wavelengths in comparison to the value of the bulk semiconductor. Infrared measurements revealed that the interaction of CdSe nanoparticles and starch chains takes place via OH groups. Although the onset of the temperature of decomposition of CdSe-starch nanocomposite is lower than that of the pure matrix, thermogravimetric analysis also showed that introduction of CdSe nanoparticles significantly reduced starch degradation rate leading to high residual mass at the end of the degradation process.

Adsorption of sulfide ions onto a surface of starch capped silver nanoparticles upon addition of thioacetamide was investigated. UV-vis absorption spectroscopy revealed that the adsorption of the sulfide ion on the surface of the silver nanoparticles induced damping as well as blue shift of the silver surface plasmon resonance band. Further increase in thioacetamide concentration led to shift of the resonance band toward higher wavelengths indicating the formation of the continuous Ag2S layer on the silver surface. Thus fabricated nanoparticles were investigated using electron microscopy techniques (TEM, HRTEM, and HAADF-STEM) and X-ray photoelectron spectroscopy (XPS), which confirmed their core-shell structure.

Solid organ transplant has been steadily increasing in number both nationally and internationally. Caring for the transplant patients in the hospital setting, right after the patient is moved from the intensive care unit to the ward, is one of the most challenging tasks in nursing. It involves many procedures, rigid protocols, tight monitoring, and intensive data gathering for use by the other coordinating healthcare professionals. The complexity is further increased when a nurse has to take care of several transplant patients in a single shift. Of late, there has been a growth of computer applications in nursing and clinical information systems. Their acceptability and usability determine the ultimate success of computer support for this complex task. In this paper, we present a case study in which we combine two well-known software engineering techniques--namely, agile programming and user centered design--toward the goal of developing an interactive system for supporting the activities of transplant nurses in a hospital setting. This has resulted in a usable end-product and the user centered approach has motivated the nurses to move towards the use of computers in their jobs for better productivity. The product's usability was formally evaluated and is reported herein. The strengths and limitations of this approach are also discussed. The software product developed has been well accepted and is currently being planned to replace the manual methods followed in the transplant ward of a large metropolitan hospital.