ABSTRACT
Background:Influenza is an important respiratory infection, causing 250,000 to 500,000 deaths annually. Influenza virus A is the most virulent and associated with winter epidemics in temperate regions, more persistent transmission in the tropics, and occasional large-scale global pandemics. But, there is variability in the pattern, and the H1N1 pandemic of 2009-2010 was unusually with a large spike in spring and a sharp decline continuing throughout winter. Varying in pattern is due to antigenic shift and drift and reassortment of the virus. Methods:A prospective study was carried out in Advance Basic Sciences & Clinical Research Lab, Department of Micro- biology in SMS Medical College & Hospital, Jaipur for diagnosis of Influenza A virus as well as subtyping was done using RT-PCR technique over 1 year period (July 2019 to June 2020) and demographic data was noted. Results:Total of 7213 samples were tested, out of which 498 (6.90%) were positive for Influenza A which is less from the previous year’s 22.46%. Out of total positive cases Influenza a (H1N1) pdm09 was 24.9% and InfA H3N2 was 75.10%. InfA H3N2 was the prominent circulating strain in all months while Influenza a (H1N1) pdm09 was prominent strain pre- vious year. Majority of positive cases were found in March 2020 (43.17%), September 2019 (28.51%). Most of these cases 36.14% were from age group between 20 to 40 years. Conclusions: A decline in the positivity of influenza infection compared to last year is seen which could be in part due to circulation of SARS COV 2 and measures of prevention undertaken by community to prevent it. Demographic parame- ters and seasonal variation of Influenza A virus give ideas to create awareness and to improve control strategies to mini- mize the morbidity, mortality and spread of disease.
ABSTRACT
During the COVID-19 pandemic, people across the world are worried and are highly concerned. The overall purpose of to study and research was to help society by providing a digital solution to this problem which was a chatbot through which people can at some extent self-evaluate that they are safe or not. In this paper, we propose a chatbot for answering queries related to COVID-19 by using artificial intelligence. Various natural language processing algorithms have been used to process datasets. By artificial neural network, the model is created, and it is trained from the processed data, so that appropriate response can be generated by our chatbot. Assessment of the chatbot is done by testing it with a hugely different set of questions, where it performed well. Also, accuracy of chatbot is likely to increase upon increasing dataset.