Two NCC-supported and AI-related research papers @SymOrg 2024 conference

Representatives from NCC Montenegro in joint efforts with young researchers from UDG, published two scientific papers at the SymOrg 2024 conference, organized by the Faculty of Organizational Science, University of Belgrade, at Zlatibor, Serbia on June 12-14, 2024. The conference, traditionally envisioned as a platform for knowledge innovation and empirical research, bringing together representatives from the scientific and professional community, was themed: ”Unlocking The Hidden Potential Of Organization Through Merging Of Humans And Digitals”, aiming to address the newfound need for balance in the era of AI.

Image source: SymOrg 2024 website

The scientific paper “Detection of Scoliosis” by Elvis Taruh, Enisa Trubljanin, and Dejan Babić explores the application of a deep learning model integrated with a web application to detect scoliosis using x-ray images. Utilizing a dataset of 198 x-ray images from Roboflow, the initial model performance was unsatisfactory, prompting manual annotation of 245 images, which significantly improved the model’s accuracy. YOLOv8, a state-of-the-art object detection algorithm, was used to train two models, demonstrating improved performance with manual annotations. The web application, built with Flask, HTML, CSS, and JavaScript, provides a user-friendly interface for analyzing scoliosis detection results. The backend uses MySQL for data storage and management, facilitating efficient image processing, result display, and feedback from doctors. Evaluation metrics indicate that the second model, which underwent refined annotation and augmentation, performed better, avoiding overfitting and demonstrating higher precision. This approach enhances early scoliosis diagnosis and offers a scalable solution for other medical detection challenges, supporting healthcare providers with more accurate diagnostic tools and improving patient care.

Click on image to open SymOrg 2024 proceedings

In the paper “LLM Consistent Character Bias”, the authors Igor Culafic and Tomo Popovic investigate the potential of Large Language Models (LLMs) for character imitation in media, education, and entertainment. Traditionally, LLMs have been used for tasks like web search and programming, but this study focuses on their application in mimicking specific characters from books. Using a dataset created from the Ciaphas Cain anthology of Warhammer 40k, the authors trained models using Low-Rank Adaptation (LoRA) methods. Three models of varying sizes (1.1B, 7B, and 10.7B parameters) were tested, with training conducted on a NVIDIA RTX 4090 GPU. The study found that the larger models (7B and 10.7B) performed well in maintaining character consistency, though they occasionally struggled with specific details and displayed unexpected behaviors like excessive emoji usage. The smallest model (1.1B), despite higher LoRA Rank parameters, was less effective and prone to errors such as repetitive responses and long rants. The authors conclude that LLMs can successfully imitate fictional characters given adequate data and training, suggesting future improvements could make them useful in various fields, including education and therapy. These models have the potential to enhance interactive experiences in theme parks, video games, and educational tools by providing authentic character interactions. However, they caution against using these models as replacements for human therapists due to their limitations and tendency for inaccuracies.

Click on image to open SymOrg 2024 proceedings

Both research papers were partly supported by the EuroCC2 project that is funded by the European High-Performance Computing Joint Undertaking (JU) under Grant Agreement No 101101903.

IHMS precise weather forecast at VEGA HPC system

NCC Montenegro successfully submitted the proposal No. EHPC-BEN-2023B12-015 High-Resolution Weather Prediction Model for Montenegro, to the EuroHPC Benchmark Access Call, in cooperation with Institute of Hydrometeorology and Seismology of Montenegro (IHMS) on VEGA CPU for the period 15.01.-15.04.2024. The project aimed to leverage the EuroHPC resources to establish and benchmark precise weather forecast models in the complex topography of Montenegro, utilize these models to refine existing meteorological models, and ultimately enhance the accuracy of weather forecasts, particularly for severe weather events.

Simulations used the Weather Research and Forecasting Non-Hydrostatic Mesoscale Model (WRF-NMM) combining advanced numerical techniques with HPC, for studying atmospheric phenomena with high spatial and temporal resolution and providing accurate and efficient simulations of regional weather patterns. Key activities included installing and fine-tuning the model based on previous verification results, preparing input data, running and fine-tuning the model, and analyzing results in the context of weather prediction and parallel computing performance. WRF model is tested on complex Montenegrin terrain on resolutions 0.5km, 1km, 3km, and 5km. Application scalability was tested on up to 8 nodes, running up to 1024 tasks simultaneously. Simulations were executed for different timespans, but results/overall execution time was scaled to one day period to calculate application speedup and efficiency.

Vega HPC has significantly enhanced research capabilities, allowing to achieve results more quickly and with greater accuracy: scalability was successfully tested on 64-512 CPU cores and the model was successfully downscaled to the resolution of 0.5 km. The final report on granted EUROHPC JU Benchmark Access and effective utilization of the VEGA CPU system assigned is submitted.

International Conference: Global commodity chains from a risk assessment perspective, BfR, May 2024

FoodHub and NCC Montenegro team attended the “International Conference: Global Commodity Chains from a Risk Assessment Perspective” in Berlin, hosted by German federal institute for Risk Assessment BfR. This conference brought together national and international experts in feed and food chains, digitalization, and consumer health protection. It was a fantastic platform to exchange knowledge on innovative techniques and digital solutions for evaluating risks in global commodity chains. The focus was on integrating data and insights about hazards, exposure, and technologies to enhance risk assessment along feed and food chains.

We proudly presented two abstracts in the poster/software session, as part of FoodDecide project:

  • Andrea Milacic, Amil Orahovac, Luka Filipovic, “Optimizing the Montenegrin Milk Supply Chain: A Data Visualization Approach”
  • Luka Filipovic, Andrea Milacic, Amil Orahovac, Aleksandra Martinovic, “HoneyChain: Enhancing Honey Production Monitoring System”

High-Performance Computing: A Powerful Tool for Industry Leaders

You want to optimize your business processes and accelerate innovations?

You need additional computing resources for your R&D&I process?

You need expert support to parallelize or scale your software solutions?

You need access to HPC infrastructure to train AI models?

In the digital era of data explosion, traditional computing methods are struggling to keep pace. High-Performance Computing (HPC) offers powerful solutions, allowing analysis of massive datasets in real-time, running complex simulations, and extraction of valuable insights and actionable results – all within a secure and scalable environment. Big industries and SMEs use HPC systems or Supercomputers to build innovative strategies, techniques, and products.
NCC Montenegro serves as a gateway to European supercomputing expertise and infrastructure and supports researchers, engineers, and entrepreneurs in their HPC and AI needs. NCC experts provide HPC/HPDA/AI technical consultations, training, and support services, adapted to the business environment and industry domains.

NCC Montenegro service portfolio

You will learn about HPC and AI and get ready to use it! Our HPC expert will assist you with your software development or code parallelization and will guide you through the application process to access the European most powerful supercomputers, significantly reducing your workload and work time. NCC services are free of charge, i.e. subsidized by EuroCC program support for innovation, research, and development.

Contact us for a free consultation and discover how HPC can empower your business, competitiveness and innovation!

Scientific paper at the 23rd INFOTEH-JAHORINA conference

A scientific paper “Output Manipulation via LoRA for Generative AI” by I. Culafic et al., was presented at the 23rd International Symposium INFOTEH-JAHORINA, 20-22 March 2024. The training for the prediction models was takin around six hours on an NVIDIA RTX 4090 24GB VRAM GPU. This research will serve as a basis for a future experiments on HPC resources. The paper is published at IEEE Xplore at: https://ieeexplore.ieee.org/document/10495995

ABSTRACT – Generative Artificial Intelligence has witnessed a surge in popularity in recent years, characterized by the emergence of groundbreaking models like DALL-E 2,
Midjourney, and Stable Diffusion, which have spearheaded advancements in this technological domain. This research aims to harness the potential of Stable Diffusion and its extensions for the purpose of training a LoRA (Low-Rank Adaptation) model to
generate images that closely resemble the original subject matter, utilizing a predetermined amount of example data. The primary objective of this research is to demonstrate the prowess of Stable Diffusion and generative AI in a broader context, delving into the possibilities offered by open-source frameworks, highlighting the
challenges associated with poorly organized training data and the advantages of properly organized and edited datasets, conducting a comparative analysis of diverse diffusion models and examining various LoRA strength examples. This research also aims to
compare the results from larger training parameters on both small and relatively large training models for the purpose of determining if overfitting, over training on one specific subject, is more prevalent with smaller or larger datasets.

The 28th international conference of Information Technology 2024 (IEEE IT2024)

In the period from 21st – 24th of February the international scientific and professional conference “INFORMATION TECHNOLOGIES 2024” will traditionally be hosted in Žabljak. These 28th years in a row scientific and professional conference is organized with the aim of a comprehensive and multidisciplinary view of current and development trends in the field of information and communication technologies.

The conference will be held in the organization of the University of Montenegro – Faculty of Electrical Engineering, University of Donja Gorica – Faculty of Information Systems and Technologies, IT Society Montenegro, University of Belgrade – Faculty of Organizational Sciences, Institute of Electrical and Electronics Engineers – IEEE Association and IEEE Section for Serbia and Montenegro, with full support of the company Čikom from Podgorica.

Click to watch the video announcement (in Montenegrin)

The Conference shall host lectures and round table discussions about development trends in the field of information and communication technologies, as well as actual problems in this field in Montenegro. In agreement with the Organizing Committee of the Conference, interested institutions are invited to organize presentations of their scientific, research, professional, development, and production projects and achievements. Besides mentioned above, papers submitted and reviewed will be presented at the Conference.

We invite all those interested to follow the activities at the Conference online as well, through the video conference access links available on the official website

Learn more at the conference website: https://www.it.ac.me/en/

Click on image to open IT2024 conference website

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