Welcome to SDU Institutional Repository
Communities
Select a community to browse its collections.
Recent Submissions
MICROLEARNING IN COMPUTER NETWORKS
(Faculty of Engineering and Natural Science, 2012) Zhamanov A.
In nowadays we have much kind of problems in the system of higher education. Actually there are a lot of reasons. But in this thesis I will explain only one reason. Only one but in my opinion it is one of the main reasons. Students especially in our university everyday get very huge amount of information. Every student can take up to 8-9 courses in one semester. During one day student will have to go to 5 - 6 lessons. From every lesson he will have to read at least one chapter. It will take about 1 - 2 hour to read chapter and to understand it. So you can see that it will take very big amount of time for a student to understand all lessons and it will be very hard for him/her to do everything in time. But this is only one side of a coin. According to a Soviet Union system of education. Student has to read very much if he wants to learn some topic. He reads a lot of information about the things that are concerned with his topic. This is a good practice but unfortunately not now. Because now it is information age. Information is increased every day. And it is not possible to know everything. Especially this is true for information technologies sphere where new technologies are developed every day. The thing that you learned yesterday may be not needed tomorrow because it will be old and new technologies will come and you will have to relearn again. So what can we do in this situation? We can use the microlearning method which is very popular now in the world. The main principle of this method is to divide one huge complex information into many small pieces and try to make them as easy as possible. Leave only main parts, only necessary things and try to give more good examples. This makes work very easy. You can learn a small part of information in 15 minutes and then practice it. And in this way you learn step by step until you will learn everything at all. Now when you know enough about this topic you can deal with complex things related to your topic. Because you are aware of what it is about. You have so called fundament. Let me show an example. Say you want to learn what Computer Networks is. We have many books that explain you what is this Science about. But most of these books are very huge and sometimes boring books. Instead many people are making search request in Google and find good tutorials for them. For example w3schools.com. Why? Because it will take about 20-30 minutes for you to understand the main principle of Computer Networks without going into details. If you want to learn more about this topic, ] mean if you want to learn some specific or more detailed information about it, then you can read a book. And because it has exhaustive examples that can teach you a lot. Also it is very good to memorize this topic. Now I will try to explain my idea more clearly.
Real-time Sound Anomaly Detection in Industrial Environments with Deep Learning
(Faculty of Engineering and Natural Science, 2024) Zhailau M.
This research uses deep learning to explore the field of sound anomaly detection in industrial settings in response to the growing need for improved industrial efficiency and safety. Centered on taking care of the constraints of conventional techniques, the study examines the effectiveness of several deep learning architectures, such as hybrid models, recurrent neural networks (RNNs), and convolutional neural networks (CNNs), in identifying abnormal noises. With a focus on rigorous evaluation of datasets, preprocessing methods, and benchmarks, the survey offers a thorough picture of the most recent models and their uses in a variety of industrial areas. This research compares deep learning with traditional methods for sound anomaly identification and looks at performance evaluation criteria. Case studies and realworld implementations demonstrate the usefulness of the enhancements. While highlighting the need for innovative approaches to enhance the practical usefulness and robustness of deep learning-based sound anomaly detection in industrial settings, the research also points out its shortcomings and makes recommendations for future directions. This research not only contributes valuable insights into the intersection of deep learning and industrial sound analysis but also serves as a pivotal guide for researchers and practitioners seeking to navigate the complexities of deploying effective sound anomaly detection systems.
Personalized Career-Path Recommender System for STEM Students
(Faculty of Engineering and Natural Science, 2024) Zhalgassova Zh.
This dissertation introduces a Personalized Career-Path Recommender System (PCRS) designed to help high school students in Kazakhstan, particularly those interested in STEM (Science, Technology, Engineering, and Mathematics) fields. The system uses the Myers-Briggs Type Indicator (MBTI) personality types and students’ academic performance to offer personalized recommendations for university specializations. The research addresses the common challenges faced by students, such as high dropout rates and frequent changes in majors, often due to the lack of structured career guidance. To tackle these issues, the study collected a variety of data, including students’ demographics, academic records, and personal attributes, as well as detailed profiles of university majors. Advanced machine learning techniques, including content-based filtering, collaborative filtering, fuzzy logic, and hybrid approaches, were used to process this data and generate accurate recommendations. The effectiveness of the PCRS was tested with real data from students at SDU University. The results show that the system can provide relevant and personalized career guidance, significantly improving students’ decision-making processes and satisfaction with their chosen specializations. By combining MBTI personality assessments with academic performance data, this research offers a fresh approach to educational technology and career counseling. The insights and methods developed in this study can be adapted for use in other regions facing similar challenges, ultimately helping more students make informed and satisfying career choices.
Automatization of object detection with AI
(Faculty of Engineering and Natural Science, 2024) Ulykbek A.
This study performs a comprehensive analysis of the YOLO (You Only Look Once) object detection method, painstakingly evaluating its performance on a wide range of image formats. The investigation’s main focus is on critical metrics that are carefully examined across set of different images, including processing time, frames per second (FPS), and important metrics related to object detection. By means of this rigorous examination, the research reveals noteworthy variations in the algorithm’s effectiveness, illuminating its intrinsic merits and demerits under various circumstances and situations.These results provide a vital source of information for practitioners and researchers working in the field of real-time object recognition applications. They enable them to make informed decisions and create optimization plans specifically for YOLO-based systems. This study provides stakeholders with the tools and considerations needed to efficiently negotiate the complexity of real-world deployments by providing a detailed understanding of the algorithm’s performance peculiarities, thereby promoting improvements and innovation in the field of computer vision.
Road traffic sign recognition using computer vision
(Faculty of Engineering and Natural Science, 2024) Alsiyeu U.
Road traffic accidents are a major public problem in Kazakhstan, with driver inattention and ignorance of traffic signs among the leading causes. Current driver assistance systems integrated in map apps may be inaccurate and irrelevant, especially in rural areas and on highways. The solution proposed by the research includes a computer vision algorithm for accurate and robust detection and recognition of road traffic signs in real time which will be integrated into a mobile application with a notification system. The algorithm will use deep learning neural networks to detect and recognize traffic signs in real time. The algorithm will be trained on a dataset, which will be collected manually and augmented using machine learning techniques. The proposed system has the potential to improve road safety in Kazakhstan by helping drivers to be more aware of traffic signs and to reduce driver inattention.