PHD theses : Computer Science

Permanent URI for this collectionhttps://repository.neelain.edu.sd/handle/123456789/12169

Browse

Now showing 1 - 20 of 25

RECOMMENDED APPROACH FOR SOFTWARE PROJECT PLANNING AND COST ESTIMATIONS IN THE SUDAN
(2002) AWAD ELKARIM MOHAMMED YOUSIF
ABSTRACT Most -if not all - the software projects, of demand, in Sudan are small- sized or, possibly, medium-sized in some cases. The software projects that the various institutions, developers and the software houses have attempted, during the elapsed decades were not inclined to adopting software engineering basics. The standard techniques, standard documentation and systematic project reviews have been neglected. Consequently, the products came too feeble to suffice customers’ requirements or, as in the overwhelming majority of cases, a complete failure to serve the cause and purpose, for which it was originally entitled. In other cases the projects were terminated at earlier stages than completion and left unfinished due to the perplexed approaches during their development. The local software project development has been born accompanied by the problems of immaturity, because it did neither follow the systematic planning nor the proper cost estimation. Recently and when software projects were in demand the problem has escalated into a severe crisis. A tremendous effort has to be made clearing the present messy situation. indeed, a start from scratch is needed to revive the proper conception of the software project development, built on understanding the basics of software engineering fundamentals. ‘- The author made a keen survey upon 26 companies that practice software project development. A careful study has been made on the ways they adopt in planning and estimating the costs of software projects. Great efforts were made attempting to put these methods as indicators that could possibly be compared with the techniques, tools and systematic approaches adopted in Software Engineering. lt was observed that Software Engineering training progress was lacking and thus leading to insufficiency in software Engineering infrastructure. Eventually, Software Engineering methodology, tools, techniques and procedures were often absent. As a consequence schedules suffered frequent changes, the thing that lead to over-budgeting and conformed a mighty causal to time slips. Beyond that, no planning for standards, as well as no proper software development procedures were maintained and plans for Quality Assurance and Risk Management were rarely considered. The study has proposed some indicators and practical procedures that can be adopted and easily followed to achieve satisfactory results in this aspect.
A new Conjugate Gradient Algorithm of Unconstrained Optimization Using Parallel Processor
(Neelain University, 2007) Nadwa Ali Ahmad Al-Abbas
ABSTRIACT ln optimization methods, we try to find and determine the best solution to certain mathematically defined problems: Minimize f(x) , xeil?” Optimization problems can be classified as constrained and unconstrained problems; however, as constrained optimization problems can be transformed into unconstrained cases, the majority of recent research works have been focused on unconstrained optimization problems, including the new techniques. Almost all numerical methods developed to solve f(x) are iterative in nature, i.e. given an initial point xo, the methods generate a sequence of points x,,,x, until some stopping criterion is satisfied . The iterative methods are first theoretically developed to minimize convex quadratic functions in a finite number of iterations and they are extended to solve the general problems. These numerical methods can be divided into two classes according to whether derivatives are evaluated or not (first or second derivative). The method which evaluates derivatives is called gradient method. Within this thesis, we first choose, one of the well-known methods, Conjugate Gradient “CG~method" which can solve iteratively both linear and nonlinear functions. This method is extended to find the minima (or maxima) using two kinds of searches to find the minimum solution. These are called: 1- Exact line search , i.e. g,+,’d, = 0 for i=1,2,... . 2- lnexact line search. We choose about ten nonlinear functions and we use the program of this method to optimize these functions using special starting points with different dimensions for many of them. ln this thesis, a new algorithm is developed for minimization of the quadratic and extended quadratic function using the inexact line search. This thesis is concerned with the development and testing of the new algorithm using line search to solve different standard functions. We have extended our work to other two methods, quasi- Newton method and BFGS method, which begin the search along a gradient line as the CG-method and use gradient information to build a quadratic. Then we studied the parallel solution of these algorithms and the effect of using parallelism on these algorithms. Programs have been written using sequential design (to be executed serially). We have used the parallel models of these methods (design and analysis) and the parallelism of these methods in different ways. Further study was made of the important measures used in parallel computing. We have found that parallelism is only effective in linear functions and hence linearization methods for solving nonlinear functions. The other important measures of the efficiency of these algorithms are NOF (number of function evaluation). We have tried to reduce NOF by using inexact line search with extended conjugate gradient methods to optimize the unconstrained nonlinear problems. lt is found that in some functions NOF are reduced, especially high dimension ones. In others, NOF are not reduced. So it is difficult to conclude whether this method is better or worse compared with others. However, we may say it is competing. lt gave good result with Powell function, which is generally accepted as a good function, and it may add a new algorithm for solving these types of problems. In general, this statement in common with all algorithms of solving nonlinear equations. The function is the main factor.
A new Conjugate Gradient Algorithm of Unconstrained Optimization Using Parallel Processor
(Neelain University, 2007) Nadwa Ali Ahmad Al-Abbas
ABSTRIACT ln optimization methods, we try to find and determine the best solution to certain mathematically defined problems: Minimize f(x) , xeil?” Optimization problems can be classified as constrained and unconstrained problems; however, as constrained optimization problems can be transformed into unconstrained cases, the majority of recent research works have been focused on unconstrained optimization problems, including the new techniques. Almost all numerical methods developed to solve f(x) are iterative in nature, i.e. given an initial point xo, the methods generate a sequence of points x,,,x, until some stopping criterion is satisfied . The iterative methods are first theoretically developed to minimize convex quadratic functions in a finite number of iterations and they are extended to solve the general problems. These numerical methods can be divided into two classes according to whether derivatives are evaluated or not (first or second derivative). The method which evaluates derivatives is called gradient method. Within this thesis, we first choose, one of the well-known methods, Conjugate Gradient “CG~method" which can solve iteratively both linear and nonlinear functions. This method is extended to find the minima (or maxima) using two kinds of searches to find the minimum solution. These are called: 1- Exact line search , i.e. g,+,’d, = 0 for i=1,2,... . 2- lnexact line search. We choose about ten nonlinear functions and we use the program of this method to optimize these functions using special starting points with different dimensions for many of them. ln this thesis, a new algorithm is developed for minimization of the quadratic and extended quadratic function using the inexact line search. This thesis is concerned with the development and testing of the new algorithm using line search to solve different standard functions. We have extended our work to other two methods, quasi- Newton method and BFGS method, which begin the search along a gradient line as the CG-method and use gradient information to build a quadratic. Then we studied the parallel solution of these algorithms and the effect of using parallelism on these algorithms. Programs have been written using sequential design (to be executed serially). We have used the parallel models of these methods (design and analysis) and the parallelism of these methods in different ways. Further study was made of the important measures used in parallel computing. We have found that parallelism is only effective in linear functions and hence linearization methods for solving nonlinear functions. The other important measures of the efficiency of these algorithms are NOF (number of function evaluation). We have tried to reduce NOF by using inexact line search with extended conjugate gradient methods to optimize the unconstrained nonlinear problems. lt is found that in some functions NOF are reduced, especially high dimension ones. In others, NOF are not reduced. So it is difficult to conclude whether this method is better or worse compared with others. However, we may say it is competing. lt gave good result with Powell function, which is generally accepted as a good function, and it may add a new algorithm for solving these types of problems. In general, this statement in common with all algorithms of solving nonlinear equations. The function is the main factor.
Anew Conjugate Gradient Algorithm of Unconstrained Optimization Using Parallel Processor
(Al Neelain University, 2007-02) Nadwa Ali Ahmad Al-Abbas
ln optimization methods, we try to find and determine the best solution to certain mathematically defined problems: Minimize f(x) , x em" Optimization problems can be classified as constrained and unconstrained problems; however, as constrained optimization problems can be transformed into unconstrained cases, the majority of recent research works have been focused on unconstrained optimization problems, including the new techniques. Almost all numerical methods developed to solve f(x) are iterative in nature, i.e. given an initial point xo, the methods generate a sequence of points x,,,x,,... until some stopping criterion is satisfied . The iterative methods are first theoretically developed to minimize convex quadratic functions in a finite number of iterations and they are extended to solve the general problems. These numerical methods can be divided into two classes according to whether derivatives are evaluated or not (first or second derivative). The method which evaluates derivatives is called gradient method. Within this thesis, we first choose, one of the well-known methods, Conjugate Gradient "CG-method" which can solve iteratively both linear and nonlinear functions. This method is extended to find the minima (or maxima) using two kinds of searches to find the minimum solution. These are called: 1- Exact line search , i.e. g,+,Td, = 0 for i=1,2,... . 2- inexact line search. We choose about ten nonlinear functions and we use the program of this method to optimize these functions using special starting points with different dimensions for many of them. ln this thesis, a new algorithm is developed for minimization of the quadratic and extended quadratic function using the inexact line search. This thesis is concerned with the development and testing of the new algorithm using line search to solve different standard functions. We have extended our work to other two methods, quasi- Newton method and BFGS method, which begin the search along a gradient line as the CG-method and use gradient information to build a quadratic. Then we studied the parallel solution of these algorithms and the effect of using parallelism on these algorithms. Programs have been written using sequential design (to be executed serially). We have used the parallel models of these methods (design and analysis) and the parallelism of these methods in different ways. Further study was made of the important measures used in parallel computing. We have found that parallelism is only effective in linear functions and hence linearization methods for solving nonlinear functions. The other important measures of the efficiency of these algorithms are NOF (number of function evaluation). We have tried to reduce NOF by using inexact line search with extended conjugate gradient methods to optimize the unconstrained nonlinear problems. lt is found that in some functions NOF are reduced, especially high dimension ones. In others, NOF are not reduced. So it is difficult to conclude whether this method is better or worse compared with others. However, we may, say it is competing. lt gave good result with Powell function, which is generally accepted as a good function, and it may add a new algorithm for solving these types of problems. In general, this statement in common with all algorithms of solving nonlinear equations. The function is the main factor.
Monte Carlo Based Digital Image Simulation Processing
(Neelain University, 2009) Hassan Hamad Abuelhassan Abdallah
Abstract lmage segmentation is a fundamental first step image processing technique which helps attaining the objectives of computer vision. The primary objective of this thesis is to enhance existing image segmentation methods based on Monte Carlo integration. We have suggested Monte Carlo techniques to ﬁnd the ensemble average of neighboring image properties. This way, more precise image operations such as edge detection, merging areas of similar properties and meshing techniques will be possible. Examples from everyday's activities using advanced computer graphics and image analysis techniques are used. Future work includes using of enhanced algorithms in medical image segmentation and analysis.
A design of simulation model and Analysis Program to Identify the order of carcinogenesis process Associated with bladder cancer
(Al Neelain University, 2013) Elshibli Mohamed Ahmed
This study aimed to design simulation model to predict the order of events correlated with speciﬁc result. A total of 23 genetic mutations tested in l76 bladder cancer patients used as data of the real system. The simulation model was designed using the frequency of mutation assuming that the most frequent events are the ﬁrst-happing ones. Correlation test was used to identify the order of the events. Application of designed model resulted in six pathways of which two were main pathways whereas the remaining were sub pathways. The ﬁrst main pathway was long and characterized by 10 events whereas the second main pathway was short, contain only 2 events. To validate the simulation results the data compared with the biological and genetic models showing complete accordance between the 2 models.
Devlopment of secure framework for cloud compuing Environment
(AlNEElAN UNVERSLTY, 2016) Salwa Awad Abbas Idris
A Multi-Traits Dynamic User Model for Adaptive Educational Hypermedia Systems
(Al Neelain University, 2018-01) Nafisa Abdou Hassan Ahmed
Adaptive Educational hypermedia systems (AEHSs), was one of the first application areas for Adaptive Hypermedia. AEHSs, which deliver a personalized content to users, are evolved as an alternative educational model to the traditional one that provides same content to all users. An AEHS consist of three main components; the domain model (DM), which is the knowledge domain area where the AEHS is used as a learning resource. The user model (UM), which is a collection of user characteristics that are used to adapt the content in the domain model. And the adaptation model (AM) which describes the parts of the hypermedia system that to be adapted and the conditions under which this adaptation is to occur. In AEHS, the user model is the heart of the system, based on which the adaptation model personalize the content. A user model in AEHS is either static, where the information about the user characteristics is collected and updated before starting the adaptation or in habitual intervals, or dynamic, where the user information is updated continuously as the user interact with the system. In this research, a Multi Traits Dynamic User Model for Adaptive Educational Hypermedia Systems (AEHS) was proposed. The model incorporates four dynamic user characteristics; knowledge, learning style, goals, and behavior. The proposed dynamic user model is build to support adaptivity in lesson-based AEHS using those criterions. A user characteristics valuation algorithm is developed to evaluate the user's dynamic characteristics before moving to the next lesson. The valuation algorithm is based on link analysis on the user’s set of navigation links in the current lesson before the knowledge test. The algorithm assigns values to user learning style, goals and behavior, and knowledge and passes the valuation to the adaptation engine to generate adapted content of the next lesson page. The test of the model shows its flexibility and high adaptivity to user knowledge, learning style, goals, and behavior.
A proposed Figure Plagiarism Detection Techniques
(Al Neelain University, 2018-03) Mohammed Altyab Mohammed Ali
Plagiarism detection and prevention became one of the research and educational challenges. Many students and researchers tend to copy others work and ideas when doing research, projects, and assigned tasks. Most of the researches and papers that are meant for plagiarism detection are focusing on the plagiarism from text point of view. So far there is no significant works in figure plagiarism detection. One of these researches evaluate the effectiveness of two methodologies that capture the useful features in order to achieve higher classification accuracy from figure images, This work presents a novel method of figure plagiarism detection based on combination of two feature extraction methods : Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) compression techniques .These methods are used to extract the essential features to build the Perceptual Hash which is used as a feature in figure images plagiarism detection. The combined model had an accuracy of 99.32% when the number of features is 32. Also another model that extracts the essential feature using the Discrete Wavelet transform (DWT), Discrete Cosine Transform (DCT) and Optical Character Recognition (OCR) is constructed. This model combines the three extractor features and in the classification stage uses Support Vector Machine (SVM) technique in order to achieve higher classification accuracy. The experimental results showed that the average classification accuracy is 84% for 32 features when the figure images caption and text on the figure were used, and 75% for 32 features when text on the figure without the figure images caption were used. Farther investigations were recommended using large corpuses and different classification. This study recommends the inclusion of the text in the figure and text of caption in detecting figure plagiarism.
Data Stream Analysis for neural network tissues detection
(Al-Neelain University, 2019) Samir Salah Thabit Yaseen
Abstract Accurate brain tissues image segmentation can be considered as effective diagnosis support system for detecting affected edema and tumor tissues. Despite all the previous and existing efforts on segmenting these tissues and classifying them for the purposes of accurate diagnosis, still a lot of optimization works can be done in terms of increasing the accuracy and effectiveness of these tissues segmentation and classification. A number of challenges still can be address particularly for preprocessing and the utilization of neural networks and Fast-Fourier Transformation for classifying the contents of the tissues. This proposed solution is motivated by the achievement of reaching high-level of optimization solution for accurate human brain tissues segmentation and classification. For this purpose, a complete pipeline of algorithms for preprocessing and skull stripping, 2D image processing (such as Binarization and Normalization) as well as transformations techniques (such as Fast-Fourier transformation from continuous to digital domain). Also, artificial-intelligence techniques as neural-network supported by Self-Organizing Map (SOM) are all together integrated to achieve the highest possible optimized solution. Implementation of each process of the proposed pipeline algorithms solution has been implemented and performance evaluation of the proposed solution confirmed that accuracy of segmenting the different tissues types as well as the effected edema and tumor tissues reached above the 90.7% of accuracy. Keywords: Brain Tissues, Segmentation, Diagnosis, Preprocessing, Neural-Network, Self-Organizing Mapيمكن اعتبار التقسيم الدقيق لصورة أنسجة المخ كنظام دعم تشخيصي فعال للكشف عن أنسجة الورم والوذمة المصابة. على الرغم من كل الجهود السابقة والحالية لتقسيم هذه الأنسجة وتصنيفها لأغراض التشخيص الدقيق ، لا يزال من الممكن القيام بالكثير من أعمال التحسين من حيث زيادة دقة وفعالية تجزئة وتصنيف هذه الأنسجة. لا يزال هناك عدد من التحديات التي يمكن معالجتها بشكل خاص للمعالجة المسبقة واستخدام الشبكات العصبية وتحويل فورييه السريع لتصنيف محتويات الأنسجة. يتم تحفيز هذا الحل المقترح من خلال تحقيق الوصول إلى مستوى عالٍ من حل التحسين لتجزئة وتصنيف أنسجة المخ البشري بدقة. لهذا الغرض ، خط أنابيب كامل من الخوارزميات للمعالجة المسبقة وتجريد الجمجمة ، ومعالجة الصور ثنائية الأبعاد (مثل الثنائيات والتطبيع) بالإضافة إلى تقنيات التحويل (مثل تحويل فورييه السريع من المجال المستمر إلى المجال الرقمي). أيضًا ، تم دمج تقنيات الذكاء الاصطناعي كشبكة عصبية مدعومة بخريطة التنظيم الذاتي (SOM) معًا لتحقيق أعلى حل محسن ممكن. تم تنفيذ كل عملية من حل خوارزميات خط الأنابيب المقترح ، وأكد تقييم الأداء للحل المقترح أن دقة تقسيم أنواع الأنسجة المختلفة وكذلك الوذمة المصابة وأنسجة الورم وصلت إلى أكثر من 90.7٪ من الدقة. الكلمات الرئيسية: أنسجة المخ ، التجزئة ، التشخيص ، المعالجة المسبقة ، الشبكة العصبية ، خريطة التنظيم الذاتي
Title Design Adaptive Educational framework for Teaching Using Hypermedia Case study (University of holy Quran and Islamic science, Al Noor Institute for Blind Students)
(Neelain University, 2019-11) Abdoalgadir doalbait yousef doalbait
Abstract The design and implementation of Adaptive educational hypermedia systems (AEHS) web-based have grown exponentially in the last decade. AEHS are built on a base of the goals, preferences, behavior and knowledge of individual users to adapt to their specific needs. The ‘one size fits all’ is not an efficient educational philosophy. Instead teachers would be better applying the principle of ‘each student are unique’. Students have various strengths, challenges and interests. This requires teachers to be ﬂexible and open-minded. The research attempt to design Adaptive Educational Framework for Teaching using Hypermedia (AEH) web and mobile based to support students (visual and blind) learning progress at both the University of Holy Quran and Islamic sciences and Al Noor Institute for Blind Student. In addition, the research also attempts to support most the features of the e-learning standard. Moreover, illustrating student model (visual and blind) and teacher model. Also the framework includes Voice Courses Application for teaching blind students. It assists the blind student in all educational levels: primary, secondary, undergraduate. It is an interactive application through voice which can be run on the tablet or any android based phone. The research uses an analytical descriptive method. Also, the agile methodology which is used for the design of adaptive educational framework it is eXtreme Programming (XP) methodology, which was created in response to problem domains which requires change. The research uses modern tools to implement the framework and JAVA, C# are used for programming, Visual Studio 2017 and Android Studio 3.5 are used to design interfaces. Furthermore, it utilizes SQL server 2014 Database, and UML for representation of all artifacts. The adaptive educational framework has helped students learn based on individual needs and style. Also helps blind students to study and review in an easy and simple way by voice. It also helped measure the level of students for each stage in a particular course. Easy to use, managing and monitoring the course of student learning through their studies The researcher recommends that the arterial intelligence methods is suitable for improving adaptive engine processes and speech recognition. moreover, to develop the adaptive educational framework in order to include all the special educational needs. المستخلص لقد اصبح تصميم وتنفيذ أنظمة الوسائط التعليمية الفائقة على شبكة الإنترنت تنمو بشكل كبير في العقد الأخير. تعتمد هذه الانظمة على خصائص عديدة منها الاهداف والأفضليات والسلوك والمعرفة لكل طالب للتكيف مع احتياجاته بشكل فردي. إن مفهوم (مقاس واحد يناسب الجميع) ليس فلسفة تعليمية فعالة. بدلاً عن ذلك ، سيكون من الأفضل للمعلمين تطبيق مبدأ "كل طالب فريد". وهذا يتطلب أن يكون المعلمون مرينين ومتطلعين. يهدف البحث الى تصميم منصة التعليم التكيفي للتدريس باستخدام الوسائط الفائقة تعتمد على شبكة الإنترنت والموبايل لدعم الطلاب (المبصرين والمكفوفين) في العملية التعليمة في كل من جامعة القرآن الكريم والعلوم الإسلامية ومعهد النور للطلاب المكفوفين. ايضا يحاول البحث دعم معظم خصائص معايير التعليم الالكتروني. وعلاوة على ذلك ، يهدف البحث الى توضيح نموذج الطالب (المبصر والمكفوف) ونموذج المعلم. كما تضمن المنصة تطبيق المادة الصوتية لتعليم الطلاب المكفوفين. يساعد التطبيق الطلاب المكفوفين في جميع المستويات التعليمية: الابتدائية والثانوية ، والجامعية. وهو تطبيق تفاعلي من خلال الصوت الذي يمكن تشغيله على الجهاز المحمول أو أي هاتف يعمل بنظام اندرويد. يستخدم البحث طريقة التحليل الوصفي. وكذلك ، المنهجية الرشيقة التي استخدمت لتطوير المنصة المتكاملة للتعليم التكيفي. منهجية البرمجة السريعة تم إنشاؤها استجابة لنطاق المشكلة الذي يتطلب التغيير. يستخدم البحث أدوات حديثة لتنفيذ منصة التعليم التكيفي قد استخدم لغات البرمجة التالية ـ JAVA و C # ، وايضا استخدمت Visual Studio 2017 و Android Studio 3.5 لتصميم الواجهات. وعلاوة على ذلك ، فقد استخدمت SQL server 2014و UML لتوثيق النظام . منصة التعليم التكيفي ساعدت الطلاب على التعلم بناءً على احتياجات وأسلوب كل طالب على حدة. ايضا ساعدت الطلاب المكفوفين على الدراسة والمراجعة بطريقة سهلة وبسيطة من خلال الصوت. كذلك ساعدت في قياس مستوى الطلاب لكل مرحلة في كورس معين. سهولة الاستخدام وإلادارة ومراقبة مسار تعلم الطلاب من خلال دراستهم. يوصي البحث بأن أساليب الذكاء الصناعي مناسبة لتحسين عمليات التعلم التكيفي وايضا التعرف على الصوت. بالاضافة الى تطوير عمليات المنصة بحيث تشمل كل ذوي الاحتياجات الخاصة.
Path Computation Element Model on the Super Computer
(Al-Neelain University, 2019-12) Rawya Elmahi Gobara Saliem
Abstract High-performance computing has become important in this era, especially for applications that need high-speed and more accurate processing, such as meteorological research, climate research, and digital signal processing. In light of this development, it was necessary to develop the computing environment.Therefore, this research aims to develop Dijkstra's algorithmin the open source program (Path computation element) and apply the concepts of parallel and hierarchical computing using map reduction. In order to reach the shortest path in the network at the lowest cost and the highest speed of implementation while reducing the risk of failure, it is worth mentioning that Dijkstra's algorithm is dominant in solving the shortest path problems between all the nodes in the network.The researcher used the analytical and descriptive methodology to find the shortest path in the network through the hierarchical and parallel Dijkstra algorithm. 200 nodes and 36 processors as a sample implementation. The results of the researcher in the hierarchy were that the percentage of the total performance of the first 100 nodes is 430 seconds, while the percentage of the total performance of the nodes is 920 seconds, and the uptime decreases with the increase in the number of cores, the speed increases with the increase in the number of cores until it reaches the value Then the speed decreases, the cost decreases when the operating time decreases.In parallel, the percentage of total performance for the first 100 nodes is 55 seconds, and the percentage of total performance for the first 100 nodes is 100 seconds. The running time decreases in parallel with the increase in the number of nodes when all the cores are in the same node. The researcher also reached recommendations, the most important of which is the use of Dijkstra's algorithm in large and medium schemes. When the network structure is hierarchical, the Dijkstra hierarchical algorithm is used. When the source node is one layer and the destination node is in another layer, searching for the shortest path will cover not only each layer but also the short paths of the interlayer. This algorithm is based on Dijkstra's parallel algorithm, where it is divided into parallel groups in any topological layers, and each hierarchical layer will form another layer of groups. Dijkstra's algorithm does not handle negative edges. The researcher recommends using the Dijkstra algorithm using both parallel and hierarchical methods to complete the process of finding the shortest path for all nodes in the network.اﻟﻤﺴﺘﺨﻠﺺ اﻟﺤﻮﺳﺒﺔ ﻋﺎﻟﯿﺔ اﻻداء اﺻﺒﺤﺖ ﻣﮭﻤﺔ ﻓﻲ ھﺬا اﻟﻌﺼﺮ ،ﺧﺎﺻﺔ اﻟﺘﻄﺒﯿﻘﺎت اﻟﺘﻲ ﺗﺤﺘﺎج اﻟﻲ ﻣﻌﺎﻟﺠﺔ ﺑﺴﺮﻋﺔ ﻋﺎﻟﯿﺔ واﻛﺜﺮ دﻗﺔ ،ﻣﺜﻞ اﺑﺤﺎث اﻻرﺻﺎد اﻟﺠﻮي ،واﺑﺤﺎث اﻟﻤﻨﺎخ ،وﻣﻌﺎﻟﺠﺔ اﻻﺷﺎرات اﻟﺮﻗﻤﯿﺔ .وﻓﻲ ظﻞ ھﺬا اﻟﺘﻄﻮر ﻛﺎن ﻻﺑﺪ ﻣﻦ ﺗﻄﻮﯾﺮ ﺑﯿﺌﺔ اﻟﺤﻮﺳﺒﺔ. ﻟﺬا ﯾﮭﺪف ھﺬا اﻟﺒﺤﺚ اﻟﻲ ﺗﻄﻮﯾﺮ ﺧﻮارزﻣﯿﺔ دﯾﻜﺴﺘﺮا ﻓﻲ اﻟﺒﺮﻧﺎﻣﺞ ﻣﻔﺘﻮح اﻟﻤﺘﻮازﯾﺔ واﻟﮭﺮﻣﯿﺔ ﺑﺎﺳﺘﺨﺪام ﺗﻘﻠﯿﻞ ) element computation Path ( وﺗﻄﺒﯿﻖ ﻣﻔﺎھﯿﻢ اﻟﺤﻮﺳﺒﺔ اﻟﻤﺼﺪر اﻟﺨﺮﯾﻄﺔ . وذﻟﻚ ﻟﻠﻮﺻﻮل اﻟﻲ اﻗﺼﺮ ﻣﺴﺎر ﻓﻲ اﻟﺸﺒﻜﺔ ﺑﺎﻗﻞ ﺗﻜﻠﻔﺔ واﻋﻠﻲ ﺳﺮﻋﺔ ﻟﻠﺘﻨﻔﯿﺬ ﻣﻊ ﺗﻘﻠﯿﻞ ﻣﺨﺎطﺮ اﻟﻔﺸﻞ ،واﻟﺠﺪﯾﺮ ﺑﺎﻟﺰﻛﺮ ان ﺧﻮارزﻣﯿﺔ دﯾﻜﺴﺘﺮا ﻣﮭﯿﻤﻨﺔ ﻋﻠﻲ ﺣﻞ ﻣﺸﺎﻛﻞ أﻗﺼﺮ اﻟﻄﺮق ﺑﯿﻦ ﻛﻞ اﻟﻌﻘﺪ اﻟﻤﻮﺟﻮدة ﻓﻲ اﻟﺸﺒﻜﺔ .اﺳﺘﺨﺪم اﻟﺒﺎﺣﺚ اﻟﻤﻨﮭﺞ اﻟﺘﺤﻠﯿﻠﻲ واﻟﻮﺻﻔﻲ ﻛﻄﺮﯾﻘﺔ ﻋﻠﻤﯿﺔ ﻓﻲ ھﺬا اﻟﺒﺤﺚ، ﻟﻠﻌﺜﻮر ﻋﻠﻲ اﻗﺼﺮ ﻣﺴﺎر ﻓﻲ اﻟﺸﺒﻜﺔ ﻋﻦ طﺮﯾﻖ ﺧﻮارزﻣﯿﺔ دﯾﻜﺴﺘﺮا اﻟﮭﺮﻣﯿﺔ واﻟﻤﺘﻮازﯾﺔ وﺗﻢ ذﻟﻚ ﻋﻦ طﺮﯾﻖ ﺗﺼﻤﯿﻢ ﺑﺮﻧﺎﻣﺞ ﺑﻠﻐﺔ اﻟﺒﺎﯾﺜﻮن ، ﻟﻠﺒﺤﺚ ﻋﻦ اﻗﺼﺮ ﻣﺴﺎرﻓﻲ اﻟﺸﺒﻜﺔ ﻋﺒﺮ اﻟﺘﺴﻠﺴﻞ اﻟﻤﺘﻮازي واﻟﮭﺮﻣﻲ وﯾﻘﻮم ﺑﺤﺴﺎب اﻟﺰﻣﻦ واﻟﺘﻜﻠﻔﺔ ﻣﻌﺎﻟﺞ ﻛﻌﯿﻨﺔ ﻟﻠﺘﻨﻔﯿﺬ.اﻟﻨﺘﺎﺋﺞ اﻟﺘﻲ ﺗﻮﺻﻞ اﻟﯿﮭﺎ اﻟﺒﺎﺣﺚ ﻓﻲ ﻋﻘﺪة و36 200 واﻟﺴﺮﻋﺔ ، اﺳﺘﺨﺪام اﻟﺒﺎﺣﺚ اﻟﺘﺴﻠﺴﻞ اﻟﮭﺮﻣﻲ ﻛﺎﻧﺖ اﻟﻨﺴﺒﺔ اﻟﻤﺌﻮﯾﺔ ﻟﻼداء اﻟﻜﻠﻲ ﻻول 100 ﻋﻘﺪة ھﻲ 430 ﺛﺎﻧﯿﺔ ،ﻓﻲ ﺣﯿﻦ ان اﻟﻨﺴﺒﺔ اﻟﻤﺌﻮﯾﺔ ﻟﻼداء اﻟﻜﻠﻲ ﻟﻠﻌﻘﺪ ھﻲ 920 ﺛﺎﻧﯿﺔ ، ﯾﺘﻨﺎﻗﺺ وﻗﺖ اﻟﺘﺸﻐﯿﻞ ﻣﻊ ذﯾﺎدة ﻋﺪد اﻟﻨﻮي ،ﺗﺬداد اﻟﺴﺮﻋﺔ ﻣﻊ ذﯾﺎدة ﻋﺪد اﻟﻨﻮي ﺣﺘﻲ ﺗﺼﻞ اﻟﻲ اﻟﻘﯿﻤﮫ اﻟﻘﺼﻮي ﺛﻢ ﺑﻌﺪ ذﻟﻚ ﺗﺘﻨﺎﻗﺺ اﻟﺴﺮﻋﺔ ،ﺗﻘﻞ اﻟﺘﻜﻠﻔﺔ ﻋﻨﺪﻣﺎ ﯾﻘﻞ زﻣﻦ اﻟﺘﺸﻐﯿﻞ . وﻓﻲ اﻟﺘﻮازي اﻟﻨﺴﺒﺔ اﻟﻤﺌﻮﯾﺔ ﻟﻼداء اﻟﻜﻠﻲ ﻻول 100 ﻋﻘﺪة ھﻲ 55 ﺛﺎﻧﯿﺔ ، اﻟﻨﺴﺒﺔ اﻟﻤﺌﻮﯾﺔ ﻟﻼداء اﻟﻜﻠﻲ ﻓﻲ اﻟﻌﻘﺪ ھﻲ ﯾﺘﻨﺎﻗﺺ وﻗﺖ اﻟﺘﺸﻐﯿﻞ ﻓﻲ اﻟﺘﻮازي ﻣﻊ ذﯾﺎدة ﻋﺪد اﻟﻌﻘﺪ ﻋﻨﺪﻣﺎ ﺗﻜﻮن ﺟﻤﯿﻊ اﻟﻨﻮي ﻓﻲ ﻧﻔﺲ ﺛﺎﻧﯿﺔ . 100 اﻟﻌﻘﺪة،اذا ﺗﻢ اﺳﺘﺨﺪام اﻟﻨﻮي ﻣﻦ ﻋﻘﺪ ﻣﺨﺘﻠﻔﺔ ﯾﺬاد وﻗﺖ اﻟﺘﺸﻐﯿﻞ ﺑﺸﻜﻞ اﻛﺒﺮ ، اﻣﺎ ﻣﻦ ﻧﺎﺣﯿﺔ اﻟﺴﺮﻋﺔ ﺗﺬداد اذا .ﻛﺬﻟﻚ ﺗﻮﺻﻞ .ﻋﻨﺪﻣﺎ ﯾﻜﻮن ﻛﺎن اﻟﻨﻮي ﻣﻦ ﻧﻔﺲ اﻟﻌﻘﺪة ،واﻟﻌﻜﺲ ﺗﺘﻨﺎﻗﺺ اﻟﺴﺮﻋﺔ ﻋﻨﺪ اﺳﺘﺨﺪام اﻟﻨﻮي ﻣﻦ ﻋﻘﺪ ﻣﺨﺘﻠﻔﺔ اﻟﺒﺎﺣﺚ اﻟﻲ ﺗﻮﺻﯿﺎت اھﻤﮭﺎ اﺳﺘﺨﺪام ﺧﻮارزﻣﯿﺔ دﯾﻜﺴﺘﺮا ﻓﻲ اﻟﻤﺨﻄﻄﺎت اﻟﻜﺒﯿﺮة واﻟﻤﺘﻮﺳﻄﺔ ھﯿﻜﻞ اﻟﺸﺒﻜﺔ ھﺮﻣﯿًﺎ ﯾﺘﻢ اﺳﺘﺨﺪام ﺧﻮارزﻣﯿﺔ دﯾﻜﺴﺘﺮا اﻟﮭﺮﻣﯿﺔ .ﻋﻨﺪﻣﺎ ﺗﻜﻮن اﻟﻌﻘﺪة اﻟﻤﺼﺪر طﺒﻘﺔ واﺣﺪة وﺗﻜﻮن اﻟﻌﻘﺪة اﻟﻮﺟﮭﺔ ﻓﻲ طﺒﻘﺔ أﺧﺮى ، ﻓﺈن اﻟﺒﺤﺚ ﻋﻦ أﻗﺼﺮ ﻣﺴﺎر ﻟﻦ ﯾﻐﻄﻲ ﻓﻘﻂ ﻛﻞ طﺒﻘﺔ وﻟﻜﻦ أﯾﻀًﺎ اﻟﻤﺴﺎرات ﺣﯿﺚ ﺗﻘﺴﻢ اﻟﻲ اﻟﻤﺘﻮازﯾﺔ Dijkstra .ﺗﻌﺘﻤﺪ ھﺬه اﻟﺨﻮارزﻣﯿﺔ ﻋﻠﻰ ﺧﻮارزﻣﯿﺔ اﻟﻘﺼﯿﺮة ﻟﻠﻄﺒﻘﺔ اﻟﺒﯿﻨﯿﺔ ﻣﺠﻤﻮﻋﺎت ﻣﺘﻮازﯾﺔ ﻓﻲ أي طﺒﻘﺎت طﻮﺑﻮﻟﻮﺟﯿﺔ وﻛﺬﻟﻚ ﺳﺘﺸﻜﻞ ﻛﻞ طﺒﻘﺔ ھﺮﻣﯿﺔ طﺒﻘﺔ أﺧﺮى ﻣﻦ اﻟﻤﺠﻤﻮﻋﺎت . ﺧﻮارزﻣﯿﺔ دﯾﻜﺴﺘﺮا ﻻ ﺗﺘﻌﺎﻣﻞ ﻣﻊ اﻟﺤﻮاف اﻟﺴﺎﻟﺒﺔ . اوﺻﻲ ﺑﺎﺳﺘﺨﺪام ﺧﻮارزﻣﯿﺔ اﻟﺪﯾﻜﺴﺘﺮا ﺑﺎﻟﻄﺮﯾﻘﺘﯿﻦ اﻟﻤﺘﻮازﯾﺔ واﻟﮭﺮﻣﯿﺔ ﻟﺘﻜﻤﻠﺔ ﻋﻤﻠﯿﺔ اﻟﺒﺤﺚ ﻋﻦ اﻗﺼﺮ ﻣﺴﺎر ﻟﺠﻤﯿﻊ اﻟﻌﻘﺪ ﻓﻲ اﻟﺸﺒﻜﺔ .
Development of Hybrid Intrusion Detection System for False Rate Reduction
(Al-Neelain University, 2020) Mohamed Ahmed Elmubarak Mohamed
ABSTRACT This thesis investigates Network Intrusion Detection System (NIDS) methods, in order to enhance the detection accuracy into NIDS systems, a new hybrid model implemented efficiently to reduce the false alerts into NIDS systems. also a comparison has been made between NIDS detection techniques to show the pros and cons of each approaches. The main objective is to study these techniques to get the advantages of each one by combining them in one model; The implemented model will be a combination of misuse and anomaly detection methods. This model showed an efficient NIDS implementation that can increase the performance of detection accuracy, hybrid model has -4122sec detection rate compared to anomaly model and -54301 sec detection rate compared to misuse; indicate the speed of detection rate is lower in hybrid compared to the other two models. Moreover, hybrid model captured 70.70% of attack traffic compared with misuse model 31% and anomaly 67.02%; hybrid showed more reliability over misuse and anomaly models. المستخلص تبحث هذه الرسالة في طرق نظام اكتشاف اختراق الشبكة (NIDS) ، من أجل تعزيز دقة الكشف في أنظمة NIDS ، تم تنفيذ نموذج هجين جديد بكفاءة لتقليل التنبيهات الخاطئة في أنظمة NIDS. كما تم إجراء مقارنة بين تقنيات الكشف عن NIDS لإظهار إيجابيات وسلبيات كل نهج. الهدف الرئيسي هو دراسة هذه التقنيات للحصول على مزايا كل واحدة من خلال دمجها في نموذج واحد ؛ سيكون النموذج الذي تم تنفيذه مزيجًا من طرق اكتشاف سوء الاستخدام والعيوب. أظهر هذا النموذج تنفيذًا فعالًا لـ NIDS يمكن أن يزيد من أداء دقة الكشف ، والنموذج الهجين لديه معدل اكتشاف -4122 ثانية مقارنة بنموذج الشذوذ ومعدل اكتشاف -54301 ثانية مقارنة بسوء الاستخدام ؛ تشير إلى أن سرعة الكشف أقل في الهجين مقارنة بالنموذجين الآخرين. علاوة على ذلك ، استحوذ النموذج الهجين على 70.70٪ من حركة الهجوم مقارنة بنموذج سوء الاستخدام 31٪ والشذوذ 67.02٪ ؛ أظهر الهجين مزيدًا من الموثوقية على نماذج سوء الاستخدام والشذوذ.
An Algorithm for Choosing Best Approach for Developing Mobile Application Focusing on Performance: Applied to Diabetes Self-management Application, Khartoum State, Sudan (2019)
(Al-Neelain University, 2020) Sara Ali Abd Elrahim Said
Abstract Mobile application is an application that design to run on mobile device like smart phones , pads and tablets. Mobile application like desktop application has different types of applications development approaches : native , web and hybrid are the three main approaches. Every one of these approaches has targets, advantages and disadvantages. The purpose of this study is to find out the differences between the three main approaches for developing mobile applications, with focusing on the performance of native and hybrid applications due to an increasing market for platform independent applications. In this research work, the results of different previous studies were analyzed which compared between the three approaches to find out the best approach depending on different considerations. The current findings were presented concerning performance efficiency in mobile applications. At first, user experience and performance is the most discussed consideration. 33.3% of the introduced previous studies compared the performance of the three approaches and they all agree that native application is better than hybrid application when the developed application requires performance and need to use device features, and web application would be a good choice for lightweight applications that do not use device features. Although native applications have higher performance but the publications of the web applications (41.6% ) and hybrid applications (38.3%) on the IEEE (2000-2018) were higher compared to native application (20%) and that because all the new studies try hard to optimize the performance of the web and hybrid applications to be as same as native applications. Also an algorithm was introduced to help mobile application developers in deciding which one of the three approaches is the best approach for their proposed applications. Then this algorithm was applied to an application for self-management of diabetes to find out the best approach for this application and the result is native approach. In the future it is recommend to optimize the performance of the hybrid and web applications to have high performance close to native application performance. خوارزمية لاختيار الطريقة المناسبة للتطبيق النقال مع التركيز على الأداء وتطوير تطبيق نقال للإدارة الذاتية لمرض السكري، ولاية الخرطوم ،السودان 2019م ساره علي عبد الرحيم سعيد ملخص الدراسة التطبيق النقال هو تطبيق مصمم للتشغيل على الجهاز المحمول تمامًا مثل الهواتف الذكية والأجهزة اللوحية. وقد أصبح في يومنا هذا أكثر شعبية. يحتوي التطبيق النقال ، مثل تطبيق سطح المكتب ، على أنواع مختلفة من أساليب تطوير التطبيقات: أصلي (Native) ، شبكي Web)) و هجين ((Hybrid. كل واحد من المنهجيات الثلاثة له أهداف ومزايا وعيوب. الغرض من هذه الدراسة هو معرفة الفرق بين المنهجيات الرئيسية الثلاثة لتطوير التطبيقات مع التركيز على أداء التطبيقات النقالة: الأصلي و الهجين بسبب زيادة السوق للتطبيقات المعتمدة على النظام الأساسي. في هذا البحث ، تعد نتائج الدراسات السابقة المختلفة بمثابة تحليلات تقارن بين الطرق الثلاثة لاكتشاف النهج الأفضل وفقًا لاعتبارات مختلفة. نقدم النتائج الحالية المتعلقة بكفاءة الأداء في التطبيقات النقالة. في البداية ، وجدنا أن أداء التطبيقات هو الاعتبار الأهم في تقييم التطبيقات، 33..3% من الدراسات السابقة قارنت بين أداء المنهجيات الثلاثة وجميعها اتفقت أن ألتطبيق الأصلي أفضل من ألتطبيق الهجين عندما يحتاج التطبيق إلي أداء عالي ويتطلب استخدام ميزات الجهاز و أيضاً ألتطبيق الشبكي يمكن أن يكون خيار جيد للتطبيقات البسيطة التي لا تحتاج لاستخدام ميزات الجهاز. بالرغم من أن ألتطبيقات الأصلية لها الأداء الأعلى لكن عدد النشر في IEEE في الفترة (2000-2018) في مجال ألتطبيقات الشبكية (41.6%) والتطبيقات الهجين (38.3%) أكثر من النشر في جانب ألتطبيقات الأصلية والسبب وراء ذلك هو أن الدراسات الحديثة اغلبها تحاول تحسين أداء ألتطبيقات الشبكية والهجين ليصبح لديها أداء عالي مماثل لأداء التطبيقات الأصلية. كما تم تقديم خوارزمية لمساعدة مطوري التطبيقات النقالة في تحديد أي من المنهجيات الثلاثة هي أفضل منهجية لتطبيقاتهم المقترحة. ثم تم تطبيق هذه الخوارزمية على تطبيق للإدارة الذاتية لمرض السكري لمعرفة أفضل منهجية لهذا التطبيق والنتيجة هي ألمنهجية الأصلية (Native Approach). في الدراسات المستقبلية يوصى بتحسين أداء التطبيقات ألشبكية والهجين للحصول علي أداء مساوي لأداء التطبيقات الأصلية .
Framework for Factors Influencing the Adoption of Information Technology (IT) in Small and Medium sized Enterprises (SME’S) in Sudan Case study Shaikan Company
(Al-Neelain University, 2020) Nagmeldeen FadolAbdalla Ahmed
Abstract The problem of the study is that there are a set of factors that influence the adoption of IT in small and medium-sized companies in different parts of the world. Given the emergence of the Sudanese market, SMEs depend to some extent on supply from outside the country. This requires extensive use of information technology to facilitate business contacts with their business partners. It is not entirely clear what is the real obstacle preventing SMEs from adopting IT in Sudan. The study aimed to determine the factors affecting the adoption of information technology by small and medium enterprises in Sudan. The study tested the hypotheses that there is a statistically significant relationship between activity and knowledge of information technology and small and medium-sized companies. There is a statistically significant relationship between factors affecting IT adoption and SMEs. There is a statistically significant relationship between the impact of implementing information technology and SMEs. There is a statistically significant relationship between the problems and obstacles of using information technology. And small and medium businesses. The study used the descriptive and analytical approach. The target community for the study was (240) small and medium companies within the city of Khartoum. This constitutes 10% of the total sample, and it was represented by (81) individuals. The study used descriptive and inferential statistics to analyze the data using SPSS Mac version 22. One of the most important results of the research is that all the factors mentioned in the literature have a significant impact on the adoption of information technology, that the factors are beneficial to small and medium-sized companies in terms of profitability and performance, that the adoption of information technology by SMEs in Sudan has led to improved accountability. However, the influencing factors are already positive towards the profitability and growth of SMEs. The study recommended the necessity of penetrating the knowledge spread gap about the factors affecting the adoption of information technology. Continuous research is required, as more factors emerge as a result of market stability and industry maturity, the necessity for SMEs to adopt information technology in Sudan. The government should take responsibility and lead the awareness process in Sudan to educate SME owners of the potential benefits of adopting IT for their companies.. المستخلص مشكلة الدراسة هي أن هناك مجموعة من العوامل التي تؤثر على اعتماد تكنولوجيا المعلومات في الشركات الصغيرة والمتوسطة الحجم في أنحاء مختلفة من العالم. نظرا لظهور السوق السوداني ، تعتمد الشركات الصغيرة والمتوسطة إلى حد ما على العرض من خارج البلاد. وهذا يتطلب استخدامًا مكثفًا لتكنولوجيا المعلومات لتسهيل الاتصالات التجارية مع شركائهم التجاريين. ليس من الواضح تمامًا ما هو العائق الحقيقي الذي يمنع الشركات الصغيرة والمتوسطة من تبني تكنولوجيا المعلومات في السودان. هدفت الدراسة إلى تحديد العوامل المؤثرة في تبني الشركات الصغيرة والمتوسطة لتقنية المعلومات في السودان. اختبرت الدراسة فرضيات وجود علاقة ذات دلالة إحصائية بين نشاط ومعرفة تقنية المعلومات والشركات الصغيرة والمتوسطة. هناك علاقة ذات دلالة إحصائية بين العوامل التي تؤثر على تبني تكنولوجيا المعلومات والشركات الصغيرة والمتوسطة. توجد علاقة ذات دلالة إحصائية بين تأثير تطبيق تقنية المعلومات والمؤسسات الصغيرة والمتوسطة. توجد علاقة ذات دلالة إحصائية بين مشكلات ومعوقات استخدام تقنية المعلومات. والشركات الصغيرة والمتوسطة. استخدمت الدراسة المنهج الوصفي والتحليلي. كان المجتمع المستهدف للدراسة (240) شركة صغيرة ومتوسطة داخل مدينة الخرطوم. ويشكل هذا نسبة 10٪ من إجمالي العينة ومثلها (81) فرداً. استخدمت الدراسة الإحصاء الوصفي والاستنتاجي لتحليل البيانات باستخدام SPSS Mac الإصدار 22. ومن أهم نتائج البحث أن جميع العوامل المذكورة في الأدبيات لها تأثير كبير على تبني تقنية المعلومات ، وأن هذه العوامل تعود بالفائدة على الشركات الصغيرة والمتوسطة من حيث الربحية والأداء ، وأن أدى تبني الشركات الصغيرة والمتوسطة لتكنولوجيا المعلومات في السودان إلى تحسين مستوى المسئولية. ومع ذلك ، فإن العوامل المؤثرة إيجابية بالفعل تجاه ربحية ونمو الشركات الصغيرة والمتوسطة. أوصت الدراسة بضرورة سد فجوة انتشار المعرفة حول العوامل المؤثرة في تبني تقنية المعلومات. البحث المستمر مطلوب ، مع ظهور المزيد من العوامل نتيجة لاستقرار السوق ونضج الصناعة ، ضرورة اعتماد الشركات الصغيرة والمتوسطة لتكنولوجيا المعلومات في السودان. يجب على الحكومة أن تتحمل المسؤولية وتقود عملية التوعية في السودان لتثقيف أصحاب المشروعات الصغيرة والمتوسطة بالفوائد المحتملة لاعتماد تكنولوجيا المعلومات لشركاتهم ..
QUALITY ASSURANCE IN E-LEARNING SOFTWARE SYSTEM WITH RESPECT TO USER EXPECTATIONS (SUDAN CASE)
(Al-Neelain University, 2020-09) Fatima Mustafa Hassan Amin
Abstract Software quality assurance (SQA) nowadays is an integral part in software that is established for any purpose, like development process and the quality of the product, and so on. The efficiency, effectiveness of software and response to user' needs and requirements are the main objective for the success of the products. Software manages information in the form of operating system. Software has two major sections, system software: which control the basic job of the computer, and application software: which handles multiple tasks of the user needs to do. Electronic learning (E-learning), mainly it has given the meaning of use the computer and internet technology to communicate and deliver every things. This study intends to create E-learning model (The System, Instructor and Student Model (SISM)) with its critical success factors (CSFs) which can achieve software quality assurance in E-learning application, by simplifying the usage of E-learning software and protects the defect in E-learning. The proposed E-learning critical success factors are surveyed and grouped into four categories namely, instructor side, student side, system side and their interactions. The study has implemented the model (SISM) and achieved required software quality assurance by satisfying the requirements and needs easily without defects. Software application has been developed to considering the factors of the system, student, instructor and the intersection of the model. ASP.NET is used for building the application along with C# programming language. The graphical user interface was build using HTML5. The application was tested over three educational institutions in Sudan. The obtained results were compared to determine if they really satisfy the needs, requirements and acquisition of the right knowledge according to quality assurance. The model has corrected the mistake easily in the previous models and addressed the defects that occurred. The given result was accurate and promising satisfying the model tests. We hope that this model serves as a basis for the evaluation of other E-learning software in the future. الملخص يعد ضمان جودة البرمجيات (اس كيو اي) في الوقت الحاضر جزءًا لا يتجزأ من البرنامج الذي تم إنشاؤه لأي غرض ، مثل عملية التطوير وجودة المنتج، وما الي ذلك. تعد كفاءة وفعالية البرامج والاستجابة لاحتياجات ومتطلبات المستخدم الهدف الرئيسي لنجاح المنتجات. يدار برنامج المعلومات في شكل نظام التشغيل. يحتوي البرنامج على قسمين رئيسيين ، برنامج النظام:الذي يتحكم في الوظيفة الإساسية للكمبيوتر،وبرنامج التطبيقات : الذى يتولى مهام متعدة يحتاج المستخدم الى القيام بها. التعلم الالكترونى، وقد أعطى بشكل أساسى معنى استخذام تكنلوجيا الكمبيوتر والنترانت للتواصل وتقديم كل الاشياء. تهدف هذه الدراسة إلى إنشاء نموذج للتعلم الإلكتروني (النظام ، المعلم ، طالب والنموزج(اس اي اس ام)) مع عوامل النجاح الحرجة(سي اس افس) التي يمكن أن تحقق ضمان جودة البرمجيات في تطبيق التعليم الإلكتروني، من خلال تبسيط استخدام برنامج التعلم الإلكتروني ويحمي الخلل في التعلم الإلكتروني. يتم مسح عوامل النجاح الحاسمة للتعلم الإلكتروني المقترح وتقسيمها إلى أربع فئات هي: جانب المعلم ، جانب الطالب ، جانب النظام وتفاعلاتهم. نفذت الدراسة على النموذج(اس اي اس ام) وحققت ضمان جودة البرمجيات المطلوبة من خلال تلبية الاحتياجات و المتتطلبات بسهولة دون عيوب. تم تطوير تطبيق البرنامج لدراسة عوامل النظام والطالب والمدرب وتقاطع النموذج. يستخدم اسب دوت نت لإنشاء التطبيق مع لغة البرمجة سي شارب. تم إنشاء واجهة المستخدم الرسومية باستخدام اتش تى ام ال 5. تم اختبار التطبيق على ثلاث مؤسسات تعليمية في السودان. تمت مقارنة النتائج التي تم الحصول عليها لتحديد ما إذا كانت تفي حقًا بالاحتياجات والمتطلبات واكتساب المعرفة الصحيحة وفقًا لضمان الجودة. قام النموذج بتصحيح الخطأ بسهولة في النماذج السابقة ومعالجة العيوب التي حدثت. كانت النتيجة المعطاة دقيقة وواعدة لإرضاء اختبارات النموذج. نأمل أن يكون هذا النموذج بمثابة أساس لتقييم برامج التعليم الإلكتروني الأخرى في
A Design of an Intelligent Information System Based on Feature Sensitivity Algorithm for Diabetes Emergency Medicine
(Al-Neelain University, 2021) Ali Abdallah Abaker Adam
Abstract Diabetes is a chronic disease and considered a serious global health challenge. Diabetes complications happen when diabetes is uncontrolled. Every 21 seconds, a new case of diabetes is diagnosed globally. Diabetes is responsible of 1.6 million deaths annually and 30 percent of the healthcare spending goes to address diabetes complications. This research addresses data loss which is a frequent problem facing machine learning models at both the training and production phases. Loss of values negatively affects the accuracy of the models, especially in the medical field where accuracy is very sensitive. The previous studies addressed the missing values in the model-training phase. In addition, the previous missing value treatment methods were based on replacing the missing value with one value and there is no flexibility in the replacement. The dataset collected from Alsukari Hospital. It contains 644 records and 29 attributes of diagnosed diabetes patients who were admitted to the emergency department in the period from January 2018 to April 2019 for building the model and verified using a dataset from online repository (https://data.mendeley.com/datasets/jx3sv3p2hm/1) containing 177 records and 22 features. The study proposed feature sensitivity algorithm to identify within feature sensitivity. Also, we designed three machine learning models: the first model to predict diabetes complications with an accuracy of 0.81 using logistic regression algorithm which outperformed random forest and KNN. The second model designed to predict diabetic ketoacidosis (DKA), which achieved an accuracy of 0.81using random forest classifier. The third to predict COVID-19 using survey data based on k-mode algorithm with 0.71 accuracy. We designed an intelligent information system (IIS) and deployed the three machine learning models into (IIS). We used input slider in designing the system for replacing the missing values, which provided flexibility and usability to the system users. Doctors need to be allowed to identify and monitor patients at risk of complications for the early introduction of medical interventions. المستخلص مرض السكري هو مرض مزمن ويعتبر من اخطر التحديات الصحية العالمية. تحدث مضاعفات السكري عندما يكون مرض السكري خارج عن السيطرة. في كل 21 ثانية يتم تشخيص حالة جديدة للسكري على مستوى العالم. مرض السكري مسؤول عن وفاة 1.6 مليون حالة سنويًا ، ويتم تخصص 30 بالمائة من إنفاق الرعاية الصحية لمعالجة مضاعفات مرض السكر. يتناول هذا البحث مشكلة فقدان البيانات وهي مشكلة متكررة تواجه نماذج التعلم الآلي في كل من مرحلتي التدريب والتشغيل. يؤثر فقدان القيم سلبًا على دقة النماذج ، خاصة في المجال الطبي حيث تكون الدقة مهمة للغاية. تناولت معظم الدراسات السابقة معالجة القيم المفقودة في مرحلة تدريب النموذج. استندت طرق معالجة القيمة المفقودة السابقة إلى استبدال القيمة المفقودة بقيمة واحدة ولا توجد مرونة في الاستبدال. تم جمع مجموعة البيانات من مستشفى السكري. تحتوي البيانات على 644 سجلاً و 29 صفة(attributes) لمرضى السكري الذين تم إدخالهم إلى قسم الطوارئ في الفترة من يناير 2018م إلى أبريل 2019م.اسخدمت هذه البيانات في بناء النموذج وتم التحقق من النموذج بأستخدام بيانات من الانترنت https://data.mendeley.com/datasets/jx3sv3p2hm/1 تحتوي علي 177 سجل و 22 صف. اقترحت الدراسة خوارزمية حساسية الصفات (feature sensitivity algorithm) للتحقق من حساسية الصفة. كما تم تصميم ثلاثة نماذج للتعلم الآلي: النموذج الأول للتنبؤ بمضاعفات مرض السكري ، حقق النموذج النهائي دقة بلغت 0.81 باستخدام خوارزمية الانحدار اللوجستي(logistic regression) التي تفوقت على random forest و KNN ، والنموذج الثاني للتنبؤ بالحماض الكيتوني السكري (DKA) الذي حقق دقة بلغت 810. باستخدام random forest ، والثالث يتنبأ بـ COVID-19 باستخدام بيانات استبيان وخوارزمية K-mode بدقة بلغت 0.71. كما تم تصميم نظام معلومات مبني علي استخدام نماذج تعلم الألة وتشغيل النماذج الثلاثة في النظام. تم إستخدام (input slider) في تصميم النظام مما أعطي مرونة و سهولة في الاستخدام . يسمح هذا النظام للأطباء بتصنيف ومراقبة المرضى المعرضين لخطر المضاعفات للتدخل الطبي المبكر.
A Design of a Model for Analyzing Political Sudanese Arabic Tweets Using Deep Learning
(ِِAl-neelain University, 2021) Fatima Salih Ibrahim
Sentiment analysis of the Arabic language has gained the attention of many researchers because of the increasing number of Arabic internet users, and the exponential growth of Arabic content online. Sentiment detection of Arabic tweets is at interesting research topic and it enables scholars to analyze huge resources of shared opinions in social media websites such as Facebook and 1 weeter. Sentiment analysis has many applications ranging from ﬁnancial analysis to political decision-making domains. It is one of the more complex natural language processing tasks due to the informal noisy contents and the rich morphology of Arabic language. Many studies have been investigated for Arabic sentiment analysis. However, most of these works ignore analyzing political Arabic tweets, speciﬁcally the Sudanese Arabic dialect. Ehis thesis, focus t: analyz _ Arabic tweets during Sudanese revolution 2018 and developed a deep leaming model for classifying the tweets. The ;w:=;~ "~»cvf:~:»-.?=.~’»~' is a deep learning-based approach. This approach employed word embedding with convolutional neural network and long short-tenn memory network techniques to represent the tweets and extract the feature vectors. Aﬁer that, the feature vectors \\\-to fed to the classiﬁer to detect the sentiments. This approach exploited Word2Vec, convolutional neural networks and recurrent neural networks algorithms. The proposed model has three steps namely data preprocessing, feature extraction, and classiﬁcation phase. The model has a network architecture to represent the tweets and improve the classiﬁcation performance. \\. < -_‘.\._1'Li . -»>
development of an international airports standard framework case tool (khartoum international airport)
(Al-Neelain University, 2022) imad mohummed alsayid abdalla
Abstract The Main Problem of the study is there is no tool that gives enough information about International Airport Standards around the World like Comprehensive tool, and the missed tools of assessment according to quick change in environment, the Objectives of the study is to design a Mixed Framework Standards, development International Airport Standards, and design a tool to assess the Airports environment, the Methodology of the Study is Identify, Detect, Assess, Protect(IDAP), and in the study tools is the enterprise Architect program was used in the analysis phase of UML diagrams, and the XD Design program in the design phase of the study, and in the implementation phase used the Android, the Results of the study is developed Mixed International Airport Standards Framework, and designed a new Case Tool to provide automated assistance for assessment the current secure framework position, and the Recommendations of the study is continuous work in developing International Standards Framework to comply with the requirements of change in airports environment, simplify Passengers procedures.
Enhanced Data Mining Algorithm (B-knn) - (B-knn)
(Al-Neelain University, 2022-02) Hiba Mohamed sulieman saliem
Abstract The enhanced algorithm B-kNN , it is a variation of kNN algorithm equipped with notion of minimum and maximum points (MMP) and boundary subsets (BS) which is a subset for each class consisted the boundary of classes for preprocessing the training dataset to reduce the size and improve the efﬁciency of kNN. The B-kNN algorithm evaluates test element belonging to the MMP of each class. If there exists a class whose MMP include the object, the object is predicted to be of the class. If not, BS are fed into B-kNN .In some cases the size of (BS) maybe big and the MMP of classes are overlapping which is made it useless and erodes the efficiency of B-kNN algorithm. To address this, we present the EB-kNN algorithm built upon the notion of readjusting boundary of classes to avoid the element that fall out of range in prediction phase and eliminate the overlap of classes to improve the efﬁciency of B-kNN algorithm. We conducted experiment applied EB- kNN algorithm using the iris dataset and measure its accuracy, recall, precision, and F1 score using confusion matrices to evaluate EB-kNN. We employment our algorithm using The Java programming language and the weka standard Java tool for performing both machine learning experiments and for embedding trained models in Java applications. The results of experiment show that EB-kNN improves an average of 97% in efﬁciency over B-kNN using the entire training dataset . خلاصة البحث خوارزمية B-kNN هى خوارزميه محسنه لزيادة فعالية اداء خوارزمية knn التقليديه إحدى خوارزميات المصنف التمهيدي الخاضعة للإشراف والتي تعالج مشكلات التعرف على الأنماط ، وأيضًا أفضل الخيارات لمعالجة بعض المهام المتعلقة بالتصنيف. خوارزمية B-kNN مجهزة بمفهوم الحد الأدنى والحد الأقصى للنقاط (MMP) والمجموعات الفرعية للحدود (BS) وهي عباره عن مجموعة فرعية لكل فئة تحتوي على واحده من حدود الفئات (MMP) لمجموعة بيانات التدريب وذلك لتقليل حجمها وتحسين كفاءة kNN . حيث تقوم خوارزمية B-kNN بتقييم عنصر الاختبار الذي نريد ان نحدد انه ينتمي الى اي مدى MMP من الفئات وفي حالة وجود فئة تشتمل على قيم الكائن فانه ينتمي لهذه الفئه ، وإذا وقعت قيم الكائن خارج جميع مدى الفئات يتم اللجؤ الى المجموعه الفرعية للحدود (BS) وقياس المسافه بين جميع قيم كائنات هذه المجموعه و كائن الاختبار لتحديد اقصر مسافه لتكون هى فئة كائن الاختبار. ولكن في بعض الحالات ، قد يكون حجم (BS) كبيرًا ومن المتوقع ايضاً تتداخل MMP للفئات مما يجعلها ذات فائدة اقل ويؤدي إلى تقليل كفاءة خوارزمية B-kNN. لمعالجة هذا الأمر ، قدمنا خوارزمية EB-kNN المبنية على فكرة إعادة ضبط حدود الفئات لتجنب العنصر الذي يقع خارج النطاق في مرحلة التنبؤ وايضاً تفادي تداخل الفئات مما يودي من التحسين في كفاءة خوارزمية B-kNN. أجرينا تجربة عمليه تم تطبيق خوارزمية EB- kNN باستخدام مجموعة البيانات iris dataset حيث قمنا بقياس دقتها , واسترجاعها , ودقتها , ودرجة F1 باستخدام مصفوفات الارتباك confusion matrices وذلك لتقييم اداء الخوارزميه . وتم التنفيذ باستخدام لغة البرمجة Java وأداة Java القياسية Weka وذلك لإجراء تجارب التعلم الآلي ولتضمين النماذج المدربة في تطبيقات Java. وقد اظهرت نتائج التجربة أن EB-kNN تحسنت بمتوسط 97٪ في الكفاءة على B-kNN باستخدام مجموعة بيانات التدريب بأكملها.