Detection and Classification of Diabetic Retinopathy Using DCNN and BSN Models

Diabetes is associated with many complications that could lead to death. Diabetic retinopathy, a complication of diabetes, is difficult to diagnose and may lead to vision loss. Visual identification of micro features in fundus images for the diagnosis of DR is a complex and challenging task for clinicians. Because clinical testing involves complex procedures and is time-consuming, an automated system would help ophthalmologists to detect DR and administer treatment in a timely manner so that blindness can be avoided. Previous research works have focused on image processing algorithms, or neural networks, or signal processing techniques alone to detect diabetic retinopathy. Therefore, we aimed to develop a novel integrated approach to increase the accuracy of detection. This approach utilized both convolutional neural networks and signal processing techniques. In this proposed method, the biological electro retinogram (ERG) sensor network (BSN) and deep convolution neural network (DCNN) were developed to detect and classify DR. In the BSN system, electrodes were used to record ERG signal, which was pre-processed to be noise-free. Processing was performed in the frequency domain by the application of fast Fourier transform (FFT) and mel frequency cepstral coefficients (MFCCs) were extracted. Artificial neural network (ANN) classifier was used to classify the signals of eyes with DR and normal eye. Additionally, fundus images were captured using a fundus camera, and these were used as the input for DCNN-based analysis. The DCNN consisted of many layers to facilitate the extraction of features and classification of fundus images into normal images, non-proliferative DR (NPDR) or early-stage DR images, and proliferative DR (PDR) or advanced-stage DR images. Furthermore, it classified NPDR according to microaneurysms, hemorrhages, cotton wool spots, and exudates, and the presence of new blood vessels indicated PDR. The accuracy, sensitivity, and specificity of the ANN classifier were found to be 94%, 95%, and 93%, respectively. Both the accuracy rate and sensitivity rate of the DCNN classifier was 96.5% for the images acquired from various hospitals as well as databases. A comparison between the accuracy rates of BSN and DCNN approaches showed that DCNN with fundus images decreased the error rate to 4%.     

Energy Sensitive Cluster Level Security Selection Scheme for MANET

Wireless Personal Communications - Most of the current Mobile Ad hoc Network (MANET) nodes are battery powered devices with different processing and data handling capacities. The ratio of sensitive...     

Stability constants of adipate complexes of copper(II), nickel(II), zinc(II), cobalt(II), uranyl(II) and thorium(IV) determined by electrophoresis

Stability constants of Copper(II), Nickel(II), Cobalt(II), Zinc(II), Uranyl(II) and Thorium(IV) adipates have been determined by paper electrophoresis. Adipic acid (0.005 mol dm^?3) was added to the background electrolyte: 0.1 mol dm^?3 HClO₄. The proportions of (CH₂)₄COOH COO^? and (CH₂)₄C₂O⁼₂ were varied by changing the pH of the electrolyte. These anions yielded the complexes Zn(CH₂)₄COOH COO⁺, Co(CH₂)₄COOH COO⁺, Ni(CH₂)₄COOH COO⁺, Th(CH₂)₄COOH COO³⁺, Th[(CH₂)₄COOH COO]₄, Cu(CH₂)₄ C₂O₄ and UO₂[(CH₂)₄(C₂O₄)]^2?₂, whose stability constants are found to be 10^2.8, 10^2.8, 10^3.2, 10^5.2, 10^15.3, 10^2.7 and 10^11.8 respectively (μ = 0.1, temp. 40°C).     

Magnetic and dielectric studies of barium hexaferrite (BaFe 12 O 19 ) ceramic synthesized by chemical route

Barium hexaferrite BaFe12O19 (BHF) ceramic was synthesized by chemical route on sintering at 1050 °C for 12 h. The synthesized material was characterized by XRD, SEM, AFM and TEM analysis. Metal oxide stretching frequencies corresponding to Fe-O, Ba-O, and Fe-O-Fe bands are confirmed by FTIR studies. The hexagonal nature of the BHF ceramic was confirmed by TEM analysis and Rietveld refinement with space group P63/mmc. The particle size observed by TEM is 175 nm. The root means square and average roughness were found to be 61.048 nm and 44.025 nm respectively. The M-T and M-H hysteresis loop indicates temperature dependent ferromagnetic behavior of BHF ceramic. The temperature and frequency dependent dielectric properties were explained by Maxwell-Wagner theory. The value of dielectric constant (ε′) for BHF ceramic was found to be 22× 103 at 100 Hz and 483 K.     

Novel organomodified kaolin/silica hybrid fillers in natural rubber and its blend with polybutadiene rubber

Phosphorylated cashew nut shell liquid prepolymer (PCNSL) was used as an organomodifier for kaolin and the role of the PCNSL-modified kaolin as a reinforcing nanofiller in natural rubber (NR) and its blends with polybutadiene rubber (BR) was studied. The organomodified kaolin was characterized using thermogravimetric analysis, powder X-ray diffraction, Fourier transform infrared spectroscopy (FTIR), high-resolution transmission electron microscopy and scanning electron microscopy. It was found that PCNSL could act as a coupling agent and compatibilizer between kaolin and rubber. Improved physico-mechanical properties were observed at a dosage of 6 phr of the modified kaolin in NR. Blends of NR with BR containing precipitated silica/PCNSL-modified kaolin hybrid filler showed improved tensile properties, tear strength and flex fatigue resistance along with lower heat build-up which could be beneficial for applications such as automobile tire sidewall.     

Growth of iron diselenide nanorods on graphene oxide nanosheets as advanced electrocatalyst for hydrogen evolution reaction

Advanced electrocatalysts for the fabrication of sustainable hydrogen from water splitting are innermost to energy research. Herein, we report the growth of iron diselenide (FeSe₂) nanorods on graphene oxide (GO) sheets using two-step process viz., simple hydrothermal reduction and followed by wet chemical process. The orthorhombic phase of FeSe₂ incorporated GO nanosheet was developed as a low-cost and efficient electrocatalyst for hydrogen evolution reaction (HER) by water splitting. The phase purity, crystalline structure, surface morphology and elemental composition of the synthesized samples have been investigated by UV–visible absorption spectroscopy (UV–vis), fourier transform-infrared spectroscopy (FT-IR), X-ray diffraction (XRD), field emission scanning electron microscopy (FE-SEM) and energy dispersive X-ray analysis (EDS). Voltammetry and Tafel polarization methods have been utilized to assess the performance of various weight ratio of GO nanosheet in FeSe₂ nanorods towards H₂ evolution. Detailed electrochemical investigations revealed that the 30% FeSe₂/GO composite showed a tremendous electrocatalytic HER activity in acidic medium with high cathodic current density of 9.68 mA/cm² at η = 250 mV overpotential and with a Tafel slope of 64 mV/dec. The 30% FeSe₂/GO composite offers a high synergistic effect towards HER activity, which is mainly due to high electrochemical active catalytic sites, low charge-transfer resistance and enhanced electrocatalytic performances of H₂ production. The present analysis revealed the possible application of FeSe₂/GO composite as a promising low-cost alternative to platinum based electrocatalysts for H₂ production.     

Green synthesis of TiO2 nanoparticles prepared from Phyllanthus niruri leaf extract for dye adsorption and their isotherm and kinetic studies

Herein, the green synthesis of TiO₂ nanoparticles using Phyllanthus niruri leaf extract was accomplished by the sol‐gel method. The structure and particle size of the synthesised TiO₂ nanoparticles were characterised by X‐ray diffraction (XRD) analysis and the size was found to be 20 nm. The Fourier‐transform infrared spectra determined the existence of carboxyl and hydroxyl functional groups. The images from SEM analysis recommended a porous and heterogeneous surface. The methyl orange (MO) dye removal was examined using different parameters such as pH, time, dose, temperature and dye concentration. Maximum dye elimination percentage was achieved at pH 6.0 and 0.02 g as the optimum adsorbent dose. The kinetic analysis suggested that the pseudo‐second‐order kinetic model finely defines adsorption dynamics. Langmuir adsorption isotherm studies revealed endothermic monolayer adsorption of the methyl Orange dye. The negative value of ∆G° and positive value of ∆H° showed the spontaneous and endothermic adsorption method.     

Studies on conductive silicone rubber compounds

The electrical conductivity of silicone rubber vulcanizates containing carbon blacks [e.g., acetylene black, lamp black, and ISAF (N-234) black] were investigated. The change in electrical conductivity with varying amounts of carbon blacks and the temperature dependence was measured. The mechanical properties like tensile strength, tear strength, elongation at break, hardness, etc., of the vulcanizates were determined. A comparative study of the electrical conductivity of the composites revealed that the electrical conductivity of the composites made with acetylene black was higher than that of the composites made of other blacks. © 1998 John Wiley & Sons, Inc. J Appl Polym Sci 69: 1043–1050, 1998     

Metastable Phase Transformation in Ti-5Ta-2Nb Alloy and 304L Austenitic Stainless Steel under Explosive Cladding Conditions

Ti-5Ta-2Nb alloy was clad on 304L austenitic stainless steel (SS) using the explosive cladding process. Both Ti-5Ta-2Nb and 304L austenitic steel were severely deformed due to high pressure (in the gigapascal range) and strain rate (10⁵/s), which are characteristics of explosive loading conditions. Consequent changes produced in the microstructure and crystal structure of both the alloys are studied using electron microscopy techniques. The microstructure of both Ti-Ta-Nb alloy and 304L steel showed evidence for the passage of the shock waves in the form of a high number density of lattice defects such as dislocations and deformation twins. In addition, both the alloys showed signatures of phase transformation under nonequilibrium conditions resulting in metastable transformation products. 304L SS showed martensitic transformation to both ????(bcc) and ??(hcp) phases. Microscopic shear bands, shear band intersections, and twin boundaries were identified as nucleation sites for the formation of strain-induced phases. Ti-Ta-Nb alloy underwent metastable phase transformation to an fcc phase, which could be associated with regions having a specific morphology.