NCC Admin, Author at HPC Montenegro

15.06.2023.16.06.2023.

NCC Montenegro participated at “Central European NCCs Workgroup Meeting”

Representatives of NCC Montenegro participated (online) in the “Central European NCCs Workgroup Meeting” organized within the scope of ASHPC23 – Austrian-Slovenian HPC Meeting 2023 (June 13–15, 2023) at the Institute of Information Science in Maribor (IZUM), to actively discuss, exchange experiences and follow up-to-date EuroCC2 and NCCs’ initiatives. Agenda of the NCCs’ meeting covered topics:

NCCs industry’ approach (SMEs engagement, service portfolio, infrastructure access, expected outcomes etc.),

EuroCC2 training activities (training formats, joint training events, regional collaboration, collaboration with CoEs and EDIHs, targeting SME audience etc.)

NCCs communication and disseminations tools (networking events organization, effective communication channels, choosing subjects & speakers, attracting industry stakeholders etc.)

NCC Austria presented their SMEs/Start-ups boosting initiative “EuroCC Supercomputing accelerator” and training initiative on webinar series assuming NCCs and CoEs shared contribution and collaboration. NCC Slovenia presented “SLING Open Doors Days”, their success story on successfully organized community and networking event.

06.06.2023.07.06.2023.

EuroCC2 Twinning opportunities with NCC Cyprus

Representatives from the NCCs of Montenegro and Cyprus (CaSToRC), held an initial meeting on June 6, 2023, with the primary purpose to explore potential cooperation, knowledge sharing opportunities and best practice exchange through effective peer’s cooperation and Twinning activities.

During the meeting, the NCCs’ teams expressed mutual interest in exchanging experiences and learning opportunities, particularly in the areas of productive industrial cooperation and HPC/AI related training activities. Additionally, they discussed the exchange of operational practices and proven initiatives related to NCC management, cooperation and communication activities.

The next steps involve organizing administrative, logistic and operational support to facilitate team visits and work program with shared topics’ interest. By leveraging NCCs’ respective expertise and synergizing their efforts, both NCCs aim to strengthen their capacities and effectively address HPC+ needs/potential in their national ecosystems.

31.05.2023.07.06.2023.

EuroCC presentation to FoodDecide partners

Representatives from the NCC Montenegro presented project and their activities to FoodDecide project partners from Federal Institute for Risk Assessment (BfR), Kühne Logistics University (KLU) and FoodHub CoE. After successful presentation, they discussed on topics for potential collaboration, especially large language models and other AI algorithms.

24.05.2023.10.10.2023.

EUROCC2 project successfully presented at EDCON Conference 2023

Montenegro welcomed one of the biggest gatherings in the cryptocurrency world and blockchain technologies – EDCON (Community Ethereum Development Conference) bringing founders, developers, researchers, industry leaders, investors and innovators together to discuss the recent developments, emerging trends and overall potential of Etherium-based solutions, blockchain ecosystem, decentralised technologies and digital economy.

During a five-day event, co-organised by UDG, (https://www.edcon.io) visitors from all over the world had an opportunity to listen inspirational speakers, including Ethereum co-founder Vitalik Buterin, to attend panel discussion, interactive workshops and exhibition stands, as well as to experience multiple networking and collaboration opportunities.

NCC team members effectively showcased the EUROCC2 project at the UDG exhibition booth, and also highlighted its significance in the opening speech at the EDCON conference. Multiple high-tech enthusiasts, entrepreneurs and innovative companies’ representatives had an opportunity to understand better how NCC Montenegro, powered by of EUROCC2, brings innovative supercomputing technologies and applications to Montenegro. Visitors were captivated by HPC+ benefits and opportunities, briefly introduced to EuroCC2 project and express further interest in MNE success stories and industry onboarding process.

20.05.2023.24.05.2023.

EuroCC2 gearing up – Meeting with CoE BioExcel

Representatives of NCC Montenegro and NCC Macedonia had a joint introductory meeting organized by – Centre of Excellence for Computational Biomolecular Research from Sweden, on 18th of May 2023. BioExcel has been developing/using state-of-computational and software tools and modelling techniques since 2015, to address some of the biggest scientific challenges in the area of bimolecular research.

Research in the BioExcel focuses on structural and functional studies of the main building blocks of living organisms – proteins, DNA, membranes, solvents and small molecules such as drug components. BioExcel CoE’s activities support researcher work in core disciplines in the computational sciences such as: Integrative structural biology, Biomarkers design, Nanotechnology and materials science, Personalized medicine, Physiology, Neuroinformatics, Multi-scale QM/MM modelling.

BioExcel Ambassadors’ Program was also presented, as an attractive opportunity for the NCCs and local academic or government institutions, working in the field of computational bimolecular modelling and simulations and duly interested in collaborative research, trainings and outreach activities.

In the scope of elaborated CoE-NCC cooperation and joint efforts on HPC use in the respective domains, NCC Montenegro shortly presented its current activities and potentially interested partners in the area of bimolecular research. BioExcel emphasized its widely acknowledged software tools and training events, including its upcoming, annual flagship BioExcel Summer School (September 2023, Sardinia, Italy), which provides a comprehensive combination of lectures and tutorial sessions on bimolecular modelling and simulations, using modern applications and tools including GROMACS, HADDOCK, PMX. Registration and information: https://bioexcel.eu/events/bioexcel-summer-school-on-biomolecular-simulations-2023/

17.02.2023.28.04.2023.

IEEE IT2023: Vision-based Vehicle Speed Estimation Using the YOLO Detector and RNN

Researchers from NCC Montenegro presented a paper at the 27th IEEE Conference on Information Technology IT2023. The paper is titled “Vision-based Vehicle Speed Estimation Using the YOLO Detector and RNN” and authored by Andrija Peruničić, Slobodan Djukanović and Andrej Cvijetić

ABSTRACT : The paper deals with vehicle speed estimation using video data obtained from a single camera. We propose a speed estimation method which uses the YOLO algorithm for vehicle detection and tracking, and a recurrent neural network (RNN) for speed estimation. As input features for speed estimation, we use the position and size of bounding boxes around the vehicles, extracted by the YOLO detector. The proposed method is trained and tested on the recently proposed VS13 dataset. The experimental results show that the box position does not bring any improvement in the speed estimation performance. The proposed RNN-based estimator gives an average error of 4.08 km/h using only the area of bounding box as input feature, which significantly outperforms audio-based approaches on the same dataset.

Link : https://ieeexplore.ieee.org/document/10078639

17.02.2023.28.04.2023.

IEEE IT2023: Deep learning-based vehicle speed estimation using the YOLO detector and 1D-CNN

Researchers from NCC Montenegro presented a paper at the 27th IEEE Conference on Information Technology IT2023. The paper is titled “Deep learning-based vehicle speed estimation using the YOLO detector and 1D-CNN” and authored by Andrej Cvijetić, Slobodan Djukanović and Andrija Peruničić

ABSTRACT : This paper addresses vehicle speed estimation using visual data obtained from a single video camera. The proposed method accurately predicts the speed of a vehicle, using the YOLO algorithm for vehicle detection and tracking, and a one-dimensional convolutional neural network (1D-CNN) for speed estimation. The YOLO algorithm outputs bounding boxes around detected objects in an image, which is, in our case, the vehicle whose speed is to be predicted. As input to our 1D-CNN speed estimation model, we introduce a novel feature based on the change of area of the bounding box around the vehicle. The feature, referred to as the changing bounding box area (CBBA), is obtained by calculating the area of the bounding box, frame-to-frame, as the vehicle approaches the camera. The shape of the CBBA curve remains closely the same for all vehicles, with differences conditioned by the value of the observed vehicle’s speed. The proposed method is trained and tested on the VS13 dataset. Experiments show that it is able to accurately predict the vehicle’s speed with an average error of 2.76 km/h, with the best performing vehicle having the average error of just 1.31 km/h. The proposed method exhibits the robustness as a key advantage, eliminating the need for prior knowledge of real-world dimensions such as the vehicle size, road width, camera distance and angle in relation to the road etc.

Link : https://ieeexplore.ieee.org/document/10078518