During three-week stay at the University of Barcelona, he worked on establishing cooperation and networking with a team of researchers. He presented his work and doctoral research at their weekly seminars, as well as participation in lectures and seminars on artificial intelligence. A particularly important aspect of his stay was working at the Barcelona Supercomputing Center, where Stevan acquired new skills and met another group of researchers. This stay advanced Stevan’s research abilities and also opened new opportunities for cooperation and knowledge exchange in the field of artificial intelligence. His mentor during this stay was Petia Radeva, from Department of Mathematics and Computer Science. Mobility was funded by Ministry of Science and Technology of Montenegro.
Stevan Cakic at the Department of Mathematics and Computer Science (UB)Stevan presented his PhD research
At the University of Donja Gorica, the Faculty of Information Systems and Technologies has commenced the implementation of the project “Application of Computer Vision and Deep Learning in Agriculture and Food Production, Medicine, and Energy (AI4S3).” The project is funded within the program to promote the development of an innovation culture and organize education in the fields of smart specialization in Montenegro by the Innovation Fund (https://fondzainovacije.me/).
The implementation of AI4S3 has started
On September 28th, as part of the 9th Festival of Science and Innovation, we had the opportunity to present our plans for the project’s implementation. The key idea of the project is to bring the application of artificial intelligence closer to the S3 sectors, which represent one of the key strategies for digitization in agriculture and supply chain, medicine, tourism, and energy sectors.
Over 65 candidates applied for the training
As previously announced, on September 30th, we organized an entrance test and questionnaire for all applicants. More than 65 candidates took the entrance test and questionnaire, and after analyzing the results, we selected more than 40 of them who will undergo training over the next 2 months.
The training is supported by the Innovation fund of Montenegro
Additionally, on October 7th, we began conducting lectures, starting with Python programming language, which forms the foundation for further training and the development of artificial intelligence models through upcoming modules. This training is a continuation of previous NCC Montenegro and Open Mind Academy efforts. HPC4S3 researchers are providing are taking an active role in the implementation of the training.
Congratulations to everyone, and we look forward to collaborating with all our participants.
After the physical installaion, we performed system software installation including operating system (Oracle Linux 9) and hardware drivers for GPUs (nVidia T4). This was the next stage of the in-house lab equipment validation. Young researchers have got their user accounts and they can start migrating their projects from their local setups (laptops, Google Colab) and rented HPC resources.
Rack cabinet cotaining computing nodes and UPS
Installation of the operatying system and hardware drivers
Ms Tamara Pavlovic presented research paper “Forecasting Icterus with Machine Learning: An Advanced Classification Model Analysis” on a joint event CMBEBIH & MEDICON 2023 which held place in Sarajevo, Bosnia and Herzegovina from September 14th to September 16th. The study utilized multiple Machine Learning classification models to predict icterus type on a custom dataset and demonstrated the models’ performances in estimating icterus type. The authors are Ms Tamara Pavlovic (MSc candidate), Mr Marko Grebovic (PhD candidate), dr Armin Alibasic, prof. Milica Vukotic, and Mr Stevan Sandi (PhD candidate).
Ms Tamara Pavlovic presented the research paper “Forecasting Icterus with Machine Learning: An Advanced Classification Model Analysis”
ABSTRACT – Icterus is a medical condition characterized by the yellowing of the skin and sclera caused by the accumulation of bilirubin in the body. There are three main types of icterus: extrahepatic, intrahepatic, and prehepatic, and accurately diagnosing the type is crucial for treatment. Machine learning classification techniques can aid in the accurate and timely diagnosis of icterus types. The present study utilized multiple Machine Learning classification models to predict icterus type on a custom dataset and demonstrated the models’ performances in estimating icterus type. The MLP Classifier with five hidden layers achieved the best results. However, the models still struggled to differentiate between instances of extrahepatic and prehepatic types, indicating the need for improvements to enhance the models’ performance.
Ms Zoja Scekic presented the research paper “Thyroid Hormones Parameter-Based Classification of Patient Health Status: An Analysis of Machine Learning Techniques” on a joint event CMBEBIH & MEDICON 2023 which held place in Sarajevo, Bosnia and Herzegovina from September 14th to September 16th. The paper proposes utilization of machine learning (ML) algorithms for disease diagnosis based on patients’ thyroid hormones levels. The authors are Ms Zoja Scekic, dr Luka Filipovic, prof. Ivana Katnic, prof. Nela Milosevic, and Mr Stevan Sandi.
Results of several ML models
ABSTRACT – Thyroid autoimmune diseases are widely spread and present in the world population. The problem with these diseases is that giving the diagnosis is often challenging, as the symptoms are similar with some other health problems (for example, depression). This paper proposes utilization of machine learning (ML) algorithms for disease diagnosis based on patients’ thyroid hormones levels. The experiment was done on a dataset that consisting of 2000 data samples with following parameters: TSH, FT4, TT3, SHBG, and T total hormones. Dataset was prepared before feeding into machine learning models. ML algorithms used in the experiment were Logistic Regression, Random Forest Classifier, Naive Bayes, and Support Vector Machines (SVM). For evaluation, multiple metrics were used: confusion matrix, precision, recall, and accuracy. The whole process could be more efficient and accurate with use of good quality artificial intelligence systems as help in making a better diagnosis.
Mr Ivan Jovovic presented his research paper “Liver Diseases Classification Using Machine Learning Algorithms” on a joint event CMBEBIH & MEDICON 2023 which held place in Sarajevo, Bosnia and Herzegovina from September 14th to September 16th. The research aims to show how Artificial Intelligence (AI) can help predict liver diseases based on the patient’s parameters.
Mr Ivan Jovovic presented the research paper “Liver Diseases Classification Using Machine Learning Algorithms”
ABSTRACT – This study aims to show how Artificial Intelligence (AI) can help predict liver diseases based on the patient’s parameters. The focus is to provide a reliable and accurate tool to support healthcare professionals in decision making process. Alongside dataset preparation and feature engineering, three well known machine learning algorithms (ML) were used to achieve this goal: Support Vector Machine (SVM), Random Forest (RF), and XGBoost (XGB), alongside with simple Artificial Neural Network (ANN). The best-performing model was SVM, with an average precision of 88%, outcome that is comparable to the accuracy obtained in the studies analyzed in this paper, but with a slightly different approach, especially in dataset preparation.
Mr Dejan Babic presented the research paper “Ten Year Cardiovascular Risk Estimation: A Machine Learning Approach” on a joint event CMBEBIH & MEDICON 2023 which held place in Sarajevo, Bosnia and Herzegovina from September 14th to September 16th. The paper presented a comprehensive analysis of the use of Machine Learning and Artificial Intelligence techniques in the sense of predicting the risk, and therefore evaluate their potential in identifying patients with possibilities of developing cardiovascular disease.
Mr Dejan Babic presented his research paper “Ten Year Cardiovascular Risk Estimation: A Machine Learning Approach” at CMBEBIH&MEDICON 2023
ABSTRACT – Cardiovascular disease is one of the most common causes of death in the world. Usual practice in medicine is estimation of 10 years risk of patients developing cardiovascular disease. This practice enables taking preventive measures such as early medical treatments and lifestyle changes. The key step is to accurately assess the risk where the patients can be treated accordingly. With advancement of Artificial Intelligence and ML in medicine, this study aims to present a comprehensive analysis of the use of these techniques in the sense of predicting the risk, and therefore evaluate their potential in identifying patients with possibilities of developing cardiovascular disease. First, an analysis of the working dataset is provided. Then, various traditional classification models are implemented and trained on the dataset, and their performance is compared. The classifying models used in this research include SVC, KNN etc. The results of this study are presented in systematic comparison, where the performances of all the models are represented with discussion about challenges and possible limitations of the data regarding this particular problem. Normalization and oversampling techniques were used and reduced the overfitting problem.
Faculty of Information Systems and Technologies (UDG), with the support of the Innovation Fund of Montenegro as part of the program to encourage the development of innovation culture and the organization of education in the areas of expertise in Montenegro, organizes a three-month training called “AI4S3 – Application of computer vision and deep learning in agriculture and food production, medicine and energy” which will be held in the period from the beginning of October to the end of December 2023. The HPC4S3ME team members will participate as trainers in this 3-month education project sponsored by the Innovation Fund of Montenegro. More info is available at NCC Monteengro website at the following link.
AI4S3 – Computer vision for applications in S3 monteengro (3-month training)
EuroHPC JU organizes a virtual event “Information Day on AI and Supercomputers. This three-hours virtual event will take place on September 26th, 9:30 – 12:30 CEST. The virtual event will discuss:
how EuroHPC JU supercomputers can be used for AI applications,
the access possibilities to these supercomputers,
the current and upcoming AI related calls and activities,
the support possibilities of EuroCC national competence centres
examples of numerous success stories that used many of the possibilities provided by EuroHPC JU.
Interested participants can register to the event at the following link.
Zoja spent 17 days at Arizona State University as an attendee of the Sustainable and Innovative Solutions Summer program. During the visit, she had the opportunity to participate in classes and learn more about sustainability and innovations, as well as to network with other participants and professors. As additional activities, she visited the Virtual Reality Classroom, Innovation Center, and Downtown Campus. Furthermore, she visited the ASU Decision Theater, which utilizes advanced technology and HPC to aid in collaborative decision-making, research, and visualization. For her final group project, she presented the possibility of the usage of Artificial Intelligence for an improved education system.
