SCIENCE AND INNOVATIVE DEVELOPMENT

FACIAL EMOTION DETECTION USING PRE-TRAINED ADVANCED CONVOLUTIONAL NEURAL NETWORKS AND THE IMPROVED FER-2013 DATASET

Kurbanov Abdurakhmon Alishboevich — 2025-04-14

Emotion recognition from human facial images is one of the important
directions for human-computer interaction, security systems, mental health monitoring, and intelligent systems. Especially in the development of humanoid robots in the field of human-computer interaction, one of the important features of a humanoid robot is that the robot can communicate with humans while sensing their emotions. The development of emotion recognition systems is a significant challenge in computer vision and deep learning. In this study, we suggest a good way to recognize emotions from people's facial images by using well-known convolutional neural networks that have been trained on a better version of the FER-2013 dataset. In this study, the effectiveness of implementing the task of emotional state recognition using advanced convolutional neural networks is studied. In particular, the results of the popular pre-trained architectures ResNet-50, VGGNet-16, DenseNet-121, and EfficientNet-B0 on facial expression recognition are analyzed. The study used an improved and augmented version of the FER-2013 dataset. During data processing, imbalances between facial expressions, low-quality images, and incorrectly labeled images were detected and corrected. In addition, data augmentation techniques were used to reduce the problem of overfitting. The model results were evaluated based on criteria such as accuracy and loss function.

NUMERICAL STUDY OF SUBSTANCE TRANSFER PROBLEMS IN POROUS MEDIA ON THE BASE OF MULTI-STEP KINETICS

Salimova Shakhnoza Lutfillo kizi — 2025-04-14

This paper presents a mathematical model based on the balance
equation of substance transport, its deposition, and re-mobilization, considering multi-stage kinetics. The model accounts for anomalous transport kinetics, as well as local accumulation and diffusion in the balance equation. Specific problems are formulated based on the model, and their numerical solutions are obtained. Computational experiments examine the influence of anomalous parameters on substance transport, leading to relevant conclusions. The relevance of this study is driven by the need to develop high-precision models for drinking and wastewater treatment, improve the efficiency of oil and gas fields, and optimize hydrodynamic processes. The study's goal is to improve mathematical models that show strange substance transport in porous media by taking into account multi-stage deposition kinetics and to come up with numerical solution methods. This study focuses on applying fractional-order balance and kinetic equations to model complex processes in porous media. The research methodology includes mathematical modeling, computational mathematics, and numerical experiments. When fractional-order equations are used, they let you look at the physicochemical properties of porous media and how uncertainties change over time in the transport of substances. The study has led to the development of new mathematical models for substance transport in porous media, which incorporate multi-stage deposition kinetics. Additionally, efficient algorithms and software tools for numerical analysis of these processes have been created. The findings have scientific and practical significance in hydrogeology, fluid and gas mechanics, environmental protection, and industrial technologies.

DEVELOPMENT OF AN INTELLIGENT CONTROL SYSTEM AND SOFTWARE FOR THE WASTEWATER TREATMENT PROCESS

Eshbobaev Jaloliddin Abdurazzaqovich — 2025-04-14

Nowadays, water scarcity is one of the most pressing global issues in the world. The application of resource-ef�icient technologies in the treatment of industri-al wastewater is of signi�icant importance. This study focuses on the intelligent con-trol of the industrial wastewater treatment process. Initially, we developed and tested a wastewater treatment device using ion-exchange resins on a mixture of industrial wastewater from the Kungrad soda plant. Based on the obtained results, an automat-ic control system was designed to regulate water hardness (H) and total dissolved solids (TDS) based on the wastewater �low rate. The Adaptive Neuro-Fuzzy Inference System (ANFIS) was implemented as the control system. The results demonstrated that the ANFIS-based control system reduces adjustment time by 25–30% and de-creases static error by 12% compared to conventional PID and fuzzy logic control methods. This led to a reduction of up to 1.3% in the energy consumption of the servo valve that regulates water �low. Additionally, to enable real-time monitoring and au-tomatic control of the process, software was developed based on the MasterSCADA 4D platform. This system provides continuous monitoring and optimization of water quality parameters (H and TDS).

DEVELOPMENT OF A DRYING PROCESS CONTROL SYSTEM BASED ON INTELLIGENT MANAGEMENT USING ARTIFICIAL NEURAL NETWORKS

Rejabov Sarvar Abdirasulovich — 2025-04-14

Solar dryers are among the environmentally friendly and energy-efficient drying systems designed for effective dehydration of agricultural products under natural conditions. These systems, by utilizing solar energy, optimize the moisture content of products and help preserve their quality. However, the efficiency of solar dryers depends on external factors such as ambient temperature, solar radiation, and airflow, making real-time control of these parameters essential. Traditional PI controllers are not sufficiently effective under such variable conditions due to their long tuning time and signiicant overshoot. In this study, a predictive control system based on artificial neural networks (ANN) was developed to enhance the performance of solar dryers and was compared with a PI-controller-based system. A mathematical model of the drying process was created in the MATLAB R2014a environment using the Simulink software package, and computer simulations were carried out for various control methods. The results showed that the system controlled by the predictive neuro-controller achieved a settling time of 160 seconds, which is 36% faster compared to the PI-controlled system (settling time of 250 seconds). Additionally, the neural control system maintained temperature stability with an accuracy of ±1.2°C, demonstrating significantly higher precision compared to the PI-controller. The results confirm that a control system based on artificial neural networks plays a crucial role in ensuring the stable operation of solar dryers, optimizing energy consumption, and improving product quality. This approach enables the automation of agricultural drying technologies and ensures their environmentally sustainable implementation. The findings indicate promising prospects for the large-scale industrial application of this system.

THE EFFECT OF MICRO-NANO BUBBLES FORMED AS A RESULT OF DEPRESSURIZATION DURING THE FLOTATION PROCESS ON CHALCOPYRITE PARTICLES

Matkarimov Sokhibjon Turdalievich — 2025-04-14

This article deals with the effective beneficiation of sulfide copper ores. We used the method of creating micro- and nano-sized bubbles in the aqueous mixture. This method improves the quality of the separation of fine-grained minerals and helps to reduce the consumption of chemical reagents. In research, the effects of micro-nanobubbles and collectors (chemical reagents) formed as a result of the release of gas contained in the bottle through pressure reduction (depressurization) were studied. According to microflotation experiments, the pre-deaeration process significantly improves chalcopyrite separation. Additionally, when micro-nanobubbles form, the collector adheres to the surface of these bubbles rather than the minerals. This procedure facilitates the aggregation of small chalcopyrite particles, increasing the probability that they will stick to large bubbles during the flotation process. n top of that, the sodium diethyl dithiocarbamate collector stays strongly attached to the chalcopyrite surface even when the pressure is lowered. Thus, micro-nanobubbles have a positive effect on the flotation of small chalcopyrite particles, even if the amount of the collector is reduced. This study helps us better understand the importance of micronanobubbles in mineral beneficiation processes.

INFLUENCE OF THERMAL TREATMENT ON THE MICROSTRUCTURAL STRUCTURE AND MECHANICAL PROPERTIES OF 110G13L STEEL

Egamberdiev Ilkhom Pulatovich — 2025-04-14

Heat treatment of 110G13L steel plays a decisive role in ensuring its performance characteristics. High-manganese austenitic steel acquires the required properties only after quenching, carried out in the range of 1050–1150°C. The main purpose of heat treatment is to dissolve carbide phases, stabilize the austenitic structure, and improve mechanical properties. However, subsequent heating leads to the release of carbide compounds, which reduces the wear resistance of the steel. X-ray diffraction studies have revealed the presence of an α-phase at temperatures above 600°C, which confirms the phase transformations occurring during cooling. The effect of manganese on the microstructure of the steel was insignificant, while an increase in carbon contributes to an increase in strength properties. Casting defects, such as porosity and cracks, harm the mechanical properties of steel, especially under dynamic loads. Optimization of the chemical composition and alloying with elements such as chromium and vanadium can increase impact toughness and wear resistance. The introduction of modifiers improves the alloy structure, but industrial implementation of these methods requires additional study. Heat treatment remains a key stage in the production of products from 110G13L but does not eliminate casting defects, which requires further improvement of technological processes.

RESEARCH AND MODELING OF THE DYNAMIC BALANCE OF THE REED IN WEAVING MECHANISM

Akhunbabaev Okhunjon Abdurakhmonovich — 2025-04-14

This paper focuses on the dynamic balancing of the reed system for weaving looms to enhance the stability of the beating-up process and minimize vibrations. Special attention is given to analyzing the reed system’s oscillatory dynamics and the effect of inertial forces on weft placement accuracy. The research employs numerical modeling methods, including the second-order Lagrange equations, to describe the system’s motion. We utilized MATLAB and ANSYS software tools to verify the accuracy of the developed model and simulate the oscillatory behavior. The study results indicate that optimizing stiffness and so’nish parameters can reduce vibration amplitude by 18–22% and improve the energy efficiency of the mechanism. We also identified optimal operating parameters to prolong the equipment's service life. The findings can be applied in the design and modernization of weaving looms to enhance their operational performance.

CALIBRATION OF SOUND LEVEL METERS ACCORDING TO REQUIREMENT OF THE INTERNATIONAL STANDARD IEC 61672-3:2013

Mukhammad Aminov Akhmadbek Dilshodbek ugli — 2025-04-14

This article thoroughly studies the process of calibrating sound level
meters based on the requirements of the international standard IEC 61672-3:2013 and its significance. Accurate measurement of sound pressure level plays an important role in environmental monitoring, industrial noise control, healthcare, and occupational safety. The main goal of the research is to analyze the calibration process in accordance with the standard requirements for acoustic parameters of sound pressure level measuring instruments. The article details the theoretical foundations of the calibration of sound level meters, measurement methods, and calculation formulas. We also present the components that comprise the measurement uncertainty, which include the acoustic multifunctional calibrator, sound level meter, and its microphone. We looked at the measurement uncertainty using a visual analysis method and figured out the percentage of each uncertainty component compared to the total sum. The study used the “MK 265” microphone model from “Ассистент” with the factory number 450924, and based on the results, it looked at which parts of the uncertainty had the biggest and smallest impact on the measurement uncertainty, and suggestions were made to reduce uncertainty and improve measurement methods.

ASSESSMENT OF THE IMPACT OF ADVERSE WEATHER CONDITIONS ON CITY BUS OPERATIONS

Yuldoshev Davron Furqat ugli — 2025-04-14

Today, in large cities with developed transport systems around the world,
the leading issues are to determine the economic and social efficiency of scheduled buses, to effectively organize public transport traffic, and to fully satisfy their urgent demand for reliable transport services in any conditions. Researchers have interpreted the impact of the environment and its organizers on the movement of urban public transport differently. As a result of the analysis of environmental criteria by world researchers, it was found that the level of influence of weather conditions is an important indicator, and for the city of Tashkent, an analysis was carried out of the main parameters of adverse weather conditions on the flow of passengers and the operational speed of rolling stock and its severity. To ensure the regularity of scheduled bus traffic in adverse weather conditions, the laws of correlation with weather parameters affecting it were determined, and recommendations were made in the conclusions on the development of a schedule for scheduled buses.

INTER-LABORATORY COMPARISON OF CALIBRATION RESULTS FOR OSCILLOSCOPE

Gherlih Andrei — 2025-04-14

Results of inter-laboratory comparison show the competency of calibration laboratories and assure the quality of measurements and calibrations performed by laboratories. In addition, inter-laboratory comparisons prove that laboratories have implemented a management system based on the requirements of ISO/IEC 17025 and that the calibration procedures used have been validated. This research work also aimed to ensure the validity of results in the field of calibration of the oscilloscope between the National Institute of Metrology, Republic of Moldova, and Uzbek National Institute of Metrology. Inter-laboratory comparison was carried out during 2022 and 2023 years according to the ISO/IEC 17043 and reached positive results.