Showing papers by "Arijit Das published in 2021"

Spatio-temporal concentration of atmospheric particulate matter (PM2.5) during pandemic: A study on most polluted cities of indo-gangetic plain

Abstract: COVID-19 pandemic exhibited the entire world two aspects: human threats and environmental restoration. Due to pandemic, the nationwide lockdown in India imposed on 25 March and continued till 31 May 2020 in different phases. Again partial withdrawl of restrictions started from UnlockI (1–30 June 2020) to revive the Indian economy partially. The present research focused to assess impact of lockdown on the concentration of particulate matter (PM2.5) across the ten most polluted cities of Indo-Gangetic Plain of India alongwith incorporation of spatial distribution of PM2.5hotspots. It observed that during lockdown, the average concentration of PM2.5(μg/m3) across the cities decreased from 197 to 79 which is decrease of 60% since pre lockdown. In January 2020, the cities under considerations were in the category of ‘severe’ air quality index (AQI) but from March no cities fall under this category. The hotspot maps showed that in last three years (2017–2019), relatively higher concentration of PM2.5 was observed mostly around Delhi NCR but during same period of 2020 (lockdown and Unlock I), this concentartion decreased substantially. The findings of the study suggest that only by effective policies like short term lockdown, implementation of odd and even number motor vehicles, relocation of polluted industries need to be implemented by central and state governmental authorities to achive environmental sustainability.

Deep learning based Bengali question answering system using semantic textual similarity

Abstract: Recently, Question answering system is a major research area in language processing. Bengali isone of the most popular spoken languages in India. Still, it has faced difficulties in natural language processing.Among the semantic based systems, word mapping and keyword based approaches achieved the best results and got better attention on the user side. These systems are already implemented in various languages but not much in Indian language like Bengali. This work presents an efficient question answering system for retrieving Bengali language text. This system includes word embedding clustering and deep level feature representation for providing better grammatical similarities for retrieving the Bengali textual contents relevant to user queries. The pre-trained word embedding module is created by the help of a deep belief network. The modified density peak algorithm is employed to perform word embedding clustering.The presented work has been tested on a dataset from the Bengali corpus developed by TDIL and synthetic Bengali translated datasets accessible in English called SQuAD 2.0. This question answering system is implemented in python with NLTK tool kit and got good performance while retrieving the Bengali textual data.