11 results
Search Results
Now showing 1 - 10 of 11
Item Open Access SMM (SUPPORT MEDICAL MACHINE)(СДУ хабаршысы - 2020, 2020) Askarova A. ; Gylymmedden Y. ; Temirbekova D.; Sultanova N.Abstract. Machine learning (ML) provides methods, techniques, and tools that can help solve diagnostic and prognostic problems in various fields of medicine. ML is used to analyze clinical parameters and their combinations for prognosis, such as disease progression, for maintenance therapy of treatment, and for General patient management. In our time, computer systems have already begun to be introduced into the healthcare environment, which makes it possible to facilitate and improve the efficiency of medical professionals and ultimately improve the efficiency and quality of medical care. Below is a demonstration to tell what the main applications of ML were used in the application and show how they can be useful for medical care. The main task was to combine all the useful functions that can help people in the field of medicine. The application will help to determine the authenticity of medicines through text recognition and search through the database of official drug registers, as well as using recommendation systems and algorithms (K-nearest neighbor Algorithm) to help in the selection of medicines, using the camera and phone flash to calculate the heart rate, which will accordingly help people with blood pressure problems. The application will be available on two platforms on 10S, as well as for the Android operating system, as it was implemented through the Flutter framework in Android Studio. For the algorithms, used Google's ML-Kit libraries. Jupyter, numpy, pandas, matplotlib, scipy, and scikit-learn Notepad are also used for data preparation.Item Open Access MULTIVARIATE REGRESSION ANALYSIS AND MODELLING ON CARS DATASET(СДУ хабаршысы - 2019, 2019) Rayev Zh. ; Aipenova A. ; Suleizhan T. ; Zhumabek D. ; Duman A.Abstract. The results of the work are based on the construction of a mathematical model for determining unknown parameters using multivariate regression analysis. Structured data are given for the derivation and elimination of significant factors and coefficients. Also, machine learning simple regression models are used for modelling. The results have been evaluated and shown for comparative purposes.Item Open Access IMPROVING INDICATORS OF DIGITAL MARKETING USING ARTIFICIAL INTELLIGENCE(СДУ хабаршысы - 2020, 2020) Kaiyp K. ; Alimanova M.Abstract. In recent years, artificial intelligence (AI) has become a growing trend in various fields: medicine, education and the automotive industry. AI also reached a business, namely the marketing department of various businesses. The goal of the article is to research how deeply AI is used in digital marketing. The authors asked two research questions - which areas of AI are used in marketing and what are the positive effects of chat bots on a business. To answer these questions, the authors conducted a study of secondary data with examples of AI used for marketing purposes. An analysis of the collected examples shows that AI is widely implemented in the field of marketing, although applications are at the operational level. This may be the result of the careful implementation of the new technology, still at the level of experimentation with it. The uncertainty of the results of the implementation of AI can also affect caution when applying these innovations in practice. The collected examples proved that AI affects all aspects of the marketing structure, affecting both consumer value and the organization of marketing and business management. This document is important for the business, especially the idea of introducing artificial intelligence into marketing, developing innovation, and ideas on how to incorporate new skills into the marketing team needed for new technologyItem Open Access DESIGNING A RECOMMENDATION SYSTEM FOR SPECIALIZED COURSES FOR THE UNIVERSITY(СДУ хабаршысы - 2021, 2021) Anefiyayev N. ; Anefiyayeva D. ; Talasbek A.Abstract. Each university has compulsory subjects and there are subjects that the student must choose for themselves. This choice affects the further path of the student because he chooses not only the subject that he will study but also what he will work within the near future. I know from myself how difficult it is to choose a subject yourself. The recommendation engine is one of the most popular artificial intelligence applications, attracting many researchers from all over the world. From the moment we switched to the Internet, the recommendation system has become widely used in our daily life, even when we do not notice it. Many machine learning techniques can be used to implement a recommendation system, but in this work, we consider the KNN method for classification.Item Open Access Text Classification for AI Generated Content with Machine Learning and Deep Learning Models(5th International Conference on Smart Information Systems and Technologies (SIST), 2025) Batyr Sharimbayev; Shirali KadyrovThe rapid development of generative AI models, such as GPT-4, LLaMA, and Gemini, is causing an explosion of AI-generated text that may be akin to human writing. This poses a challenge in differentiating between AI generated content and human-authored text across a range of verticals: academic integrity, misinformation detection, and content moderation. This paper presents a comparison of machine learning and deep learning models on the classifier for AI-generated text. We compare the performance of Logistic Regression with TF-IDF features, a Bi-LSTM model, and a fine-tuned DistilBERT model on data from the COLING Workshop on MGT Detection Task 1, involving text samples from five AI models and human authors. Our experiments showed that Bi-LSTM outperforms other models, yielding the best results in accuracy (90.09%) and F1-score (90.02%). We further present the binary classification performance that distinguishes AI-generated text from human-written content, with an accuracy of 95.9%. It is suggested that deep learning methods are competent in detecting AI-generated text, though there are certain limitations, including adversarial attacks and changing styles of AI-generated writing. Future work will be focused on enhancing model robustness through adversarial training and hybrid architectures.Item Open Access Statistical inference and machine learning in big data(Faculty of Engineering and Natural Science, 2019) Temirali A.In my practice. I met with different definitions: - Big Data is when data is more than 100GB (500GB. 1TB. who likes it) - Big Data is data that cannot be processed in Excel - Big Data is data that cannot be processed on a single computer. And even such: - Big Data is generally any data. - Big Data does not exist. marketers have invented it. Thus, under Big Data I will understand not some specific amount of data or even the data itself, but their processing methods. which allow distributed information to be processed. These methods cat? be applied both to huge data arrays (such as the content of all pages on the Internet) and to small ones (such as the content of this thesis).Item Open Access EXPLORING THE IMPACT OF MACHINE LEARNING ON KYC COMPLIANCE COSTS AND CUSTOMER EXPERIENCE(СДУ хабаршысы - 2023, 2023) Sattarbek A. ; Zhumashev B.; Parmanov S.Abstract. The Know Your Customer (KYC) compliance process is a critical requirement for financial institutions to prevent money laundering, fraud, and terrorist financing. Machine learning algorithms have the potential to improve the efficiency and accuracy of KYC compliance checks. In this study, we explored the effectiveness of several classification algorithms for KYC compliance checks using a dataset with 3000 rows collected from a famous banking system in Kazakhstan. We compared the performance of four commonly used algorithms: Decision Tree, Random Forest, Logistic Regression, and Support Vector Machines. Our results showed that all four algorithms achieved high accuracy rates, with Random Forest performing the best, achieving an accuracy rate of 92.1%. These findings suggest that machine learning algorithms can effectively classify KYC checks, with Random Forest being the most effective algorithm in our study. This study provides further evidence of the potential of machine learning for KYC compliance checks in the banking industry, but also highlights the need for ongoing monitoring and validation of machine learning models and concerns about explainability and transparency.Item Open Access REALIZATION OF ALGORITHM OF SELF-GENERATING NEURAL NETWORKS(Faculty of Engineering and Natural Sciences, 2019) Abdikhaliyev Y.The development of various spheres of human activity is associated with the generation and accumulation of a huge amount of data that can contain the most important practical information. However, significant benefit from this information can be extracted only with proper processing and analysis of this data. Recently, there has been an increased interest in the field of artificial intelligence, and methods of automating the extraction of knowledge based on data mining are actively developing. Self-generating neural networks are built on the principle of biological, of course, with a number of assumptions, they have a huge number of simple processes with many connections. Like the human brain, these networks | are capable of learning. Self-generating neural networks find their application in areas such as computer vision, speech recognition, processing of natural language, etc. The thesis provides an‘analysis of the development of the theory of neural networks, their classification and mathematical formulation of the task of recognizing pattern recognition.Item Open Access USING ARTIFICIAL INTELLIGENCE TO IMPROVE DIGITAL MARKETING STRATEGIES(СДУ хабаршысы - 2020, 2020) Kaiyp K. ; Alimanova M.Abstract. The use of artificial intelligence (AI) will provide huge advantages in the digital marketing strategy of each company. This is a new face of productivity, efficiency and profitability. Making decisions about the start of a new era based on artificial intelligence should not replace the work of marketers or advertisers. It is here to unleash their true strategic and creative potential. For a business executives and marketers, the time has come to identify the problems facing the business or the marketing campaign, and how accurate ideas can solve these problems. This study discusses how AI could affect to effective of marketing strategies, shows real cases of using AI tools, and how companies could increase their profit.Item Open Access Plagiarism types and detection methods: a systematic survey of algorithms in text analysis(Frontiers in Computer Science, 2025) Makhmutova A.; Turan C.; Amirzhanov A.Plagiarism in academic and creative writing continues to be a significant challenge, driven by the exponential growth of digital content. This paper presents a systematic survey of various types of plagiarism and the detection algorithms employed in text analysis. We categorize plagiarism into distinct types, including verbatim, paraphrasing, translation, and idea-based plagiarism, discussing the nuances that make detection complex. This survey critically evaluates existing literature, contrasting traditional methods like string-matching with advanced machine learning, natural language processing, and deep learning approaches. We highlight notable works focusing on cross-language plagiarism detection, source code plagiarism, and intrinsic detection techniques, identifying their contributions and limitations. Additionally, this paper explores emerging challenges such as detecting cross-language plagiarism and AI-generated content. By synthesizing the current landscape and emphasizing recent advancements, we aim to guide future research directions and enhance the robustness of plagiarism detection systems across various domains.