DTAI – 2024

INTEGRATING LARGE LANGUAGE MODELS WITH VISUAL DATA FOR ENHANCED HUMAN-OBJECT INTERACTION DETECTION

Abdulaziz Xo'jamqulov — 2024-09-11

In recent years, the widespread use of visionbased intelligent systems has significantly advanced image and video analysis technologies. One key research area within this field is human activity recognition. Recent studies have primarily concentrated on specific tasks such as human action recognition and human-object interaction detection, employing depth data, 3D skeleton data, image data, and spatiotemporal interest point-based methods. Most of these approaches rely on bounding-box techniques to recognize human-object interactions. However, limited research has been conducted on using language models for this purpose. In this paper, we propose a model that combines language and image data to detect human-object interactions and discuss the challenges and future directions in this domain.

PREDICTION OF EJECTION FRACTION OF LEFT VENTRICLE IN PATIENTS WITH TYPE 2 DIABETES MELLITUS ON EMPAGLIFLOZIN: A SIX-MONTH ASSESSMENT

Alisher Ikramov — 2024-09-11

Diabetes mellitus type 2 (T2DM) is a growing global health concern, often leading to cardiovascular complications, including left ventricular dysfunction. Predicting left ventricular ejection fraction (LVEF) can be crucial for early intervention and management. Empagliflozin, a sodium-glucose cotransporter 2 (SGLT2) inhibitor, has garnered attention for its efficacy in managing type 2 diabetes mellitus (T2DM) and its potential cardiovascular benefits. This study aims to identify significant predictors of LVEF in T2DM patients treated with Empagliflozin after six months of therapy. We aim to identify outcomes related to cardiac function and the predictive factors influencing LVEF changes during this treatment phase. We applied a systematic feature selection approach through generalized linear models (GLM) to build a predictive model based on a cohort of 130 patients.

ALGORITHMS FOR RECOGNITION OF HISTOLOGICAL IMAGES BASED ON THRESHOLD RULES

Nomaz Mirzaev — 2024-09-11

The article discusses various histological image recognition algorithms to improve the accuracy of pathology diagnostics. Particular attention is paid to the proposed threshold rule-based method, which demonstrates higher classification accuracy and training speed compared to popular machine learning methods such as SVM, Random Forest, and XGBoost. During the experiments, the proposed method showed high accuracy with minimal training and classification time. The results of a comparative analysis by key metrics are presented, confirming the effectiveness of the proposed approach for automating diagnostics in digital pathology.

A REVIEW FOR DIFFERENT APPROACHES OF TOMATO LEAF DISEASE DETECTION

Mirzaakbar Xudayberdiyev — 2024-09-11

In recent years, computer vision researchers are proposing different algorithms for agricultural domain. For example, they are using Machine learning and Deep learning for plant disease identification. This paper discussed some approaches for tomato leaf disease detection. And reviewed different researchers’ works by using different methods in tomato leaf disease identification. In the end of this paper, as a result, it is defined available methods such as strength and some limitations for different conditions.

APPLICATION OF THE RANDOM FOREST ALGORITHM FOR EARLY DETECTION OF LAMENESS IN DAIRY COWS

Geldibayev Begench — 2024-09-11

This study explores the application of pedometers as a tool for the early detection of lameness in dairy cattle. By continuously monitoring cattle activity through pedometer data, including step count, distance traveled, and other physical activity parameters, we aim to develop a machine learning-based system capable of identifying early signs of lameness. The research highlights the advantages of using pedometers attached to the legs of cattle, which offer more accurate data collection compared to other wearable devices.

Comparison of machine learning methods in bad loan predictions: analysis of micro finance data

Olmas Isakov — 2024-09-11

Credit risk management is crucial for lending institutions to safeguard themselves against financial losses and maintain financial stability. Machine learning methods have been useful in analyzing borrower data and identifying bad loans that would be almost impossible for humans to detect. Client data from Microfinance Institution (MFI) in Uzbekistan have been used to build machine learning methods to predict loan delinquency. Their performances were evaluated based on five metrics: accuracy, sensitivity, specificity, negative (npv) and positive predictive value (ppv). The findings suggest that none of the machine learning used in the study methods have absolute advantage over the rest in all five-performance metrics. However, Extreme Gradient Boosting (XGBoost) produced the highest average performance compared to other methods.

DATA INTEGRATION IN A MULTI-TYPE DATA ENVIRONMENT

Elyor Egamberdiyev — 2024-09-11

The digital revolution in numerous fields of life has caused the rapid increase of multi data-types, therefore more demand for a suitable and efficient data integration. In multi-type data environment this paper presents a systematic way of data integration using the APMDE (Ability prediction in a multitype data environment) software tool. Built to process numerical, categorical as well as time series data, this tool combines advanced models including ANFIS (Adaptive Neuro-Fuzzy Inference System) and genetic algorithms for potent predictive performance. We describe how data integration is performed, its issues and difficulties, as well the algorithmic basis behind the impact a system can accomplish with examples of how to solve different tasks mathematically reducing them into several steps and providing formulas or algorithms.

OPTIMIZATION OF FUZZY INFERENCE SYSTEMS WITH GENETIC ALGORITHMS

Bakhodir Muminov — 2024-09-11

This paper explores the optimization of Fuzzy Inference Systems (FIS) using Genetic Algorithms (GAs) to enhance accuracy, efficiency, and decision-making processes. FIS, widely used for handling uncertain and imprecise data, can benefit significantly from the adaptive capabilities of GAs, which mimic natural selection to search for optimal solutions in complex, multi-modal problem spaces. The integration of GAs with FIS allows for the systematic fine-tuning of parameters such as membership functions, rule bases, and fuzzy operators, leading to improved system performance. This study demonstrates that GA-optimized FIS not only achieve greater accuracy but also offer robust and reliable models for real- world applications across fields such as engineering, medicine, and finance. The paper highlights key optimization techniques, including selection, crossover, and mutation, and compares GA-optimized systems with traditional methods, showcasing the superior performance of GAs in terms of accuracy, computational efficiency, and scalability. Additionally, the research suggests that future improvements can be realized through hybrid optimization approaches and the use of parallel computing techniques. These strategies promise to further enhance the capabilities of FIS, making them more efficient and adaptable to increasingly complex decision-making tasks.

EXPLAINABILITY OF THE SVM CLASSIFICATION MODEL FOR SENTIMENT ANALYSIS TASK OF UZBEK LANGUAGE

Sanatbek Matlatipov — 2024-09-11

This paper investigates the integration of local model-agnostic explanations with support vector machine models to enhance explainability in sentiment analysis for the Uzbek language. While SVM models are effective for classification tasks, they often function as black-box models with limited transparency. To address this, we used LIME, which perturbs input data and observes changes in the model's output, revealing the text features that most influence classification. This approach improves transparency and trust in AI systems. Our case study focuses on sentiment analysis in the low-resource Uzbek language, showing how LIME aids in understanding SVM model decisions.

ASSESSING MACHINE LEARNING ALGORITHMS FOR CHRONIC DISEASE PREDICTION THROUGH PERFORMANCE METRICS

feruz96 Ro`ziboyev — 2024-09-11

This research examines the efficacy of machine learning (ML) algorithms in the early detection and prediction of chronic diseases by utilizing a mix of structured and unstructured data. Chronic conditions such as diabetes and heart disease require advanced diagnostic methods due to their complex nature. Using algorithms like Support Vector Machines, Decision Trees, and Logistic Regression, this study aims to create predictive models that surpass traditional diagnostic methods. These models are rigorously tested with real-world data to ensure they are both accurate and practical for clinical use. The goal is to enhance early detection and management of chronic diseases, potentially reducing healthcare costs and improving patient outcomes. This innovative approach advances the application of artificial intelligence in healthcare, setting new standards for predictive diagnostics in chronic diseases.

EVALUATING THE PERFORMANCE OF CONVOLUTIONAL NEURAL NETWORKS AND HYBRID CNN-SVM MODELS FOR SYMBOL RECOGNITION IN COMPLEX DATASETS

Ravshan Shirinboyev — 2024-09-11

In this paper, we propose an algorithm for identifying symbols in various contexts using intelligent data analysis methods. With the increasing need for automated systems to process symbolic data from sources such as images, texts, or audio, we explore several state-of-the-art techniques, including machine learning models, pattern recognition, and feature extraction. The proposed method improves symbol identification accuracy by integrating supervised learning with advanced feature engineering. Our results show a significant enhancement in symbol recognition rates compared to traditional approaches.

TRAFFIC SIGN RECOGNITION USING DEEP LEARNING ALGORITHMS

Muhriddin Umarov — 2024-09-11

This paper explores the neural network architecture of traffic sign recognition. The YOLO model based on deep learning is used to recognize traffic signs in order to implement safety. In the study, processes such as pre-processing of images, object detection and classification are widely covered. According to the results of the study, the accuracy of traffic sign recognition was increased by 3.9% using the improved neural network model. This method is effective in different weather conditions and is important in preventing traffic accidents.

Revolutionizing Classrooms: The Role of AI in Personalized Learning and Student Engagement

Marufjon Abdusalomov — 2024-09-11

This paper explores the transformative impact of artificial intelligence (AI) on education, specifically focusing on personalized learning and student engagement. By analyzing recent advancements, practical applications, and challenges, it aims to illustrate how AI can revolutionize classroom experiences. This study employs a mixed-methods approach, including literature review, case studies, and expert interviews, to provide a comprehensive overview of AI's role in modern education.

Is Journalism School Making Journalists Obsolete?

Shahnoza Uzokova — 2024-09-11

This topic explores the evolving landscape of journalism and the role of journalism education in preparing students for the challenges of the modern media environment. It raises questions about whether traditional journalism curricula are equipping graduates with the necessary skills to thrive in the digital age. The media industry has undergone significant transformations in recent years, with the rise of digital platforms, social media, and citizen journalism. Traditional journalism education may not be keeping pace with these changes, resulting in graduates who are ill-prepared for the demands of the modern media landscape. As audiences become increasingly sophisticated and discerning, they expect journalists to provide high-quality, original content that is relevant and engaging. Traditional journalism education may not be adequately preparing students to meet these expectations, leading to a decline in the value of journalism degrees. The proliferation of digital tools has empowered individuals to become citizen journalists, sharing their own news and stories online. This trend may challenge the traditional role of professional journalists and reduce the demand for journalism graduates.

CREATION OF INTELLIGENCE SYSTEMS RELATED TO INFORMATION-LIBRARY ACTIVITIES

Odil Urinkulov — 2024-09-11

In this article, the need for adaptive learning platforms for students of higher education institutions is analyzed, the issues of creating an information model and functional structure of an adaptive learning platform that provides electronic literature, taking into account the indicators of students' mastery, are researched.

THE USE OF ARTIFICIAL INTELLIGENCE IN EDUCATION AND ITS IMPACT ON EDUCATION

shoxista Iskandarova — 2024-09-11

In this article, we will analyzes the potential advantages and disadvantages of AI in education, as well as the extent to which AI has an impact on education, improved assessment, teacher and student convenience, i.e. new learning opportunities. the introduction of teaching methods using technologies is studied. Drawing on various studies and perspectives, the article argues that while AI has its own risks and drawbacks, its benefits in education are significant. The article suggests the need for more empirical research on the impact of AI on education, and for educators to collaborate with experts in the creation of AI.

THE ROLE OF HUMAN JOURNALISTS IN AN AI-DRIVEN MEDIA LANDSCAPE

Shahnoza Uzokova — 2024-09-11

As artificial intelligence (AI) continues to advance, its impact on the journalism industry is becoming increasingly evident. AI-powered tools are being used to automate tasks such as content creation, fact-checking, and distribution. However, while AI can enhance efficiency and productivity, it cannot fully replace the unique contributions of human journalists. Human journalists bring a level of critical thinking, creativity, and empathy that AI cannot replicate. They are able to interpret complex information, identify biases, and provide context to news stories. Additionally, human journalists can develop relationships with sources and build trust with audiences, which is essential for credible and reliable journalism. However, the role of human journalists is evolving in an AI-driven media landscape. Journalists must adapt to new technologies and develop skills such as data analysis, digital storytelling, and social media engagement. They must also be mindful of the ethical implications of using AI and ensure that it is used responsibly and transparently. So, human journalists will continue to play a vital role in the media industry, even as AI becomes more sophisticated. By combining their unique skills with the capabilities of AI, journalists can produce more accurate, informative, and engaging content that serves the public interest.

THE DEVELOPMENT STRATEGY AND IMPORTANCE OF ONLINE EDUCATION SYSTEM

Bunyodbek Bekmuxammedov — 2024-09-11

This article analyzes the advantages and
challenges of traditional and online education, exploring key
aspects such as the flexibility, cost-effectiveness, and
significance of online education during the pandemic. Online
learning allows students and teachers to set individual learning
paces, expands remote teaching opportunities, and enables
effective use of time and resources. The article also discusses the
problems encountered in online education and strategies for
overcoming them, including the need to enhance digital literacy,
support teachers, and develop the infrastructure of educational
institutions.

ARTIFICIAL INTELLIGENCE AND ITS CAPABILITIES

zavqiddin9090 Temirov Zavqiddin — 2024-09-11

Artificial Intelligence (AI) is rapidly transforming our world, revolutionizing industries and impacting everyday life. AI encompasses a range of capabilities, including machine learning, natural language processing, computer vision, robotics, and expert systems. These capabilities empower AI to perform tasks that typically require human intelligence, leading to advancements in healthcare, finance, manufacturing, transportation, education, and customer service. However, AI also presents challenges, including potential job displacement, bias and fairness concerns, privacy issues, and the development of autonomous weapons systems. A collaborative approach involving researchers, policymakers, and the public is crucial to ensure that AI is developed and deployed responsibly for the benefit of society.

OPTIMIZING AN AI-DRIVEN CHATBOT THROUGH NATURAL LANGUAGE PROCESSING AND REAL-TIME FEEDBACK FOR PERSONALIZED RECOMMENDATIONS

Go'zal Absalamova — 2024-09-11

In recent years, the application of artificial intelligence (AI) in the field of recommendation systems has gained significant traction due to its ability to handle complex and non-linear data. This paper explores the optimization of an AI-driven chatbot designed to provide personalized recommendations. By leveraging Natural Language Processing (NLP) and real-time feedback mechanisms, the chatbot continuously learns and adapts to user preferences, enhancing its recommendation accuracy. The study demonstrates how integrating these technologies into the chatbot's architecture can improve user satisfaction and interaction efficiency. The results indicate a significant enhancement in the chatbot's ability to offer tailored suggestions, thereby underscoring the potential of AI-driven systems in personalized user experiences.

THE ROLE AND APPLICATION OF ARTIFICIAL INTELLIGENCE IN IDENTIFYING THREATS TO INFORMATION SYSTEMS

Obidjon Bekmirzayev — 2024-09-11

In this article, In recent years, artificial intelligence has become a necessary technology to enhance the efforts of information security professionals. From a security point of view, it is important that artificial intelligence can identify and prioritize risks, immediately detect any malware on the network, respond to incidents and detect attacks in advance, and develop algorithms to detect and block botnets in computer networks.

THE ROLE AND SIGNIFICANCE OF ARTIFICIAL SATELLITE DATA IN DESIGNING OIL AND GAS SYSTEMS.

Marhabo Shukurova — 2024-09-11

In this article, the design of oil and gas systems and the determination of new oil reserves using satellite geodata and the creation of their 3D models, as well as generalized mathematical models and numerical models of non-stationary filtration processes of inhomogeneous liquids and gases in porous media , the processes of developing effective computing algorithms and creating software products based on modern information technologies are described.

ARCHITECTURE AND PRIORITY ISSUES OF INTELLIGENT MILKING SYSTEM ON THE FARM

Khurshid Toliev — 2024-09-11

The dairy industry relies heavily on accurate milk measurement for productivity and quality control. Traditional manual methods are error-prone and labor-intensive. This paper discusses the development of smart milking systems that use advanced sensors and computational devices to measure milk parameters such as volume, flow, fat content, and pH in real time. These systems not only improve accuracy and efficiency but also enhance herd management, animal health, and farm profitability. Additionally, they aid in early disease detection and ensure milk safety. The paper explores the design, sensor selection, and integration of these systems, and proposes an intelligent milking system architecture.

CLOUD COMPUTING AND DATA STORAGE

Lazizbek Ablazov — 2024-09-11

Bulutli hisoblash - bu mahalliy serverlar yoki shaxsiy kompyuterlarda emas, balki Internet tarmog'ida joylashgan tarmoq serverlarida katta hajmdagi ma'lumotlarni saralash, saqlash va qayta ishlash uchun talab bo'yicha xizmatdir. Tarmoqdagi ilova va bulut xizmatlarini ishga tushirish orqali foydalanuvchiga virtual resurs taqdim etiladi. Ushbu hujjatni namoyish qilish uchun Hadoop va MapReduce infratuzilmasiga asoslangan dastur amalga oshirildi. Ushbu ilova turli parametrlar bo'yicha sinovdan o'tgan. Taklif etilgan usulning samaradorligi eksperimental natijalarda ko'rsatilgan. Ushbu usul boshqa zamonaviy hisoblash usullariga nisbatan sezilarli yaxshilanishni anglatadi.

ALGORITHM FOR CONSTRUCTING AND CONFIGURING PARAMETERS OF A MODEL FOR SEARCHING FOR TRACES OF ATTACKS IN AN INFORMATION SYSTEM

Obidjon Bekmirzayev — 2024-09-11

In the information system, it is not possible to constantly monitor the activity of users, that is, monitoring in real time mode is inconvenient. Therefore, it is important to form the actions of users in the system on the basis of parameters based on their role, and to create rules for searching for attack traces in the future detection of attacks, and to configure models and parameters for searching and detecting attack traces based on these rules.

MATHEMATICAL SUPPORT OF THE IMPEDANCE SPECTROSCOPY METHOD OF DETERMINING THE COMPOSITION OF UNDERGROUND RESERVE WATERS

Jamoljon Djumanov — 2024-09-11

This article is about finding an effective solution for determining the composition of groundwater. The spectral-impedance method proposed in the article allows to create devices for measuring all the main quality indicators of water [1]. The proposed method, in comparison with the currently used methods, increases the reliability of the assessment of the composition of underground water based on the measurement of the spectral impedance of the ions contained in the hydrogen indicator at the same time [2] [3] [4] [5].

USING DIFFERENTIAL EQUATIONS IN SOLVING FILTRATION PROBLEMS, SOLUTION BY EULER AND RUNGE-KUTTA METHODS AND COMPARISON WITH REAL VALUE

Marhabo Shukurova — 2024-09-11

In this article, it is known from ordinary differential equation courses, ifin a differential equationand if the equation is complex, to find the appropriate solution, it is important to use approximate methods. In this article, the concepts and examples of the approximate calculation of differential equations solved with respect to the derivative are considered and compared with the analytical solution.

IMPORTANCE OF DIGITAL TECHNOLOGIES IN MEASUREMENT OF KIDNEY FUNCTION

Nasiba Xalikova — 2024-09-11

Non‐adherence to medications is a critical challenge in the management of people with chronic kidney disease (CKD). This review explores the complexities of adherence in this population, the unique barriers and enablers of good adherence behaviours, and the role of emerging digital health technologies in bridging the gap between evidence‐based treatment plans and the real‐world standard of care.

EMPLOYMENT OF UNIVERSITY GRADUATES IN THE LABOR MARKET

Farkhad Parmankulov — 2024-09-11

The article notes that the modern labor market is characterized by the accelerated dynamics of transformational changes associated with the ongoing processes of adaptation of the economy to global challenges on a national and global scale, in the conditions of digitalization of the economy, the rapid development of new technologies, including in the interests of ensuring import substitution, the transformation process is accelerating professional competencies necessary for the implementation of the labor process,in connection with which the requirements of employers for applicants for available vacancies are constantly changing, which contributes to increased competition in the labor market, in which university graduates occupy far from leading positions, employment is becoming one of the acute problems of the modern labor market, characterized by the development of contradictory trends, on the one hand, employers report a shortage of qualified personnel, and, on the other hand, there is unemployment among university graduates who cannot find a job for several years after graduation.

POSSIBILITIES OF APPLYING INTELLIGENT TECHNOLOGIES IN PRODUCTION AUTOMATION

Khurshida Bakhrieva — 2024-09-11

This paper examines the potential for using intelligent technologies in technological processes. These technologies are widely used in electric power organizations to automate production management. The main objective of this study is to analyze the main development trends and study the Smart Grid concept, as well as determine the potential for its implementation based on the goals and needs of key stakeholders in different industries.

MODELING AND STORING DATA IN GRAPH DATABASES

Khurshida Bakhrieva — 2024-09-11

This paper presents the study of graph databases and their application in the context of social networks. It describes a data model that represents users, communities, and the relationships between them as a graph, where nodes represent objects and edges represent their relationships. The data structure in graph databases is compared to relational databases, emphasizing the freedom and flexibility to create and modify relationships between nodes without strict restrictions. A method for storing graph data structures is discussed, including the possibility of storing them in SQL tables using JSON, and the use of specialized graph DBMSs such as Neo4j. The specifics of data storage in Neo4j are highlighted, including caching for improving read/write performance and optimizing graph traversal. The paper emphasizes the Cypher query language, which is specifically used in Neo4j to work with graph data. Example queries with explanations are provided, demonstrating the capabilities of the Cypher language for working with data in graph databases. The conclusion discusses the application areas of graph databases, including fraud detection and supply chain mapping, how graph databases provide flexible options for storing information, and highlights their wide range of applications in various fields.

THE MAIN COMPONENTS OF "SMART FARM" FARMS WITH ADVANCED TECHNOLOGY

Elmurod Babajanov — 2024-09-11

This article examines the impact of smart farming technologies on livestock management, focusing on the implementation of an automated management information system. By leveraging IoT devices, sensors, and RFID systems, the system streamlines farm operations, reduces costs, and enhances product quality. Using the IDEF0 methodology, we model farm processes and design a robust communication infrastructure and databases to support real-time decisionmaking. The findings highlight significant improvements in efficiency, animal welfare, and overall productivity, demonstrating the critical role of smart technologies in the future of sustainable livestock farming.

ON APPROACH TO EVALUATE THE WORKFLOW FUNCTIONALITIES IN PROCESS-BASED INFORMATION SYSTEM DEVELOPMENT

Nargiza Usmanova — 2024-09-11

The study addresses the need for flexible, scalable systems capable of adapting to dynamic market demands. Business Process Management Systems (BPMS) are considered as the key technology for optimizing workflows through process automation, coordination, and real-time monitoring. The Semiotic Interoperability Evaluation Framework (SIEF) is introduced to assess interoperability at technical, formal, and informal levels, identifying key issues and the need for organizational standards. Process-Based Information System (PBIS) provides robust infrastructure, enhancing process management, flexibility, and overall organizational efficiency while authors present an approach to evaluate the workflow functionalities using the Design Science Research (DSR) methodology.

OFFICIAL SOCIAL RELATIONS IN UNIVERSITY GRADUATES’ ADAPTATION TO THE LABOR MARKET

Farkhod Parmankulov — 2024-09-11

The selection of students’ informal (friendly) social connections as a significant determinant influencing their adaptation to the labor market is justified by the challenges of combining the concepts of social capital and network analysis; the reasons for the insufficient efficiency of interaction between the labor market and the higher education institution in the context of a multi-level system of professional training are systematized; three categories of elements have been identified as contributing to the establishment of students’ social networks, as well as the usual structure of these networks when they are studying together. The factors that influence choosing between pursuing a master’s degree and starting a career after earning a bachelor’s degree have been recognized as components of the process of labor market adaption;

THE INFLUENCE OF INVESTMENTS ON INNOVATIVE ACTIVITIES IN ENTERPRISES ON THE PROFITABILITY OF ASSETS

Shaxodat Bahronova — 2024-09-11

The article analyzes the impact of investments in innovative activities on the profitability of the company's assets. The article examines the mechanisms of this effect, provides statistical analysis data, and develops recommendations for managing investments in innovation to increase the profitability of assets.

THE ROLE OF ARTIFICIAL INTELLIGENCE-BASED SOLUTIONS IN ANTI-MONEY LAUNDERING COMPLIANCE

Azizjon Khatamov — 2024-09-11

In this study, we will explore the role of artificial intelligence-based solutions in tackling Anti-Money Laundering efforts of commercial banks with due focus on efficiency enhancement in solving various tasks. Particular attention will be paid on the applicability of AI-based solutions in Anti-Money Laundering Compliance units of commercial banks in conditions of Uzbekistan. The study will reveal that the use of AI-based technologies in AML Compliance enhances efficiency leading to decrease of time and costs while processing customer transactions and increase overall performance of these units in commercial banks.

EXPERIENCE OF FOREIGN COUNTRIES IN APPLICATION OF AI INSTRUMENTS TO ENSURE THE ECONOMIC SECURITY OF INDUSTRIAL ENTERPRISES

Rukhsora Kholikova — 2024-09-11

The article examines the role of Artificial intelligence (AI) as an increasingly important tool for ensuring the economic security of industrial enterprises. Analyzed the level of development of AI in Uzbekistan, highlighted governmental strategy and support in this area. Furthermore, experience of foreign developed countries in using AI instruments in ensuring economic security of industrial enterprises, such as USA, China and Japan were analyzed.

DIGITAL TRANSFORMATION AND ARTIFICIAL INTELLIGENCE IN UZBEKISTAN: CHALLENGES, INNOVATIONS, AND FUTURE TRENDS

Ilmurod Kungratov — 2024-09-11

The digital transformation and integration of artificial intelligence (AI) are pivotal to the advancement of modern economies. Uzbekistan, a country in Central Asia, is making significant strides in these areas despite facing numerous challenges. This paper explores the current state of digital transformation and AI in Uzbekistan, identifies key challenges, highlights recent innovations, and discusses emerging trends. The findings suggest a growing emphasis on building digital infrastructure, fostering innovation, and creating a supportive regulatory environment, which are crucial for Uzbekistan’s economic and social development.

INTEGRATION OF AI AND BUSINESS FOR A SUSTAINABLE FUTURE

Marufjon Abdusalomov — 2024-09-11

The integration of artificial intelligence (AI) into business operations presents transformative opportunities for promoting sustainability and efficiency. This paper investigates how AI technologies can be harnessed to advance sustainable business practices. Through a detailed literature review, methodological analysis, and discussion of results, this study aims to offer a robust framework for leveraging AI in pursuit of long-term sustainability goals.

APPLICATION OF THE ALGORITHM FOR ENRICHMENT THE KNOWLEDGE GRAPH WITH NUMERICAL PREDICATES IN DECISION-MAKING SUPPORT SYSTEM

Dilmurod Khasanov — 2024-09-11

In this paper, the theoretical and practical principles of creating a knowledge graph by forming a set of rules for expert systems are studied. At the same time, the method of enriching the graph made from the predicates created according to First Order Logic by numerical predicates was studied. as the object of the research, the classification problem of selecting crops for repeated cropping was taken, among which, using the set of real data collected in agriculture, test-experimental work was carried out on the algorithm mentioned above and the results were obtained. All results were presented in table and graph form.

MAIN CHALLENGES RELATED TO ARTIFICIAL INTELLIGENCE IN THE FIELDS OF INFORMATION TECHNOLOGY

Husniya Salimova — 2024-09-11

The change of generations of computing technology is equivalent to another scientific and technological revolution. With the advent of new generations of computers, communication facilities, multiprocessor systems and the development of Internet technologies, it will be possible not only to solve fundamentally new problems in all areas of science and technology, but also to significantly expand the possibilities for their implementation. Solving previously traditional problems at a new, qualitative level, the qualitative level of solving problems, first of all, involves providing the necessary and sufficient intellectual support. Intellectualization of information and computing systems means not only the use of new-generation tools, but also the use of a new generation of mathematical, algorithmic and software tools. Information and computing systems with intellectual support are usually used to solve complex problems where logical information processing is superior to computational processing. Examples of such problems are: understanding and synthesizing texts in natural language, understanding and synthesizing speech, analyzing visual information, controlling robots, analyzing situations and making decisions.

REVOLUTIONIZING MEDICAL IMAGING: THE ROLE OF AI AND DEEP LEARNING IN DIAGNOSIS AND TREATMENT

Nazokat Sabitova — 2024-09-11

The integration of Artificial Intelligence (AI) into medical imaging has revolutionized diagnostic practices, offering the potential for enhanced accuracy, speed, and reduction of errors in clinical decision-making. This article explores the key applications of AI in medical imaging, such as image segmentation, classification, object detection, and image generation, highlighting advanced techniques like U-Net, ResNet, YOLO, and Generative Adversarial Networks (GANs). Despite its transformative potential, AI in medical imaging faces significant challenges, including data privacy concerns, the need for large annotated datasets, model interpretability, and the risk of overfitting. Furthermore, current AI models are limited by potential biases in training data and difficulties in generalizing across diverse populations and imaging modalities. Addressing these challenges is essential to ensure that AI can be effectively and ethically integrated into healthcare, ultimately improving patient outcomes and advancing the field of medical diagnostics.

COMPARATIVE ANALYSIS OF FACE RECOGNITION ALGORITHMS FOR AUTOPROCTORING: EIGENFACES, FISHERFACES, CNNS, AND YOLO

Mehriddin Saidov — 2024-09-11

Auto proctoring, leveraging automated surveillance technologies, has emerged as a solution to monitor online examinations in educational settings. However, its efficacy and ethical implications remain subject to scrutiny. This scientific article presents a thorough investigation into the effectiveness and ethical considerations surrounding auto proctoring systems. Through a review of existing literature and empirical analysis, we aim to provide insights into the benefits, limitations, and ethical challenges associated with the widespread adoption of auto proctoring in educational assessment. Our findings underscore the need for a balanced approach that ensures both academic integrity and student privacy

CREATION OF A MULTI-FUNCTIONAL DEVICE FOR REAL-TIME MONITORING IN EVALUATION OF THE BASIC CHARACTERISTICS OF WATER

Rajabov Farxat — 2024-09-11

This article is about finding an effective solution to the problems of determining the temperature, acidity PH and salinity TDS of groundwater. The spectral-impedance method proposed in the article allows for the creation of devices for measuring all the main quality indicators of water . Increasing the accuracy of remote monitoring devices using artificial intelligence.The purpose of this paper is to improve the accuracy of well water quality assessment using the IoT measurement method. For this purpose, a device in the form of a "poke" floating on the water surface with many electrodes (sensors) is lowered into the well, and the main indicators of the water are monitored using wireless radio waves. It was found that the measurement results from the multi-electrode sensor correspond to the quadratic approximation. The proposed method, in comparison with the currently used methods, increases the reliability of the estimation of the composition of groundwater based on the simultaneous measurement of the spectral impedance of the ions contained in the hydrogen indicator.

SEMI-STRUCTURED DECISIONS MAKING ON THE BASIS FUZZY MEASURES

Holida Primova — 2024-09-11

The task selection, i.e. quality assessment of alternatives analyzed objects (information - communication systems, technical - technological objects, varieties of agricultural crops, etc.) and a selection of the best alternative in many cases solved in conditions of information, procedural and functional, parametric and criteria uncertainties of various types. The article considers the fuzzy-set approach to the construction of models of description and evaluation of alternatives, as well as problem solving semi-structured decision making based on fuzzy measures and fuzzy integral

OPTIMAL SOLUTIONS FOR DETERMINING THE DISTANCE TO AN OBJECT IN AN AUTONOMOUS MOBILE DEVICE FOR PEOPLE WITH DISABILITIES

Uktir Khamdamov — 2024-09-11

This article describes an analysis of methods for measuring the distance to obstacles and objects for a device that helps people with disabilities move independently inside the house and find the necessary objects, as well as the results of the process of selecting the most optimal method for this device. The article also presents the results of an analysis of the capabilities of the methods used for this purpose.

Selection of features in the problems of personal identification by keystroke dynamics

Makhamadaziz Rasulmukhamedov — 2024-09-11

In this article examines the problem of identifying features when authenticating the identity of a user of computer systems based on keyboard handwriting. To solve this problem, a feature extraction method is proposed. The main idea of this method is to search for a set of representative features. In this case, the search for representative features is carried out in two stages. At the first stage, time and frequency features are determined. At the second stage, the following are determined: 1) a subset of strongly related features 2) a set of representative features. Experimental studies have been conducted to assess the performance of the proposed method. The results of the experimental study showed that the proposed method of feature extraction showed high accuracy in solving the problem of personal authentication by keyboard handwriting.

PARALLELISM AND SUPERPOSITION: REASONS FOR THE SUPERIORITY OF QUBIT OVER CLASSICAL BIT

Oybek Primqulov — 2024-09-11

The future of computing is greatly influenced by the revolutionary characteristics of quantum bits (qubits) and quantum superposition, which offer significant advantages over classical computing. This paper explores the superiority of qubits compared to classical bits, delving into the principles of quantum superposition and its mathematical representation. Additionally, it examines the differences between Shor's algorithm and classical algorithms. Qubits, with their ability to exist in multiple states simultaneously due to quantum superposition, dramatically enhance computational efficiency. This paper provides an in-depth analysis of the mathematical aspects of qubits, highlights the advantages of quantum computing through algorithms like Shor's, and compares quantum and classical algorithms, discussing the capabilities and limitations of quantum computing.