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.

This project is a result of sustainability efforts by NCC Montenegro team and collaboration betweeb Faculty for information systems at University of Donja Gorica and Faculty of medicine at University of Montenegro.

Click to open AI-AGE website

NCC Montenegro: Meeting at UoM

University of Montenegro, NCC Montenegro’s affiliated partner, organized a EuroCC2 project meeting on December 13th, gathering deans, professors, and researchers from its Engineering and Science (Mathematics, Biology, Physics) Faculties, interested in HPC-powered research, development and innovation opportunities.

Professors Bozo Krstajic, UoM and Tomo Popovic, UDG provided introductory session on EuroCC2 project and joint UDG and UoM activities. Professor Luka Filipovic presented NCC Montenegro training activities, services and industry success stories.

The engaging discussion allowed academic participants to gain valuable insights into: HPC practical applications across various research domains, NCC infrastructure opportunities with Yotta Advanced Computing and application process for accessing EUROHPC resources. The next steps will be defined through HPC/AI-aligned research and project initiatives, and supported cooperation with public administration and big industry.

Quantum computing lecture

NCC Montenegro is organizing online introductory lecture about quantum computing and its applications.

Quantum computing is a cutting-edge field of computer science that leverages the principles of quantum mechanics to perform complex calculations at speeds far beyond what classical computers can achieve. Instead of using classical bits, quantum computers use quantum bits or qubits, which can exist in multiple states simultaneously due to superposition. This enables them to solve certain problems, such as factoring large numbers or simulating quantum systems, much faster than traditional computers. Quantum computing has the potential to revolutionize fields like AI/ML applications, cryptography, bioinformatics, digital manufacturing, optimization of traffic systems…

We are privileged to have Dr. Jaka Vodeb as our speaker. Dr. Vodeb is a postdoctoral researcher at the Jozef Stefan Institute and Fz Juelich (NCC Germany). His extensive expertise in quantum computing and quantum simulator ensures inspirational lectures.

Dr. Vodeb will give an overview of the quantum computing landscape, existing quantum hardware, quantum algorithms, quantum error correction and the quantum internet.

Date: 20.10.2023.
Time: 12:00 PM
Duration: Half Day lectures
Registration: https://forms.gle/nTf2aW3kGsbzcSz2A

Don’t miss this opportunity to explore the future of computing.
We look forward to your participation!

For any additional information, inquiries, or updates, please reach us on luka.filipovic@udg.edu.me

Meeting with colleagues from FON UoB

Researchers from University of Donja Gorica (UDG) and NCC Montenegro visited partners from Faculty of organizational sciences University of Belgrade (FON UoB) during their summer school at Perast. Colleagues from FON presented their exhibition of AI generated images titled “Imagine Boka” and their activities about startups and marketing.

We presented the most interesting activities on UDG along with activities on NCC Montenegro and the EuroCC project. We spoke about possibilities of future collaboration on educational programs, training courses, digital transformation topics, AI and similar subjects.

NCC Turkey presented White Paper – SME HPC Maturity Model

NCC Montenegro representatives attended CASTIEL supported, presentation of White Paper “Development of a Maturity Assessment Tool to Improve SME HPC Capabilities” for EuroCC2 industry working group. Dr Özlem Sarı, NCC Turkey, presented industrial users acquisition process and development of HPC Maturity Assessment Tool to improve SME HPC capabilities.

During the presentation, Proof of Concept study, Course of Action, GAP analyses, as well as methodological approach and validation process were duly elaborated. In addition, there was a vibrant discussion on challenges faced and experiences were shared regarding SME collaboration and industry interaction, especially regarding assessment results/HPC maturity levels, identifying HPC-suitable problems and business benefits of HPC integration.

A journal paper: Machine Learning Models for Statistical Analysis

Researchers from UDG and NCC Montenegro published a paper “Machine Learning Models for Statistical Analysis” by M. Grebovic et al. in The International Arab Journal of Information Technology, Vol. 20, No. 3A, Special Issue 2023. This was a follow up effort on the paper previously presented at the ACIT2023 conference.

Click on image to open

ABSTRACT – Compared to traditional statistical models, Machine Learning (ML) algorithms provide the ability to interpret, understand and summarize patterns and regularities in observed data for making predictions in an advanced and more sophisticated way. The main reasons for the advantage of ML methods in making predictions are a small number of significant predictors of the statistical models, which means limited informative capability, and pseudo-correct regular statistical patterns, used without previous understanding of the used data causality. Also, some ML methods, like Artificial Neural Networks, use non-linear algorithms, considering links and associations between parameters. On the other hand, statistical models use one-step-ahead linear processes to improve only short-term prediction accuracy by minimizing a cost function. Although designing an optimal ML model can be a very complex process, it can be used as a potential solution for making improved prediction models compared to statistical ones. However, ML models will not automatically improve prediction accuracy, so it is necessary to evaluate and analyze several statistical and ML methods, including some artificial neural networks, through accuracy measures for prediction purposes in various fields of applications. A couple of techniques for improving suggested ML methods and artificial neural networks are proposed to get better accuracy results.

The paper is available at the following link.