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”
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.
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
A resarch paper on forecasting meningitis with machine learning written by B. Dobardzic, A. Alibasic, N. Milosevic, B. Malisic and M. Vukotic just appeared in the 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 Healthcareat the following link.
Abstract – Meningitis is a life-threatening disease that can lead to severe neurological damage and death if not diagnosed and treated in a timely manner. In this study, the application of machine learning methods to create a predictive model for meningitis diagnosis based on clinical signs, blood, protein, and other health parameters is explored. Our goal is to determine the most reliable and accurate method of meningitis prediction. We analyze a sizable dataset of meningitis patients using cutting-edge classification techniques, such as Support Vector Machines and Random Forest. Findings have shown that machine learning techniques can accurately estimate a patient’s risk of meningitis. The importance of features for meningitis diagnosis is determined by evaluating them, and the effectiveness of various models is also compared.
The thesis underscores the effectiveness of artificial intelligence in combating phishing attacks and underscores the importance of continued research and innovation to safeguard users and their data in the digital realm. Beyond technical aspects, the paper provides a theoretical framework on cyber security, phishing attacks, and the role of artificial intelligence in modern cyber defense. It emphasizes the ongoing need for research and improvement in this area due to the evolving nature of cyber threats. This BSc theis work was done by Mr Ivan Novakovic under the menthorship of prof. Armin Alibasic.
Mr Novakovic defended his BSc thesis on AI in cybersecurity
ABSTRACT – This thesis addresses the critical issue of detecting phishing URLs, a prevalent cyber threat, using advanced artificial intelligence techniques. It examines three models—Logistic Regression, Random Forest, and LightGBM—through rigorous analysis and real data testing to assess their effectiveness in identifying malicious URLs. The results demonstrate that these models, when properly trained and calibrated, can achieve high accuracy in predicting the maliciousness of URLs.
The widespread use of ChatGPT has reshaped the labor market, offering both opportunities and challenges for companies and employees across various industries. This thesis has highlighted that the most positive impacts are likely to be seen in fields like medicine, trade, and education, while sectors such as customer support, media, and administration face significant challenges. ChatGPT should be viewed as a valuable ally for enhancing daily business tasks and boosting productivity. Ths BSc theis was done by Marko Raicevic under the mentorship of prof. Armin Alibasic.
Mr Marko Raicevic defending his BSc thesis on ChatGPT and AI in business
While the current version of this technology excels in certain areas like automation, information processing speed, and knowledge base, it is not poised to replace the majority of employees in the labor market. The future of businesses hinges on how we harness and deploy ChatGPT; it can either be a chance or a threat, depending on our development and utilization of this technology.
ABSTRACT – This thesis examines the groundbreaking impact of OpenAI’s ChatGPT, a revolutionary conversational AI, on the field of natural language processing. ChatGPT’s exceptional performance and capabilities have led to widespread adoption for daily business tasks, setting new trends in the job market. The paper explores ChatGPT’s role in various branches of artificial intelligence and its implications for diverse industries, considering its potential, limitations, and ethical concerns. The research draws on relevant literature to highlight the opportunities and challenges this technology presents. While routine tasks may be automated, ChatGPT is seen as a tool to enhance productivity, emphasizing that workers will not be replaced but augmented by its usage.
Mr Anel Gredic defended his BSc thesis titled “Time series and their application in meteorology” under mentorship of prof. Luka Filipovic. Thesis discusses the significance of time series analysis in meteorology. Time series, which are continuous records of meteorological data like temperature, precipitation, humidity, and wind speed, play a vital role in meteorological science. They are collected by specialized weather stations and satellites and are essential for meteorologists and climate researchers. Time series analysis involves using statistical methods and models to understand the variability of weather conditions over time. It helps identify seasonal patterns, trends, and extreme events, which in turn aids in weather forecasting and climate change monitoring. The application of time series analysis extends beyond meteorology, impacting various aspects of everyday life. This research has profound implications for society and various industries, improving safety, sustainability, and efficiency.
ABSTRACT – Time series are continuous sequences of meteorological data, such as temperature, precipitation, humidity, wind speed, etc., recorded over time at the same location. These data sets are often collected by specialized weather stations and satellites, and are an invaluable resource for meteorologists and climate researchers. Time series analysis is a fundamental component of meteorological science. Through the use of statistical methods, models and techniques, meteorologists can better understand the variability of weather conditions over time. This analysis enables the identification of seasonal patterns, trends and extreme events. It also helps develop models for weather forecasting and climate change monitoring. The application of time series extends to various aspects of our everyday life. Analysis of time series and their application in meteorology are crucial for understanding and predicting weather phenomena, climate change and protection against extreme weather events. This research has a profound and far-reaching impact on our society and various industries, contributing to the improvement of safety, sustainability and efficiency.
