National Competence Centre for High-Performance Computing
Within the Next Castiel training, a member of NCC Montenegro, Ass. professor Armin Alibasic will take part with the topic, “How to engage younger students, including high schools, on HPC”. Through the training, Armin will bring to the attention of all the methods and techniques used by NCC Montenegro, to bring a topic that was almost unknown to the general public, especially to young people, and develop certain knowledge and skills in them.
HPC NCC Montenegro representatives Luka Filipovic and Sanja Nikolic organized initial meeting with colleagues from NCC Turkey and exchanged experience and learnings on dissemination strategies, industry collaboration and training activities.
Turkish Academic Network and Information Centre (TUBITAK ULAKBIM), as lead beneficiary, is responsible for the management of NCC Turkey. As the Third-Parties of NCC Turkey, Middle East Technical University, Sabancı University, and Istanbul Technical University National Center for High-Performance Computing (UHeM) share their HPC and domain expertise through the dedicated training events, schools, and consultancies.
The NCC has organized wide range of events (>60 events with >11.000 participants) that strengthen the HPC environment by emphasizing the benefits of HPC-related technologies to the private and public sectors (trainings, seminars, webinars, workshops, info days, hackathons, conferences). Training activities and course models are organized in variety of fields like CFD, Parallel Computing with CUDA, SME interaction, Big Data, AI in Medical Image Understanding and Anomaly Detection, Materials Modelling, Graph School.
NCC Montenegro agreed future cooperation in the areas of HPC, HPDA and AI related training courses and industry interaction within EuroCC 2 project scope, with further discussion on research and innovation possibilities.
Researchers from the Institute of Hydrometeorology and Seismology, department for numerical weather analysis and prediction, visited NCC Montenegro and University of Donja Gorica. Mr Angel Marcev and mr Aleksandar Marcev met with our team to discuss the next steps in the collaboration. The discussion was about the results achieved with the simulated weather data prediction models and we made plans for future work based on HPC simulations. We discussed possibilities of usage of weather prediction with higher resolution that could be used for smaller areas for smart agriculture, energy and similar domains and possibilities of machine learning usage on data with meteorological conditions.
How can you show what a Machine Learning model does once it’s trained?
In this talk, you’re going to learn how to create Machine Learning apps and demos using Streamlit and Gradio, Python libraries for this purpose. Additionally, you’ll see how to share them with the rest of the Open Source ecosystem. Learning to create graphic interfaces for models is extremely useful for sharing with other people interesting them. The lecture will take place on 2 November 2022, 18:30h. Expected duration is 1 hour.
For registration please click on the following link.
What is required to follow it?
👉 Basic knowledge of Python
👉 Conceptual knowledge of ML
👉 A google Colab account
👉 A Hugging Face Hub account
Ms Zoja Scekic, a student of the Faculty of Applied Sciences, defended her BSc Thesis in Electrical Engineering and Computer Science. The topic of the thesis work was the use of machine learning to detect and classify the parking spaces by processing images from camera sensors. Such a solution could find application in Smart city solutions. The work focused on the creation of a prediction model as well as validation with images collected at the UDG parking. She has done her thesis work under the supervision of prof. Tomo Popovic, PhD, and mr Stevan Cakic, MSc.
ABSTRACT – Smart city is one area with the growing use of Internet of Things and Artificial Intelligence. The concept of smart cities relies on making quality of life better, and solving important problems, such as global warming, public health, energy and resources. Smart parking management is one of the smart city use cases. This paper describes the use of deep learning algorithms to process images of parking lots and determine their current occupancy. The development of prediction models was done using PKLot dataset with 12417 images, Detectron2 software library, and Faster R-CNN algorithm. The resulting models can be integrated into parking space sensors and used for building smart parking solutions, and thus lead to more efficient use of space in urban areas, reduced traffic congestion, as well as reducing parking surfing to minimum.
FF4EuroHPC Experiment 1003 focused on AI/ML Based Computer Vision for Next Generation Poultry Farms was presented at the OC1 Workshop today. We discussed the project objectives, experiment approach, the benefits of the use of HPC and Deep Learning. Learn more about FF4EuroHPC project and HPC experiments at https://www.ff4eurohpc.eu/.
The fourth workshop took place on October 19th, 2022 and included presentations of the experiments related to Maintenance, Agriculture & Assets Management Sectors. University of Donja Gorica and NCC Montenegro were part of the experiment presentation related to the use of HPC to develop AI/ML computer vision solutions for smart agriculture.
The first tranche of 16 experiments under the FF4EuroHPC Open Call #1 was successfully completed. FF4EuroHPC organized several workshops to present the outputs and results through business benefits organisations gained while implementing HPC, AI and other advanced technologies for business in various sectors.
The fourth workshop will be held on October 19th, 2022 and will present the experiments related to Maintenance, Agriculture & Assets Management Sectors. University of Donja Gorica and NCC Montenegro will be a part of the presentation pertaining to the use of HPC to develop AI/ML computer vision solutions for smart agriculture. More information and the link for registration are available here.
19.10.2022 AGENDA