Automated detection of exudates and macula for grading of diabetic macular edema

Medical systems based on state of the art image processing and pattern recognition techniques are very common now a day. These systems are of prime interest to provide basic health care facilities to patients and support to doctors. Diabetic macular edema is one of the retinal abnormalities in which diabetic patient suffers from severe vision loss due to affected macula. It affects the central vision of the person and causes total blindness in severe cases. In this article, we propose an intelligent system for detection and grading of macular edema to assist the ophthalmologists in early and automated detection of the disease. The proposed system consists of a novel method for accurate detection of macula using a detailed feature set and Gaussian mixtures model based classifier. We also present a new hybrid classifier as an ensemble of Gaussian mixture model and support vector machine for improved exudate detection even in the presence of other bright lesions which eventually leads to reliable classification of input retinal image in different stages of macular edema. The statistical analysis and comparative evaluation of proposed system with existing methods are performed on publicly available standard retinal image databases. The proposed system has achieved average value of 97.3%, 95.9% and 96.8% for sensitivity, specificity and accuracy respectively on both databases.     

User profiling for big social media data using standing ovation model

Multimedia Tools and Applications - Online Social Networks (OSNs) have recently been the subject of numerous studies that have attempted to develop effective methods for classifying and analyzing...     

A robust and efficient convolutional deep learning framework for age-invariant face recognition

Extensive research has been carried out in the past on face recognition, face detection, and age estimation. However, age-invariant face recognition (AIFR) has not been explored that thoroughly. The facial appearance of a person changes considerably over time that results in introducing significant intraclass variations, which makes AIFR a very challenging task. Most of the face recognition studies that have addressed the ageing problem in the past have employed complex models and handcrafted features with strong parametric assumptions. In this work, we propose a novel deep learning framework that extracts age-invariant and generalized features from facial images of the subjects. The proposed model trained on facial images from a minor part (20–30%) of lifespan of subjects correctly identifies them throughout their lifespan. A variety of pretrained 2D convolutional neural networks are compared in terms of accuracy, time, and computational complexity to select the most suitable network for AIFR. Extensive experimental results are carried out on the popular and challenging face and gesture recognition network ageing dataset. The proposed method achieves promising results and outperforms the state-of-the-art AIFR models by achieving an accuracy of 99%, which proves the effectiveness of deep learning in facial ageing research.     

The 12<Superscript>th</Superscript> World Conference on Titanium presents research and applications of “wonder metal”

The International Conference on Titanium was begun in 1968 to assess the national significance attached to the development of titanium in relation to the technical needs of the participating countries. The conference, held every four years, attracts strong international participation. This article reviews the 12^th World Conference on Titanium, hosted by the Nonferrous Society of China and held in Beijing, China, 19–24 June 2011.     

Application of a novel microwave plasma treatment for the sintering of nickel oxide coatings for use in dye-sensitized solar cells

In this study the use of microwave plasma sintering of nickel oxide (NiO_x) particles for use as p-type photoelectrode coatings in dye-sensitized solar cells (DSSCs) is investigated. NiO_x was chosen as the photocathode for this application due to its stability, wide band gap and p-type nature. For high light conversion efficiency DSSCs require a mesoporous structure exhibiting a high surface area. This can be achieved by sintering particles of NiO_x onto a conductive substrate. In this study the use of both 2.45 GHz microwave plasma and conventional furnace sintering were compared for the sintering of the NiO_x particles. Coatings 1 to 2.5 μm thick were obtained from the sintered particles (mean particle size of 50 nm) on 3 mm thick fluorine-doped tin oxide (FTO) coated glass substrates. Both the furnace and microwave plasma sintering treatments were carried out at ~ 450 °C over a 5 min period. Dye sensitization was carried out using Erythrosin B and the UV–vis absorption spectra of the NiO_x coatings were compared. A 44% increase in the level of dye adsorption was obtained for the microwave plasma sintered samples as compared to that obtained through furnace treatments. While the photovoltaic performance of the DSSC fabricated using the microwave plasma treated NiO_x coatings exhibited a tenfold increase in the conversion efficiency in comparison to the furnace treated samples. This enhanced performance was associated with the difference in the mesoporous structure of the sintered NiO_x coatings.     

High frequency response to the impedance complex properties of Nb-doped CaCu3Ti4O12 electroceramics

Impedance analyses was performed on undoped and Nb-doped CaCu₃Ti₄O₁₂ (CaCu₃Ti_4−xNb_xO_12+x/2; x = 0, 0.01, 0.03, 0.05, 0.1) to investigate their electrical properties. The pellet samples were prepared using the solid state reaction method. Silver electrode was deposited on both pellets’ surfaces for electrical measurement. The thermally etched samples showed tiny bumped domains within the grains. The existence of both domain and grain boundaries are believed to strongly influence the dielectric constant of CaCu₃Ti₄O₁₂ (CCTO). Undoped CCTO showed two arcs of impedance complex plane while Nb-doped samples have three arcs. Each arc represents the constituent elements of the CCTO. The highest frequency arc is evidence that CCTO consists of conductive domains which measure about 1 Ω and are insulated by two types of barriers, i.e. domain boundary and grain boundary.     

W-type hexaferrite nanoparticles: A consideration for microwave attenuation at wide frequency band of 0.5-10 GHz

The static and dynamic magnetic properties of W-type hexaferrites are tuned to meet the requirements of wide band frequencies for attenuation of electromagnetic interference and microwave absorptions purposes. For this purpose, the W-type hexaferrite of entirely new composition of BaCoZnFe_16−2yAl_yCe_yO₂₇ (y = 0, 0.2, 0.4, 0.6, 0.8 and 1.0) has been synthesized by the chemical co-precipitation. The material is characterized using X-ray diffraction (XRD), scanning electron microscopy (SEM) and vibrating sample magnetometer (VSM). The complex permittivity (?_r = ?′ − j?″) and permeability (μ_r = μ′ − jμ″) spectra are determined using Vector Network Analyzer (VNA) in a range from 0.5 GHz to 10 GHz. During this study, it is noticeable that the Al³⁺ and Ce³⁺ ions have considerable effect on the shape of the nanoparticles. Samples having Al-Ce contents y = 0.2 and y = 0.4 showed large values for magnetization (70.5 emu/g) and remanent magnetization (32.9 emu/g). In addition, more than 99% absorption (>−20 dB) is noted for this sample composition. Based on these results it is concluded that the microwave absorption characteristics of these compounds can be tuned for the required frequency by varying the thickness of the absorber. Due to this reason, potential employment of the synthesized nanoparticles for absorption of electromagnetic radiations at wide frequency band of 0.5-10 GHz has been proposed.