Birla Institute of Technology, Mesra

About: Birla Institute of Technology, Mesra is a education organization based out in Ranchi, India. It is known for research contribution in the topics: Computer science & Dielectric. The organization has 2801 authors who have published 4789 publications receiving 52426 citations. The organization is also known as: BIT.

TLCoV- An automated Covid-19 screening model using Transfer Learning from Chest X-ray images

Abstract: The Coronavirus disease (Covid-19) has been declared a pandemic by World Health Organisation (WHO) and till date caused 585,727 numbers of deaths all over the world. The only way to minimize the number of death is to quarantine the patients tested Corona positive. The quick spread of this disease can be reduced by automatic screening to cover the lack of radiologists. Though the researchers already have done extremely well to design pioneering deep learning models for the screening of Covid-19, most of them results in low accuracy rate. In addition, over-fitting problem increases difficulties for those models to learn on existing Covid-19 datasets. In this paper, an automated Covid-19 screening model is designed to identify the patients suffering from this disease by using their chest X-ray images. The model classifies the images in three categories - Covid-19 positive, other pneumonia infection and no infection. Three learning schemes such as CNN, VGG-16 and ResNet-50 are separately used to learn the model. A standard Covid-19 radiography dataset from the repository of Kaggle is used to get the chest X-ray images. The performance of the model with all the three learning schemes has been evaluated and it shows VGG-16 performed better as compared to CNN and ResNet-50. The model with VGG-16 gives the accuracy of 97.67%, precision of 96.65%, recall of 96.54% and F1 score of 96.59%. The performance evaluation also shows that our model outperforms two existing models to screen the Covid-19.

ISFC-BLS (Intelligent and Secured Fuzzy Clustering Algorithm Using Balanced Load Sub-Cluster Formation) in WSN Environment

Abstract: Wireless sensor networks (WSNs) have variety of applications and comprise of numerous tiny sensor nodes that are deployed to process and transmit the sensed data to the base station. Security and energy efficiency are the two major concerns for prolonging the lifetime of the WSN. Due to their broadcast nature, WSNs are prone to several threats that needs to be resolved. An effective clustering scheme can overcome these security threats and enhance the energy efficiency as well as lifetime of the network. A secured and energy efficient Intelligent and Secured Fuzzy Clustering Algorithm using Balanced Load Sub-cluster formation (ISFC-BLS) routing protocol for WSNs is proposed and corresponding maintenance methods and routing algorithms are established. On the basis of previous works, in order to select cluster heads in hierarchical topology, in this paper, a solution based on fuzzy based clustering technique is proposed which facilitates cooperative communication in the network and the balanced load sub cluster formation is proposed that helps to determine the nodes which joins the cluster. Ant colony optimization is used for determining the optimal path to the destination. Experimental results and performance analysis demonstrate that ISFC-BLS is more effective and secure than energy efficient heterogeneous ring clustering and other existing clustering techniques, for enhancing the networks lifetime and achieving better energy efficiency by decreasing the number of control messages and the node energy consumption.

Imidazole as an anti-epileptic: an overview

Abstract: Imidazole is incorporated into many important biological molecules. The major revolution in the field of imidazole derivatives with antiepileptic properties came with the synthesis of Denzimol and Nafimidone, which leads in its effectiveness among other molecules. The pharmacophore and substitution necessary to elevate the pharmacological effect of these derivatives in curing epilepsy are presented in this review, which can serve the medicinal chemist working on epileptic research to focus on this untouched class of molecules and enlarge its category and synthesize more active and potent anticonvulsant agents.