Birla Institute of Technology and Science

About: Birla Institute of Technology and Science is a education organization based out in Pilāni, Rajasthan, India. It is known for research contribution in the topics: Computer science & Population. The organization has 8897 authors who have published 13947 publications receiving 170008 citations.

Complex permittivity and microwave absorption properties of a composite dielectric absorber

Abstract: Two types of composite samples were prepared using dielectric particulates such as BaTiO3, polyaniline and conducting carbon in polyurethane matrix. One of the composite samples contains synthesized BaTiO3 and polyaniline, while the other sample using, the commercial ingredients. Structural properties of both synthesized and commercial BaTiO3 and polyaniline have been investigated. Complex permittivity ( e r ′ - j e r ″ ) and microwave absorption properties of the prepared composites were studied in X-band (8.2–13.5 GHz). An optimized composite sample with synthesized BaTiO3 and polyaniline has shown a maximum reflection loss of −25 dB (>99% power absorption) at 11.2 GHz with a bandwidth (full frequency width at half of the maximum response) of 2.7 GHz in a sample thickness of 2.5 mm. The measured absorption values have been validated by theoretical calculations. Materials can find applications in suppression of electromagnetic interference (EMI) and reduction of radar signature.

Supervised Machine Learning Models for Prediction of COVID-19 Infection using Epidemiology Dataset

Abstract: COVID-19 or 2019-nCoV is no longer pandemic but rather endemic, with more than 651,247 people around world having lost their lives after contracting the disease. Currently, there is no specific treatment or cure for COVID-19, and thus living with the disease and its symptoms is inevitable. This reality has placed a massive burden on limited healthcare systems worldwide especially in the developing nations. Although neither an effective, clinically proven antiviral agents' strategy nor an approved vaccine exist to eradicate the COVID-19 pandemic, there are alternatives that may reduce the huge burden on not only limited healthcare systems but also the economic sector; the most promising include harnessing non-clinical techniques such as machine learning, data mining, deep learning and other artificial intelligence. These alternatives would facilitate diagnosis and prognosis for 2019-nCoV pandemic patients. Supervised machine learning models for COVID-19 infection were developed in this work with learning algorithms which include logistic regression, decision tree, support vector machine, naive Bayes, and artificial neutral network using epidemiology labeled dataset for positive and negative COVID-19 cases of Mexico. The correlation coefficient analysis between various dependent and independent features was carried out to determine a strength relationship between each dependent feature and independent feature of the dataset prior to developing the models. The 80% of the training dataset were used for training the models while the remaining 20% were used for testing the models. The result of the performance evaluation of the models showed that decision tree model has the highest accuracy of 94.99% while the Support Vector Machine Model has the highest sensitivity of 93.34% and Naive Bayes Model has the highest specificity of 94.30%.

Detecting misinformation in online social networks using cognitive psychology

Abstract: The paper explores the use of concepts in cognitive psychology to evaluate the spread of misinformation, disinformation and propaganda in online social networks. Analysing online social networks to identify metrics to infer cues of deception will enable us to measure diffusion of misinformation. The cognitive process involved in the decision to spread information involves answering four main questions viz consistency of message, coherency of message, credibility of source and general acceptability of message. We have used the cues of deception to analyse these questions to obtain solutions for preventing the spread of misinformation. We have proposed an algorithm to effectively detect deliberate spread of false information which would enable users to make informed decisions while spreading information in social networks. The computationally efficient algorithm uses the collaborative filtering property of social networks to measure the credibility of sources of information as well as quality of news items. The validation of the proposed methodology has been done on the online social network `Twitter’.