مواقع التدريسيينجامعة الكوفة
0Publications
0Lectures
0Interests

About

-holds a Bachelor's degree in Computer Science from the College of Universities, Al-Mustansiriya - 2005.
Master's degree in Computer Science - Russia 2014. holds a PhD in Computer Science - Russia 2022.
Teaching at the College of Education for Girls - Computer Department from 2007 to the present.

Research Interests

4

Publications

8
2025

Optimizing Distance Education with Emotionally Intelligent Decision Support Systems

AuthorsMurtadha N. Rasol, Wisam K. Madhloom Aljeazna3, Salah M.M.Alghazali2
JournalInternational Journal of Computational and Experimental Science and Engineering (IJCESE)N
Date2025-06-01
Abstract

This article discusses the rapid development of emotional artificial intelligence and its significance in distance education. It highlights the necessity of considering students emotions to enhance educational quality. The analysis shows that emotions are reactions to stimuli and help the body adapt, with facial expressions being a universal method to express emotions. These expressions can be encoded using a facial movement coding system, simplifying the process of reading emotions. Additionally, the article also examines the influence of personality types on emotions and presents existing classifications of personality types. A functional model has been developed to organizing personalized distance education, integrating a decision support system within the LMS that considers students’ emotional states. furthermore, a mathematical model for managing the distance education process has been created, taking into account students’ emotional information, focusing on five primary emotions and four personality types. The article details the development of an algorithm for providing emotional support to influence students’ emotional states, which has been implemented in the decision support system for distance education. Enhancing distance education presents significant opportunities, such as a personalized learning, reduced stress, increased motivation, and efficiency all contributing to a higher quality of education.

2025

Deep Learning Models for Accurate Brain Tumor Classification from MRI Images

Authorsوسام كامل مظلوم, صلاح مهدي مدلول
Journal11th international conference on education and technology(ICET)
Date2025-11-29
2023

Software Quality Assurance Models and Application to Defect Prediction Techniques

AuthorsJammel Mona, Radhwan Hussein Abdulzhraa Al-Sagheer Salah.M.M. Alghazali
Journal(IJISAE)
Abstract

ABSTRACT The needs for hardware and software applications have emerged because of recent technological breakthroughs. Along with this advancement in technology, the need for software across a wide range of applications has dramatically increased. Any software sector, creating high-quality software and preserving its renown for users the most crucial undertaking for the expansion of the software industry. This must be accomplished, for software industries, software engineering is crucial. However, applying such standards to instill trust in the minds of consumers is not always straightforward. In general, the software development team perceives quality assurance in software development as an additional lengthy and extremely documentation-intensive operation that is of little value to the client. Consequently, this paper will demonstrate that the quality of the notion can be addressed from various perspectives depending on the individual's take and interest might be challenging to determine. In addition, we discussed some standards, models and applications of quality and assurance in software engineering by utilizing soft computing-based machine learning approaches that help to forecast, optimize, and efficiently learn the features, we intend to develop an effective method for predicting software defects.

2021

Detection of resource inquiries to databases on the basis of application of self-organizing maps and fuzzy output

Authors1) Ahmad M. Hailan Thi-Qar University, Mostafavia St, Thi-Qar, 64001, Iraq E-mail: [email protected] , 2) Konstantin A. Polshchikov,Belgorod State University, 85 Pobeda St, Belgorod, 308015, Russia , [email protected] , 2) Salah M.M. Alghazali , Kufa university,iraq [email protected]
JournalEconomics. information technology
Abstract

Abstract. Research is focused on identifying resource-intensive requests that consume an unacceptable amount of time, processor, disks and memory resources. The tools for monitoring and optimizing queries used in modern database management systems are analyzed, their shortcomings are indicated. The urgency of the development of new intelligent tools for the timely and reliable detection of resource-intensive queries to databases has been substantiated. It is concluded that the analysis of an extended set of statistical parameters is of interest to identify resource-intensive queries. The initial set of query parameters was reduced by preliminary normalization of the set of indicators using the sigmoidal function and subsequent selection of a finite number of principal components based on the Cattell criterion. The clustering of a set of queries was performed using a self-organizing Kohonen map, in order to avoid overfitting of which an algorithm for finding the recommended radius of the topological neighborhood of active neurons was developed. To differentiate

2021

Development of Intelligent Tools for Detecting Resource-intensive Database Queries

AuthorsSalah M.M. Alghazali, Konstantin Polshchykov, Ahmad M. Hailan, Lyudmila Svoykina
JournalThe Science and Information (SAI) Organization
Abstract

The detection of resource-intensive queries which consume an excessive amount of time, processor, disk, and memory resources is one of the most popular vulnerabilities of Database Management Systems (DBMS). The tools for monitoring and optimizing queries typically used in modern DBMS were analyzed, and their shortcomings were identified. Subsequently, the relevance of new intelligent tools’ development for timely and reliable detection of resource-intensive queries to databases was distinctly justified. The study concluded a set of analysis of an extended statistical parameter which indicated to be of interest for identifying resource-intensive queries. The initial set of queries’ parameters reduced by two consecutive methods. Firstly, normalizing the set of indicators using a sigmoid function. Secondly, selecting a finite number of principal components based on the Cattell test. Whereas the clustering of a set of queries performed using self-organizing Kohonen maps. Suggestions for further studies in the classification algorithm context were indicated in lights of the study’s conclusions.

2019

NEURAL NETWORK AND PROBABILISTIC METHODS FOR IMPROVING EFFICIENCY DBMS ADMINISTRATION TOOLS НЕЙРОСЕТЕВЫЕ И ВЕРОЯТНОСТНЫЕ МЕТОДЫ ПОВЫШЕНИЯ ЭФФЕКТИВНОСТИ СРЕДСТВ АДМИНИСТРИРОВАНИЯ СУБД

AuthorsА.В. Кузнецова, С.М.М. Алгазали,
JournalИзвестия ТулГУ. Технические науки. 2019. Вып. 12 УДК 004.658
Abstract

The possibility of solving the problem of searching for inefficient SQL queries in large software systems (OLTPIDW.BI, etc.) based on an extended set of parameters stored in the long-term memory of an industrial DBMS. Neural network clustering based on the self- organizing Kohonen network allows you to divide significant volumes of executable requests into groups with a different profile of the load on the system, providing an easy-to-understand visualization of query performance parameters. The subsequent use of the Bayesian classifier, based on a limited set of queries with low performance, automates the processes of evaluating the effectiveness of SQL queries. Keywords: SQL query, self-organizing neural network, clustering, statistical performance parameters, Bayesian classifier, Gaussian mixture of distributions. The growth in the volume of stored data in large distributed client systems exacerbates the problem of searching for long and resource-intensive SQL queries. The number of requests that need to be analyzed in a short time by software system support specialists and/or DBMS, exceed human capabilities. The complexity of the task increases in the case of a gradual drop in productivity without the presence of obvious signs. Searching for really inefficient requests among hundreds, thousands, and even tens of thousands of requests in the analyzed time period becomes far from a trivial task. Traditional data sources in identifying resource - intensive- The main characteristics of the query execution plan and statistical performance parameters that characterize the consumption of time resources of the processor and the I/O system are the pros. Utility tool software or self-written queries to the DBMS provide quite extensive sets of SQL queries with limiting parameters and characteristics , but not every one of these queries requires replacement or transformation. This is due to the fact that the execution of SQL queries is performed in a highly dynamic environment in which peak load, insufficient or, conversely, frequent updating of statistical parameters of data distribution, absence of the required data in the cache, etc. All this has a difficult-to-diagnose effect on query performance parameters and can be regarded as a noise component with unknown distribution parameters. One of the ways to improve the procedure for searching for inefficient SQL queries in such conditions is their preliminary clustering based on a symbiosis of self-organizing Kohonen neural networks (SOM) [1] and the restoration of the distribution density by constructing a Gaussian mixture of distributions (Gaussian Mixture Model, GMM), with subsequent evaluation of query performance based on the Bayesian classifier. Selection of clustering object parameters. In [1,2] , the characteristics of the Oracle DBMS SQL query execution plan are described and analyzed for their use as parameters of clustered objects. It is noted that the characteristics of the plan can only be a starting point to assess the true effectiveness, since they largely depend on: 1) the relevance of statistical information on the distribution of values in the indexes and database tables at the time of generating the plan; 2) settings of the DBMS optimizer component, which generates a set of execution plans and ultimately selects the plan with the lowest complexity estimate. It is shown that a more accurate vector for evaluating SQL queries is statistical data on the progress of query execution - the so-called performance statistics that the DBMS collects during query execution and stores, along with a variety of system information, in various internal structures and repositories. Among the various sources of service information storage, the best for the purpose - searching for inefficient SQL queries in the absence of obvious reasons - according to the authors, is a specialized diagnostic long-term data warehouse (Advanced Workload Repository, AWR). Performance statistics for a single query in AWR are stored in two representations : in total since the start of the DB instance (DataBase Instance) and in the form of changes for a certain time interval. Analysis of the first type of data showed that they are not suitable for solving the problem of preliminary grouping of SQL queries due to resetting when restarting the instance DB and in a number of other cases. The second type of data represents the difference between the aggregate statistics at the beginning and end of a given period and is more suitable for the analysis of productivity.

2014

Biorthogonal approach to image scaling (биортогональный подход к масштабированию изображений )

AuthorsSalah MahdiMadlol Alghazali
Journal Курский государственный университет
Abstract

Biorthogonal approach to image scaling (биортогональный подход к масштабированию изображений )

2014

SCALING IMAGE-SPM WITH WAVELET-INTERPOLATION (МАСШТАБИРОВАНИЕ ИЗОБРАЖЕНИЙ-СЗМ (Сканирующая Зондовая Микроскопия) С ИСПОЛЬЗОВАНИЕМ WAVELET-ИНТЕРПОЛЯЦИИ)

AuthorsSalah M M Alghazali
JournalКурский государственный университет
Abstract

В статье раскрываются вопросы обработки и редактирования изображений-СЗМ с помощью универсальной wavelet-технологии увеличения и оптимизации цифровых снимков в режиме реального времени.

Lectures

6
View details