An Efficient Medical Image Deep Fusion Model Based on Convolutional Neural Networks

Medical image fusion is considered the best method for obtaining one image with rich details for efficient medical diagnosis and therapy. Deep learning provides a high performance for several medical image analysis applications. This paper proposes a deep learning model for the medical image fusion process. This model depends on Convolutional Neural Network (CNN). The basic idea of the proposed model is to extract features from both CT and MR images. Then, an additional process is executed on the extracted features. After that, the fused feature map is reconstructed to obtain the resulting fused image. Finally, the quality of the resulting fused image is enhanced by various enhancement techniques such as Histogram Matching (HM), Histogram Equalization (HE), fuzzy technique, fuzzy type Π, and Contrast Limited Histogram Equalization (CLAHE). The performance of the proposed fusion-based CNN model is measured by various metrics of the fusion and enhancement quality. Different realistic datasets of different modalities and diseases are tested and implemented. Also, real datasets are tested in the simulation analysis.     

Dynamic S-Box Generation Using Novel Chaotic Map with Nonlinearity Tweaking

A substitution box (S-Box) is a crucial component of contemporary cryptosystems that provide data protection in block ciphers. At the moment, chaotic maps are being created and extensively used to generate these S-Boxes as a chaotic map assists in providing disorder and resistance to combat cryptanalytical attempts. In this paper, the construction of a dynamic S-Box using a cipher key is proposed using a novel chaotic map and an innovative tweaking approach. The projected chaotic map and the proposed tweak approach are presented for the first time and the use of parameters in their working makes both of these dynamic in nature. The tweak approach employs cubic polynomials while permuting the values of an initial S-Box to enhance its cryptographic fort. Values of the parameters are provided using the cipher key and a small variation in values of these parameters results in a completely different unique S-Box. Comparative analysis and exploration confirmed that the projected chaotic map exhibits a significant amount of chaotic complexity. The security assessment in terms of bijectivity, nonlinearity, bits independence, strict avalanche, linear approximation probability, and differential probability criteria are utilized to critically investigate the effectiveness of the proposed S-Box against several assaults. The proposed S-Box’s cryptographic performance is comparable to those of recently projected S-Boxes for its adaption in real-world security applications. The comparative scrutiny pacifies the genuine potential of the proposed S-Box in terms of its applicability for data security.     

Mixed convective peristaltic flow of Eyring‐Prandtl fluid with chemical reaction and variable electrical conductivity in a tapered asymmetric channel

The influence of inconstant electrical conductivity and chemical reaction on the peristaltic motion of non‐Newtonian Eyring‐Prandtl fluid inside a tapered asymmetric channel is investigated. The system is concerned by a uniform external magnetic field. The heat and mass transfer are considered. The problem is controlled mathematically by a system of nonlinear partial differential equations which describe the velocity, temperature, and nanoparticle concentration of the fluid. By means of long wavelength and low Reynolds numbers, our system is simplified. It is explained by using the multi‐step differential transform method as a semi‐analytical technique. The distributions of velocity, temperature, nanoparticle concentration, as well as pressure gradient and pressure rise are obtained as a function of the physical parameters of the problem. The effects of these parameters on these distributions are deliberated numerically and illustrated graphically through a set of figures. The results indicate that the parameters play a significant role in controlling the velocity, temperature, nanoparticle concentration, pressure gradient, and pressure rise.     

Residue levels of DDE and PCBs in the blood serum of women in the Port Said region of Egypt.

An investigation was conducted to detect residues of 1,1-dichloro-2,2-bis(p-chlorophenyl) ethylene (DDE) and polychlorinated biphenyls (PCBs) in blood serum samples collected from a cohort of fasting females attending the health insurance outpatient clinic at Port Said between July 1999 and July 2000. Females involved in the study included 43 females diagnosed with invasive adenocarcinoma of the breast, 21 female suffering benign breast disease, and 11 normal healthy females. Serum was separated and its contents of DDE and PCBs were extracted and determined, using gas chromatography, equipped with electron capture detector. Mean residues of DDE detected in the three examined groups of females were 41+/-5.2, 48+/-6.2 and 31+/-2.5ng/g for breast cancer cases, benign breast disease cases and controls, respectively, indicating some significantly less residues in blood serum of control females. While PCBs residues detected were 54+/-17, 59+/-23 and 61+/-21ng/g, for the three groups, respectively. Residues of DDE detected in all females alike in the present study are about 15 times higher than residues detected in Canada and The Netherlands.     

Environmentally Inert Nano-Crystalline Materials

A novel process to generate environmentally-inert nano-crystalline materials is discussed here. In this process, nano-crystals of different metals such as Ni, Cu, Al, Ti etc. can be produced in a single processing step with each crystal protected by several carbon ((graphite) layers. The technology is an adaptation of the arc technique utilized to produce carbon nano-crystals (Fullerenes) and can be controlled to produce nano-crystals with a variety of coatings including graphite. These nano-crystals are in the 10-50 nm diameter range (typically 30 nm) and of uniform size distribution. These nano-crystals were chemically stable in air and inert to various acids. Further, initial (unoptimized) experiments demonstrated the feasibility of consolidating these coated nano-particles using conventional processing approaches. Novel applications of these nano-crystals such as in the magnetic recording industry are also discussed here.     

Gene expression of 49 kDa apyrase,cytoskeletal proteins,ATPase, ADPase and amino acid contents of <i>Pisum sativum</i> (L.) cells germinated in E<i>uryops arabicus</i> (Steud. ex Jaub. & Spach) water extract

The present research reports of quick and marked changes induced by plant extract of Euryops arabicus in the gene expression of 49-kDa apyrases, cytoskeletal proteins, ATPases, ADPase and amount of amino acid of pea (Pisum sativum L. var. Alaska). Pellets of cytoskeletals proteins (27000 xg) were probed with anti-apyrase antibody, biotinylated anti-rat, actin and alpha and beta-tubulin for Western blotting. ATPase and ADPase activities were determined based on the hydrolytic efficacy of adenine triphosphate and adenine diphosphate. By 72 hours, the abundance of apyrases, cytoskeletal proteins and amount of amino acid in pellets of 27000 xg of germinated pea seeds in E. arabicus extracts were sharply increased than those sown in distilled water. All the samples exhibited that the stems had more amount from apyrases, cytoskeletal proteins, amino acids and ATPase and ADPase activities than primary leaves and primary roots that were germinated either on E. arabicus water extract or in distilled water. Based on the enzyme’s capability to hydrolyse nucleotide triphosphate and nucleotide diphosphate as well as the direct association between expression of 49-kDa apyrase and cytoskeletal proteins, E. arabicus water extract had an important effect on plant germinations.     

Improving outdoor air quality based on building morphology: Numerical investigation

Due to rapid urbanization around the world, high concentrations of vehicular pollutants have deteriorated the outdoor air quality, which can affect the physical and psychological well-being of humans. Numerous strategies have been proposed to overcome these harmful impacts by improving the dispersion of air pollutants. Consequently, a question arises regarding the potential effects of building morphology on the dispersion of pollutants. Subsequently, transient three-dimensional Computational Fluid Dynamics (CFD) simulations are performed to examine the effect of building morphology on PM₁₀ dispersion. Eleven cases with various prototypes and morphological methods are compared with a simple building form to identify the patterns of PM₁₀ dispersion within a given time sequence under a prevailing inflow condition. The results indicate that the different designs of building morphology with varying Relative compactness (R_C) indicator highlight the importance of considering morphological factors to improve outdoor air quality. In addition, the proposed prototypes can reduce PM₁₀ concentrations by approximately 30%–90% at specific points in the studied time sequence. In particular, the vertical, horizontal, and grid folded prototypes can be considered more effective as an approximate decrease between 70% and 90% in PM₁₀ concentrations is observed, which reflects the influence of building morphology on improving outdoor air quality.     

Gauss Gradient and SURF Features for Landmine Detection from GPR Images

Recently, ground-penetrating radar (GPR) has been extended as a well-known area to investigate the subsurface objects. However, its output has a low resolution, and it needs more processing for more interpretation. This paper presents two algorithms for landmine detection from GPR images. The first algorithm depends on a multi-scale technique. A Gaussian kernel with a particular scale is convolved with the image, and after that, two gradients are estimated; horizontal and vertical gradients. Then, histogram and cumulative histogram are estimated for the overall gradient image. The bin values on the cumulative histogram are used for discrimination between images with and without landmines. Moreover, a neural classifier is used to classify images with cumulative histograms as feature vectors. The second algorithm is based on scale-space analysis with the number of speeded-up robust feature (SURF) points as the key parameter for classification. In addition, this paper presents a framework for size reduction of GPR images based on decimation for efficient storage. The further classification steps can be performed on images after interpolation. The sensitivity of classification accuracy to the interpolation process is studied in detail.     

Analysis of Optimal Heat Transfer in a PEM Fuel Cell Cooling Plate

An analysis of three‐dimensional computational fluid dynamics (CFD) is conducted to investigate the coupled cooling process involved in fluid flow and heat transfer between the solid plate and the coolant flow for optimization of the cooling design of a fuel cell stack. A conception of IUT (Index of Uniform Temperature) across the entire area is presented to evaluate the degree of uniform temperature profile across the cooling plates. Six cooling modes, including three serpentine‐type modes and another three parallel‐type modes, are presented and analyzed for optimization of the cooling mode of fuel cells. The prediction finds that the cooling effect of serpentine‐type cooling modes could be better than that of parallel‐type cooling modes.