National Competence Centre for High-Performance Computing
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.
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.
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/
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.
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.
Researchers from NCC Montenegro presented a paper at the 27th IEEE Conference on Information Technology IT2023.
The paper is titled “Vehicle Speed Estimation From Audio Signals Using 1D Convolutional Neural Networks” and authored by Ivana Čavor and Slobodan Djukanović.
ABSTRACT : This paper presents an approach to acoustic vehicle speed estimation using audio data obtained from single-sensor measurements. One-dimensional convolutional neural network (1D CNN) is used to estimate the vehicle’s speed directly from raw audio signal. The proposed approach does not require manual feature extraction and can be trained directly on unprocessed time-domain signals. The VS13 dataset, which contains 400 audio-video recordings of 13 different vehicles, is used for training and testing of the proposed model. Two training procedures have been evaluated and tested, one based on determining optimal number of training epochs and the other based on recording model state with minimal validation loss. The experimental results show that the average estimation error on VS13 is 9.50 km/h and 8.88 km/h, respectively.
Researchers from NCC Montenegro presented a paper at the “Special Issue for magazine Technology and health care: official journal of the European Society for Engineering and Medicine”. The paper titled “Verification of temperature, wind and precipitation fields for the high-resolution WRF NMM model over the complex terrain of Montenegro” is written by Zečević Aleksandar, Filipović Luka and Marčev Angel.
ABSTRACT :
BACKGROUND: The necessity of setting up high-resolution models is essential to timely forecast dangerous meteorological phenomena.
OBJECTIVE: This study presents a verification of the numerical Weather Research and Forecasting non-hydrostatic Mesoscale Model (WRF NMM) for weather prediction using the High-Performance Computing (HPC) cluster over the complex relief of Montenegro.
METHODS: Verification was performed comparing WRF NMM predicted values and measured values for temperature, wind and precipitation for six Montenegrin weather stations in a five-year period using statistical parameters. The difficult task of adjusting the model over the complex Montenegrin terrain is caused by a rapid altitude change in in the coastal area, numerous karst fields, basins, river valleys and canyons, large areas of artificial lakes on a relatively small terrain.
RESULTS: Based on the obtained verification results, the results of the model vary during time of day, the season of the year, the altitude of the station for which the model results were verified, as well as the surrounding relief for them. The results show the best performance in the central region and show deviations for some metrological measures in some periods of the year.
CONCLUSION: This study can give recommendations on how to adapt a numerical model to a real situation in order to produce better weather forecast for the public.
Link : https://content.iospress.com/articles/technology-and-health-care/thc229016