Iskanje po katalogu digitalne knjižnice

Opis: Corn drying is a critical post-harvest process to ensure product quality and compliance with moisture standards. Traditional optimization approaches often overlook dynamic interactions between operational parameters and environmental factors in industrial continuous flow drying systems. This study integrates statistical analysis and deep learning to predict outlet moisture content, leveraging a dataset of 3826 observations from an operational dryer. The effects of inlet moisture, target air temperature, and material discharge interval on thermal behavior of the system were evaluated through linear regression and t-test, which provided interpretable insights into process dependencies. Three neural network architectures (LSTM, GRU, and TCN) were benchmarked for multivariate time-series forecasting of outlet corn moisture, with hyperparameters optimized using grid search to ensure fair performance comparison. Results demonstrated GRU’s superior performance in the context of absolute deviations, achieving the lowest mean absolute error (MAE = 0.304%) and competitive mean squared error (MSE = 0.304%), compared to LSTM (MAE = 0.368%, MSE = 0.291%) and TCN (MAE = 0.397%, MSE = 0.315%). While GRU excelled in average prediction accuracy, LSTM’s lower MSE highlighted its robustness against extreme deviations. The hybrid methodology bridges statistical insights for interpretability with deep learning’s dynamic predictive capabilities, offering a scalable framework for real-time process optimization. By combining traditional analytical methods (e.g., regression and t-test) with deep learning-driven forecasting, this work advances intelligent monitoring and control of industrial drying systems, enhancing process stability, ensuring compliance with moisture standards, and indirectly supporting energy efficiency by reducing over drying and enabling more consistent operation.
Ključne besede: advanced drying technologies, continuous flow drying, time-series forecasting, LSTM, GRU, TCN, deep learning, statistical analysis, optimization of the drying process
Objavljeno v DKUM: 03.11.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (3,02 MB)
Gradivo ima več datotek! Več...

Opis: This work presents a task-oriented framework for optimizing robotic surface finishing to improve efficiency and ensure feasibility under realistic kinematic and geometric constraints. The approach combines surface subdivision, optimal placement of the workpiece, and region-based toolpath planning to adapt machining strategies to local surface characteristics. A novel time evaluation criterion is introduced that improves our previous kinematic approach by incorporating dynamic aspects. This advancement enables a more realistic estimation of machining time, providing a more reliable basis for optimization and path planning. The framework determines both the optimal position of the workpiece and the subdivision of its surface into regions systematically, enabling machining directions and speeds to be adapted to the geometry of each region. The methodology was validated on several semi-complex surfaces through simulation and experimental trials with collaborative robotic manipulators. The results demonstrate that improved region-based optimization leads to machining time reductions of 9–26% compared to conventional single-direction machining strategies. The most significant improvements were achieved for larger, more complex geometries and denser machining paths, confirming the method’s industrial relevance. These findings establish the framework as a practical solution for reducing cycle time in specific robotic surface finishing tasks.
Ključne besede: robot surface finishing, collaborative robot, region-based machining, automatic surface subdivision, realistic machining time estimation
Objavljeno v DKUM: 17.10.2025; Ogledov: 0; Prenosov: 13
Celotno besedilo (7,69 MB)

Opis: Pancreatic ductal adenocarcinoma (PDAC) remains one of the most deadly malignancies with a highly immunosuppressive tumor immune microenvironment (TIME) that hinders effective therapy. PDAC is characterized by significant heterogeneity in immune cell composition, spatial distribution and activation states, which impacts tumor progression and treatment response. Tumour-infiltrating lymphocytes (TILs), including CD4+ T-helper cells, CD8+ cytotoxic T-cells and FOXP3+ regulatory T-cells, play a key role in immune regulation, yet PDAC is largely an immunologically "cold" tumour with limited effector T-cell infiltration. The surrounding cellular microenvironment, particularly Cancer Associated Fibroblasts (CAFs) and macrophages, contributes to immune evasion by promoting a fibrotic and desmoplastic barrier that limits TIL infiltration. The prognostic significance of TILs is increasingly recognized, with higher densities correlating with improved survival, whereas regulatory T-cell infiltration and immunosuppressive stromal interactions are associated with poor outcomes. Emerging therapeutic strategies targeting the TIME (e.g., CAFs), immune checkpoint inhibitors, and TIL-based therapies offer the potential to overcome resistance. Future research must focus on optimizing immunotherapy strategies and unravelling the complex stromal-immune interactions to improve clinical translation.
Ključne besede: immune system, pancreatic adenocarcinoma (PDAC), spatial analysis, tumor immune microenvironment (TIME), tumor infiltrating lymphocytes (TILs)
Objavljeno v DKUM: 18.08.2025; Ogledov: 0; Prenosov: 1
Celotno besedilo (6,62 MB)
Gradivo ima več datotek! Več...

Opis: This paper presents the results of a study whose primary goal was to determine the level of future teachers’ knowledge of historical content taught in primary school, the ways they self-assess their abilities to organize the learning and teaching of historical content, and their beliefs about the possibilities of teaching history in primary education. The research was conducted using a survey of 157 fourth- and fifth-year students in teacher education programs. The results indicate that students demonstrate a satisfactory level of knowledge about historical content taught in primary education. They self-assess their skills for teaching of historical content as mostly developed and have positive beliefs about the possibilities of teaching and learning history at the primary education level.
Ključne besede: competences of future teachers, learning outcomes, history, primary education, time comprehension
Objavljeno v DKUM: 29.07.2025; Ogledov: 0; Prenosov: 6
Celotno besedilo (394,85 KB)
Gradivo ima več datotek! Več...

Opis: Debate regarding the use of airplanes or high-speed trains in middle-distance passenger transportation has evolved into a strong field of research. With the aim to mitigate the environmental footprint of air travel, the European Union’s initiatives are focused on redirecting passengers from airplanes to high-speed trains. This shift is hampered by significant variations in train accessibility across Europe. Using Sweden as an example, we tested the break-even distance and evaluated the findings from both a time-efficiency perspective and a sustainability perspective. Airplanes hold the upper hand on high-speed trains in middle-distance passenger transportation from the time perspective. This perspective provides us with a clear answer, but if we consider the sustainability perspective, it may affect the results. The results indicate that the presented proof of concept makes sense and can be easily adapted to any decision-making process regarding the choice of the preferable transportation mode, although the procedure is extremely time consuming. For policymakers, this proof of concept can represent a priceless tool because the resulting figures carry valuable information about (under)developed and (less-)integrated transportation modes in commuting and transportation systems.
Ključne besede: time efficiency, sustainability, breakeven distance, high-speed-rail (HSR) travel, air travel
Objavljeno v DKUM: 01.07.2025; Ogledov: 0; Prenosov: 2
Celotno besedilo (2,04 MB)
Gradivo ima več datotek! Več...