The deep learning algorithm has recently achieved a lot of success, especially in the field of computer vision. This research aims to describe the classification method applied to the dataset of multiple types of images (Synthetic Aperture Radar (SAR) images and non-SAR images). In such a classification, transfer learning was used followed by fine-tuning methods. Besides, pre-trained architectures were used on the known image database ImageNet. The model VGG16 was indeed used as a feature extractor and a new classifier was trained based on extracted features.The input data mainly focused on the dataset consist of five classes including the SAR images class (houses) and the non-SAR images classes (Cats, Dogs, Horses, and Humans). The Convolutional Neural Network (CNN) has been chosen as a better option for the training process because it produces a high accuracy. The final accuracy has reached 91.18% in five different classes. The results are discussed in terms of the probability of accuracy for each class in the image classification in percentage. Cats class got 99.6 %, while houses class got 100 %.Other types of classes were with an average score of 90 % and above.
In this paper, an algorithm is suggested to train a single layer feedforward neural network to function as a heteroassociative memory. This algorithm enhances the ability of the memory to recall the stored patterns when partially described noisy inputs patterns are presented. The algorithm relies on adapting the standard delta rule by introducing new terms, first order term and second order term to it. Results show that the heteroassociative neural network trained with this algorithm perfectly recalls the desired stored pattern when 1.6% and 3.2% special partially described noisy inputs patterns are presented.
In this article, we design an optimal neural network based on new LM training algorithm. The traditional algorithm of LM required high memory, storage and computational overhead because of it required the updated of Hessian approximations in each iteration. The suggested design implemented to converts the original problem into a minimization problem using feed forward type to solve non-linear 3D - PDEs. Also, optimal design is obtained by computing the parameters of learning with highly precise. Examples are provided to portray the efficiency and applicability of this technique. Comparisons with other designs are also conducted to demonstrate the accuracy of the proposed design.
This study focused on spectral clustering (SC) and three-constraint affinity matrix spectral clustering (3CAM-SC) to determine the number of clusters and the membership of the clusters of the COST 2100 channel model (C2CM) multipath dataset simultaneously. Various multipath clustering approaches solve only the number of clusters without taking into consideration the membership of clusters. The problem of giving only the number of clusters is that there is no assurance that the membership of the multipath clusters is accurate even though the number of clusters is correct. SC and 3CAM-SC aimed to solve this problem by determining the membership of the clusters. The cluster and the cluster count were then computed through the cluster-wise J
... Show MoreAn effort is made to study the effect of composite nanocoating using aluminum-9%wt silicon alloys reinforced with different percentage (0.5,1,2,4)wt.% of carbon nanotubes (CNTs) using plasma spraying. The effect of this composite on corrosion behavior for AA6061-T6 by extrapolation Tafel test in sea water 3.5wt% NaCl was invested. Many specimens where prepared from AA6061-T6 by the dimension (15x15x3)mm as this first set up and other steps include coating process, X-ray diffraction and SEM examination .The results show the CNTs increase the corrosion rate of the nanocomposite coatings with increasing the weight percentage of CNTs within the Al-Si matrix. Al-9wt%Si coating layer itself has less corrosion rate if compared with both n
... Show MoreIn this paper, we have investigated some of the most recent energy efficient routing protocols for wireless body area networks. This technology has seen advancements in recent times where wireless sensors are injected in the human body to sense and measure body parameters like temperature, heartbeat and glucose level. These tiny wireless sensors gather body data information and send it over a wireless network to the base station. The data measurements are examined by the doctor or physician and the suitable cure is suggested. The whole communication is done through routing protocols in a network environment. Routing protocol consumes energy while helping non-stop communic
... Show MoreFullerene nanotube was synthesized in this research by pyrolysis of plastic waste Polypropylene (PP) at 1000 ° C for two hours in a closed reactor made from stainless steel using molybdenum oxide (MoO3) as a catalyst and nitrogen gas. The resultant carbon was purified and characterized by energy dispersive X-ray spectroscopy (EDX), X-ray powder diffraction (XRD). The surface characteristics of C60 nanotubes were observed with the Field emission scanning electron microscopy (FESEM). The carbon is evenly spread and has the highest concentration from SEM-EDX characterization. The result of XRD and FESEM shows that C60 nanotubes are present in Nano figures, synthesized at 1000 ° C and with pyrolysis tempera
... Show MoreThis work deals with determination of optimum conditions of direct diffusion bonding welding of austenitic stainlesssteel type AISI 304L with Oxygen Free High Conductivity (OFHC) pure copper grade (C10200) in vacuum atmosphere of (1.5 *10-5 mbr.). Mini tab (response surface) was applied for optimizing the influence of diffusion bonding parameters (temperature, time and applied load) on the bonding joints characteristics and the empirical relationship was evaluated which represents the effect of each parameter of the process. The yield strength of diffusion bonded joint was equal to 153 MPa and the efficiency of joint was equal to 66.5% as compared with hard drawn copper. The diffusion zone reveals high microhardness than coppe
... Show MoreIn this paper, Touchard polynomials (TPs) are presented for solving Linear Volterra integral equations of the second kind (LVIEs-2k) and the first kind (LVIEs-1k) besides, the singular kernel type of this equation. Illustrative examples show the efficiency of the presented method, and the approximate numerical (AN) solutions are compared with one another method in some examples. All calculations and graphs are performed by program MATLAB2018b.
In this research, Haar wavelets method has been utilized to approximate a numerical solution for Linear state space systems. The solution technique is used Haar wavelet functions and Haar wavelet operational matrix with the operation to transform the state space system into a system of linear algebraic equations which can be resolved by MATLAB over an interval from 0 to . The exactness of the state variables can be enhanced by increasing the Haar wavelet resolution. The method has been applied for different examples and the simulation results have been illustrated in graphics and compared with the exact solution.
Software testing is a vital part of the software development life cycle. In many cases, the system under test has more than one input making the testing efforts for every exhaustive combination impossible (i.e. the time of execution of the test case can be outrageously long). Combinatorial testing offers an alternative to exhaustive testing via considering the interaction of input values for every t-way combination between parameters. Combinatorial testing can be divided into three types which are uniform strength interaction, variable strength interaction and input-output based relation (IOR). IOR combinatorial testing only tests for the important combinations selected by the tester. Most of the researches in combinatorial testing appli
... Show More