National Institute of Technology, Karnataka

About: National Institute of Technology, Karnataka is a education organization based out in Mangalore, Karnataka, India. It is known for research contribution in the topics: Computer science & Corrosion. The organization has 5017 authors who have published 7057 publications receiving 70367 citations.

Food classification from images using convolutional neural networks

Abstract: The process of identifying food items from an image is quite an interesting field with various applications. Since food monitoring plays a leading role in health-related problems, it is becoming more essential in our day-to-day lives. In this paper, an approach has been presented to classify images of food using convolutional neural networks. Unlike the traditional artificial neural networks, convolutional neural networks have the capability of estimating the score function directly from image pixels. A 2D convolution layer has been utilised which creates a convolution kernel that is convolved with the layer input to produce a tensor of outputs. There are multiple such layers, and the outputs are concatenated at parts to form the final tensor of outputs. We also use the Max-Pooling function for the data, and the features extracted from this function are used to train the network. An accuracy of 86.97% for the classes of the FOOD-101 dataset is recognised using the proposed implementation.

The Uptake Mechanism of Cd(II), Cr(VI), Cu(II), Pb(II), and Zn(II) by Mycelia and Fruiting Bodies of Galerina vittiformis

Abstract: Optimum concentrations of heavy metals like copper, cadmium, lead, chromium, and zinc in soil are essential in carrying out various cellular activities in minimum concentrations and hence help in sustaining all life forms, although higher concentration of these metals is lethal to most of the life forms. Galerina vittiformis, a macrofungus, was found to accumulate these heavy metals into its fleshy fruiting body in the order Pb(II) > Cd(II) > Cu(II) > Zn(II) > Cr(VI) from 50 mg/kg soil. It possesses various ranges of potential cellular mechanisms that may be involved in detoxification of heavy metals and thus increases its tolerance to heavy metal stress, mainly by producing organic acids and phytochelatins (PCs). These components help in repairing stress damaged proteins and compartmentalisation of metals to vacuoles. The stress tolerance mechanism can be deduced by various analytical tools like SEM-EDX, FTIR, and LC-MS. Production of two kinds of phytochelatins was observed in the organism in response to metal stress.

Multispectral Satellite Image Denoising via Adaptive Cuckoo Search-Based Wiener Filter

Abstract: Satellite image denoising is essential for enhancing the visual quality of images and for facilitating further image processing and analysis tasks. Designing of self-tunable 2-D finite-impulse response (FIR) filters attracted researchers to explore its usefulness in various domains. Furthermore, 2-D FIR Wiener filters which estimate the desired signal using its statistical parameters became a standard method employed for signal restoration applications. In this paper, we propose a 2-D FIR Wiener filter driven by the adaptive cuckoo search (ACS) algorithm for denoising multispectral satellite images contaminated with the Gaussian noise of different variance levels. The ACS algorithm is proposed to optimize the Wiener weights for obtaining the best possible estimate of the desired uncorrupted image. Quantitative and qualitative comparisons are conducted with 10 recent denoising algorithms prominently used in the remote-sensing domain to substantiate the performance and computational capability of the proposed ACSWF. The tested data set included satellite images procured from various sources, such as Satpalda Geospatial Services, Satellite Imaging Corporation, and National Aeronautics and Space Administration. The stability analysis and study of convergence characteristics are also performed, which revealed the possibility of extending the ACSWF for real-time applications as well.

Microbial disinfection of water with endotoxin degradation by photocatalysis using Ag@TiO2 core shell nanoparticles.

Abstract: The studies on photocatalytic disinfection of water contaminated with Escherichia coli using Ag core and TiO2 shell (Ag@TiO2) nanoparticles under UV irradiation showed that these nanoparticles are very efficient in water disinfection both in their free and immobilised form. Complete disinfection of 40 × 108 CFU/mL could be achieved in 60 min with 0.4 g/L catalyst loading and in 35 min with 1 g/L catalyst loading. Ag@TiO2 nanoparticles were found to be superior to TiO2 nanoparticles in photocatalytic disinfection of water. Kinetics of disinfection followed Chick’s law, and the pseudo-first-order rate constant was 0.0168 min−1 for a catalyst loading of 0.1 g/L. Disinfection of water and degradation of endotoxins (harmful disinfection residual) occurred simultaneously during photocatalysis thereby making the treated water safe for use. Endotoxin degradation showed a shifting order of kinetics. The rate of photocatalysis with nanoparticles immobilised in cellulose acetate film was marginally lower as compared to that of free nanoparticles. Negligible Ag ion leakage and re-growth of cells post-photo-catalytic treatment of water confirmed that complete disintegration of E. coli occurred during photocatalysis making the treated water safe for use. Therefore, Ag@TiO2 nanoparticles have a potential for large-scale application in drinking water treatment plants and household purification units.