A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an

With the growth of mobile phones, short message service (SMS) became an essential text communication service. However, the low cost and ease use of SMS led to an increase in SMS Spam. In this paper, the characteristics of SMS spam has studied and a set of features has introduced to get rid of SMS spam. In addition, the problem of SMS spam detection was addressed as a clustering analysis that requires a metaheuristic algorithm to find the clustering structures. Three differential evolution variants viz DE/rand/1, jDE/rand/1, jDE/best/1, are adopted for solving the SMS spam problem. Experimental results illustrate that the jDE/best/1 produces best results over other variants in terms of accuracy, false-positive rate and false-negative

Deepfake is a type of artificial intelligence used to create convincing images, audio, and video hoaxes and it concerns celebrities and everyone because they are easy to manufacture. Deepfake are hard to recognize by people and current approaches, especially high-quality ones. As a defense against Deepfake techniques, various methods to detect Deepfake in images have been suggested. Most of them had limitations, like only working with one face in an image. The face has to be facing forward, with both eyes and the mouth open, depending on what part of the face they worked on. Other than that, a few focus on the impact of pre-processing steps on the detection accuracy of the models. This paper introduces a framework design focused on this asp

This research include design and implementation of an Iraqi cities database using spatial data structure for storing data in two or more dimension called k-d tree .The proposed system should allow records to be inserted, deleted and searched by name or coordinate. All the programming of the proposed system written using Delphi ver. 7 and performed on personal computer (Intel core i3).

This research was conducted to study the histological structure of the eye in the tree frog (Hyla arborea savignyi) and showed that it is composed of the eyeball and the lens and optic nerve. Appeared eyeball is surrounded by three Tunica from the inside to the outside are Tunica Interna, Tunica vasculosa, Tunica fibrosa. The tunica interna consists of the retina that consists of 10 layers are from outer to inner pigment epithelial layer, rods and cones layer, external limiting membrane, outer nuclear layer, outer plexiform layer, inner nuclear layer, inner plexiform layer , ganglion cells layer , nerve fibers layer, internal limiting membrane .The vascular tunic or Uvea consists of the choroid, ciliary body , and iris . The fibrous coat co

Image steganography is undoubtedly significant in the field of secure multimedia communication. The undetectability and high payload capacity are two of the important characteristics of any form of steganography. In this paper, the level of image security is improved by combining the steganography and cryptography techniques in order to produce the secured image. The proposed method depends on using LSBs as an indicator for hiding encrypted bits in dual tree complex wavelet coefficient DT-CWT. The cover image is divided into non overlapping blocks of size (3*3). After that, a Key is produced by extracting the center pixel (pc) from each block to encrypt each character in the secret text. The cover image is converted using DT-CWT, then the p

Journal of Theoretical and Applied Information Technology is a peer-reviewed electronic research papers & review papers journal with aim of promoting and publishing original high quality research dealing with theoretical and scientific aspects in all disciplines of IT (Informaiton Technology

Generally, radiologists analyse the Magnetic Resonance Imaging (MRI) by visual inspection to detect and identify the presence of tumour or abnormal tissue in brain MR images. The huge number of such MR images makes this visual interpretation process, not only laborious and expensive but often erroneous. Furthermore, the human eye and brain sensitivity to elucidate such images gets reduced with the increase of number of cases, especially when only some slices contain information of the affected area. Therefore, an automated system for the analysis and classification of MR images is mandatory. In this paper, we propose a new method for abnormality detection from T1-Weighted MRI of human head scans using three planes, including axial plane, co