Iskanje po katalogu digitalne knjižnice

Opis: In response to the growing demand for accurate freight forecasting in sea-rail intermodal transportation, particularly under the constraints of stringent data protection regulations, we introduce a privacy-preserving, AI-based framework that focuses on the micro-level identification of container transport potential. The framework combines Vertical Federated Learning (VFL) with advanced feature and sample selection techniques. It leverages privacy-preserving methods, such as homomorphic encryption and random noise, enabling secure collaboration between ports and railways while safeguarding commercially sensitive data. Through extensive experiments, our framework demonstrates superior performance in predicting container transport demand, significantly improving the accuracy of resource allocation and scheduling decisions for rail operators. The framework not only ensures compliance with data protection regulations but also provides valuable insights into intermodal transportation planning, optimizing both railway operations and customer service quality. This approach offers a practical solution for improving strategic decision-making in the sea-rail intermodal sector amid increasing privacy demands and complex logistical challenges.
Ključne besede: freight demand forecasting, container transportation demand forecasting, vertical federated learning, privacy-preserving methods, sample and feature selection, machine learning, homomorphic encryption, resource allocation and scheduling
Objavljeno v DKUM: 20.01.2026; Ogledov: 0; Prenosov: 0
Celotno besedilo (1,37 MB)
Gradivo ima več datotek! Več...
Gradivo je zbirka in zajema 1 gradivo!

Opis: The automotive industry is increasingly confronted with challenges in managing complex requirements and test cases arising from the integration of advanced electronic systems, software functionalities, and compliance with international standards. Conventional manual validation of requirements is time-consuming, error-prone, and resource-intensive, underscoring the need for more efficient and reliable approaches. This thesis investigates the automation of test case generation through the application of Retrieval-Augmented Generation (RAG) in combination with Large Language Models (LLMs). A complete RAG workflow was implemented in Python, incorporating LangChain, LangGraph, Ollama, and ChromaDB to facilitate indexing, retrieval, and generation. The system was trained and evaluated on datasets comprising automotive requirements and test cases, with experiments examining embedding quality, retrieval strategies, prompt engineering techniques, and generative model parameters. The results demonstrate that RAG is capable of generating high-quality, contextually relevant test cases on consumer-grade hardware, thereby significantly enhancing efficiency, consistency, and productivity relative to manual methods. Furthermore, the findings suggest that RAG-based systems are best positioned as complementary tools that support, rather than replace, human engineers. This research provides a foundation for future work on hybrid retrieval methods, advanced embedding techniques, and the integration of more powerful LLMs into requirement and test case management processes.
Ključne besede: automotive requirements validation, test case generation, large Language Models, Retrieval-Augmented Generation
Objavljeno v DKUM: 01.10.2025; Ogledov: 0; Prenosov: 0
Celotno besedilo (5,84 MB)

Opis: This article examines eye gaze while a multimodal text with vibrant and colourful images is read and furthermore specifically investigates the effect of the Stroop test on eye gaze. The Stroop colour-word test was designed to test the ability of a reader to suppress a habitual response. This particular variation of the test presented readers with words that refer to colour, but are presented in a different colour. Results indicate images are used when unfamiliar objects are referred to and faces and characters attract attention. The use of incongruent colours definitely causes cognitive dissonance and negatively affect reading.
Ključne besede: cognitive processing, eyetracking experiment, eye gaze, Stroop colour-word test, multimodal text
Objavljeno v DKUM: 28.07.2025; Ogledov: 0; Prenosov: 7
Celotno besedilo (2,48 MB)
Gradivo ima več datotek! Več...

Opis: Namen diplomskega dela je bil raziskati in predstaviti povezanost med hranjenostjo in koordinacijo predšolskih otrok. Za empirično raziskavo je bil uporabljen neslučajnostni vzorec predšolskih otrok, starih od pet do šest let. V raziskavi je sodelovalo dvajset otrok, od tega osem deklic in dvanajst dečkov, ki obiskujejo vrtec Plavček pri Osnovni šoli Tišina. Pri zbiranju podatkov smo uporabili kavzalno ne-eksperimentalno metodo. Z meritvami telesnih razsežnosti smo pridobili podatke za izračun indeksa telesne mase (ITM), koeficienta razmerja med obsegom pasu in telesno višino (WHtR) in koeficientom razmerja med obsegom pasu in obsegom bokov (WHR). Sledila je izvedba testa KTK, s katero je bila določena koordinacijska sposobnost testiranih otrok. Zbrane podatke smo nato analizirali s pomočjo programa SPSS in ugotovili, da izbrane neodvisne spremenljivke (ITM, WHR, WHtR, spol) ne pojasnjujejo odvisne spremenljivke MQ (rezultati testa KTK).
Ključne besede: hranjenost, koordinacija, test KTK, predšolski otroci, ITM, WHtR, WHR
Objavljeno v DKUM: 18.06.2025; Ogledov: 0; Prenosov: 45
Celotno besedilo (1,37 MB)

Opis: During the corona virus (COVID-19) pandemic, there was a sharp increase in the need for diagnostic tests that could detect the presence of SARS-CoV-2 virus or its antibodies quickly and reliably. An important type in the group of diagnostic tests are rapid antigen lateral flow immuno-assay (LFIA) tests, which operate on the immuno-chromatographic principle with the lateral flow of analyte. Clinical practice in the last year has shown that such diagnostic tests can be effective in preventing the spread of the SARS-CoV-2 virus.The development, and, thus, the production of the rapid antigen LFIA tests, is influenced by a number of factors that determine their sensitivity and accuracy indirectly. These factors are directly dependent on the type of antibody produced, which is formed as an immune response when infected with the virus. The production of the rapid antigen LFIA tests is associated with the appropriate selection of basic components that determine the type and quality of these tests. The basic components include: substrates and membranes, antigens, antibody labels and compatible buffers. The correct choice of membranes and their materials is crucial to compiling an effective rapid antigen LFIA test. This study therefore presents a comparative analysis of four commercially available SARS-CoV-2-rapid LFIA tests using state-of-the-art characterisation techniques scanning electron microscopy (SEM), inductively coupled plasma-optical emission spectrometry (ICP-OES), environmental scanning electron microscope / energy-dispersive X-ray spectroscopy (ESEM/EDX), Fourier-transform infrared spectroscopy / attenuated total reflection (FTIR/ATR) for the individual components. The obtained results were the starting point for the development and assembling of our own rapid antigen LFIA test based on gold nanoparticles as antibody labels.
Ključne besede: hitri antigenski testi, komponente, karakterizacija, analize, rapid antigen test, components, characterisation, analysis
Objavljeno v DKUM: 26.03.2025; Ogledov: 0; Prenosov: 7
Povezava na celotno besedilo
Gradivo ima več datotek! Več...