Researched and developed mechanisms for optimizing the identification of random time series based on mechanisms for searching for unknown knowledge, hidden properties, patterns, relationships, features of non-stationary objects under the condition of limited a priori information, uncertainty, non-stationary processes. A generalized model for optimizing the identification of RTS based on the use of neural networks, neuro-fuzzy networks of dynamic models, as well as fuzzy logic algorithms is implemented. Instruments for data reliability control are obtained based on statistical, dynamic, intelligent approaches suitable for the conditions of transmission of incomplete, heterogeneous, partially given information with large parametric uncertainty. The principles and methods of data reliability control in a fuzzy environment are developed based on the generalization and use of the properties of neural networks, fuzzy logic and statistical modeling methods. Algorithms for searching for correlations, trends, interrelations and regularities in data, forming training, control and test sets for solving problems of recognition, classifying images of micro-objects and predicting power supply indicators are synthesized. The results of the research are implemented in the form of a software package for identifying non-stationary objects, which ensures the adaptability of model variables, high data processing performance and accuracy of results.

Methods and algorithms have been developed for identifying non-stationary objects of various types using statistical, dynamic, neural network models, which are taken into account when solving problems of conditions of a priori insufficiency, uncertainty, low reliability of data. Mechanisms are proposed that provide effective identification based on combining the features of dynamic models with the properties of random time series. The possibilities of algorithms based on mechanisms that use statistical, dynamic, specific data characteristics, as well as the properties of self-adaptation, approximation, organization, self-learning of neural networks have been expanded. A generalized function identification algorithm has been developed and its functions have been expanded by adaptive segmentation of time series, setting the informative interval of element values, the size of the training set, training multilayer neural networks, database, and knowledge base. The training algorithms for a three-layer neural network are modified based on the mechanisms for regulating interneuronal connections in layers, weight coefficients of neurons, variable activation functions, network architecture, and superposition of continuous input-output dependencies. A software package for identifying random time series in the C++ language in the CUDA parallel computing environment has been developed to predict the annual power consumption of the industrial zone of the Samarkand region using software tools for data preprocessing, filtering, smoothing; determining the boundaries of the informative interval of time series elements.

Automatic classification of pollen grains in microscopic images supports melissopalynology and honey quality control but is complicated by class imbalance and morphologically similar classes. We evaluated factors affecting classification on the Cretan Pollen Dataset v1 (CPD-1; 20 classes, 4025 images) with YOLOv8s-cls, YOLO11s-cls, YOLO26s-cls, EfficientNet-B3 and a reproduced RCANet. Each configuration was trained with five seeds; hyperparameters and ensembles were selected on validation data only. Augmentation improved the macro F1-score by about 1.2 percentage points; a size-matched unbalanced control showed that this gain came from the larger training set, not from class balancing. The most difficult class, Ceratonia, was misclassified mainly as Vitis and Olea; its F1-score fell from 0.878 to 0.778 when its original training images were reduced from 26 to 10. Focal Loss and Squeeze-and-Excitation blocks did not improve Ceratonia reproducibly (changes in its F1-score from −0.03 to +0.03, not significant after Holm correction), and the YOLO architectures could not be ranked reliably. An ensemble of EfficientNet-B3 and YOLO models selected on validation data outperformed the best single model in all seeds (macro F1-score 0.9720 vs. 0.9631). Several single-run effects were not reproduced with multiple seeds, underlining the need for multi-seed evaluation and validation-only selection.