COVID-19 Article Classification Using Word-Embedding and Different Variants of Deep-Learning Approach

The COVID-19 pandemic has changed the way we go about our everyday lives, and we will continue to see its impact for a long time. These changes especially apply to the business world, where the market is very volatile as a result. Requirements of the people are changing rapidly, as are the restrictions on transport and trade of goods. Due to the intense competition and struggles brought about due to the pandemic, acting first on profit opportunities is crucial to businesses doing well in the current climate. Thus, getting the relevant news in time, out of the huge number of COVID-19 related articles published daily is of utmost importance. The same applies to other industries, like the medical industry, where innovations and solutions to managing COVID-19 can save lives, and money in other parts of the world. Manually combing through the massive number of articles posted every day is both impractical and laborious. This task has the potential to be automated using Natural Language Processing (NLP) with Deep Learning based approaches. In this paper, we conduct exhaustive experiments to find the best combination of word-embedding, feature selection, and classification techniques;and find the best structure for the Deep Learning model for article classification in the COVID-19 context. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Sex Work, COVID-19, and Half-truths: Results from a Multistate Survey of Sex Workers

The COVID-19 pandemic and associated lockdowns have affected informal labour markets in India at large. But how have they affected sex workers in particular? Going beyond the urban-centric reportage of exploited sex workers confined to brothels with no incomes and heavy debts, how were they affected and what were their coping strategies? In this paper, we draw upon the results of a multistate survey of female/male/ transgender sex workers to present a more realistic and nuanced narrative. In particular, we revisit and complicate some of the stereotypes concerning the immobility of sex workers within informal labour markets, their indebtedness, and bondage to informal creditors. At the same time, we draw attention to the much-needed support from the state in tiding over the pandemic-induced crises. © 2022 Economic and Political Weekly. All rights reserved.

COVID-19 Article Classification Using Word-Embedding and Extreme Learning Machine with Various Kernels

The impact of the COVID-19 pandemic on the socially networked world cannot be understated. Entire industries need the latest information from across the globe at the earliest possible. The business world needs to cope with a very volatile market due to the pandemic. Businesses need to be swift in sensing potential profit opportunities and be updated on the changing consumer demands. Technological advances and medical procedures that successfully deal with COVID-19 can help save lives on the other side of the world. This seamless passage of crucial information, now more than ever, is only possible through the networked world. There are on average 821 articles published online on COVID-19 a day. Manually going through around 800 articles in a day is not feasible and highly time-consuming. This can prevent the industries and businesses from getting to the relevant information in time. We can optimize this task by applying machine learning techniques. In this work, six different word embedding techniques have been applied to the title and content of the articles to get an n-dimensional vector. These vectors are inputs for article classification models that employ Extreme Learning Machine (ELM) with linear, sigmoid, polynomial, and radial basis function kernels to train these models. We have also used feature selection techniques like the Analysis of Variance (ANOVA) test and Principal Component Analysis (PCA) to optimize the models. These models help to filter out relevant articles and speed up the process of getting crucial information to stay ahead of the competition and be the first to exploit new market opportunities. The experimental results highlight that the usage of word embedding techniques, feature selection techniques, and different ELM kernels help improve the accuracy of article classification. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Validating social distancing through deep learning and VR-based digital twins

The Covid-19 pandemic resulted in a catastrophic loss to global economies, and social distancing was consistently found to be an effective means to curb the virus’s spread. However, it is only as effective when every individual partakes in it with equal alacrity. Past literature outlined scenarios where computer vision was used to detect people and to enforce social distancing automatically. We have created a Digital Twin (DT) of an existing laboratory space for remote monitoring of room occupancy and automatically detecting violation of social distancing. To evaluate the proposed solution, we have implemented a Convolutional Neural Network (CNN) model for detecting people, both in a limited-sized dataset of real humans, and a synthetic dataset of humanoid figures. Our proposed computer vision models are validated for both real and synthetic data in terms of accurately detecting persons, posture, and intermediate distances among people. © 2021 Copyright held by the owner/author(s).