Paginacija
-
-
Deep learning methods for segmentation of images of frozen tissue sections
-
Dario Sitnik It is well known that clinical annotation of histopathology data hinders the creation and testing of computer aided diagnostic algorithms related to histopathology image processing. Also, it is important to have correctly annotated data in order to optimize and analyze the performance of any data-driven technique, particularly supervised classification systems. Therefore, ground truth data collection must be led and supervised by experienced medical experts. However, they require a great...
-
-
Deep learning-based analysis of dental X-ray images for forensic estimation of age and sex
-
Denis Milošević Dental remains are one of the most resistant elements to blunt force, fire, bacterial decomposition, and other external factors, making them a prime candidate for forensic analysis. The forensic analysis aims to identify human remains, with the estimation of age and assessment of sex at the forefront. Current methods of forensic odontology are based on time-intensive, precise manual measurements paired with reference tables and atlases, which can lead to human error. Artificial intelligence...
-
-
Deep learning-based analysis of fuel spray images
-
Fran Huzjan Direct rail injection systems in internal combustion engines depend on various parameters, including nozzle diameter, injection pressure, and injector geometry, to shape the spray strategies. These factors influence macroscopic parameters such as spray cone angle, penetration length, and spray area, all crucial for optimizing engine efficiency and reducing pollutants and harmful emissions. To estimate these parameters from spray images, we have utilized computer vision methods, particularly...
-
-
Deep learning-based methods for defect detection from ultrasound images
-
Duje Medak Ultrasonic testing is a non-destructive evaluation (NDE) technique that is used to inspect the integrity of the material and check if there are any defects in its internal structure. The acquisition of ultrasonic data is already done in an automated fashion using robotic manipulators, but the analysis of the data is still done manually by specially trained experts. Manual analysis is subject to human errors especially when a large amount of data needs to be inspected. The goal of this...
-
-
Deep reinforcement learning for market making with time-varying order arrival intensities
-
Bruno Gašperov Market making is a problem of the optimal placement of limit orders on both sides of the limit order book with the goal of maximizing the trader’s terminal wealth while minimizing the related risks. Such risks particularly include inventory, execution, latency, adverse selection, and model uncertainty risks. Especially salient is the inventory risk, arising from the fluctuations in the value of the asset held in the market maker’s inventory, which is typically non-zero, since it depends...
-
-
Definiranje energetske strategije za globalnog proizvođača cementa
-
Dorijan Rajković Rad prikazuje definiranje europske energetske strategije, preciznije za električnu energiju, na primjeru globalnog proizvođača cementa s godišnjom potrošnjom od 2,7 TWh. Trošak električne energije raste već nekoliko godina za redom, i to gotovo u svima europskim državama. Jedinstveno tržište električne energije u Europi još uvijek ne funkcionira i čini se da deregulacija još uvijek nije donijela pravu konkurenciju na tržištu. Takva situacija iziskuje da kupac električne...
-
-
Definiranje parametara za međunarodnu koordinaciju ponovne dodjele radiofrekvencijskog pojasa
-
Ivančica Sakal U radu se razmatraju mogućnosti uporabe radiofrekvencijskog spektra oslobođenog prelaskom na digitalnu radiodifuziju u radiofrekvencijskom pojasu 790-862 MHz u Republici Hrvatskoj. U obzir se uzimaju naputci i odluke Europske Komisije, težnje za harmonizacijom na razini Europske Unije, a posebna se pozornost obraća na specifičnosti lokalnog okruženja (susjedne države) i već postojeće radiodifuzijske sustave u radu (analogna i digitalna televizija). Analizira se mehanizam dodjele...
-
-
Definiranje programskih zahtjeva zasnovano na oblikovanju modela novih poslovnih procesa
-
Bisera Bujić Rad opisuje metodu oblikovanja modela novog poslovnog procesa i proces definiranja programskih zahtjeva za razvoj poslovnog informacijskog sustava. Preduvjet oblikovanju modela novog poslovnog procesa je prikupljanje poslovnih zahtjeva, kvalitativnih i kvantitativnih podataka temeljem kojih se oblikuje poslovni proces. Oblikovanjem novog poslovnog procesa kompleksnost poslovnih zahtjeva je podijeljena na manje i jednostavnije procese. Analizom aktivnosti koje su definirane u procesu, njihove...
-
-
Design methodology for improved electromagnetic compatibility of switched-mode power converters
-
Raul Blečić Switched-mode power converters are used in various applications, such as computer and office equipment, consumer electronics, networking and telecom equipment and industrial electronics. The main advantage of switched-mode power converters is the high conversion efficiency they provide. One of their most important disadvantages is the high level of electromagnetic emissions they generate, which can exceed the limits specified in the regulations. The objective of this dissertation is to...
-
-
Design of radiation-hard CMOS sensors for particle detection applications
-
Ivan Berdalović The work focuses on the design of large-scale radiation-hard monolithic CMOS sensors for the upgrades of the detectors in the high-energy physics experiments at CERN. The sensors are manufactured using a novel process modification implemented in the TowerJazz 180 nm CMOS process, which uses small collection electrodes to achieve a low sensor capacitance in the order of a few femtofarads, resulting in low noise and low analogue power consumption. The process modification provides full...
Paginacija
