ABSTRACT
Due to sudden evolution and spread of COVID-19, the entire community in the globe is at risk. The covid has affected the health and economy and caused loss of life. In India, due to social economic factors, several thousands of people are infected, and India is seen as one of the top countries seriously impacted by the pandemic. Despite of having a modern medical instruments, drugs, and technical technology, it is very difficult to contain the spread of virus and save people from risk. Healthcare system and government personnel need to get an insight of covid outbreaks in the near future to decide on stepping up the healthcare facilities, to take necessary actions and to implement prevention policies to minimize the spread. In order to help the government, this study aims to build model a forecast COVID-19 model to foretell growth curve by predicting number of confirmed cases. Three variant models based on long short-term memory (LSTM) were built on the Indian COVID-19 dataset and are compared using the root mean squared error (RMSE) and mean absolute percentage error (MAPE). The findings have revealed that the proposed stacked LSTM model outperforms the other proposed LSTM variants and is suitable for forecasting COVID-19 progress in India. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
ABSTRACT
The recent COVID-19 pandemic has made important changes to the everyday practice of anaesthetists. Current research has shown that the virus spreads via respiratory droplets and aerosolisation. The aim of this study was to examine the extent of contact contamination, droplet spread and aerosolisation, which may occur with normal breathing and intubation in a mannequin study. In the first experiment, an Ambu bag was attached to the simulation mannequin’s trachea and an atomiser device was placed into the mannequin’s pharynx. This model simulated normal ventilation as 0.5 ml of luminescent fluid was sprayed through the atomiser. In the second experiment, the mannequin was intubated with a videolaryngoscope while spraying 0.5 ml of luminescent fluid through the atomiser, after which the laryngoscope was removed. The spread of the luminescent aerosol cloud after three full breaths, droplet spread and contact contamination were visualised using ultraviolet light. The extent of spread was evaluated using a 4-point Likert scale (0 to 3) by two observers. Each of the experiments was repeated five times. For the first experiment, aerosol formation, droplet spread and contact contamination were 2.5 (2–3), 1 (0–1), 0 (0–1) points. In the second experiment, aerosol formation, droplet spread and contact contamination were 0.5 (0–1), 1 (0–1), 3 (2–3) points, accordingly. Noticeable contact contamination occurs during laryngoscopy and removal of the laryngoscope, whereas droplet contamination with laryngoscopy and normal breathing is minimal. Normal breathing leads to significant aerosol formation.
ABSTRACT
This study aimed to realize Sustainable Development Goals (SDGs), i.e., no poverty, zero hunger, and sustainable cities and communities through the implementation of an intelligent cattle-monitoring system to enhance dairy production. Livestock industries in developing countries lack the technology that can directly impact meat and dairy products, where human resources are a major factor. This study proposed a novel, cost-effective, smart dairy-monitoring system by implementing intelligent wireless sensor nodes, the Internet of Things (IoT), and a Node-Micro controller Unit (Node-MCU). The proposed system comprises three modules, including an intelligent environmental parameter regularization system, a cow collar (equipped with a temperature sensor, a GPS module to locate the animal, and a stethoscope to update the heart rate), and an automatic water-filling unit for drinking water. Furthermore, a novel IoT-based front end has been developed to take data from prescribed modules and maintain a separate database for further analysis. The presented Wireless Sensor Nodes (WSNs) can intelligently determine the case of any instability in environmental parameters. Moreover, the cow collar is designed to obtain precise values of the temperature, heart rate, and accurate location of the animal. Additionally, auto-notification to the concerned party is a valuable addition developed in the cow collar design. It employed a plug-and-play design to provide ease in implementation. Moreover, automation reduces human intervention, hence labor costs are decreased when a farm has hundreds of animals. The proposed system also increases the production of dairy and meat products by improving animal health via the regularization of the environment and automated food and watering. The current study represents a comprehensive comparative analysis of the proposed implementation with the existing systems that validate the novelty of this work. This implementation can be further stretched for other applications, i.e., smart monitoring of zoo animals and poultry.
ABSTRACT
Today COVID-19 pandemic articulates high stress on clinical resources around the world. At present, physical and viral tests are slowly emerging, and there is a need for robust pandemic detection that biomedical sensors can aid. The utility of biomedical sensors is correlated with the medical instruments with physiological metrics. These Biomedical sensors are integrated with the systematic device to track the target analytes with a biomedical component. The COVID-19 patients' samples are collected, and biomarkers are detected using four sensors: blood pressure sensor, G-FET based biosensor, electrochemical sensor, and potentiometric sensor with different quantifiable measures. The imputed data is then profiled with chest X-ray images from the Covid-19 patients.Multi-Layer Perceptron (MLP), an AI model, is deployed to identify the hidden signatures with biomarkers. The performance of the biosensor is measured with three parameters such as sensitivity, specificity and detection limit by generating the calibration plots that accurately fits the model.