OJS Tashkent State University of Economics
Not a member yet
554 research outputs found
Sort by
MODELS OF INFORMATION EXCHANGE PROCESSES IN ELECTRONIC BUSINESS SYSTEMS
No full textIn the era of digital transformation, efficient information exchange is a critical factor in the success of electronic business systems. This article explores various models of information exchange, emphasizing graph models, neural networks, and artificial intelligence (AI). The study investigates the structural and functional aspects of information flow within e-business environments, analyzing how different computational models enhance data processing, security, and decision-making. Using graph theory, we model the relationships between business entities, while neural networks optimize data-driven interactions. AI-driven approaches further refine exchange processes by enabling adaptive learning and automation. The research employs a comparative analysis of these models, supported by quantitative metrics, simulation results, and case studies. Findings demonstrate that hybrid AI-graph models significantly improve transaction efficiency and security, reducing processing time and enhancing reliability. The article contributes to the theoretical and practical development of intelligent information exchange frameworks, offering insights for businesses seeking to optimize their digital ecosystems. Future research directions include integrating blockchain and quantum computing to further enhance security and efficiency
TRANSPORT POG‘ONA PROTOKOLLARI ASOSIDA SHIFRLANGAN TRAFIKNI TASNIFLASH VA BOSHQARISH MODELI
No full textUshbu maqolada transport pog‘onasi protokollari asosida shifrlangan tarmoq trafikini tasniflash va boshqarish modeli taklif etilgan. Hozirgi kunda shifrlangan trafikning keng tarqalganligi tufayli, trafikni tasniflash va boshqarilishi masalasi dolzarb muammo bo‘lib qolmoqda. Maqolada taklif etilgan yondashuv transport pog‘onasi darajasida protokollarni tahlil qilishga asoslanadi va shifrlangan trafikni tasniflash uchun transport pog‘onasi segmentlarini ishlatadi, bu esa ilgari mavjud bo‘lgan metodlarga qaraganda samarali va tezkor yechimlar yaratadi. Ushbu dasturiy ta\u27minot yordamida ilovalar darajasidagi protokollarni aniqlashda 98-99% aniqlikka erishilgan. Ushbu model shifrlangan trafikni aniqlashda qo‘llanilishi mumkin bo‘lgan yangi yondashuvlarni taqdim etadi. Bunga qo‘shimcha ravishda, tarmoq trafigini boshqarish mexanizmlari ishlab chiqilib, foydalanuvchi interfeysi orqali oqimlarni nazorat qilish va cheklash imkoniyati yaratildi. Ushbu model tarmoq xavfsizligini ta\u27minlashda samarali vosita bo‘lib, uning amaliy qo‘llanishi tarmoq infratuzilmasining xavfsizligini yaxshilashga yordam beradi
USING CONVOLUTIONARY NEURAL NETWORK (CNN) TO DETECT CANCER FROM MRI IMAGES
No full textThis study explores the step-by-step process of using a Convolutional Neural Network (CNN) model for detecting breast cancer from MRI images. Initially, the images undergo preprocessing, including denoising and normalization to improve quality. CNNs are highly effective in image processing, with each layer identifying different features of the image. Convolutional operations extract these features, and then neural networks analyze them to determine the presence or absence of cancer. Mathematically, the CNN model evaluates images using convolutional layers, activation functions, and loss functions. Parameters are optimized through gradient descent methods. The model’s performance was evaluated using metrics like accuracy (92%), sensitivity (89%), and specificity (94%). Compared to other algorithms like Random Forest (85% accuracy) and SVM (87% accuracy), CNN outperformed them, though it required more computational time (1200 seconds vs. 800 and 950 seconds for Random Forest and SVM, respectively). This model can be applied in clinical practice, helping physicians make quick and reliable diagnoses. The combination of MRI imaging and artificial intelligence significantly improves breast cancer diagnosis and offers new opportunities for detecting other oncological diseases in the future
RESPONSIV WEB-DIZAYN YARATISH USULLARINING QIYOSIY TAHLILI
No full textUshbu maqola responsiv veb-dizayn (RWD) yaratishning asosiy usullarini qiyosiy tahlil qilishga bag‘ishlangan bo‘lib, zamonaviy veb-saytlarning turli qurilmalar va ekran o‘lchamlariga moslashuvchanligini ta’minlashda qo‘llaniladigan yondashuvlarni o‘rganadi. Maqolada moslashuvchan sxemalar (Fluid Grid Layouts), media so‘rovlar (Media Queries), moslashuvchan rasmlar (Flexible Images), CSS frameworklari (Bootstrap, Foundation), nisbiy birliklar, Progressive Enhancement va Graceful Degradation kabi usullar batafsil ko‘rib chiqiladi. Har bir usulning texnik xususiyatlari, afzalliklari, kamchiliklari va qo‘llanilish sohalari tahlil qilinadi. Ushbu tahlil veb-dasturchilar va dizaynerlar uchun eng samarali usulni tanlashda yo‘l-yo‘riq sifatida xizmat qiladi, shu bilan birga RWDning kelajakdagi rivojlanish yo‘nalishlariga xizmat qiladi
INTELLEKTUAL ALGORITMLAR ASOSIDA SHAXSNI TANIB OLISHDA NUTQ SIGNALLARINING XUSUSIYATLARI VA PARAMETRLARINI SHAKLLANTIRISH
No full textUshbu maqolada shaxsni tanib olish tizimlarida nutq signallarini qayta ishlash orqali informatsion xususiyatlarni ajratib olish va ularning asosida shaxsga oid parametrlarni shakllantirish masalalari ko‘rib chiqiladi. Tadqiqotda sun’iy intellekt texnologiyalari, xususan, mashinali o‘rganish va chuqur neyron tarmoqlar asosida ishlovchi algoritmlar qo‘llanilib, nutq signalining tembr, ton, formant chastotalar, energiya spektri kabi statistik va spektral xususiyatlari aniqlanadi. Shuningdek, Mel-chastota spektral koeffitsiyentlari (MFCC), Linear Predictive Coding (LPC) va prosodik parametrlar asosida foydalanuvchini identifikatsiyalash uchun optimal atributlar tanlash va klassifikatsiya modellarini qurish yo‘llari tahlil qilinadi. Eksperimental natijalar keltirilgan bo‘lib, ularda ishlab chiqilgan intellektual algoritmlarning aniqligi, barqarorligi va turli akustik sharoitlarga nisbatan moslashuvchanligi ko‘rsatib berilgan. Mazkur tadqiqot natijalari shaxsni tanib olish tizimlarining samaradorligini oshirishda muhim ahamiyatga ega bo‘lishi mumkin. Usullar va algoritmlar yordamida shaxsni tanib olishga qaratilgan muhim ilmiy ishlanmalar tahlil qilingan
HAS MULTIMODAL LEARNING SUCCEEDED ENOUGH TO CAPTURE CONTEXTUAL MEANING OF HUMAN-TO-HUMAN INTERACTION? A SURVEY
No full textHuman communication is inherently multimodal, involving speech, facial expressions, gestures, body language, and even contextual cues. Variability and ambiguity make more complex to understand contextual meaning of human-to-human interaction (HHI) as gestures and expressions may have different meanings across cultures and personal habits and styles influence behavior interpretation. To tackle these problems, this article systematically analyses past and current state-of-the-art researches in multimodal learning techniques for contextual understanding of HHI using audio, text, and vision data
G‘OVAK-ELASTIK MUHITDA SIRT TO‘LQININING TARQALISHINI SONLI MODELLASHTIRISH (ANIZOTROP MUHIT TA’SIRIDA)
No full textMazkur maqolada g‘ovak-elastik va anizotrop xossalarga ega bo‘lgan muhitda sirt to‘lqinlarining tarqalishini matematik va sonli modellashtirish masalasi ko‘rib chiqilgan. Biot nazariyasiga asoslangan tenglamalar tizimi asosida sirt to‘lqinlar uchun chegaraviy shartlar aniqlangan, Finite Difference Method (FDM) orqali ularning sonli yechimi berilgan. Modelda elastiklik, g‘ovaklik, suyuqlik viskozligi kabi parametrlar hisobga olingan. Kompyuter modellashtirish orqali to‘lqin tarqalishidagi dispersiya va amplituda o‘zgarishlari tahlil qilingan
SMART ENERGY MANAGEMENT SYSTEM FOR HIGH-CONSUMPTION HOUSEHOLDS USING RASPBERRY PI AND HYBRID INVERTER
No full textThis paper introduces the design and implementation of a hardware-based smart energy management system which is designed for high load residential houses with solar panels, battery storage, and hybrid inverter. Using a Raspberry Pi microcomputer the system monitors household consumption and electricity prices in real time, automatically switching from solar battery power in peak periods to grid power when tariffs are lower. The hybrid inverter makes it possible to export excess power to the grid, while also supplying emergency power in the event of grid failure. The system is made up of voltage and current sensors, relay control modules, and a backend service which gathers and retrieves peak hour tariff data. Simulation results confirm that electricity cost can be significantly decreased and the system efficiency can be advanced
ADVANTAGES OF OPEN-SOURCE HARDWARE. THE DEVELOPMENT OF SOFTWARE BASED ROUTER APPILICATIONS UNDER SINGLE-BOARDS.
No full textThese article is highlighted features and technical capabilities of devices in information communication systems with the Open-source hardware. The results of research are working on the development of test-bed software application. These article might be useful for IT professionals dealing with computer network security and hardware programmer issue
SYN FLOOD HUJUMINI ANIQLOVCHI NEYRON TARMOQ HUJUMLARINI ANIQLASH TIZIMINI QURISH TAMOYILI
No full textUshbu maqolada tarmoq hujumlari turkumiga kiruvchi SYN Flood hujumini aniqlashda belgilangan tarmoqda hujumni aniqlash tizimi (IDS)ni intellektuallashtirish asosida qurish usuli berilgan. Neyron tarmoqni modellashtirish uchun Trojan 4.0 neyron simulyatori va optimal tarmoq strukturasini tanlash uchun turli tuzilmalarga ega bo‘lgan ko‘p sonli neyron tarmoqni tahlil qilish imkonini beruvchi Intelligent Problem Solver funksiyasidan foydalanildi. Shuningdek, istiqbolli neyron tarmoq hujumlarni aniqlash tizimini sxemasi taklif qilingan