Computer-Assisted Surgery (CAS) involves applying various computer-based methodologies and devices to plan, guide, and perform surgical procedures, thereby improving outcomes throughout the surgical process. This study integrates the Characteristic Product Features (CPF) methodology with Method Of anatomical Features (MAF), both developed in-house to improve CAS. It enables the creation of the human organs’ geometrical models by including different relations between Regions of Interest (RGIs) models and specific properties, like functional, materials, and topological. Enhancing existing methodologies in CAS aims to offer a more comprehensive geometrical description of human organs, leading to the development of more precise and anatomically accurate personalized geometrical models. Creating customized geometry with accurately defined features is expected to enable surgeons to prepare and execute surgical interventions better, consequently improving patient care and recovery. The demonstration of successful geometry adaptation is shown by prototyping developed models using 3D FDM printing.

The ornaments from the Serbian medieval frescoes belong to the religious decorative art with the restricted set of possible motifs, frequently related to a cross, and thus the basic motifs can fit in a very limited number of symmetry groups. The main criterion for the quality of such ornamental art could be the richness and variety of patterns obtained from a very small number of symmetry groups, proving the creativity of their authors-their ability to create variety with a very restricted number of initial symmetry groups. Here we analyze these ornaments and their symmetry group and give an introductions to further work on automated symmetry group recognition and pattern reconstruction.

CNNs have grown to form the backbone of modern computer vision systems, producing outstanding object detection and classification performance within diverse application domains. However, the manual development of suitable CNN architectures and, correspondingly, the selection of optimal hyperparameter sets are still inconvenient and time-consuming processes. The aim of this survey is to contribute a comprehensive review regarding how meta-heuristic optimization algorithms such as Genetic Algorithms, Particle Swarm Optimization, and other swarm intelligence-based methods are embedded in the CNN-based pipelines with the intent to achieve better detection and classification results. We gather recent progress regarding automated architecture search, hyperparameter tuning, model compression, and ensemble learning. We identify how hybrid optimization approaches consistently yield superior accuracy with computational efficiency by systematically reviewing applications in medical imaging, agriculture, vehicular recognition, and remote sensing. Optimized CNN models outperform their baseline versions many times, especially in health diagnostics, where several fine-tuned architectures reach accuracies greater than 99%. This survey provides a structured and updated overview of methodological developments, implementation practices, and emerging research directions for those practitioners and researchers who will apply meta-heuristic optimization within deep learning-based computer vision systems.

SCADA systems in district heating systems (DHS) often record data at irregular time intervals due to various technical, infrastructural, and operational factors. This irregularity complicates the application of standard machine learning models, which typically require uniformly sampled time series. In addition, irregular time series negatively affect the operation of numerous specialized energy software tools, including those used for simulation and optimization of energy systems, consumption management, billing, and reporting modules that require precise time-based aggregation. To address this challenge, this paper proposes a methodology for generating synthetic time series that realistically emulate operational system behavior and complement irregular or incomplete data records. Special emphasis is placed on the use of models based on generative neural networks, as well as statistical approaches for data reconstruction. In the experimental part of the paper, a comparative validation of the reconstruction quality of irregular series will be conducted using:(1) real data extended with synthetic generations and (2) interpolated data. The results will demonstrate the extent to which synthetic data and filling methods improve the accuracy, robustness, and reliability of subsequent analyses and software tools for energy systems.