Masters

Permanent URI for this collection

https://repository.sdu.edu.kz/handle/123456789/1252

Browse

Now showing 1 - 20 of 132

Open Access
3D modeling of the offshore wind turbines integrated structure for Kazakhstan Region
(2017) Khassanov D.
In this thesis project examined meteorological characteristics of the field “Kashagan” located in the north Caspian Sea, the types of offshore oil and gas constructers, offshore wind turbine structure integrated for the middle depths of the Caspian shelf, and the load acting on them during operation on a shelf. Dimensional solid 3D model and 3D animation presentation of offshore wind turbine is built in the program Autodesk Maya 2012. Created the design scheme of supporting jacket for offshore wind turbine.Jacket designed for the field in the middle depths of the Caspian Sea. Carried out joint account of supporting columns and turbine structure on the static load - own weight of construction and the wind turbine weight of the structure, and the wind load by finite-elements. Also the calculations studied the stress-strain state of the structure. The finite element method are mastered and calculated by using a software package Autodesk Inventor Professional 2014. The calculation results can be used in the design of offshore wind turbine structures for oil and gas platforms.Also, the thesis presents the basic calculation of the estimated cost of construction and installation works supporting truss design and offshore wind turbine, its payback period. Sections health and the environment are considered potential risks to personnel and possible threats to the environment, and provide measures for their prevention and reduction.
Open Access
A Career Path Recommendation System For Computer Science Students
(Faculty of Engineering and Natural Science, 2024) Shaikym A.
This thesis presents the design, implementation, and evaluation of the Hybrid Career Path Recommendation System (HCPR), a sophisticated tool tailored specifically for guiding computer science students in their career decisions. The HCPR system innovatively combines Content-Based Filtering (CBF) and Collaborative Filtering (CF) methods into a hybrid model to enhance the accuracy and personalization of job recommendations. This integration addresses the inherent limitations of using either approach in isolation and leverages their combined strengths to improve recommendation quality. The system utilizes a comprehensive dataset that includes detailed user profiles from Stack Overflow and job postings from LinkedIn. The CBF component analyzes user profiles to match students with jobs that align with their skills and educational backgrounds, while the CF component predicts user preferences based on historical interaction patterns, enhancing the system’s ability to recommend jobs that users are likely to find appealing. The HCPR system’s performance is rigorously evaluated using precision, recall, F1-score, and ranking metrics such as Mean Reciprocal Rank (MRR) and Normalized Discounted Cumulative Gain (NDCG). The results demonstrate a significant improvement in recommendation accuracy and user satisfaction compared to standalone filtering approaches. The theoretical contributions of this thesis include advancements in hybrid recommendation system methodologies and a novel application of these systems to career guidance for computer science students. Practically, the HCPR system provides actionable insights that help students navigate the complex job market, potentially improving educational and career outcomes. This thesis concludes with suggestions for future research, emphasizing the potential for further refinement of the system and its adaptation to other fields beyond computer science. This work contributes to the fields of educational technology and recommender systems by demonstrating how integrated data-driven approaches can be effectively applied to personal and professional development tools.
Open Access
A thorough survey into the recognition of face emotion expression:experimental study, practical uses, and recommendations for the future
(Faculty of Engineering and Natural Science, 2024) Kuanyshbayev D.
The growth of the volume of information, as well as the expansion of the range of technically complex decision-making tasks require the systematization of existing methods and the development of new techniques and algorithms for their solution. The master’s thesis examines the possibility of using a neural network to solve the problem of recognizing human emotions. Artificial neural networks offer promising prospects for development, and software has a great advantage in using them. Moreover, each task performed has an unlimited and non-standard set of solution methods. The article considers the possibility of using a neural network to solve the problem of recognizing human emotions. The increasing volume of data, along with the breadth of technologically sophisticated issues with solving, necessitates the systematization of existing approaches and the creation of new techniques and algorithms for their resolution. The master’s thesis investigates the feasibility of utilizing a neural network to tackle the challenge of identifying human emotions. Artificial neural networks provide tremendous growth opportunities, and software can benefit greatly from their use. Furthermore, each challenge contains an infinite and non-standardized collection of solution techniques. The article discusses the feasibility of utilizing a neural network to tackle the difficulty of identifying human emotions.
Open Access
Analysis and development of system for predict psychological portrait of a person
(2020) Atanbekov A.
Text content is one of the widespread media types. A question which we are trying to find out in this study is the following: can we identify a psychological portrait or psychological type of a person by given a short text document written by that person? There are different techniques to identify personality types by given text. In this study, the model has been developed to predict the psychological type of the person based on XGBoost. This study is going to explore machine learning algorithms to predict the psychological portrait of a person based on a given text. The psychological portrait will be described by Myers-Briggs Type Indicators (MBTI) which is the most reliable and popular method. This question ‘5 motivated by essays of students at the beginning of their courses to understand their psychological portrait and how it can be met with the profession they choose. The results of this study will help HR specialists and teachers to better understand their students.
Open Access
Analysis of Creation Scientific Library System with MARC21
(2021) Abubakirova A.
Automation solutions come to centralization and internalization in every part of processes in different spheres. The reason is that the philosophy of humanity changed to “win to win”, assist each other, be a team and develop systems that give effectiveness, focus and open source. In this research work analyzed CIS Library systems and their formats, advantages and disadvantages from the development part. In the result identified 4 criterias in the development of the corresponding software in the creation of the Library System. For a more detailed analysis of problems between different formats, we used OCLC WSKey and found authority tags. Analyzed timeline of creation of basic modules of library system and influence in each other, accent was in analyzing and implementing cataloging modules with comparing desktop and web software and the additional task possibility of transferring metadata with XML files between different formats. In future work was testing and comparison of analysis.
Open Access
Analysis of data to improve system of an educational organization
(2020) Serek A.
In this thesis, there was done a set of computational experiments on the datasets of educational organizations. In the first part of the work, there were executed lots of experiments with decision tree ID3 algorithm on the educational camp dataset (”Educon”) that automatically predicts a participant’s feedback using Scikit-learn library and extrapolatory data analysis of that was done using Pandas library and Python programming language. The experimental results showed that the most optimal maximum depth (which is the number of edges starting from the root till the leaf) for the decision tree is 3 and the most optimal minimum number of splits (which is the minimum amount of samples of the dataset that are required to split an internal node of the decision tree) is 192. Based on that, there was achieved optimum results of precision, recall, and f1 score machine learning metrics that vary between 75 to 98 depending on the change of tunable variables of the ID3 algorithm. In the subsequent parts of the thesis, the information extraction system was built based on an educational camp dataset and recommendations for hackathon improvement were derived. The datasets are not open-source and were collected manually through the use of surveys.
Open Access
Analysis of effective machine learning techniques for improvement of student performance
(2023) Tolbassy B.
It is advantageous to use machine learning (ML) algorithms to assess student performance based on their prior performances and current behaviour because they can project both positive and negative outcomes at different educational levels. Learning outcomes can be improved by early performance prediction for students. The prediction of a student’s academic performance is important because it shapes changes in university academic policies, guides instructional strategies, evaluates the efficacy and efficiency of learning, provides teachers and students with pertinent feedback, and modifies learning environments. All of these elements support higher graduation rates. There is currently no clear winner among the various machine learning techniques for predicting student performance while enhancing learning outcomes. Therefore, this study is going to present the most effective machine learning techniques using and analysing open-source data from the Kaggle platform.
Open Access
Analysis of students’ behavior and progress on Learning Management System using Machine Learning
(Faculty of Engineering and Natural Science, 2024) Kalekes D.
Many students do not put in sufficient effort at the beginning of the academic year, leading to grades that are insufficient for completing courses or obtaining scholarships. This study aims to analyze and predict student performance on the Moodle platform to provide early interventions and improve academic outcomes. The analysis focused on various courses from the 2023-2024 academic year at SDU University, selected due to their high average number of students and well-established structures. The research involved collecting data on three predictive factors: the number of completed assignments, the total time spent on the course, and the number of actions on the platform. Six machine learning algorithms were applied to predict student performance: k-Nearest Neighbor, Random Forest, Decision Tree, Logistic Regression, Naive Bayes, and Support Vector Machine. The study compared the effectiveness of early prediction at 5, 10, and 15 weeks into the courses. Key findings indicate that student activities on Moodle are significantly correlated with higher academic performance. The Support Vector Machine model showed the best results in the early weeks, while the Random Forest model demonstrated stable results over longer periods. These findings highlight the potential of machine learning models to identify at-risk students early, allowing for timely support and interventions. The implications of this research are significant for educators and administrators. The ability to predict student performance early can facilitate timely interventions, helping students improve their academic results and reduce withdrawal rates. This study contributes to the growing body of knowledge in educational data analysis and learning analytics, providing a foundation for future research to refine and expand predictive capabilities in educational institutions.
Open Access
Analysis of students’ interest in programming
(2023) Saimassay G.
The proportion of women working in and studying computer science (CS) remains much lower than that of men. Young women’s perceptions of computer science as a career are highly impacted by their sense of self and identity. We believe that if young girls are introduced to software programming in a way that enables them to explore their identities early on, they will be more likely to pursue careers in CS. This research looks at the role of gender diversity and cultural stereotypes in affecting girls’ job choices outside of information technology (IT). The study attempts to explore the underlying causes of this trend by investigating gender inequalities and identifying the primary factors impacting girls’ views and attitudes about computers and ICT education. Furthermore, the research intends to establish an optimum atmosphere that fosters girls’ interest in IT and encourages women’s engagement in IT careers. The study looks at the relationship between confidence and satisfaction levels using a case study technique using before and post questionnaires. The obtained data is evaluated to identify the influence of these elements on the vision and interest of females in IT. The results help to explain gender discrepancies in job choices and provide suggestions for developing a supportive and inclusive atmosphere to enhance girls’ interest in IT. The report emphasizes the necessity of tackling cultural preconceptions and encouraging gender diversity in order to create an atmosphere that encourages girls to pursue careers in IT and promotes women’s participation in IT occupations.
Open Access
ANALYSIS OF SYSTEMS PYTHON VS. RUBY
(2013) Kopbayeva Zh.
Nowadays web development programming is very popular. Using object- oriented programming (OOP) languages in it made it fun to design overall architectures, functionality and ease of usability. As the scripting languages did not lose their popularity in this process, on their own field they also were making progress for making web development interesting for a programmer. Also scripting languages’ popularity is stable because of their compatibility and ease of use with the other languages. Considering these in this paper the comparison of basic items is made, that exist in Ruby and Python. Python itself was already popular, but coming of Ruby into the world of developers made them to begin many discussions. This work will give you basic view to make yourself a conclusion which one to choose and here it’s assumed that you already know one of the OOP languages or at least have some basic understanding of it. It won’t be just the basic interview with Python and Ruby, but from the introduction part the main concepts for language differences like dynamic versus static typing, strong and weak typing, compiled versus interpreted properties’ overview will be made. At the end developers will be able to conclude for themselves how to start and continue, while making clear reasoning. Because the work was made to do a rational overview of both Ruby and Python so that there won’t be any prejudice of a particular individual.
Open Access
ANALYSIS OF SYSTEMS PYTHON VS. RUBY
(Faculty of Engineering and Natural Science, 2013) Kopbayeva Zh.
Nowadays web development programming is very popular. Using object- oriented programming (OOP) languages in it made it fun to design overall architectures, functionality and ease of usability. As the scripting languages did not lose their popularity in this process, on their own field they also were making . progress for making web development interesting for a programmer. Also scripting languages’ popularity is stable because of their compatibility and ease of use with the other languages. Considering these in this paper the comparison of basic items is made, that exist in Ruby and Python. Python itself was already popular, but coming of Ruby into the world of developers made them to begin many discussions. This work will give you basic view to make yourself a conclusion which one to choose and here it’s assumed that you already know one of the OOP languages or at least have some basic understanding of it. It won’t be just the basic interview with Python and Ruby, but from the introduction part the main concepts for language differences like dynamic versus Static typing, strong and weak typing, compiled versus interpreted properties’ overview will be made. At the end developers will be able to conclude for themselves how to start and continue, while making clear reasoning. Because the work was made to do a rational overview of both Ruby and Python so that there won’t be any prejudice of a particular individual.
Open Access
Analyze and Development System with Multiple Biometric Identification
(2020) Dadakhanov Sh.
In the case of quick progress in technological improvement, growing shopper cheating, fraud, the threat to private knowledge is additionally increasing daily. Ways developed earlier to confirm personal info from the crimes weren't effective and safe. Statistics were introduced once it had been needed technology for more practical security of personal info. Recent ancient procedures like Personal identification number, keys, passwords, login ID may be forgotten, stolen, or lost. During a biometric identification system, the user might not get any keys or transfer any keys. In biometric authentication system, user may not remember any passwords or carry any keys. As people they recognize each other by the physical appearance and behavioral characteristics that biometric systems use physical characteristics, such as fingerprints, facial recognition, voice recognition, in order to distinguish between the actual user and scammer. In order to increase safety in 2005, biometric identification methods were developed government and business sectors, but today it has reached almost all private sectors as Banking, Finance, home security and protection, healthcare, business security and security etc. Since biometric samples and templates of a biometric system having one biometric character to detect and the user can be replaced and duplicated, the new idea of merging multiple biometric identification technologies has so-called multimodal biometric recognition systems have been introduced that use two or more biometric data characteristics of the individual that can be identified as a real user or not.
Open Access
Application for predicting the business orientation based on analysis of user desires
(2023) Anefiyayev N.
In today’s competitive business landscape, understanding customer desires and preferences is crucial for the success of any organization. Customer churn is a significant problem for companies and describes moving out of customers to competitors. Predicting such behavior in advance offers companies valuable insights, empowering them to take measures to retain their customer base and potentially d it. One key decision informed by data analysis involves identifying the development. Machine learning algorithms can data and predict business direction. This helps expand the most promising areas for business to be leveraged to analyze customer organizations, make data-driven decisions and tailor their products, services, and marketing strategies to meet customers expectations. The thesis work describes studies using their feedback, and analyzed parte for the company. To solve the problem, hms from different areas were used to how customer preferences and transactions to predict income several stages and machine learning algorithm ect for further use- Neural networks showed the best result in comparison and self business and linear regression to find out a profit. determining the direction. After that, a website and a motion of the company was visualized, and a page page where the saved model was used to predict a new partner and his income.
Open Access
Application of loT Technologies for Managing the Educational Process in University
(2019) Mamatnabiyev Zh.
Recently, applications of Internet of Things (IoT) technologies have been established in many organizations offering low-costed, low-powered, automatic systems. In addition, loT systems are secure, less time-consuming, and controlled remotely. Implementing loT technologies in managing the educational process makes huge changes by creating digital classrooms and automation systems. However, taking students’ absence report is still critical element or issues in the education sector that is more paperwork, which is time-consuming, requires much workforce aud efforts, and imposes inefficiency. Various automatic identification technologies have been developed using Radio Frequency Identification (RFID). Many research works and projects are produced to take maximum benefits of using this technology. RFID is an automatic technology and identifies tagged objects from an environment through radio waves. RFID reads data from RFID tag and sends it to server or cloud using IoT hardware platforms like microcontrollers and microprocessors. The current work proposes an automatic attendance monitoring system (AMS) using IoT technologies including RFID and hardware platforms. The objectives of the proposed system are to check attendance of students automatically with human interface, inform students about gaps in attendance, and monitoring instructors whether they come to lessons on time. Based on the results, the proposed AMS time-effective, economically available, and has not any power consumption. The system is analyzed and criticized respect to other authors' works. Future works are also discussed and identified.
Open Access
Applications of computer vision in examination proctoring
(2022) Sapargali N.
In 2019, a disease called COVID-19 hit the whole world and with the appearance of this disease, a new era of distance learning has begun. Learning has moved to apps like Google Meet, Microsoft Teams, Zoom, Webex and messengers like Whatsapp, Telegram, etc. Almost all universities and schools changed their courses to reflect what is going on in the world now. With all of this going on, their grades and scores should be going down, but many students did better than the average. This is because there has never been a way to do a well-organized test online without using different methods for each student. To solve the problem at hand, we need a system that can help us figure out how students are cheating. When it comes to online tests, the use of proctoring procedures is a big problem for the research community. This work shows us how to make a full multi-model system using computer vision so that people don’t have to be there during the inspection. We propose a system with many features that students can use during the test object identification, and estimating head posture using facial landmarks and face detection(is it the same student or another).
Open Access
AR and VR technologies in Education
(2019) Arystanbekov S.
This thesis work focuses on research on the impact of technologies, like virtual and augmented reality in the educational and professional training system. The major aims are to study and review of the quality of perception, understanding of educational information and define the role of technologies in the education process as well. We also consider the theoretical foundations of visual thinking, early researches, reaction, and problems. The history, current situation, prospects for the growth and development of virtual and augmented reality technologies in the nearest future are considered as well. For the practical part of the research were developed several mobile applications with educational materials from the general education school program and experiment was held. Experiment results were studied and examined to define if new technologies like Virtual and Augmented Reality effect on the quality of education.
Open Access
Aspect-oriented definition of emotional tonality of documents in the Kazakh language.
(2018) Chapayev D.
In our time, every person in his everyday life is facing artificial intelligence even without noticing it. We use it literally everywhere, from searching the Internet and ending with the location of a fast route from point A to point B. Over the past 10 years, developments in the field of artificial intelligence have acquired a new breath. Since many studies were made as far back as the twentieth century, they were not used in the right case because there was a lack of a large amount of data. But now in the world there is a lot of data on which it is possible to train and create the so-called weak artificial intelligence (weak AI) which performs one specific task. A good example of a weak AI is Apple Siri and Google Assistant. The task of which is to Support the conversation with a real person (Question & Answering). Along with this, in the processing of natural language there are other tasks such as the sentiment analysis of the text, machine translation and speech recognition. The sentiment analysis of the text is used in many ways to understand the end user, but applications for analyzing the mood are endless. More and more we see that it is used in monitoring social networks and VOC (voice of the customer) to track Customer feedback, survey responses, competitors, etc. However, it is also practical for use in business analytics and situations, in which the text needs analysis. In such areas as product quality development, improvement of customer service, and crisis Management. In this thesis, the work of the application, which will determine the emotional tone of the text in the Kazakh language, will be explained. As the input, we will give the text in Kazakh. and the program should accordingly give an answer in the form of Negative or positive.
Open Access
Automatic error detection and correction of Kazakh text
(2022) Tolegenova A.
The amount of complicated documents and texts has increased exponentially in recent years, necessitating a deeper understanding of machine learning technologies in order to effectively identify texts in numerous applications. Text normalization is one of the best decisions. It is the reduction of all words of the text to the original form. This paper investigates a layered strategy for fixing mistakes in Kazakh language literature downloaded from the Internet. This work is devoted to the study of automatic systems for checking the spelling of the Kazakh language using natural language processing tasks. Currently, most of these types of machines are designed for English, and few are processed for the Kazakh language. The paper discusses the methodology for evaluating automatic spelling checkers and error correction, developed by the author. A description of the selected systems is given. The main goal is to validate the use of n gram for agglutinative languages. On the basis of the study, the best system of use is distinguished, between the n gram and Symspell.
Open Access
Automatic Handwritten Digit Recognition on Images Using Machine Learning Methods
(2022) Kalken M.
With the transformation to digital information exchange, many papers, including invoices, taxes, notes and surveys, historical data, and test results, still require handwriting. In this context, handwritten digit recognition is required, which is a computer-automated method for decoding records. To achieve this purpose, machine learning mostly employs neural networks, with the convolution neural network being the most common. The primary objective of this dissertation is to develop an automatic technique for detecting handwritten digits by determining the optimal hyperparameter of a convolutional neural network and analyzing the impact of various hyperparameters on network performance. To do this, several values of each hyperparameter were chosen within a specified range using the MNIST database for training and testing. As a result, a large amount of data was collected in which a very high influence of hyperparameter selection on the performance of the neural network was determined, and a 99.2% accurate pure CNN design was achieved.
Open Access
Automatic Monitoring System of emissions
(Faculty of Engineering and Natural Science, 2024) Makhanbet B.
”Sergeks” in area of Ecology Our country is very polluted because of the incorrect ecological laws, old manufactures and irresponsible users of natural resources. And our the state has no tools to control it. Our research work will solve this problem by using informational technologies. It is very important to constantly evaluate the air quality in urban areas to warn residents to risks posed by air they breathe. However, the construction typical monitoring networks in poor countries will impractical due to their enormous cost. Nationwide Air Quality Network monitoring was created to offer air quality indicators, and this is important for citizen to be informed about the present and upcoming air quality in its current place to avoid overexposure. This network made it possible to broadcast frequently quality control and development the most important information system that helps prevent dangerous circumstances. Difficulty in collection and interpretation of time series and Direct data is fundamental disadvantage of an unusual network topology. Old mathematical simulation model Actually in this area I acted more like as a developer. We had collabration of 2 ecological companies of Kazakhstan and Russia, ”Koktem Tech” where I am tech lead of company and ”Integral” Russian biggest green tech company. Little bit about current situation of environmental permits of Kazakhstan, we are currently using model approved in 1986 named OND-86. This model does not coincide with current realities and gives incorrect sanitary protection zones for residential areas, which could lead to an environmental disaster. Our country uses at this moment computer Russian program called ”ERA” which they themselves have not used since 2013. But for out Ministry of ecology doesnt see ant problem. We will also try to solve this problem and develop new desktop or web application which will correspond to current realities.