Deep learning techniques allow us to achieve image segmentation with excellent accuracy and speed. However, challenges in several image classification areas, including medical imaging and materials science, are usually complicated as these complex models may have difficulty learning significant image features that would allow extension to newer datasets. In this study, an enhancing technique for object detection is proposed based on deep conventional neural networks by combining levelset and standard shape mask. First, a standard shape mask is created through the "probability" shape using the global transformation technique, then the image, the mask, and the probability map are used as the levelset input to apply the image segmentation. The test results show that when using the proposed method with DCNN, it can achieve a close segmentation area and extract features with higher detail than traditional segmentation. The proposed model achieved 94.43% in precision and 95.91% in recall %, so it got 95.16% in F1-score. When comparing the proposed model with the same CNN model without Levelset, the result shows that the proposed model achieved accuracy of 0.951, which is higher than CNN model without Levelset that achieved 0.902.
Steganography is a technique of concealing secret data within other quotidian files of the same or different types. Hiding data has been essential to digital information security. This work aims to design a stego method that can effectively hide a message inside the images of the video file. In this work, a video steganography model has been proposed through training a model to hiding video (or images) within another video using convolutional neural networks (CNN). By using a CNN in this approach, two main goals can be achieved for any steganographic methods which are, increasing security (hardness to observed and broken by used steganalysis program), this was achieved in this work as the weights and architecture are randomized. Thus,
... Show MoreThis research presents a method for calculating stress ratio to predict fracture pressure gradient. It also, describes a correlation and list ideas about this correlation. Using the data collected from four wells, which are the deepest in southern Iraqi oil fields (3000 to 6000) m and belonged to four oil fields. These wells are passing through the following formations: Y, Su, G, N, Sa, Al, M, Ad, and B. A correlation method was applied to calculate fracture pressure gradient immediately in terms of both overburden and pore pressure gradient with an accurate results. Based on the results of our previous research , the data were used to calculate and plot the effective stresses. Many equations relating horizontal effective stress and vertica
... Show MoreNew types of modules named Fully Small Dual Stable Modules and Principally Small Dual Stable are studied and investigated. Both concepts are generalizations of Fully Dual Stable Modules and Principally Dual Stable Modules respectively. Our new concepts coincide when the module is Small Quasi-Projective, and by considering other kind of conditions. Characterizations and relations of these concepts and the concept of Small Duo Modules are investigated, where every fully small dual stable R-module M is small duo and the same for principally small dual stable.
In this paper it was presented the idea quasi-fully cancellation fuzzy modules and we will denote it by Q-FCF(M), condition universalistic idea quasi-fully cancellation modules It .has been circulated to this idea quasi-max fully cancellation fuzzy modules and we will denote it by Q-MFCF(M). Lot of results and properties have been studied in this research.
The base of the ELWE MPF-1 microcomputer is the Z80 microprocessor. The Z80 programs are written in assembly language. The main advantage of assembly language is that: it is much faster to code and the mnemonics makes it easier for the user to remember the instruction. The purpose of this paper is to improve the monitor process for didactic microcomputer ELWE MPF-1 by appending new powerful commands (MOVE, FILL, SEARCH and COMPARE) to the existing monitor to make it more useful and flexible. 8085 assembly language is used to execute this program. The letters used for abbreviation: M for MOVE, F for FILL, S for SEARCH and C for COMPARE.
The objective of this study is to examine the properties of Bayes estimators of the shape parameter of the Power Function Distribution (PFD-I), by using two different prior distributions for the parameter θ and different loss functions that were compared with the maximum likelihood estimators. In many practical applications, we may have two different prior information about the prior distribution for the shape parameter of the Power Function Distribution, which influences the parameter estimation. So, we used two different kinds of conjugate priors of shape parameter θ of the <
... Show MoreThis investigation presents an experimental and analytical study on the behavior of reinforced concrete deep beams before and after repair. The original beams were first loaded under two points load up to failure, then, repaired by epoxy resin and tested again. Three of the test beams contains shear reinforcement and the other two beams have no shear reinforcement. The main variable in these beams was the percentage of longitudinal steel reinforcement (0, 0.707, 1.061, and 1.414%). The main objective of this research is to investigate the possibility of restoring the full load carrying capacity of the reinforced concrete deep beam with and without shear reinforcement by using epoxy resin as the material of repair. All be
... Show MoreThe interests toward developing accurate automatic face emotion recognition methodologies are growing vastly, and it is still one of an ever growing research field in the region of computer vision, artificial intelligent and automation. However, there is a challenge to build an automated system which equals human ability to recognize facial emotion because of the lack of an effective facial feature descriptor and the difficulty of choosing proper classification method. In this paper, a geometric based feature vector has been proposed. For the classification purpose, three different types of classification methods are tested: statistical, artificial neural network (NN) and Support Vector Machine (SVM). A modified K-Means clustering algorithm
... Show MoreIn this work, ZnO quantum dots (Q.dots) and nanorods were prepared. ZnO quantum dots were prepared by self-assembly method of zinc acetate solution with KOH solution, while ZnO nanorods were prepared by hydrothermal method of zinc nitrate hexahydrate Zn (NO3)2.6H2O with hexamethy lenetetramin (HMT) C6H12N4. The optical , structural and spectroscopic properties of the product quantum dot were studied. The results show the dependence of the optical properties on the crystal dimension and the formation of the trap states in the energy band gap. The deep levels emission was studied for n-ZnO and p-ZnO. The preparation ZnO nanorods show semiconductor behavior of p-type, which is a difficult process by doping because native defects.
It is an established fact that substantial amounts of oil usually remain in a reservoir after primary and secondary processes. Therefore; there is an ongoing effort to sweep that remaining oil. Field optimization includes many techniques. Horizontal wells are one of the most motivating factors for field optimization. The selection of new horizontal wells must be accompanied with the right selection of the well locations. However, modeling horizontal well locations by a trial and error method is a time consuming method. Therefore; a method of Artificial Neural Network (ANN) has been employed which helps to predict the optimum performance via proposed new wells locations by incorporatin