Search

Coronavirus pandemic that has spread all over the world, is one of its kind in the recent past, that has mobilized researchers in areas such as (not limited to) pre-screening solutions, contact tracing, vaccine developments, and crowd estimation. Pre-screening using symptoms identification, cough classification, and contact tracing mobile applications gained significant popularity during the initial outbreak of the pandemic. Audio recordings of coughing individuals are one of the sources that can help in the pre-screening of COVID-19 patients. This research focuses on quantitative analysis of covid cough classification using audio recordings of coughing individuals. For analysis, we used three different publicly available datasets i.e., COUGHVID, NoCoCoDa, and a self-collected dataset through a web application. We observed that wet cough has more correlation with covid cough as opposed to dry cough. However, the classification model trained with wet and dry coughs, both, has similar test performance as that of the model trained with wet cough samples only. We conclude that audio-signal recordings of coughing individuals have the potential as a pre-screening test for COVID-19.

This paper analyzes the potential of using shortwave NIRS (near-infrared spectroscopy) for fruit classification problems. The research focuses on O-H and C-H overtone features of fruit and its correlation with NIRS and therefore opens a new dimension of fruit classification problems using NIRS. Eleven fruits, which include apple, cherry, hass, kiwi, grapes, mango, melon, orange, loquat, plum, and apricot, were used in this study to cover physical characteristics such as peel thinness, pulp, seed thickness, and size. NIR spectral data is collected using the industry-standard F-750 fruit quality meter (wavelength range 300-1100nm) for all fruit mentioned above. Different shallow machine learning architectures were trained to classify fruits using spectral feature vectors. At first, using 83 features vectors within the range of 725-975nm (3nm-resolution) and then using only four features of wavelength 770nm, 840nm, 910nm, and 960nm (corresponding to O-H and C-H overtone features). For the 83 spectral features range as an input, the QDA classifier achieved a cross-validation accuracy of 100% and a test data accuracy of 93.02%. For the four features vector as an input, the QDA classifier achieved a cross-validation accuracy of 97.1% and test data accuracy of 90.38%. The results demonstrate that fruit classification is mainly a function of absorptivity of short wave NIR radiation primarily with respect to O-H and C-H overtones features. An LED-based device mainly having 770nm, 840nm, 910nm, and 960nm range LEDs can be used in applications where automation in fruit classification is required.