Identification of intracranial haemorrhage (ICH) using ResNet with data augmentation using CycleGAN and ICH segmentation using SegAN

Multimedia Tools and Applications - Intracranial Haemorrhage (ICH) occurring due to any injury to the brain is a fatal condition and its timely diagnosis is critically important. In this work, we...     

Significance of incorporating chrominance information for effective color-to-grayscale image conversion

This paper provides an alternative framework for color-to-grayscale image conversion by exploiting the chrominance information present in the color image using singular value decomposition (SVD). In the proposed technique of color-to-grayscale image conversion, a weight matrix corresponds to the chrominance components is derived by reconstructing the chrominance data matrix (planes a* and b*) from the eigenvalues and eigenvectors computed using SVD. The final grayscale converted image is obtained by adding the weighted chrominance data to the luminous intensity which is kept intact for the CIEL*a*b* color space of the given color image. The effectiveness of the proposed grayscale conversion is confirmed by the comparative analysis performed on the color-to-gray benchmark dataset across 10 existing algorithms based on the standard objective measures, namely normalized cross-correlation, color contrast preservation ratio, color content fidelity ratio, E score and subjective evaluation.     

Effect of replacement of fat with sesame oil and additives on rheological, microstructural, quality characteristics and fatty acid profile of cakes

Effect of replacement of fat with 25, 50, 75 and 100% sesame oil (on fat basis); 50% sesame oil, hydrocolloids and emulsifiers on the rheological, microstructural, quality characteristics and fatty acid profile of cake was studied. Addition of increasing amount of sesame oil decreased viscosity, increased specific gravity of cake batter; decreased cake volume and overall quality score. Microstructure studies showed disrupted gluten matrix. Among the two different hydrocolloids [hydroxypropylmethylcellulose (HPMC) and xanthan] and emulsifiers [glycerol monostearate (GMS) and sodium stearoyl-2-lactylate (SSL)] tried, HPMC and SSL increased the batter viscosity, decreased the specific gravity, increased the volume and overall quality score. Use of combination of HPMC and SSL improved significantly the quality characteristics of cake with 50% sesame oil in such a way that the overall quality score was higher than that of the control cake with fat. The microstructure of cake crumb with 50% sesame oil and HPMC showed a smooth structure with less number of cavities and SSL showed a continuous protein matrix. On replacing the fat with 50% sesame oil, there was a decrease in saturated fatty acids and increase in unsaturated fatty acids, particularly linoleic acid. The fatty acid profile of cake with 50% sesame oil was better than the control cake as there was 2.4 times decrease in palmitic acid content and 5.9 times increase in essential fatty acids (EFA) content.     

Evaluation of Protease-producing Ability of Fish Gut Isolate Bacillus cereus for Aqua Feed

Extracellular protease production by Bacillus cereus isolated from the intestine of fish Mugil cephalus has been investigated in shake-flask experiment using different preparations of tuna-processing waste such as raw fish meat, defatted fish meat, alkali hydrolysate, and acid hydrolysate as nitrogen source. Among the tuna preparations tested, defatted fish meat supported the maximum protease production (134.57 ± 0.47 U ml⁻¹), and 3% concentration of the same was found to be optimum for maximizing the protease production (178.50 ± 0.28 U ml⁻¹). Effect of carbon sources on protease production in the optimized concentration of defatted tuna fish meat revealed that galactose aided the higher protease production (259.83 ± 0.04 U ml^–1) than the other tested carbon sources and a concentration of 1.5% galactose registered as optimum to enhance the protease production (289.40 ± 0.16 U ml⁻¹). The halotolerancy of B. cereus for protease production indicated that 3% of sodium chloride was optimum to yield maximum protease (301.63 ± 0.20 U ml⁻¹). Among the surfactants tested, protease production was high in Triton X 100-added medium (298.63 ± 0.12 U ml⁻¹) when compared to other surfactants, and its optimum concentration recorded was 0.8% (320.57 ± 0.17 U ml⁻¹) for more protease production. Partial characterization of crude enzyme revealed that pH 7.0 (278.90 ± 0.08 U ml⁻¹) and 60°C temperature (332.37 ± 0.18 U ml⁻¹) were optimum for better protease activity by B. cereus.     

CADSE: communication aware design space exploration for efficient run-time MPSoC management

Real-time multi-media applications are increasingly mapped on modern embedded systems based on multiprocessor systems-on-chip (MPSoC). Tasks of the applications need to be mapped on the MPSoC resources efficiently in order to satisfy their performance constraints. Exploring all the possible mappings, i.e., tasks to resources combinations exhaustively may take days or weeks. Additionally, the exploration is performed at design-time, which cannot handle dynamism in applications and resources’ status. A runtime mapping technique can cater for the dynamism but cannot guarantee for strict timing deadlines due to large computations involved at run-time. Thus, an approach performing feasible compute intensive exploration at design-time and using the explored results at run-time is required. This paper presents a solution in the same direction. Communicationaware design space exploration (CADSE) techniques have been proposed to explore different mapping options to be selected at run-time subject to desired performance and available MPSoC resources. Experiments show that the proposed techniques for exploration are faster over an exhaustive exploration and provides almost the same quality of results.     

Highly conducting and transparent Ga2O3 doped ZnO thin films prepared by thermal evaporation method

Amorphous zinc oxide thin films are obtained by thermally evaporating pure zinc oxide powder. Films obtained have an excellent conductivity of 90 ??^?1 cm^?1 with transparency of up to 90% in the visible region. On doping with gallium oxide a great improvement in the conductivity of up to 8.7 × 10³ ??^?1 cm^?1 is observed and the optical band gap of the films is decreased from 3.25 to 3.2 eV, retaining the transparency. Measurements of activation energy show that the doped ZnO film has one donor level at 68 meV and other at 26 meV bellow the conduction band.     

Network Simulation Environment (NSE): A Generic Framework for Network Graphs

A Network Simulation Environment (NSE) tool for identifying various routes within the network graphs based on clustering concept is proposed. The proposed tool is designed using object-oriented approach in Microsoft Windows environment. It allows the user to create, modify and display network graphs. One of the main features of the simulation package is the visualisation of the clustering of the graph to the acyclic level. It shows the step by step clustering of the network graph. The reverse process of unclustering is also featured in the proposed package. It offers a generic framework for comparing different types of routing algorithms by computing routing times and many other attributes for various algorithms. In addition, the simulation package provides facilities for printing and saving the network graphs.     

Band selection using variational mode decomposition applied in sparsity-based hyperspectral unmixing algorithms

In this work, a frequency-based dimensionality reduction technique using variational mode decomposition (VMD) is proposed. Dimensionality reduction is a very important aspect of preprocessing in case of hyperspectral image (HSI) analysis where this step helps in elimination of the lesser informative bands, thereby reducing the size of the data and making its processing computationally less challenging. In contrast to the standard dimensionality reduction methods such as inter-band block correlation (IBBC) where bands are eliminated based on their similarity with the consecutive bands, the proposed method uses frequency information of each band to categorize it as a less or more informative band. In this way, only the topmost informative bands of HSI are selected to form the reduced dataset. In our experiment, in order to verify the efficiency of VMD as a dimensionality reduction technique, the hyperspectral unmixed results obtained for IBBC reduced dataset is compared with those obtained for VMD reduced dataset. From the parametric measures such as classification accuracy, root-mean-square error (RMSE) and visual results obtained after unmixing for both IBBC and VMD reduced datasets, it is noticed that the VMD reduced dataset performs better by achieving higher classification accuracy and lower RMSE than that of the existing IBBC method.     

Proactive modeling: a new model intelligence technique

This article discusses a model intelligence technique called proactive modeling. The goal of proactive modeling is to reduce the amount of manual modeling required when using a graphical DSML and to assist in step-by-step creation of a model. Proactive modeling accomplishes this goal by examining the metamodels syntax and constraints, automatically executing model modifications, and prompting the modeler for assistance when more than one valid model modification exists, but none are necessary. We have integrated proactive modeling into the generic modeling environment (GME) as a generic add-on that can operate on any domain-specific modeling language implemented in GME. Lastly, results from applying proactive modeling to several DSMLs in GME show that it can reduce modeling effort.     

Static Modeling of GMAW Process Using Artificial Neural Networks

Due to the complexity of the welding process, neural network based approach is being considered as an effective way to represent the required model. This paper describes the steps adopted to construct the neural network model for GMAW (Gas Metal Arc Welding) welds. A detailed analysis of the simulation results has been carried out to evaluate the proposed neural network model. Some practical considerations that may come across in the modeling process are also discussed. Finally, a suitable proposal to improve the construction of the model has also been presented in the paper.