OJS Tashkent State University of Economics
Not a member yet
554 research outputs found
Sort by
ARTIFICIAL INTELLIGENCE AND ITS CAPABILITIES
No full textArtificial 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
SEMI-STRUCTURED DECISIONS MAKING ON THE BASIS FUZZY MEASURES
No full textThe 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 integra
REVOLUTIONIZING MEDICAL IMAGING: THE ROLE OF AI AND DEEP LEARNING IN DIAGNOSIS AND TREATMENT
No full textThe 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
CISCO TARMOQ XAVFSIZLIGI: ZARURATLAR VA YECHIMLAR
No full text“ Cisco Tarmoq Xavfsizligi: Zaruratlar va Yechimlar” tarmoq xavfsizligining muhimligi va uni ta’minlash uchun zaruratlar va yechimlar haqida ma’lumot beradi. Maqola, tarmoq xavfsizligining muhimiyatiga e’tibor qaratiladi va xavfsizlik muammoatlari, ularning kelajakdagi tasirini, va ularga qarshi kurashishning muhimligi ko’rsatiladi
THE ROLE AND SIGNIFICANCE OF ARTIFICIAL SATELLITE DATA IN DESIGNING OIL AND GAS SYSTEMS.
No full textIn 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
EVALUATING THE PERFORMANCE OF CONVOLUTIONAL NEURAL NETWORKS AND HYBRID CNN-SVM MODELS FOR SYMBOL RECOGNITION IN COMPLEX DATASETS
No full textIn 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
THE MAIN COMPONENTS OF "SMART FARM" FARMS WITH ADVANCED TECHNOLOGY
No full textThis 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
THE ROLE AND APPLICATION OF ARTIFICIAL INTELLIGENCE IN IDENTIFYING THREATS TO INFORMATION SYSTEMS
No full textIn 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
FAST VOICE FILTERING IN A FEW STEPS USING VOICE CONVERSION AS A POSTPROCESSING MODULE ADAPTATION OF A SPEAKER FROM UZBEK TEXT TO SPEECH
No full textText-to-Speech (TTS) systems developed in recent years require hours of recorded speech data to generate high-fidelity human-like synthetic speech. Low resources or small amount of speech can lead to several problems in the development of TTs models, which makes it difficult to train TTS systems with limited resources. This paper proposes a new lowresource TTS method called Voice Filter that uses only one minute of the target speaker\u27s speech. It applies Voice Conversion (VC) as a post-processing module added to an already existing high-quality TTS system, which marks a conceptual change in the current TTS paradigm by recasting the multi-frame TTS problem as a VC task. In addition, it has been proposed to use a TTS system with controlled duration to create a parallel speech corpus that facilitates the VC task. The results show that Voice Filter outperforms modern multi-frame speech synthesis methods based on objective and subjective metrics using only one minute of speech from a diverse set of sounds, and at the same time with the Uzbek TTS model. remains competitive. 25 times more data
DEVELOPMENT OF INFORMATION TRANSMISSION STRUCTURE BASED ON VISIBLE COMMUNICATION
No full textThe operation of currently widespread wireless data transmission methods, such as 3G, LTE, Wi-Fi, etc., is based on the use of radio frequency channels. Furthermore, the rapid increase in the speed of information exchange on the Internet motivates scientific research in the field of information exchange. Such technologies are less common at present, but a promising alternative to Li-Fi, which is based on the energy of light. In addition to the above, Li-Fi optical wireless technology can be used without restriction in places where the use of equipment that emits extraneous radio waves that may interfere with the normal operation of critical equipment is prohibited. Such places, of course, include intensive care wards of medical institutions, aircraft cabins and some other places