javad nourinia

It has been a long time since we use magnetic resonance imaging (MRI) to detect brain diseases and many useful techniques have been developed for this task. However, there is still a potential for further improvement of classification of brain diseases in order to be sure of the results. In this research we presented, for the first time, a non-linear feature extraction method from the MRI sub-images that are obtained from the three levels of the two-dimensional Dual tree complex wavelet transform (2D DT-CWT) in order to classify multiple brain disease. After extracting the non-linear features from the sub-images, we used the spectral regression discriminant analysis (SRDA) algorithm to reduce the classifying features. Instead of using the deep neural networks that are computationally expensive, we proposed the Hybrid RBF network that uses the k-means and recursive least squares (RLS) algorithm simultaneously in its structure for classification. To evaluate the performance of RBF networks with hybrid learning algorithms, we classify nine brain diseases based on MRI processing using these networks, and compare the results with the previously presented classifiers including, supporting vector machines (SVM) and K-nearest neighbour (KNN). Comprehensive comparisons are made with the recently proposed cases by extracting various types and numbers of features. Our aim in this paper is to reduce the complexity and improve the classifying results with the hybrid RBF classifier and the results showed 100 percent classification accuracy in both the two class and the multiple classification of brain diseases in 8 and 10 classes. In this paper, we provided a low computational and precise method for brain MRI disease classification. the results show that the proposed method is not only accurate but also computationally reasonable.

In this paper, we simulated a diffusion adaptive network in the underwater environment. The communication method between the nodes of this network is assumed to be the visible light communication technology (VLC) which in the underwater condition is known as the UVLC. The links between the nodes in this case are contaminated with the optical noise and turbulence. These contaminations are modeled with the proper statistical distributions depending on the underwater conditions. The optical turbulence modeling link coefficients are shown to be following the Log-normal distribution which its mean and variance are directly dependent on the temperature and the salinity of the simulated water and the assumed distance between the diffusion network nodes. The performance of the diffusion network in using UVLC technology is then analyzed both with simulations and theoretical calculations and the results are presented using the steady-state error metrics. Our analysis showed that the diffusion network can be implemented underwater with the VLC technology providing that the distance between the network nodes is less than 10 meters. Also, in order to guarantee the convergence of the adaptive network, the water salinity level and temperature must not exceed the values that are presented in our simulations.

A new design of a dual-band printed dipole antenna with integrated balun is presented in this study. The antenna in simple form is composed of a printed dipole, integrated balun, a Γ-shaped feed, and a square-shaped ground plane, which achieves a fundamental resonance at 2.4 GHz frequency. A pair of rectangular-shaped resonators are positioned on two sides of the Γ-shaped feed in the second designing step innovatively to accomplish the additional resonance at 5.5 GHz as the second frequency band of the WLAN. Two electromagnetically coupling mechanisms prepared between the Γ-shaped feed and dipole arms, and rectangular-shaped resonators, which lead to creating two operating frequency bands. An equivalent circuit and a parametric study presented to explain the antenna performance in this work. Experiments approve that the proposed dual-band antenna has two impedance bandwidths of 14.1% (2.23-2.57 GHz) and 25.7% (4.83-6.26 GHz) with average gains of 12.10 dBi and 6.36 dBi over the first and second frequency bands, respectively, which is cover the 2.4/5.5 GHz WLAN frequency bands successfully.

Merging the adaptive networks with the free space optical (FSO) communication technology is a very interesting field of research because by adding the benefits of this technology, the adaptive networks become more efficient, cheap and secure. This is due to the fact that FSO communication uses unregistered visible light bandwidth instead of the overused radio spectrum. However, in spite of all the benefits of FSO communication, this technology suffers from optical noise and turbulence. In this paper, we investigate the exact effect of the negative exponential and k-distribution modeled very strong turbulence conditions on the performance of diffusion adaptive networks. The simulation and theoretical results based on the steady state Mean square deviation (MSD) and Excess mean square Error (EMSE) vlaues show the deteriorating effects of these link models on diffusion networks. The FSO communication technology, while very profitable and applicable, is not always a suitable means of implementing wireless networks. For this reason, we suggested the channel estimation for these conditions.