Ruslan Abdulkadirov

SwarmPNM combines an adaptive second-moment estimate and positive–negative gradient momentum with attraction towards the lowest-loss weights stored along a single training trajectory. The attraction is inspired by particle swarm optimization, but the method does not maintain a particle population. We specify the update, analyze the attraction locally under Hessian assumptions and obtain a conditional regret bound for an auxiliary strongly convex projected-gradient model with controlled perturbations. Experiments cover 15 analytic test functions, molecular classification with MolCLR-pretrained GIN and GCN encoders on the blood–brain barrier penetration (BBBP), beta-secretase-1 inhibitor (BACE) and human immunodeficiency virus replication-inhibition (HIV) datasets, and nuclear cross-section regression with a multilayer perceptron. SwarmPNM attains the highest mean ROC–AUC in five of six molecular dataset–encoder combinations. In the four-library nuclear comparison, it has the lowest mean absolute error and the highest coefficient of determination; a separate three-seed nuclear experiment under a different protocol favors AdamW. Repeated-run, sensitivity and ablation studies establish that the contribution of attraction depends on the task and tuning, with the learning rate having the largest observed influence in the analytic sensitivity tests. We also report the additional computational cost relative to AdamW. The auxiliary theory does not establish convergence of the complete nonconvex optimizer.

Food shortages are becoming increasingly urgent due to the growing global population. Enhancing oil crop yields, particularly sunflowers, is key to ensuring food security and the sustainable provision of vegetable fats essential for human nutrition and animal feed. However, sunflower yields are often reduced by diseases, pests, and other factors. Remote sensing technologies, such as unmanned aerial vehicle (UAV) scans and satellite monitoring, combined with machine learning algorithms, provide powerful tools for monitoring crop health, diagnosing diseases, mapping fields, and forecasting yields. These technologies enhance agricultural efficiency and reduce environmental impact, supporting sustainable development in agriculture. This systematic review aims to assess the accuracy of various machine learning technologies, including classification and segmentation algorithms, convolutional neural networks, random forests, and support vector machines. These methods are applied to monitor sunflower crop conditions, diagnose diseases, and forecast yields. It provides a comprehensive analysis of current methods and their potential for precision farming applications. The review also discusses future research directions, including the development of automated systems for crop monitoring and disease diagnostics.

In this paper, we propose an approach for finding balanced special-type sets of moduli for high-speed digital signal filtering using the residue number system and utilizing the truncated multiply-accumulate blocks. The primary focus is to conduct a thorough analysis of the computational delay associated with individual residue number system moduli sets as well as their various combinations. Our proposed approach reduces the digital filtering delay by 60.85% depending on the computational range and bit-width of residue number system moduli for 16-, 24-, 32-, and 48-bit filters. The proposed approach can significantly enhance the performance of digital devices where data processing speed is critical. Further research will explore applying these filters to tackle various challenges in both digital signal and image processing.

The rapid development of unmanned aerial vehicles (UAVs) has had a significant impact on the growth of the economic, industrial, and social welfare of society. The possibility of reaching places that are difficult and dangerous for humans to access with minimal use of third-party resources increases the efficiency and quality of maintenance of construction structures, agriculture, and exploration, which are carried out with the help of drones with a predetermined trajectory. The widespread use of UAVs has caused problems with the control of the drones’ correctness following a given route, which leads to emergencies and accidents. Therefore, UAV monitoring with video cameras is of great importance. In this paper, we propose a Yolov12 architecture with positive–negative pulse-based optimization algorithms to solve the problem of drone detection on video data. Self-attention-based mechanisms in transformer neural networks (NNs) improved the quality of drone detection on video. The developed algorithms for training NN architectures improved the accuracy of drone detection by achieving the global extremum of the loss function in fewer epochs using positive–negative pulse-based optimization algorithms. The proposed approach improved object detection accuracy by 2.8 percentage points compared to known state-of-the-art analogs.

In this paper, we propose a physics-informed neural network controller for quadcopter dynamics modeling. Physics-aware machine learning methods, such as physics-informed neural networks, consider the UAV dynamics model, solving the system of ordinary differential equations entirely, unlike proportional–integral–derivative controllers. The more accurate control action on the quadcopter reduces flight time and power consumption. We applied our fractional optimization algorithms to decreasing the solution error of quadcopter dynamics. Including advanced optimizers in the reinforcement learning model, we achieved the trajectory of UAV flight more accurately than state-of-the-art proportional–integral–derivative controllers. The advanced optimizers allowed the proposed controller to increase the quality of the building trajectory of the UAV compared to the state-of-the-art approach by 10 percentage points. Our model had less error value in spatial coordinates and Euler angles by 25–35% and 30–44%, respectively.