Paginacija

A multi-objective optimization procedure for locally adaptive time-frequency analysis with application in EEG signal processing
A multi-objective optimization procedure for locally adaptive time-frequency analysis with application in EEG signal processing
Vedran Jurdana
This dissertation addresses the challenges in the spectral representation of nonstationary signals using joint time-frequency distributions (TFDs). Heuristic time-frequency methods introduce additional interfering energy clusters, while the wrong choice of parameters in advanced methods may lead to the loss of useful components, thus restricting their practical use. Existing concentration and entropy measures, along with their optimization methods, are appropriate when the structure of...
A shear deformable beam model for stability analysis of composite frames
A shear deformable beam model for stability analysis of composite frames
Damjan Banić
This dissertation addresses the issue of non-linear stability of frame structures consisting of thin-walled composite beam elements. To this end, a numerical approach is presented that involves the development of an original 1D finite element model. The research delves into several key aspects. Firstly, the dissertation introduces the research problem and scientific motivation and outlines the main objectives and purpose of the study. A brief overview of previous studies on...
An Intelligent System for Urinary Bladder Cancer Diagnostics
An Intelligent System for Urinary Bladder Cancer Diagnostics
Ivan Lorencin
Objectives: Urinary bladder cancer is one of the most common malignancies of the urinary tract. It begins when cells of the bladder mucosa start to grow uncontrollably with the tendention to spread. Such a spread can cause cancer to expand to other parts of the human body. It is characterized with a high metastatic potential and a high recurrence rate. For these reasons, the correct and timely diagnosis and treatment is an absolute imperative. To increase the accuracy and speed of ...
Analiza energetske učinkovitosti termotehničkih sustava s latentnim spremnikom topline
Analiza energetske učinkovitosti termotehničkih sustava s latentnim spremnikom topline
Fran Torbarina
U doktorskoj disertaciji provedena je numerička analiza izmjene topline u termotehničkim sustavima grijanja koji koriste dizalicu topline i latentni spremnik topline, s ciljem povećanja njihove energetske učinkovitosti. U tu svrhu, temeljem fizikalnog problema izmjene topline u latentnom spremniku topline, postavljen je odgovarajući matematički model koji opisuje nestacionarni problem izmjene topline između fluida prijenosnika topline i akumulatora topline u latentnom...
Analiza povećanja učinkovitosti cijevnih lamelnih izmjenjivača topline ugradnjom generatora vrtloga
Analiza povećanja učinkovitosti cijevnih lamelnih izmjenjivača topline ugradnjom generatora vrtloga
Josip Batista
U radu je provedena numerička analiza strujanja i izmjene topline u unakrsnom cijevnom lamelnom izmjenjivaču topline zrak-voda s generatorima vrtloga. Prilikom izrade numeričkog modela, u obzir su uzete karakteristike strujanja i toplinski otpori na strani oba fluida. Za postavljeni fizikalni problem izdvojen je segment u središtu izmjenjivača topline koji zajedno s proširenjima u smjeru strujanja zraka predstavlja proračunsku domenu. Trodimenzijski matematički model...
Analiza tehnoloških parametara i deformacija polimernih nanokompozitnih ploča tijekom inkrementalnog oblikovanja u jednoj točki
Analiza tehnoloških parametara i deformacija polimernih nanokompozitnih ploča tijekom inkrementalnog oblikovanja u jednoj točki
Andrej Borić
Proteklih godina, nekoliko inovativnih postupka oblikovanja deformiranjem je razvijeno s ciljem proizvodnje visoko individualiziranih proizvoda s razumnim troškovima proizvodnje. Inkrementalno oblikovanje ploča (engl. Incremental Sheet Forming – ISF) predstavlja jednu od tih novih tehnologija koja je postala fokusom interesa mnogih znanstvenika i znanstvenih institucija. Inkrementalno oblikovanje u jednoj točki (engl. Single Point Incremental Forming – SPIF) je jedan od...
Binary classification of peptides using deep neural networks and transfer learning
Binary classification of peptides using deep neural networks and transfer learning
Erik Otović
Machine learning is increasingly used for high-throughput peptide screening, providing a rapid and efficient method to identify peptides with desired functions in contrast to traditional trial-and-error approaches that are time-consuming and resource-intensive. It streamlines the exploration of the vast peptide space in a data-driven way and accelerates the discovery of novel peptides. This thesis investigates three dominantly used peptide representation schemes and analyzes them based on...
Characterization of parameters influencing friction in the nanometric domain
Characterization of parameters influencing friction in the nanometric domain
Marko Perčić
Friction and wear are recognized as one of the most puzzling problems, not only in many engineering and manufacturing applications, but also in a fundamental scientific sense. In fact, friction is a nonlinear stochastic effect with a distinct time, position and temperature variability. While frictional phenomena on the macro- and meso-scales can be considered well described, and their characteristic features can be simulated via suitable models, as well as generally efficiently...
Design of miniaturized wearable broadband energy harvesters
Design of miniaturized wearable broadband energy harvesters
Petar Gljušćić
Energy harvesting (EH) is the process of collecting low-level ambient energy and converting it into electrical energy to be used for powering miniaturized autonomous devices, wearable electronics or Internet-of-Things components. The use of kinetic energy, converted into electrical energy via the piezoelectric principle, is of special interest in this frame. The main drawback of piezoelectric EH devices is the narrow area of optimal operation around the eigenfrequency of a specific...
Detection of gravitational - wave signals from time - frequency distributions using deep learning
Detection of gravitational - wave signals from time - frequency distributions using deep learning
Nikola Lopac
This thesis proposes a method for classifying noisy, non-stationary signals based on deep learning algorithms and Cohen’s class of time-frequency distributions (TFDs). The proposed approach is demonstrated on the challenging task of detecting gravitationalwave (GW) signals in intensive real-life, non-stationary, non-Gaussian, and non-white noise. By retrieving real-life measurements from Laser Interferometer Gravitational-Wave Observatory detectors and performing extensive GW waveform...
Digital signal classification utilizing adaptive information entropy measures and machine learning
Digital signal classification utilizing adaptive information entropy measures and machine learning
Ana Vranković Lacković
This thesis proposes a new approach for preprocessing method for signal classification based on blind source separation of signal components from noisy data in the timefrequency domain. The method is based on the local entropy, which is calculated within adaptive, data-driven 2D regions. One of the advantages of the proposed technique is that it requires no prior knowledge of the signal, its components or the noise, but the processing is performed on the noisy signal mixtures....
Eksperimentalna i numerička analiza povećanja učinkovitosti latentnog spremnika topline
Eksperimentalna i numerička analiza povećanja učinkovitosti latentnog spremnika topline
Mateo Kirinčić
U doktorskoj disertaciji provedena je eksperimentalna i numerička analiza izmjene topline pri spremanju i korištenju topline iz latentnog spremnika topline u svrhu povećanja njegove učinkovitosti. Razmatrani latentni spremnik topline izmjenjivač je topline konfiguracije snopa cijevi u plaštu s uzdužnim lamelama na vanjskoj strani svake cijevi, koji kao akumulator topline koristi parafin RT 25, smješten oko cijevi, a kao fluid prijenosnik topline vodu, koja struji kroz ...

Paginacija