National Competence Centre for High-Performance Computing
AIMHiGH project, a FF4EuroHPC application experiment, was presented at the SmAgTech EXPO2022. Mr Stevan Cakic gave a presentation at the conference during the plenary sessions on 24 Nov 2022. AIMHIGH was also featured in the virtual EXPO platform in the Projects section.
One of our Euro CC members, dr Armin Alibasic got an invitation to speak at the workshop Human Engagement in HPC. Dr Alibasic presented our success stories on how to engage younger students, including high schools, on HPC. Regarding this topic, one of our biggest achievements is creating an Open Mind academy where so far we had over 200 high school students participating in our training on courses such as Analyzing Social Media Trends, Python Video Game Programming, HPC/AI and Machine Learning, Parallel Programming, Hugging Face, and others.
In addition, he talked about several lectures held at UDG where we invited young researches which gave a very interesting talks on AI/ML and their practical applications. Finally, dr Alibasic concluded by mentioning several conferences organized withing Montenegro, but as well the international events.
The second consecutive virtual online fair “SmAgTech EXPO 2022” on the application of information and communication technologies in agriculture, will be held in the period 23-24/11/2022. The fair is organized within the ERASMUS+ project VIRAL. More than 60 institutions, companies, projects, and programs in the fields of agriculture and ICT will be presented at the fair. Through 20 plenary and section lectures, visitors will be able to hear more about new scientific and practical knowledge in this field. A representative from NCC Montenegro, mr Stevan Cakic, will give a presentation on the use of HPC/AI to develop computer vision solutions for smart poultry farms. More information about the event can be found on the following link.
EUROCC project was featured at the exhibition organized within the “Days of Science and Innovation” festival. This event is traditionally the central annual event of the Ministry of Science and Technological Development and it aims to bring science and innovation closer to the widest population. University of Donja Gorica and NCC Montenegro supported the organization of the event and participated in various activities and exhibits. EUROCC had its own stand in the exhibit where we discussed the aims and results of the project with the visitors and displayed the materials (videos, brochures). During the exhibit we were visited by the Minister of Science and Technological Development, prof. Biljana Šćepanović, as well as by the S3 Montenegro team.
This is the livestream recording from the Day 2 of #EuroCCME22 conference in Montenegro (public part).
This is the livestream recording from the Day 1 of #EuroCCME22 conference in Montenegro (public part).
Researchers from EuroCC Montenegro presented two papers at the IEEE International Conference on Omni-Layer Intelligent Systems (COINS). IEEE COINS (link) is the right place to be. IEEE COINS brings together experts in Digital Transformation (from AI and IoT to Cloud, Blockchain, Cybersecurity, and Robotics) from around the globe. IEEE COINS includes a multi-disciplinary program from technical research papers, to panels, workshops, and tutorials on the latest technology developments and innovations addressing all important aspects of the IoT & AI ecosystem. The conference took place 1-3 August in Barcelona.
This paper was a result of the collaboration on FF4EuroHPC application experiment project called AIMHiGH that focuses on computer vision and the use of HPC to develop object detection prediction models for the use in smart agriculture, more specifically in the poultry sector. The title of the paper is “Developing Object Detection Models for Camera Applications in Smart Poultry Farms”.
ABSTRACT – This paper proposes the use of high-performance computing and deep learning to create prediction models that can be deployed as a part of smart agriculture solutions in the poultry sector. The idea is to create object detection models that can be ported onto edge devices equipped with camera sensors for the use in Internet of Things systems for poultry farms. The object detection prediction models could be used to create smart camera sensors that could evolve into sensors for counting chickens or detecting dead ones. Such camera sensor kits could become a part of digital poultry farm management systems in shortly. The paper discusses the approach to the development and selection of machine learning and computational tools needed for this process. Initial results, based on the use of Faster R-CNN network and high-performance computing are presented together with the metrics used in the evaluation process. The achieved accuracy is satisfactory and allows for easy counting of chickens. More experimentation is needed with network model selection and training configurations to increase the accuracy and make the prediction useful for developing a dead chicken detector. (link)
