Tražilica
Pronađeno je 18 rezultata u 0,0250 sekundi.
project investigates the potential of machine learning methods for optimizing resource allocation problems of combinatorial nature in large, heterogeneous networked systems. Traditional heuristic algorithms, while computationally less in- tensive, often result in sub-optimal solutions that lead to resource wastage and increased energy consumption. As a milestone in the project we introduce DeepGANTT, a novel learning-based sched- uler that leverages Graph Neural Networks and Transformers to solve an NP-hard combinatorial resource allocation problem for IoT networks with battery-free sensor tags
/aiotwin/activities/1st_summer_school/phd_forum 29. 9. 2023. u 15:22 - Sadržaj
Projects and Laboratories
15:00-15:15
Machine Vision in Dimensional Metrology – Applications in National Laboratory for Length
Marko Horvatek and Marko Katić
University of Zagreb, Croatia
15:15-15:30
An Overview of Research Activities: FESB, Computer Intelligence for Recognition and Support of Human Activities Group
Vladan Papić
University of Split, Croatia
15:30-15:45
EICACS: European Initiative for Collaborative Air Combat Standardization - A Project Overview
Donik Vršnak, Ivan Sabolić, Marko Subašić, Siniša Šegvić and Sven Lončarić
University of Zagreb, Croatia
15:45-16:00
Recognizing Human Activity for Vehicles of the New Mobility - VoNoMobil Project Overview
Siniša
/crv/ccvw2023/program 30. 3. 2023. u 16:40 - Sadržaj
project coordinated by Cloudonia d.o.o. in collaboration with the Faculty of Electrical Engineering and Computing (partner).
Image analysis of shelved products in supermarkets is important for optimal product management in the retail industry in order to minimize sales losses and increase the number of customers.
The project goal is to develop a methodology for the automatic analysis of images containing shelved products in supermarkets. The image analysis problems are solved using deep-learning methods.
Objectives
Specific objectives are to develop:
methods for detection of shelves
methods for detection of price tags
/ipg/research/shelved_product_analysis 15. 2. 2023. u 10:09 - Sadržaj
project’s technological contribution lies in two inter-related areas: underwater acoustics and marine robotics , with a novel underwater acoustic scheme for fish stock measurement that will combine probabilistic analysis with machine learning integrated into a novel design of an autonomous low-power and low-cost floater as a platform for marine exploration, resulting in a TRL6 prototype for selected pilot tests.
Project outcomes and pilot tests:
Design and implement five Lagrangian floaters that autonomously collaborate to determine their depth for the optimal detection of fish. The price tag
/uwin-labust/results/projects/schmidt_ocean_grant_-_sound 18. 1. 2023. u 14:32 - Sadržaj
project team consists of researchers from the University of Rijeka, University of Ljubljana, University of Mannheim and Medical University of Graz.
, Institution: University of Rijeka Faculty of Engineering (RITEH)
Project description: The project will advance existing knowledge concerning modelling for medical image analysis, by introducing a common transfer-learning platform for domain-specific challenges in medical radiology CAD. The objectives will be achieved by fusing the available data sources (pixeldata, DICOM tags
/karijere/ponuda_poslova 22. 7. 2022. u 15:49 - Obavijesti
projects, build know-how, share it, and coach your colleagues.
, The competencies you need
At least one year of experience in development, preferably in an agile environment.
Solid knowledge of Java EE and web applications using J2EE (servlets, JSP, custom tags
/karijere/ponuda_poslova 12. 4. 2022. u 16:16 - Obavijesti
Project objectives will be achieved by fusing the available data sources from a large PACS database of medical radiology exams, using machine learning for multi-step data-driven modelling.
, Institution: University of Rijeka Faculty of Engineering (RITEH)
Project description: The project will advance existing knowledge concerning modelling for medical image analysis, by introducing a common transfer-learning platform for domain-specific challenges in medical radiology CAD. Project objectives will be achieved by fusing the available data sources (pixeldata, DICOM tags
/karijere/ponuda_poslova 15. 2. 2021. u 11:27 - Obavijesti
projects,
Performing basic technical implementation of web analytics solutions with Google Tag Manager or supporting the team on larger projects,
Creating reports for the client and Performance Marketing department,
Coordinating campaign tracking setups with Digital
/karijere/ponuda_poslova 30. 8. 2019. u 11:51 - Obavijesti
projects (non-exhaustive list), Indoor localization of human workers in a robotized warehouse
Status: Looking for candidates
Description: Due to safety requirements there is need to develop algorithms for human localization in robotized warehouses (think of Amazon Robotics, i.e., Kiva warehouses). The idea is to develop an algorithm that will handle the 3 DoF localization problem only with a stereo camera and and an IMU worn by a human. The method will also use ID tag
/lamor/students_corner 23. 8. 2016. u 10:19 - Sadržaj
project, we work on cooperative autonomy for a fleet of unmanned vehicles working together in the aerial, water surface, and underwater domains. Each of these systems work well independently, but our goal is to integrate their performance into one system of vehicles that can safely perform cooperative tasks. The challenges we are working on include creating reliable communications links between vehicles in the harsh low bandwidth maritime environment, integrating novel onboard sensors and inter-vehicle communication to create filters to estimate the state of the network, and creating autonomous takeoff-and-landing algorithms between the aerial/underwater vehicles
/excellabust/wp2_know-how_exchange/t2.3._expert_visits 31. 5. 2016. u 08:45 - Obavijesti
project, we work on cooperative autonomy for a fleet of unmanned vehicles working together in the aerial, water surface, and underwater domains. Each of these systems work well independently, but our goal is to integrate their performance into one system of vehicles that can safely perform cooperative tasks. The challenges we are working on include creating reliable communications links between vehicles in the harsh low bandwidth maritime environment, integrating novel onboard sensors and inter-vehicle communication to create filters to estimate the state of the network, and creating autonomous takeoff-and-landing algorithms between the aerial/underwater vehicles
/excellabust 24. 5. 2016. u 09:45 - Obavijesti
project, we work on cooperative autonomy for a fleet of unmanned vehicles working together in the aerial, water surface, and underwater domains. Each of these systems works well independently, but our goal is to integrate their performance into one system of vehicles that can safely perform cooperative tasks. The challenges we are working on include creating reliable communications links between vehicles in the harsh low bandwidth maritime environment, integrating novel onboard sensors and inter-vehicle communication to create filters to estimate the state of the network, and creating autonomous takeoff-and-landing algorithms between the aerial/underwater vehicles
/labust 9. 5. 2016. u 09:50 - Obavijesti
project, we work on cooperative autonomy for a fleet of unmanned vehicles working together in the aerial, water surface, and underwater domains. Each of these systems work well independently, but our goal is to integrate their performance into one system of vehicles that can safely perform cooperative tasks. The challenges we are working on include creating reliable communications links between vehicles in the harsh low bandwidth maritime environment, integrating novel onboard sensors and inter-vehicle communication to create filters to estimate the state of the network, and creating autonomous takeoff-and-landing algorithms between the aerial/underwater vehicles and the surface
/novosti 9. 5. 2016. u 10:49 - Obavijesti
project, we work on cooperative autonomy for a fleet of unmanned vehicles working together in the aerial, water surface, and underwater domains. Each of these systems work well independently, but our goal is to integrate their performance into one system of vehicles that can safely perform cooperative tasks. The challenges we are working on include creating reliable communications links between vehicles in the harsh low bandwidth maritime environment, integrating novel onboard sensors and inter-vehicle communication to create filters to estimate the state of the network, and creating autonomous takeoff-and-landing algorithms between the aerial/underwater vehicles
/ieeesection/odjeli_chapteri/ra24 9. 5. 2016. u 09:56 - Obavijesti
project, we work on cooperative autonomy for a fleet of unmanned vehicles working together in the aerial, water surface, and underwater domains. Each of these systems work well independently, but our goal is to integrate their performance into one system of vehicles that can safely perform cooperative tasks. The challenges we are working on include creating reliable communications links between vehicles in the harsh low bandwidth maritime environment, integrating novel onboard sensors and inter-vehicle communication to create filters to estimate the state of the network, and creating autonomous takeoff-and-landing algorithms between the aerial/underwater vehicles
/ieeesection 9. 5. 2016. u 09:56 - Obavijesti
project, we work on cooperative autonomy for a fleet of unmanned vehicles working together in the aerial, water surface, and underwater domains. Each of these systems work well independently, but our goal is to integrate their performance into one system of vehicles that can safely perform cooperative tasks. The challenges we are working on include creating reliable communications links between vehicles in the harsh low bandwidth maritime environment, integrating novel onboard sensors and inter-vehicle communication to create filters to estimate the state of the network, and creating autonomous takeoff-and-landing algorithms between the aerial/underwater vehicles
/ieeesection/odjeli_chapteri/pe31 9. 5. 2016. u 13:57 - Obavijesti
projects datasets,
The following datasets have been made available for your use strictly within the scope of the TAR project:
1. Wackypedia – preprocessed (sentence splitted, tokenized, lemmatized, POS-tagged and parsed) Wikipedia dump
/predmet/apt/obavijesti 1. 4. 2014. u 17:30 - Obavijesti
projects, including mapping of seagrass and detection of long-term change trajectories, all with a focus on practical application of the results in science and management. I am currently involved in research that aims to upscale the mapping of seagrass to all of Zanzibar and use the resulting maps to investigate the effect of seagrass density, extent and species on invertebrate distributions. I am also developing projects to map seagrass and kelp in British Columbia, and to track their distribution changes over recent decades. In the future my technical focus will be on image processing including object-based classification, data
/bts/previous_years/bts_2013/lecturers 14. 1. 2013. u 19:11 - Sadržaj