Vol 33, No 4 (2025)

BibTeX is used to prepare bibliographic information for our journals. This article describes the basic structure of BibTeX files.

The digitalization of crop production has placed leaf-image-based disease recognition among the top research priorities. This paper presents a compact and reproducible system designed for rapid deployment in cloud environments and subsequent adaptation. The proposed approach combines multitask learning (simultaneous prediction of plant species and disease), physiologically motivated channel processing, and error-tolerant data preparation procedures. Experiments were conducted on the New Plant Diseases Dataset (Augmented). To accelerate training, six of the most represented classes were selected, with up to 120 images per class. Images were resized to 192×192 and augmented with geometric and color transformations as well as soft synthetic lesion patches. The ExG greenness index was embedded into the green channel of the input image. The architecture was based on EfficientNet-B0; the proposed HiP²-Net model included two classification heads for disease and species. Training was carried out in two short stages, with partial unfreezing of the base network’s tail in the second stage. Evaluation employed standard metrics, confusion matrices, test-time augmentation, and integrated gradients maps for explainability. On the constructed subset, the multitask HiP²-Net consistently outperformed the frozen baseline model in accuracy and aggregate metrics. Synthetic lesions reduced background sensitivity and improved detection of mild infections, while incorporating ExG enhanced leaf tissue separation under variable lighting. Integrated gradient maps highlighted leaf veins and necrotic spots, strengthening trust in predictions and facilitating expert interpretation. The proposed scheme combines the practicality of cloud deployment with simple, physiology-inspired techniques. Adopting the \enquote {species + disease} setup together with ExG preprocessing and soft synthetic lesions improves robustness to lighting, background, and geometric variations, and makes it easier to transfer models to new image collections.

In this paper, we for the first time propose the extension of optimal eighth-order methods to multidimensional case. It is shown that these extensions maintained the optimality properties of the original methods. The computational efficiency of the proposed methods is compared with that of known methods. Numerical experiments are included to confirm the theoretical results and to demonstrate the efficiency of the methods.

{Background} The bulk of the work on dual quaternions is devoted to their application to describe helical motion. Little attention is paid to the representation of points, lines, and planes (primitives) using them. {Purpose} It is necessary to consistently present the dual quaternion theory of the representation of primitives and refine the mathematical formalism. {Method} It uses the algebra of dual numbers, quaternions and dual quaternions, as well as elements of the theory of screws and sliding vectors. {Results} Formulas have been obtained and systematized that use exclusively dual quaternionic operations and notation to solve standard problems of three-dimensional geometry. {Conclusions} Dual quaternions can serve as a full-fledged formalism for the algebraic representation of a three-dimensional projective space.

The problem of finding the lowest-energy state in the Ising model with a longitudinal magnetic field is studied for two- and three-dimensional lattices of various sizes using the Quantum Approximate Optimization Algorithm (QAOA). The basis states of the quantum computer register correspond to spin configurations on a spatial lattice, and the Hamiltonian of the model is implemented using a sequence of quantum gates. The average energy value is efficiently measured using the Hadamard test. We simulate the QAOA operation on increasingly complex lattice configurations using the software libraries \texttt {Cirq} and \texttt {qsim}. The results of optimization, obtained using gradient-based and gradient-free methods, demonstrate the superiority of the latter in both modeling performance and quantum computer usage. Key arguments in favor of the advantages of quantum computation for this problem are presented.