The differential protection of power transformers appears to be more difficult than any type of protection for any other part or element in a power system. Such difficulties arise from the existence of the magnetizing inrush phenomenon. Therefore, it is necessary to recognize between inrush current and the current arise from internal faults. In this paper, two approaches based on wavelet packet transform (WPT) and S-transform (ST) are applied to recognize different types of currents following in the transformer. In WPT approach, the selection of optimal mother wavelet and the optimal number of resolution is carried out using minimum description length (MDL) criteria before taking the decision for the extraction features from the WPT tree

The proposed design of neural network in this article is based on new accurate approach for training by unconstrained optimization, especially update quasi-Newton methods are perhaps the most popular general-purpose algorithms. A limited memory BFGS algorithm is presented for solving large-scale symmetric nonlinear equations, where a line search technique without derivative information is used. On each iteration, the updated approximations of Hessian matrix satisfy the quasi-Newton form, which traditionally served as the basis for quasi-Newton methods. On the basis of the quadratic model used in this article, we add a new update of quasi-Newton form. One innovative features of this form's is its ability to estimate the energy functio

Three-dimensional (3D) image and medical image processing, which are considered big data analysis, have attracted significant attention during the last few years. To this end, efficient 3D object recognition techniques could be beneficial to such image and medical image processing. However, to date, most of the proposed methods for 3D object recognition experience major challenges in terms of high computational complexity. This is attributed to the fact that the computational complexity and execution time are increased when the dimensions of the object are increased, which is the case in 3D object recognition. Therefore, finding an efficient method for obtaining high recognition accuracy with low computational complexity is essentia

Many image processing and machine learning applications require sufficient image feature selection and representation. This can be achieved by imitating human ability to process visual information. One such ability is that human eyes are much more sensitive to changes in the intensity (luminance) than the color information. In this paper, we present how to exploit luminance information, organized in a pyramid structure, to transfer properties between two images. Two applications are presented to demonstrate the results of using luminance channel in the similarity metric of two images. These are image generation; where a target image is to be generated from a source one, and image colorization; where color information is to be browsed from o

In this paper, membrane-based computing image segmentation, both region-based and edge-based, is proposed for medical images that involve two types of neighborhood relations between pixels. These neighborhood relations—namely, 4-adjacency and 8-adjacency of a membrane computing approach—construct a family of tissue-like P systems for segmenting actual 2D medical images in a constant number of steps; the two types of adjacency were compared using different hardware platforms. The process involves the generation of membrane-based segmentation rules for 2D medical images. The rules are written in the P-Lingua format and appended to the input image for visualization. The findings show that the neighborhood relations between pixels o

With the continuous progress of image retrieval technology, the speed of searching for the required image from a large amount of image data has become an important issue. Convolutional neural networks (CNNs) have been used in image retrieval. However, many image retrieval systems based on CNNs have poor ability to express image features. Content-based Image Retrieval (CBIR) is a method of finding desired images from image databases. However, CBIR suffers from lower accuracy in retrieving images from large-scale image databases. In this paper, the proposed system is an improvement of the convolutional neural network for greater accuracy and a machine learning tool that can be used for automatic image retrieval. It includes two phases

We know that the experiments which conducted by latin square in one location or in one period (season), but there are many cases that need to conduct the same experiments in many locations or in many periods (seasons) to study the interaction  between the treatments and locations or between the treatments and periods (seasons) .In this research we present  an idea for  conduct  the experiment in several locations and in many period (seasons) by using LSD , it represent  acontribution in the area of design and analysis of experiments ,we had written. we had written (theoretically)  the general plans, the mathematical models for these experiments, and finding the derivations of EMS for each component (