http://hdl.handle.net/10563/1001724 Fri, 01 May 2026 17:49:43 GMT 2026-05-01T17:49:43Z http://hdl.handle.net/10563/1012805 OS-QLR: One-Shot Quantized Latent Refinement for Fast and Efficient Image Generation Li, Peng; Šenkeřík, Roman; Viktorin, Adam This paper introduces One-Shot Quantized Latent Refinement (OS-QLR), a novel two-stage generative framework designed for high-quality image generation and improved computational efficiency. OS-QLR first learns a compact, discrete latent representation using a Vector Quantized Variational Autoencoder (VQ-VAE). It then employs a single-step refinement network within this latent space to produce clean, plausible samples from noisy or random inputs. Experimental results on the FashionMNIST and CIFAR-10 datasets show that OS-QLR consistently delivers superior image quality, featuring sharper details, fewer artifacts, and significantly lower Fréchet Inception Distance scores compared to unrefined VQ-VAE models. Additionally, OS-QLR demonstrates strong performance even with various levels of latent space corruption. Importantly, the training process for OS-QLR is greatly accelerated, taking only hours instead of the days or even weeks required by Diffusion Models, Generative Adversarial Networks (GANs), and Autoregressive image generation models. The non-iterative sampling method allows for rapid image generation, making OS-QLR a compelling and efficient alternative to current computationally intensive generative models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/10563/1012805 2026-01-01T00:00:00Z http://hdl.handle.net/10563/1012803 Mechanical Resistance of PC and PMMA Safety Components in Transportation Karhánková, Michaela; Turek, Jan; Adámek, Milan; Svačinová, Lucie; Miškařík, Lukáš; Mizera, Aleš Polycarbonate (PC) and polymethyl methacrylate (PMMA) are widely used thermoplastic polymers in transportation applications due to their exceptional optical clarity, impact resistance, and durability. These materials are integral to safety-critical components such as vehicle light covers, protective shields, and sensors. In this study, PC and PMMA specimens of varying thicknesses were tested using drop-weight impact tests to evaluate their mechanical properties, specifically puncture resistance. The primary objective was to compare the impact resistance and overall performance of these materials under dynamic loading conditions. Statistical analysis revealed that PC outperformed PMMA in mechanical performance, though modifications to PMMA can enhance its impact resistance. This research provides practical insights for optimizing material selection in transportation, ensuring a balance between durability and cost-efficiency. Q29weXJpZ2h0IMKpIDIwMjUuIFB1Ymxpc2hlZCBieSBFbHNldmllciBCLlYu. Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/10563/1012803 2026-01-01T00:00:00Z http://hdl.handle.net/10563/1012804 Use of TEN-T for the movement of Search & Rescue teams within the framework of CBRN-E response Řehák, David; Janečková, Heidi; Hromada, Martin; Střítecký, Vít; Špeldová, Eliška; Benekou, Panagiota Current threats, such as natural disasters, technological accidents or targeted attacks involving CBRN-E aspects, are becoming increasingly frequent and complex. For this reason, there are constantly increasing demands not only on the population protection, but also on the Search and Rescue Teams allocated to manage these large-scale disasters. In the context of responding to possible incidents, the rapid and safe transport of these teams represents a significant logistical challenge. Specifically, this concerns the transport of specialized equipment, which, due to its size or weight, can be difficult to transport within the Trans-European Transport Network. Q29weXJpZ2h0IMKpIDIwMjUuIFB1Ymxpc2hlZCBieSBFbHNldmllciBCLlYu. Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/10563/1012804 2026-01-01T00:00:00Z http://hdl.handle.net/10563/1012727 A comparative evaluation of validation techniques in software effort estimation using eSOMCOCOMO Bajusová, Darina; Šilhavý, Radek; Šilhavý, Petr This study investigates the impact of different validation techniques on the performance evaluation of software effort estimation models. Specifically, it compares k-fold cross-validation, leave-one-out cross-validation (LOOCV), and hold-out validation using the eSOMCOCOMO approach, which enhances COCOMO model predictions through the Self-Organizing Migrating Algorithm (SOMA). The evaluation was conducted on three benchmark datasets (NASA18, Kemerer, and Miyazaki94) and assessed using standard evaluation metrics (MMRE, PRED(25), MMER, MAE, MSE, RMSE, and R2). Statistical hypothesis testing revealed significant differences among most validation techniques, except in the comparison conducted on the NASA18 dataset. LOOCV demonstrates superior stability across multiple runs, whereas hold-out validation showed high variance. Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/10563/1012727 2025-01-01T00:00:00Z