Classification brain MR images through a fuzzy multiwavelets based GMM and probabilistic neural networks

In this paper, a new approach for classification of brain tissues into White Matter, Gray Matter, Cerebral Spinal Fluid, Glial Matter, Connective and MS lesion in multiple sclerosis is introduced. This work considers fuzzy multiwavelets, Gaussian Mixture Model (GMM) and Weighted Probabilistic Neural Networks (WPNN) for the classification of the brain tissues. Multiwavelet packet transformation is employed on brain MR images. Since multiwavelet packet transformation yields larger number of subbands compared to multiwavelet and wavelet transformations, we have proposed a fuzzy-set based theory for selection of the subbands. In contrast to the standard method of subband selection, guided by the criteria of signal energy, our method is based on the discriminatory features from the multiwavelet packet transformation coefficients. Singular values are then computed from the selected subbands. The singular values of lower magnitudes are truncated for effective classification of brain tissues in the presence of noise. Probability density functions of the remaining singular values are modeled as GMM. Model parameters are estimated using stochastic EM (SEM). They are used as features for the classification. The classification is carried out using WPNN. Experiments have been carried out using the data sets composed of three modalities of brain MR images, namely T1 and T2 relaxation times and proton density weighted MR images. Experimental results prove that the proposed approach gives better classification rate at various noise levels compared to existing approaches.     

A Trusted Water Fall Model for Efficient Data Transmission in VANET

Wireless Personal Communications - Vehicular adhoc networks are slowly gaining importance as the demand for faster communication increases. The vehicular nodes need to communicate securely via an...     

Polychalcones based on triphenylamine and carbazole building blocks via Claisen–Schmidt route

Alternating and random copolymers of carbazole and triphenylamine containing polychalcones are prepared by adopting simple Claisen–Schmidt route via A₂ + B₂ approach. Terephthaldehyde derivative was used as an additional comonomer along with bisaldehyde of triphenylamine to obtain a random copolymer. The prepared polymers are readily soluble in common organic solvents and the polymers exhibited narrow poly dispersity. The polymers are thermally stable and no observable degradation is observed until 350°C. Further, the spin cast thermally annealed films on glass substrate indicated corrugated surface as measured by scanning electron microscope and atomic force microscopy, which could facilitate for greater interaction at the interfaces. Photophysical properties of the polymers in solution and in thin film showed excellent emission characteristics. Both alternating and random copolymers showed a high quantum yield of 0.74 on comparison with quinine sulfate. Polychalcones with triphenylamine/carbazole showed oxidative response in cyclic voltammetry which suggested the suitability as electrochemical sensors and antioxidant coating material.     

Correction to: Differentiation of COVID-19 conditions in planar chest radiographs using optimized convolutional neural networks

Applied Intelligence - Figure 4 in the original article unfortunately contained an error.     

An improved stability result for linear time-delay system using a new Lyapunov–Krasovskii functional and extended reciprocally convex inequality

This paper is concerned with the stability analysis of a linear system with interval time-varying delay using an augmented Lyapunov–Krasovskii (LK) functional approach. A delay-dependent stability criterion is developed in LMI framework to estimate the maximum allowable bound of the time-delay within which the system remains asymptotically stable in the sense of Lyapunov. Conservatism in the proposed delay-dependent stability analysis is reduced by introducing a new LK functional along with the Wirtinger's inequality and extended reciprocally convex matrix inequality. Finally, two numerical examples and the load frequency control problem have been solved to validate the superiority of the proposed stability criterion compared to existing literature.