AL-MANSOUR JOURNAL

This paper present a hybrid technique between two of the most popular face recognition methods, Principal Component Analysis (PCA) and singular value decomposition (SVD), and attempts to offer a study for all its mathematical equations in detail and concentrate on the hybrid place between equations in order to focus on the way of processing the hybrid method. Dot product used in mathematical equations and for testing the proposed method used Olivetti Research Laboratory (ORL) data set images were used with different number of images for training set and used various number of Eigen faces and used also dissimilar number for test images and Manhattan distance was used to measure the distances between image vectors in this system, the result shows that the recognition rate using this hybrid technique is higher than the recognition rate using PCA or SVD separately and each time increase the threshold value the accuracy rate increased and conclude that when increase the threshold value and the chosen number of Eigen faces then recognition rate increased.

Cybersecurity is a collection of techniques and processes that are designed for protecting computers, networks, database, and applications from attacks, unauthorized accessing, alteration, or destruction also can be a significant part in the development of information technology as well as Internet services. In Cybersecurity, there are several trends; the biggest one is Web application. Web application is one of the most prevalent platforms for the delivery of information and services via Internet nowadays. Therefore, the importance of web application has increased. At the same time, security risks have also increased. Based on the reports of OWASP (open web application security project), there are ten risks have been listed as the top ten security risks for any web application in the world. SQL injection is one of topmost security risks in OWASP, which is considered in this paper. So securing and maintaining the web application against SQL injection is very hard task and can be classified as a challenge. In this paper, a proposed system works on detecting and preventing SQL injection via using a method named Multi-Connect Architecture (MCA) is presented. The number of queries used in this paper is 130 query. The result of the proposed system is (95%).

This paper indicates that the potential attack to traditional/cloud network is Denial of Service (DoS) attack that effect on the availability of the resource, to solve this problem; this paper propose hidden naïve bays(HNB) classifier to enhance the accuracy of detect DoS attack in cloud network with taking into consideration the traditional environment, the system applied NB classifier firstly supported by discretization and feature selection method to show the difference between the traditional NB classifier and the new model HNB classifier. Two methods are used to select the best feature (Info Gain and Gain ratio) and by used two dataset (KDD cup 99 and NSL KDD datasets) that are used to evaluate the performance of the system. The experiential result show that the proposed system based on HNB classifier enhance the accuracy of detect DoS attack where reach to 100% in three test dataset that are different in size and content by use KDD cup 99 dataset and select only twelve features depended on gain ratio as feature selection, while when used NB classifier the accuracy of detect DoS is equal (94, 97, 98) in three different test dataset. In NSL KDD dataset the accuracy of detect DoS reach to 90% for three test dataset based on HNB classifier and by select 10 features based on GR method, while when used NB classifier is equal to (88, 87, 86) for three test dataset.

In this paper, proposed data loss protection (DLP) solutions for improving privacy of electronic Health record (EHR). Prevention method is the first phase in DLP system, it used signature-based to provide blocking the well-known attacks, also to improve system accuracy by reducing the number of alerts. On the other hand, detection phase has two levels of detection, online detection, and offline detection. Online detection by using novelty detection used to detect new attacks arrives in the system, while the offline detection detects abnormal user behavior in a period of time by using supervised detection.

The research aims to formulate an applied vision on how the relationship between managers' practices and the holistic marketing dimensions of the objectives of the organization and its partners. A sample of (three) companies was selected by the Ministry of Construction, Housing. The sample was surveyed with (144) members of these companies, divided into several administrative levels (manager, engineer, administrative). A number of hypotheses have tested for correlation and influence among search variables. A number of measures have used to verify the hypotheses, including the questionnaire as a main tool for collecting data and information, consisting of( 60) items covering research aspects (managers' practices, holistic marketing dimensions) And personal interviews, personal observation of the researcher and using a variety of statistical tools to analyze and process data and information using the program(SPSS vr23). The research found a number of conclusions, the most important of which are:( The direction of the managers of the companies investigated about the accounting practices of different types and less of the other practices, the possibility of directing the construction companies in question to build relationships with the stakeholders. , Adopt the method of recycling employees to establish cases of excellence and secure knowledge programs).

Securely transmitting data through the internet is performed with the use of steganography the idea of digital image’s information sharing. It can be defined as the science and art of disguising data in an ordinary cover media in a manner which doesn’t raises doubts of an observer. In this paper the suggested system is modeled for hiding an image in multi-image based on Bezier Curve, this approach makes use of Bezier curve equation in order to select secret image pixel locations and hide it into N cover pixels image. The proposed hiding system gives higher security and can hide larger image into multi small images. The quality of the stego images after data hiding is evaluated using PSNR and MSE and results show that this method produces a precise stego images.

There are a huge number of documents that available in many various sources in unorganized format, therefore these unstructured documents needs to be classified. In this paper, a proposed system called "Intelligent Documents Classification System" which represents the system for classifying the documents to the correct class based on its textual information. This system contain through four steps which are preprocessing, features extraction, proposed method for features selection, and finally, modify model of naïve bays. Two datasets are used to evaluate the proposed system, the first dataset its name as "bbc from ucd repository" is standard that contains technical research documents distributed over five classes which available on the internet and the second dataset is collected dataset contains books documents distributed over six classes which collected during this work. The IDC system achieved the powerful results. For the standard dataset the accuracy is 95.1%, precision is 95%, recall is 95.8%, and f1-measure is 95.39% while the accuracy for the collected dataset is 95.3%, precision is 95.16%, recall is 95.83%, and f1-measure is 95.49%.

Digital images are easy to manipulate and edit due to availability of powerful image processing and editing software. It is possible to add or remove important features from an image without leaving any obvious traces of tampering. The structure of detection forgery image in general, includes some of basic stages, and the most important stage is extract features from image because these features is the basic to detected if an image original or not. In this paper, we give a structural to build identification of anti-forensic detecting using steganalytic approaches feature vector. To identify image anti_forensic and image processing. Where several approaches of steganalysis that depend on feature based steganalytic, one of these is Image Quality Measured (IQM). This goal can be achieved by using Fuzzy C Mean (FCM) and Euclidian distains (EU). Results obtained from testing this system for identify forgery image and image operation was with accuracy of 94.8%.

In this paper, face detection based on statistical method has been implemented to get accurately estimation to the crowd counting from an individual image. Random sample is used as statistical method to the estimation purpose. Once the image is given, Viola – Jones algorithm is implemented on the image and it give the number of faces on that image, then simple random sample is choose according to predefined condition which is the value of the last bounding rectangle box that surrounding the face on that image. The results show that proposed statistical method gives good result about (98%) by estimating the nearest true number of the crowd people than the standard face detection(Viola-Jones) technique when it used alone which give about 90% detection rate.

The research aims to identify the test of the relationship between the characteristics of the management of short and innovative mental managers. The various variables witnessed by the world have shown the importance of short management and its impact on the innovative mind. The researcher tried to classify these issues in a practical way by answering the following questions: For short management at the Industrial Park in Diyala. Are there any effects of the overdraft characteristics in the innovative mind? In order to answer these questions, a default model was developed to reflect the correlation relationship, which was tested through a set of The data collected by the questionnaire is dedicated to this aspect. The research concluded on a set of conclusions that the company mentioned has intelligent systems at the administrative and technological level. The research also takes into consideration important recommendations, the most important of which are to face the obstacles and challenges represented by bureaucracy and bureaucracy

One of the most important methods of video surveillance is background subtraction and one of its main steps is modeling of initial background image. In this paper the initial background image is formed by using hybrid techniques (i.e. k-mean and histogram). When the proposed method is employed, the outcomes proposes that the correct color value of highest frequency in the greater cluster leads to modeling of the initial background image, which in turn results in more accurate image of background . This accuracy is measured through PSNR (Peak Signal to Noise Ratio) metric. Furthermore, the current study proposed a comparative study with other four methods (mean, median, histogram and k-mean) through the use of PSNR metric.