ABSTRACT
This research is focused on a highly effective and untapped feature called gammatone frequency cepstral coefficients (GFCC) for the detection of COVID-19 by using the nature-inspired meta-heuristic algorithm of deer hunting optimization and artificial neural network (DHO-ANN). The noisy crowdsourced cough datasets were collected from the public domain. This research work claimed that the GFCC yielded better results in terms of COVID-19 detection as compared to the widely used Mel-frequency cepstral coefficient in noisy crowdsourced speech corpora. The proposed algorithm's performance for detecting COVID-19 disease is rigorously validated using statistical measures, F1 score, confusion matrix, specificity, and sensitivity parameters. Besides, it is found that the proposed algorithm using GFCC performs well in terms of detecting the COVID-19 disease from the noisy crowdsourced cough dataset, COUGHVID. Moreover, the proposed algorithm and undertaken feature parameters have improved the detection of COVID-19 by 5% compared to the existing methods. © 2023 CRL Publishing. All rights reserved.
ABSTRACT
The world is experiencing Covid-19. As the pace of rate of Covid infection 2019 (COVID-19) is quickly expanding in various pieces of world, a dependable conjecture for the aggregate affirmed cases and the quantity of passing can be useful for policymakers in settling on the choices for using accessible assets in the country. The widespread of Covid 19 spoilage the world, with the highest loss of lives in US. To reduce the number of Covid-19 affected population, Vaccine are available in public domain. Some Covid 19 Vaccines are currently in human trials. For the effective result of Covid 19 Vaccine, it must be accepted by maximum number of population. A survey was conducted to analyze the health effect of the vaccine in different category of people. Information was collected such as demographic data (age, sex, gender, marital status), mental condition of people before vaccination, tobacco/smoking, alcohol consumption, people suffering from any prior disease, labour group, people taking precaution medicine after vaccination, prepare for second dose of vaccination. Using these given information we have applied machine learning algorithms to predict if the individual will take the second dose of Covid-19 vaccine or not. © 2022 IEEE.
ABSTRACT
When COVID-19 necessitated remote teaching, mechanics faculty needed to quickly convert hands-on teaching props into equally effective online equivalents. This constraint sparked a new innovation in a Mechanics of Materials course. Unable to pass around a foam beam to demonstrate concepts such as "plane sections remain plane," or an annotated wood cube to illustrate the sign convention for shear stress, dozens of interactive CAD models were developed with the open-source browser software SketchUp. The CAD models have been uploaded to SketchUp's 3D Warehouse and placed in the public domain. They are opened by students in browser windows and are manipulated in 3D space. Familiarity with the modeling software led to a second innovation: the presentation of exam problems in SketchUp. In an exam, students are provided with a hyperlink to a CAD model in the public domain. Students navigate the model in 3D space, note key dimensions, and perform requested calculations. Assessment of the impact of these innovations is ongoing in Fall 2020, as the 2D problems used on paper exams in prior years are now being presented to students in full 3D. This paper will explain how this approach is easily accessible to all faculty, including those with minimal CAD experience. Additionally, the public-domain 3D models will be demonstrated, and links shared, so that these visualizations may be used at other institutions and shared across the engineering education community. © American Society for Engineering Education, 2021