Tamil is an old Indian language with a large corpus of literature on palm leaves, and other constituents. Palm leaf manuscripts were a versatile medium for narrating medicines, literature, theatre, and other subjects. Because of the necessity for digitalization and transcription, recognizing the cursive characters found in palm leaf manuscripts remains an open problem. In this research, a unique Convolutional Neural Network (CNN) technique is utilized to train the characteristics of the palm leaf characters. By this training, CNN can classify the palm leaf characters significantly on training phase. Initially, a preprocessing technique to remove noise in the input image is done through morphological operations. Text Line Slicing segmentation scheme is used to segment the palm leaf characters. In feature processing, there are some major steps used in this study, which include text line spacing, spacing without obstacle, and spacing with an obstacle. Finally, the extracted cursive characters are given as input to the CNN technique for final classification. The experiments are carried out with collected cursive Tamil palm leaf manuscripts to validate the performance of the proposed CNN with existing deep learning techniques in terms of accuracy, precision, recall, etc. The results proved that the proposed network achieved 94% of accuracy, where existing ResNet achieved 88% of accuracy.
Two-dimensional materials have attracted the attention of many researchers. Especially in transition metal dichalcogenides (TMDs), WS2 has great surface to volume ratio, a wide range of band gaps, high thermal and oxidative stability. It also has peak carrier mobility and less effective mass than other TMDs, leading to its use in many applications, including solar cells, LED, rechargeable batteries and sensors. We have analyzed the stability and electronic properties of monolayer and doped WS2 with Cobalt, Iron, and Nickel using density functional theory. The stability of the system has been studied by the formation energy. The electronic properties were analyzed by band structure, the density of states, charge transfer, chemical potential, and total energy of the systems. These results predict that the formation energy of the doped system increases with a negative magnitude which proves that the doped structures are more stable. Comparing the WS2 monolayer with the transition metal doped WS2, we have observed reasonable changes in the band structure and density of states. Doped WS2 shows better results than monolayer WS2 in stability and improved electronic properties. These results may provide a prospective insight for making a gas sensing device
The in vitro antidiabetic efficacy of ethanolic extract Boerhavia diffusa (B.diffusa) synthesized silver nanoparticles (AgNPs) was investigated by inhibition of α-amylase, α-glucosidase, protein glycation assay, non-enzymatic glycosylation of hemoglobin, glucose uptake by yeast cells and glucose diffusion at varying concentrations (10 to 100µg/ml). The alpha-amylase assay shows that the acarbose (standard) and B. diffusa had IC50 values of 46.2 µg/ml and 55.4 µg/ml, whereas alpha-glucosidase inhibitory activity was found to be 63.4 µg/ml and 93.0 µg/ml respectively. Further, non-enzymatic glycosylation analysis showed IC50 value of metformin (standard) as 28.6 µg/ml and B. diffusa as 63.9 µg/ml. The protein glycation activity was inhibited in non-enzymatic glycosylation of hemoglobin. The glycosylation was induced using pioglitazone (standard) which gives IC50 value of 616.4 µg/ml by which B. diffusa showed 756.3 µg/ml. The uptake of glucose by yeast cells was analyzed and the result shows that the glucose concentration increased steadily from 5mM to 25mM (maximum absorption) of both metronidazole (standard) and B. diffusa. From 30 to 180 minutes, the glucose diffusion experiment revealed that the concentration of the metformin and B. diffusa extract was positively correlated with the time. The ethanolic extract of synthesized AgNPs and the reference medication employed in all experiments both benefit their curative potential for the treatment of insulin resistance. The generated silver nanoparticles can be used for industrial and therapeutic purposes and can be released into the environment without harm. More in vivo study can be reviewed, however the green synthesized ethanolic extract of B. diffusa exhibits promising affect for the treatment of diabetes mellitus.
Objectives: The aim of the present research was to evaluate the antidiabetic, hyperlipidemic, and histopathological analysis in streptozotocin-induced diabetic rats (60 mg/kg body weight) using the ethanolic extract of leaves of Boerhavia diffusa (ELBD) (500 mg/kg body weight).Method: The rats were orally administered with the leaf extract for 45 days. Fasting blood was collected at the end of the experimental period by cardiac puncture to carry out the biochemical parameters, the organs such as liver, kidney, and pancreas were also excised to perform the histopathological analysis by fixing in 10% formalin solution.Results: Oral administration with the leaf extract resulted in decrease in the levels of blood glucose, with a concomitant increase in their body weight. The extracts also produced a significant decrease in the lipid levels when compared with the diabetic groups. Moreover, the extracts also exerted a favorable effect on the histopathological changes of liver, pancreas, and kidney.Conclusion: The results of the present study revealed that the ELBD possess antidiabetic and antihyperlipidemic properties. These effects may be due to the presence of bioactive components justifying its ethnomedical use.
Advances in image processing includes foreseeing the data necessities of Governments, perceiving and following humans and things, diagnosing ailments, performing medical procedure, and programmed driving of all types of transport. The future image processing utilizations of satellite based imaging ranges from planetary exploration to surveillance applications. This paper "Enhancement and Recognition of Number Plate Using OCR Technique" is proposed to distinguish the vehicles by their number plates without direct human mediation. The proposed work is framed into 3 stages: First stage is extraction of number plate from entire assortment of vehicle image; Second Stage is segmentation of characters from the extracted number plate and third stage is to perceive the segmented characters and to show the output result. From the entire input image, just the number plate is detected and processed further using character segmentation. From the extracted number plate, each character is isolated by segmentation in the character segmentation phase. After the segmentation of character, the recognition is done by character recognition phase. The proposed framework is implemented using MATLAB.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.