News – Page 3 – HPC4S3.ME

22.04.2024.29.04.2024.

HPC4S3ME team presented a paper at 2024 Infoteh-Jahorina

Our team presented the paper “Ovarian Cancer Detection Using Computer Vision” that addresses the use of AI and HPC tools for computer vision application in medicine. The paper was authored bz A. Abazovic, A. Lekic, I. Jovovic, S. Cakic and T. Popovic. This paper is a result of engaging young researchers and interns to embrace HPC and AI technology. The successful presentation of the paper is followed by its publication in the IEEE Xplore electronics library. Information about the conference is available at the conference website.

ABSTRACT – This study explores the application of artificial intelligence (AI) and deep learning in the field of computer vision, specifically for the detection of ovarian cancer. A computer vision model was developed, utilizing two different AI models, YOLOv8 and YOLOv7, to evaluate their effectiveness in this medical context. YOLOv8, being the current state-of-the-art model in computer vision, was chosen for its advanced capabilities, while YOLOv7 was selected for its established usage and performance record. Comparative analysis revealed that YOLOv8 outperformed YOLOv7 with a significantly higher accuracy rate of approximately 0.9. This enhanced accuracy is crucial in medical applications, particularly for early cancer detection which can substantially improve patient outcomes. Additionally, the model was benchmarked against other machine learning models and existing computer vision approaches in ovarian cancer detection. While this model demonstrated superior accuracy compared to other machine learning techniques, it was observed that certain other computer vision models, leveraging more customized architectures and larger datasets, achieved marginally better results. These findings indicate potential areas for future improvement of implemented model, including the integration of more comprehensive datasets and the refinement of model architecture. Furthermore, the research proposes the incorporation of additional health parameters to enhance the model’s effectiveness and applicability in medical diagnostics.

Link to the paper at IEEE Xplore is available here.

27.03.2024.27.03.2024.

EUROCC Workshop: Application of HPC & AI in energy sector

NCC Montenegro, in collaboration with CIGRE Montenegro, is pleased to announce a collaborative workshop scheduled for March 29, 2024. This workshop is designed to enhance industry relations and explore the applications of High-Performance Computing (HPC) and Artificial Intelligence (AI) technologies within the energy sector.
The workshop will provide Montenegrin companies with a comprehensive overview.

More information about the event and registration information can be seen at the NCC Montenegro website (link).

04.03.2024.27.03.2024.

Successful realization of the IEEE IT2024 Conference

XXVIII international scientific and professional conference “Information technologies” was held from February 21 to 24, 2024 traditionally in Žabljak, organized by: University of Montenegro – Faculty of Electrical Engineering, University of Donja Gorica – Faculty of Information Systems and Technologies, IT Society Crna Gora, University of Belgrade – Faculty of Organizational Sciences, IEEE Association and IEEE Section for Serbia and Montenegro, with the full support of the company Čikom from Podgorica. Presentations of author’s works and sessions were realized live in the hotel “Gorske oči”, hotel “Žabljak”, but also online. The conference gathered around 200 national and international participants. Link to conference website: https://www.it.ac.me/en/

Authors from 20 countries took part in the conference: Montenegro, Serbia, Bosnia and Herzegovina, Croatia, Slovenia, Hungary, Romania, Greece, Cyprus, Italy, Spain, Slovakia, Ukraine, Estonia, the United Kingdom, Turkey, Egypt, Jordan, Indonesia and the Philippines. The number of submitted author’s works was 101, of which 67 were accepted and presented, which were reviewed and selected on the basis of the complete work. Topics from various fields are covered such as: image and audio signal processing, acyclic graphs, blockchain technology, information security, standardization, application of artificial intelligence in various fields, management of unmanned vessels, virtual trade and knowledge transfer.

Short video on HPC at IEEE 2024 conference

A special session was dedicated to the presentations of the EuroCC2 project – National Competence Centers for HPC: https://eurocc.udg.edu.me/, the presentation of the Montenegrin Academic Digital Innovation Hub, supported by the DigNEST project : https://dignest.me/#/ , then TRACEWINDU: https://www.tracewindu.eu/, FoodHUB – Center of excellence for digitization of risk assessment in the field of food safety and precise certification of the authenticity of pre-harvested products: https://foodhub .udg.edu.me/, HPC4S3ME: https://hpc4s3me.udg.edu.me/, AI-AGE: https://ai-age.udg.edu.me/, STECCI: https://steccihorizoneu. com/, FishEUTrust: https://fisheutrust.org/, Solar Katun: https://digitalsmart.me/innovation-fund-of-montenegro-solar-katun-project/, Enav: https://enav.ucg. ac.me and COMMECT: https://www.horizoneurope-commect.eu/ . Representatives of Fleka, Čikom and FiveG Group participated in the training.

Short video on IEEE IT2024

As part of the XXVIII scientific-professional conference, those present had the opportunity to participate in workshops, panels and trainings in the field of artificial intelligence, but also to hear the activities carried out by national competence centers in the field of high-performance computing from Cyprus, Slovenia, the Netherlands, Montenegro, Turkey , North Macedonia, Romania, participants in the EuroCC2 project. The project supports the development of innovative solutions by targeted participants in the private and public sector by providing support to interested end users in the use of HPC/HPDA/AI. Activities and innovative solutions based on the use of high-performance computing (HPC) and artificial intelligence (AI) for applications in industrial domains defined by the Smart Specialization Strategy (2019-2024) for Montenegro were presented.

Traditionally, the conference was successfully completed for the twenty-eighth year in a row, and it fulfilled its goal by pointing out the importance of a multidisciplinary overview of current events and the networking of a large number of university professors and associates, experts and young researchers in the field of information and communication technologies.

01.03.2024.09.03.2024.

Research paper: Hotel Chatbot for Smart Hospitality

The paper “Hotel Chatbot Receptionist for Smart Hospitality” by Ms Sara kovacevic, Tomo Popovic, Ivan Jovovic, and Stevan Cakic was presented at the 28th IEEE International Conference on Information Technology. This is a great example of the engagement of young researchers to utilise HPC/AI tehcnology in the priority domains of S3 Montenegro, in this case tourism and hospitality.

ABSTRACT – The dynamic changes in the global business landscape are being driven by cutting-edge technologies such as artificial intelligence and machine learning, blockchain, and high-performance computing. Recognizing the pivotal role of digital transformation, particularly in the tourism sector, Montenegro has started embracing innovative solutions. The continuous evolution of technology has significantly influenced the tourism industry presenting an opportunity for digital transformation in the sector. The introduction of chatbots in Montenegrin hotels and resorts emerges as a potential game-changer. This implementation aims not only to reduce waiting times at reception but also to elevate the overall user experience. By adopting hotel chatbots in different hotels, each establishment can have a dedicated knowledge base tailored to its specific policies and regulations. This approach ensures a seamless integration of technology that not only enhances operational efficiency, but also enriches the offerings within the tourism and hospitality sector in Montenegro.

The paper is a result of invlovement of young researchers in HPC/AI research in S3 domain

Ms Sara Kovacevic, a BSc student, presenting the paper at IT2024 conference

27.02.2024.03.03.2024.

HPC4S3ME featured at the IEEE IT2024 conference

HPC4S3ME project was presented at the 28th IEEE IT2024 Conference that took place 21-24 Feb 2024 in Zabljak, Montenegro. The presentation took place in a poster section dedicated to project presentations. We had a chance to talk to conference attendees, our colleauges from Montenegro and abroad. Also, the next day we had a large group of students participating in the EuroCC Workshop on HPC and Industry Applications, where we had a chance to discuss the project posters and take their attention to HPC4S3ME and other projects presented at the conference. Furhtermore, during the conference we had a scientific paper that was based on the research conducetd bz young researchers.

HPC4S3ME presented in the special section dedicated to project results

The attendance was over 100 people during the conference

All the project posters were present throughout the whole conference

17.02.2024.17.02.2024.

Getting ready for IEEE IT2024

As UDG is one of co-organizers of the 28th IEEE Conference on Information Technology 2024, we are actively preparing for our participation. HPC4S3ME project will be presented in the special session dedicated to project results dissemination on Wednesday. Also, we will have a conference paper presenteation that will take place on Thursday. This paper will discuss the use of AI and HPC for development of applications for cultural heritage preservations and their valorization in tourism.

The conference will have a rich program involving a whole afternoon EUROCC2 Workshop on HPC and Industry applications, as well as invited lecture on LLMs and round table discussion on AI on Friday late afternoon.

09.02.2024.

Workshop on HPC and Industry Applications by EuroCC

Registration is open for the upcoming EuroCC Training Event – High Performance Computing and Industry Applications. This event is organized in alignment with the 28th International Information Technology IEEE Conference IT 2024, traditionally taking place in Žabljak, Montenegro. The workshop is organized in hybrid mode. EuroCC NCC Montenegro is organizing this event in collaboration with NCCs from Cyprus, Slovenia, Turkiye, Romania, Netherlands, and North Macedonia. You can register for the event by clicking on the image below or at this link.

You can find the agenda and event details at the NCC Motnenegro website (link).

More info on NCC Montenegro website (click on image)

01.02.2024.16.04.2024.

AI-AGE: Artificial Intelligence Supported Identification of Novel Non-invasive Biomarkers of Aging

Another AI and S3 related project is granted for implementation at UDG. The AI-AGE project proposes the use of machine learning (ML) algorithms and evaluation of state-of-the-art AI tools to train and create prediction models to identify novel non-invasive biomarkers of aging, and increased risk for development of age-related conditions. The idea is to utilize a large dataset of annotated retinal images from the UK Biobank, to explore deep learning (DL) techniques, most commonly based on convolutional neural networks (CNNs), such as U-Net and Res-Net, and transformers, but also to expand the research on the use of ensemble methods that combine ML techniques to improve performance and accuracy.

The eye serves as a window for non-invasive assessment of retinal vascular and neural tissue, offering valuable insight into our health. Extensive research has established the association between changes in retinal morphology and the increased risk for many age-related chronic diseases. These changes are also linked to healthy aging, albeit more pronounced in the presence of age-related chronic conditions. This project will provide sustainability for HPC4S3ME activities and it implementation spans from 2024 to 2026.

AI-AGE project is implemented through partnership between the Faculty for Information Systems and Technologies (UDG) and Faculty of Medicine (UoM). The project is funded by the Ministry of Education, Science and Innovation, grant number 04-082/23-2528/1.

05.01.2024.09.02.2024.

Conference proceedings for MEDICON’23 and CMBEBIH’23

Proceedings of the Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON) and International Conference on Medical and Biological Engineering (CMBEBIH), September 14–16, 2023, Sarajevo, Bosnia and Herzegovina—Volume 1: Imaging, Engineering and Artificial Intelligence in Healthcare. The following papers submitted by the HPC4S3ME young reearchers have been published in the proceedings:

Dejan Babic, Luka Filipovic, Sandra Tinaj, Ivana Katnic, Stevan Cakic, “Ten Year Cardiovascular Risk Estimation: A Machine Learning Approach”, Proceedings of MEDICON 2023 Conference, Sarajevo, Sep 2023, pp 605-612
Ivan Jovovic, Marko Grebovic, Lejla Gurbeta-Pokvic, Tomo Popovic, Stevan Cakic, “Liver Diseases Classification Using Machine Learning Algorithms”, Proceedings of MEDICON 2023 Conference, Sarajevo, Sep 2023, pp 585-593
Tamara Pavlovic, Marko Grebovic, Armin Alibasic, Milica Vukotic, Stevan Sandi, Forecasting Icterus with Machine Learning: An Advanced Classification Model analysis”, Proceedings of MEDICON 2023 Conference, Sarajevo, Sep 2023, pp 673-683
Zoja Scekic, Luka Filipovic, Ivana Katnic, Nela Milosevic, Stevan Sandi, “Thyroid Hormones Parameter-Based Classification of Patient Health Status: An analysis of Machine Learning techniques”, Proceedings of MEDICON 2023 Conference, Sarajevo, Sep 2023, pp 673-683

The book can be accessed at the Springer website (link).

25.12.2023.31.12.2023.

EuroCC and AI4S3 Hackaton

On 23 Dec 2023, our researchers participated in the organisation of EuroCC and AI4S3 Hackaton. The hackaton was organized in the context of EuroCC implementing AI4S3 education project that was funded by the Innovation Fund of Montenegro. There was 24 teams presenting their projects and around 50 attendees. There were students from BSc, MSc and PhD level, as well as some industry representatives.