Machine learning approach for detecting Covid-19 from speech signal using Mel frequency magnitude coefficient.

The Covid-19 pandemic is one of the most significant global health concerns that have emerged in this decade. Intelligent healthcare technology and techniques based on speech signal and artificial intelligence make it feasible to provide a faster and more efficient timely detection of Covid-19. The main objective of our study is to design speech signal-based noninvasive, low-cost, remote diagnosis of Covid-19. In this study, we have developed system to detect Covid-19 from speech signal using Mel frequency magnitude coefficients (MFMC) and machine learning techniques. In order to capture higher-order spectral features, the spectrum is divided into a larger number of subbands with narrower bandwidths as MFMC, which leads to better frequency resolution and less overall noise. As a consequence of an improvement in frequency resolution as well as a decrease in the quantity of noise that is included with the extraction of MFMC, the higher-order MFMCs are able to identify Covid-19 from speech signals with an increased level of accuracy. The procedures for machine learning are often less complicated than those for deep learning, and they may commonly be carried out on regular computers. However, deep learning systems need extensive computing power and data storage. Twelve, twenty-four, thirty, and forty spectral coefficients are obtained using MFMC in our study, and from these coefficients, performance is accessed using machine learning classifiers, such as random forests and K-nearest neighbor (KNN); however, KNN has performed better than the other model with having AUC score of 0.80.

Highly selective sensor for the detection of Hg2+ ions using homocysteine functionalised quartz crystal microbalance with cross-linked pyridinedicarboxylic acid.

This study reports an insightful portable vector network analyser (VNA)-based measurement technique for quick and selective detection of Hg2+ ions in nanomolar (nM) range using homocysteine (HCys)-functionalised quartz-crystal-microbalance (QCM) with cross-linked-pyridinedicarboxylic acid (PDCA). The excessive exposure to mercury can cause damage to many human organs, such as the brain, lungs, stomach, and kidneys, etc. Hence, the authors have proposed a portable experimental platform capable of achieving the detection in 20-30 min with a limit of detection (LOD) 0.1 ppb (0.498 nM) and a better dynamic range (0.498 nM-6.74 mM), which perfectly describes its excellent performance over other reported techniques. The detection time for various laboratory-based techniques is generally 12-24 h. The proposed method used the benefits of thin-film, nanoparticles (NPs), and QCM-based technology to overcome the limitation of NPs-based technique and have LOD of 0.1 ppb (0.1 µg/l) for selective Hg2+ ions detection which is many times less than the World Health Organization limit of 6 µg/l. The main advantage of the proposed QCM-based platform is its portability, excellent repeatability, millilitre sample volume requirement, and easy process flow, which makes it suitable as an early warning system for selective detection of mercury ions without any costly measuring instruments.