Plant disease and pest detection machines were originally used in agriculture and have, to some extent, replaced traditional visual identification. Plant diseases and pests are important determinants of plant productivity and quality. Plant diseases and pests can be identified using digital image processing. According to the difference in the structure of the network, this study presents research on the detection of plant diseases and pests based on three aspects of the classification network, detection network, and segmentation network in recent years, and summarizes the advantages and disadvantages of each method. A common data set is introduced and the results of existing studies are compared. This study discusses possible problems in the practical application of plant disease and pest detection based on deep learning. Conventional image processing algorithms or manual descriptive design and classifiers are often used for traditional computer vision-based plant disease and pest detection. This method usually uses various characteristics of plant diseases and pests to create an image layout and selects a useful light source and shooting angle to produce evenly lit images. The purpose of this work is to identify a group of pests and diseases of domestic and garden plants using a mobile application and display the final result on the screen of a mobile device. In this work, data from 38 different classes were used, including diseased and healthy leaf images of 13 plants from plantVillage. In the experiment, Inception v3 tends to consistently improve accuracy with an increasing number of epochs with no sign of overfitting and performance degradation. Keras with Theano backend used to teach architectures

Nonlinear single-input single-output (SISO) systems operating under parametric uncertainty often exhibit bifurcations, multistability, and deterministic chaos, which significantly limit the effectiveness of classical linear, adaptive, and switching control methods. This paper proposes a novel synthesis framework for self-organizing control systems based on catastrophe theory, specifically within the class of elliptic catastrophes. Unlike conventional approaches that stabilize a predefined system structure, the proposed method embeds the control law directly into a structurally stable catastrophe model, enabling autonomous bifurcation-driven transitions between stable equilibria. The synthesis procedure is formulated using a Lyapunov vector-function gradient–velocity method, which guarantees aperiodic robust stability under parametric uncertainty. The definiteness of the Lyapunov functions is established using Morse’s lemma, providing a rigorous stability foundation. To support practical implementation, a data-driven parameter tuning mechanism based on self-organizing maps (SOM) is integrated, allowing adaptive adjustment of controller coefficients while preserving Lyapunov stability conditions. Simulation results demonstrate suppression of chaotic regimes, smooth bifurcation-induced transitions between stable operating modes, and improved transient performance compared to benchmark adaptive control schemes. The proposed framework provides a structurally robust alternative for controlling nonlinear systems in uncertain and dynamically changing environments.

This study presents the adaptive three-expert ensemble (A3E), a reproducible framework for joint one-hour-ahead solar and wind power forecasting. A3E combines temporal, physically informed, and high-generation Extra Trees experts through a causal local-error gate and is evaluated under a strictly chronological, leakage-free protocol. After timestamp reconciliation and causal feature construction, the primary source yielded 8,700 model-ready observations: 5,775 for training, 1,463 for validation, 719 for internal testing, and 743 for a same-source December holdout. The primary scale-neutral comparison used Macro train-SD normalized root mean square error (NRMSE) on 672 common forecast origins. A3E achieved 0.1978, compared with 0.2314 for the official photovoltaic (PV)-Client 2026 comparator and 0.2340 for TimeMixer. However, validation-optimized static weights achieved 0.2017 on the complete 719-origin internal test, compared with 0.2025 for adaptive A3E; the difference was not statistically significant under dependence-aware analysis. On the independent CISO and ERCO systems, TimeMixer outperformed A3E, demonstrating source-dependent model rankings. Event evaluation used 98 CISO and 320 ERCO high-generation events. The results support the value of heterogeneous expert integration, but not a universal accuracy advantage of adaptive weighting.

Күн энергиясы таза электр энергиясын өндіруде маңызды рөл атқарады және болашақтың интеллектуалды электр желілері үшін негіз бола алады. Алайда оның құбылмалылығы мен ауа-райына тәуелділігі электр желілерінің тұрақты жұмыс істеуі мен оларды басқаруда қиындықтар туғызады. Күн энергиясының тұрақсыз генерациясының электр желілеріне әсерін азайту үшін фотоэлектрлік қондырғылардың қуатын қысқа мерзімді болжаудың нақты әдістерін жасау қажет. Мақалада терең оқыту әдістерін қолдана отырып, фотоэлектрлік электр станцияларының қуатын қысқа мерзімді болжау әдісіне, атап айтқанда күн энергиясы туралы деректерді болжау қабілетімен бағаланатын қысқа мерзімді жады бар ұзақ мерзімді желіге (LSTM) назар аударылады. LSTM желісінің өнімділігі орташа абсолютті қателік (MAE), орташа абсолютті пайыздық қателік (MAPE), орташа квадраттық қателік (RMSE) және анықтау коэффициенті (R2) бойынша көп қабатты перцептронмен (MLP) салыстырылады. Зерттеу нәтижелері мұны көрсетеді LSTM желі фотоэлектрлік станцияларды тиімдірек пайдалануға мүмкіндік беретін әртүрлі күндер үшін ең дәл болжамдарды ұсынады. Осылайша, терең оқыту мен энергия тиімділігінің үйлесімі энергетикалық тұрақтылықты және электр энергетикасы секторын цифрландыруды ілгерілету үшін айтарлықтай перспективаларға ие болып көрінеді.

This paper addresses the problem of multi-class classification of bacterial microscopic images using a rigorous experimental protocol designed to prevent information leakage and improve performance. The dataset consists of 2034 images representing 33 taxa, organized by class. Data integrity checks confirmed the absence of corrupted or unreadable files. To formalize image characteristics and ensure quality control, indirect geometric and textural features were calculated, including minimum frame size, brightness statistics (mean and standard deviation), Shannon entropy, Laplace variance, and Sobel gradient energy. Quality checks revealed a small proportion of images with extreme brightness (2.5074%), while no samples with critically low sharpness according to the selected criteria were detected. Statistical analysis of interclass differences using the Kruskal–Wallis test with multiple comparison correction demonstrated the high discriminatory power of texture features, specifically gradient energy (ε² = 0.819987) and Laplace variance (ε² = 0.709904). Feature correlations were consistent with their physical interpretation, revealing a strong positive relationship between sharpness and gradient energy. Principal component analysis confirmed a strong structural pattern, with the first two components explaining 75.5766% of the total variance. For a unified comparison, classical machine learning, transfer learning, and modern deep architectures were evaluated within a single protocol.