SVM directed machine learning classifier for human action recognition network.

Understanding human behavior and human action recognition are both essential components of effective surveillance video analysis for the purpose of guaranteeing public safety. However, existing approaches such as three-dimensional convolutional neural networks (3D CNN) and two-stream neural networks (2SNN) have computational hurdles due to the significant parameterization they require. In this paper, we offer HARNet, a specialized lightweight residual 3D CNN that is built on directed acyclic graphs and was created expressly to handle these issues and achieve effective human action detection.

Characterization of a potential β-lactamase inhibitory metabolite from a marine Streptomyces sp. PM49 active against multidrug-resistant pathogens.

Actinobacteria is a prolific producer of complex natural products; we isolated a potential marine Streptomyces sp. PM49 strain from Bay of Bengal coastal area of India. The strain PM49 exhibited highly efficient antibacterial properties on multidrug-resistant pathogens with a zone of inhibition of 14-17 mm.

Mechanism of drug resistance, characterization of plasmid-borne determinants and transformation study in P. aeruginosa from burn and ICU units-its susceptibility pattern.

The transfer of drug resistance between hospital pathogens has led to alarming increase of multidrug resistant strains imposing therapeutic challenges. These resistant isolates harbor various mechanisms to counteract the drugs administered and have been reported to deliver these factors to sensitive strains in hostile environment. The present study aimed to screen for multidrug resistant Pseudomonas aeruginosa strains for the production of extended-spectrum β-lactamases, metallo-β-lactamases, AmpC β-lactamase, drug efflux phenotypes and co-transfer the resistance for cephalosporin and other non-beta lactam antibiotics in CaCl2 treated drug sensitive E.