OJS Tashkent State University of Economics
Not a member yet
554 research outputs found
Sort by
PREDICTION THE YIELD OF GRAIN CROPS USING BASIC MACHINE LEARNING ALGORITHMS
No full textThis article presents the development of an AI model and a software tool designed to predict the yield of grain crops using Machine Learning (ML) algorithms and a dataset from kaggle.com. The research focuses on analyzing a variety of environmental, climatic, and agricultural factors that influence crop productivity. By leveraging regression techniques, the model aims to provide accurate yield forecasts based on historical data and real-time inputs. The software tool developed offers a user-friendly interface for farmers and agricultural professionals, enabling them to make informed decisions regarding resource management, crop selection, and harvest planning. The model effectiveness is evaluated through empirical testing such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Squared Error (MSE) highlighting its potential for improving agricultural efficiency and food security
NEYRON KRIPTOGRAFIYASI VA TREE PARITY MACHINE MODELI
No full textUshbu maqolada neyron kriptografiyasi Tree Parity Machine (TPM) modeli asosida tadqiq etiladi. Ikkita neyron tarmoqning sinxronizatsiya orqali xavfsiz kalit yaratish usullari o‘rganilib, TPM o‘qitish qoidalari va xavfsizlikni ta’minlash uchun asosiy hujum turlari ko‘rib chiqilgan. Shuningdek, maqolada Hebbian, anti-Hebbian va tasodifiy yurish o‘rganish usullari hamda TPM yordamida xavfsiz kalit generatsiyasining usullari tahlil qilinadi
ANALYSIS OF METHODS FOR SOLVING DATA STRUCTURE PROBLEMS IN THE TRANSITION FROM MONOLITH ARCHITECTURE TO MICROSERVICE ARCHITECTURE
No full textThe transition from monolith architecture to microservice architecture presents a significant challenge for organizations seeking to modernize their software systems. As monolithic structures often contain tightly coupled components, breaking them down into independent microservices requires careful planning, especially regarding data management. This fundamental shift not only involves a re-evaluation of how data is stored and accessed but also compels teams to adopt new methods for solving data structure problems that arise during the transition. By integrating appropriate strategies for data extraction, transformation, and loading (ETL), and leveraging techniques such as data partitioning and replication, organizations can effectively manage the complexities of distributed systems. These methods do not merely facilitate migration; they also empower teams to harness the full potential of microservices, ensuring scalability, resilience, and improved performance in today’s fast-paced digital landscape. Thus, understanding and implementing these techniques is crucial for a successful transition
KO‘PRIK KONSTRUKSIYALARIDA DEFORMATSIYALANISH JARAYONLARINI TAHLIL QILISH UCHUN FRAKTAL ALGORITMLAR
No full textUshbu maqolada ko‘prik tuzilmalaridagi deformatsiyalanish jarayonlarini tahlil qilish uchun fraktal algoritmlarni qo‘llash imkoniyatlari o‘rganilgan. Ko‘prik konstruktsiyalari tabiatan murakkab bo‘lib, ularning deformatsion jarayonlari ko‘p o‘lchovli va noaniq xususiyatlarga ega. Fraktal geometriya va unga asoslangan algoritmlar bu jarayonlarni aniqlash, modellashtirish va baholashda samarali vosita sifatida qaraladi. Maqolada fraktal algoritmlarning asoslari, ular yordamida deformatsion jarayonlarni tahlil qilish usullari va adabiyotlarda olingan natijalar tahlil qilinadi. Dinamik vaqtni moslashtirish (DTW), fraktal spektral tahlil va multi-shkala fraktal modellashtirish kabi zamonaviy yondashuvlar deformatsiyalarni aniqlashda yuqori aniqlikni ta’minlashi qayd etilgan. Tadqiqotlar shuni ko‘rsatadiki, fraktal algoritmlar yordamida ko‘priklar monitoringini takomillashtirish va ular xavfsizligini oshirish imkoniyatlari mavjud. Ushbu maqola fraktal algoritmlar asosida ko‘priklar deformatsiyalarini chuqurroq tahlil qilish va kelgusida yanada samarali algoritmlarni ishlab chiqishga zamin yaratadi
YUQUMLI KASALLIKLARNI INDIVIDLARARO TARQALISHI VA JARAYONLARINING MATEMATIK MODELLARI TAHLILI
No full textMazkur maqolada yuqumli kasalliklarni individlarga o‘zaro va kasallik tashuvchilardan tarqalish omillari, tezligi, mexanizmlari uchun ishlab chiqilgan matematik modellar tahlil qilinadi. Tanlab olingan tahliliy modellarga COVID-19 epidemiyasi, tuyoqli hayvonlar uchun yuqumli bo‘lgan oyoq-og‘iz va mastit kasalliklarining tarqalishi uchun ishlab chiqilgan matematik modellar kiritilgan. Tahlillar natijada infeksiyani tarqalishi uchun umumlashtirilgan model sxemasi taklif etiladi
INFOKOMMUNIKASIYA TIZIMLARDA FOYDALANISHNI ROLLI CHEKLASH TIZIMINI QURISH MODELLARI VA USULLARI
No full textUshbu, maqola moslanuvchanlikni, ma’murga yuklamaning pasayishini ta’minlash va dinamik faoliyat muammosini hal etishga imkon beruvchi foydalanishni rolli cheklash tizimi dinamik modelining tavsifiga bag‘ishlangan. 1. Foydalanishni rolli cheklash RBAC modeli-foydalanuvchilarni bitta katalogda boshqarish, yoki bir xil huquqlarga ega bо‘lgan foydalanuvchilarning katta guruhlarini boshqarish va h. uchun, tizimlarda dinamik foydalanuvchiga foydalanish muammolarini hal qilishga mos emas. Ushbu muammolarni hal qilish uchun atributlarga asoslangan foydalanishni boshqarish usuli ABAC tanlab olindi. Atributlarga asoslangan siyosatning normativ talablarning murakkabligini kamaytirishi evaziga foydalanishni boshqarish samaradorligi oshadi. RBAC bilan ABACning qо‘shilishi foydalanishni boshqarishda ma’murlashni soddalashtirish va RBACdagi muammolarni bartaraf etish imkoniyatlarini beradi, lekin ikkala modelning qо‘shilishi ichki xavfsizlik tahdidlaridan himoyalamaydi. Ichki tahdidlardan xavfsiz sxemani yaratish uchun vakolatlar sathida vazifalarni taqsimlash–SODni amalga oshirish taklif etildi
PERSONAL DATA PROTECTION: REASONS FOR INCREASED INTEREST AND RISKS
No full textThe article explores the factors that are attracting increasing attention to the protection of personal data and identifies the risks involved. In the era of digital progress and the widespread use of personal data in various spheres of life, privacy has become an important issue. The authors of the article analyzed the reasons why personal data protection has become a priority, including the rise in cybercrime, data breaches and privacy breaches. The article also discusses the risks associated with inadequate protection of personal data, including financial loss, reputational damage and privacy breaches
PHYSICS INFORMED NEURAL NETWORK WITH MULTIDIMENSIONAL WEIGHT CONNECTIONS FOR DIFFERENTIAL EQUATIONS
No full textRecently, Physics-Informed Neural Network (PINN) models has shown as a promising approach for solving various types physical problems which include differential equations. However, from numerical point of view, PINN models have some issues related to local minima problems when solving with minimal initial conditions. In this work, we propose a new robust PINN model which employes neural network with multidimensional weight connections to solve this issue. The proposed PINN model shows advantages over classical neural network model which is not capable of extrapolation and does not rely on large datasets. We first investigate the numeral solution of differential equation with initial conditions with a classical neural network and the PINN with neural network with multidimensional weight connections. Computational experiments show the advantage of proposed PINN model over existing classical methods which does not demand a large number of data points and also some sophisticated mathematical methods that work linear computations
HARAKAT TAHLILING KINEMATIK ASOSLARI
No full textInson harakatini real vaqt rejimida tahlil qilish sport, tibbiyot, reabilitatsiya, tanib olish tizimlarini yaratish sohalarida dolzarb yo‘nalishlardan sanaladi. Maqolada inson harakatining kinematik parametrlar asosida tahlil qilishda foydalaniladigan SCC tizimi va G-Sensor qurilmalarining imkoniyatlari keltirilgan. Taqqoslash shuni ko‘rsatadiki, harakatni kinematik tahlil qilishda berilgan tizimlarning bir vaqtning o‘zida foydalanish samaradorlikni oshiradi va kinematik parametrlaning butunligi va aniqligini ta’minlaydi.
KOMPYUTER KO‘RISH VA TABIY TILNI QAYTA ISHLASHDAN FOYDALANGAN HOLDA INSON MEHNAT UNDORLIGINI BAHOLASH IMKONIYATLARI
No full textChuqur o‘qitish tez sur’atlar bilan rivojlanib bormoqda va bu kompyuter ko‘rish yordamida hayotimizning turli jabhalarida keng ko‘lamli muammolarni hal qilishga yordam bermoqda. Shunga qaramay, ish unumdorligini baholash uchun nisbatan kam sonli kompyuter ko‘rishga asoslangan usullar qo‘llanilgan. Bundan tashqari, tabiiy tilga ishlov berish bilan bog‘liq modellar rivojlanishda davom etmoqda, ammo tilni boshqa multimodal kirish parametrlari bilan birlashtiruvchi yagona modelni yaratish muammosi hali ham o‘rganilmagan va qiyinligicha qolmoqda. Boshqa tomondan, inson harakatini inson tabiiy nutqi orqali talqin etish mumkin. Keng miqyosli harakat modellari va til ma’lumotlari harakat bilan bog‘liq modellar faoliyatida model ishlashini yaxshilashi mumkin. Ushbu maqolada yuqoridagi jarayonni amalga oshirish imkoniyatlari va inson harakatini, shuningdek, mehnat unumdorligini baholashning metodologiyasi ko‘rib chiqiladi