Success Stories
Each of the success stories below is a summary of a successful experiment that has been conducted within one of the EuroCC projects and one or more partners from industry, society, and/or science. The summary focuses on the business benefits resulting from the experiment.
-
Intent Classification for Bank Chatbots through LLM Fine-Tuning
Building extraction in GIS (geographic information system) is pivotal for urban planning, environmental studies, and infrastructure management, allowing for accurate mapping of structures, including the detection of illegal constructions for regulatory compliance.
-
Semi-Supervised Learning in Aerial Imagery: Implementing Uni-Match with Frame Field learning for Building Extraction
Building extraction in GIS (geographic information system) is pivotal for urban planning, environmental studies, and infrastructure management, allowing for accurate mapping of structures, including the detection of illegal constructions for regulatory compliance.
-
Mapping Tree Positions and Heights Using PointCloud Data Obtained Using LiDAR Technology
The goal of the collaboration between the Slovak National Supercomputing Centre (NSCC) and the company SKYMOVE within the National Competence Center for HPC project was to design and implement a pilot software solution for processing data obtained using LiDAR (Light Detection and Ranging) technology mounted on drones.
-
Leveraging LLMs for Efficient Religious Text Analysis
The analysis and research of texts with religious themes have historically been the domain of philosophers, theologians, and other social sciences specialists. With the advent of artificial intelligence, such as the large language models (LLMs), this task takes on new dimensions.
-
Named Entity Recognition for Address Extraction in Speech-to-Text Transcriptions Using Synthetic Data
Many businesses spend large amounts of resources for communicating with clients. Usually, the goal is to provide clients with information, but sometimes there is also a need to request specic […]
-
Success Story: Transfer and optimization of CFD calculations workflow in HPC environment
Shark Aero company designs and manufactures ultralight sport aircrafts with two-seat tandem cockpit. For design development they use popular open-source software package openFOAM [1]. The CFD (Computational Fluid Dynamics) simulations […]
-
Success Story: Measurement of microcapsule structural parameters using artificial intelligence (AI) and machine learning (ML)
The main aim of collaboration between the National Competence Centre for HPC (NCC HPC) and the Institute of Polymers of SAV (IP SAV) was design and implementation of a pilot […]
-
Success Story: Anomaly Detection in Time Series Data: Gambling prevention using Deep Learning
Gambling prevention of online casino players is a challenging ambition with positive impacts both on player’s well-being, and for casino providers aiming for responsible gambling. To facilitate this, we propose […]
-
Success Story: Multimodal Prediction of Alexithymia from Physiological and Audio Signals
Alexithymia is a trait that reflects a person’s difficulty in recognizing and expressing their emotions, which has been associated with various forms of mental illness. Identifying alexithymia can have therapeutic, preventive, and diagnostic benefits. However, there has been limited research on proposing predictive models for alexithymia, and literature on multimodal approaches is almost non-existent. Using…
-
Success Story: Enabling HPC Usage for Expensive ML Tasks on Manufacturing Environments
Erste is working on two international manufacturing projects. They require Anomaly Detection and Predictive Maintenance models trained on a huge amount of data. The company is highly fluent in front- and back-end development; the R&D team was developing prediction and classification algorithms to reduce the maintenance cost and downtime of the press machines used…
-
Success Story: Performance Analysis of different biomass boiler designs using CFD tools
Condensing boilers have a higher efficiency than standard boilers as they use the latent energy of water vapor through condensation. One of the challenges for this type of boiler is to reduce the size of the boiler, which would allow it to reach a larger number of buildings and households, as well as reducing material…
-
Success Story: Fast generation of low-discrepancy sequences using accelerators
Computational accelerators offer significant advantages in terms of computational power when compared with regular CPUs. However, when dealing with the problem of fast generation of low-discrepancy sequences using accelerators, one has to take into account that any complex logic operations and branches in the code require significant rewriting of the code and may become a…
-
Success Story: The Estonian COVID-19 Data Portal and KoroGeno-EST
The aim of the KoroGeno-EST study is to sequence (determine the composition of the genome) and analyze the complete genomes of SARS-CoV-2 that have caused and are causing infections in Estonia and to perform a molecular epidemiological analysis on them. Like living organisms in the wild, viruses can be divided into different groups based on…
-
Success Story: PaRI – Nordic Pandemic Research Infrastructure
PaRI brought together the needs, interests and resources to create e-infrastructure to support research excellence in the Nordic region. The scope of the project in spite of its focus on COVID-19 pandemic related research, is significantly wider including preparedness for all pandemic related research in the future. The project activities included genome-wide association studies, drug…
-
Success Story: Anomaly Detection of Noisy Time Series
3B-the fibreglass company is producing different types of fibreglass. The products are wound onto bobbin shapes at a speed of typically 50km/h. The production is to a high degree automatic. One the remaining manual procedures is the detection of breaking fibres during the winding process. The aim of the collaboration was two-fold. The first…
-
Success Story: Improvement of the remote expert system based on software OTEA
New facilities with a growing number of Heating, Ventilation and Air-conditioning (HVAC) machines produce huge amounts of data. Usually, a deterministic system with brute force conditions was applied to detect comfort anomalies in more than 3,000 installations worldwide, with 600,000 variables monitored resulting in 3 trillion records for 5 years. The challenge of this experiment…
-
Success Story: Optimization of the anaerobic digestion process for biogas generation
Anaerobic digestion is the process by which microorganisms degrade organic matter in the absence of oxygen, producing a methane-rich biogas stream that can be used for energy generation. Industrially this process takes place in large full tanks called anaerobic digesters. The main motivation was to prove that an optimal energy balance between energy consumption and…
-
Success Story: Simulation of airflow in concentric chimneys
If a chimney is not properly designed, not enough oxygen will reach the stove and combustion will be inefficient. There are many variables involved in the optimization of the design of a chimney and physical testing is not feasible on the grounds of cost and time. Consequently, it is necessary to use advanced numerical tools…
-
Success Story: HPC-Cloud-based simulation of flange tightening
The challenge of this case study was to simulate and optimize the tightening of flanges. This required the development of a computer model for simulating the tightening process and a front-end application to control the simulations in order to improve the design of the tightening process. Given the complexity of the problem, HPC resources were..
-
Success Story: Expert system for probability and severity of network incidents
The challenge was: – to identify the main meteorological variables that influence incidents in distribution networks. – to develop reliable demand and generation forecasting models. – to develop a system that collects, processes, and integrates the information from the various data sources identified. – to develop incident forecasting algorithms based on historical data Integrate the…
-
Success Story: Rebar cutting optimisation using a cloud computing environment
The challenge faced was to modify a software to run in a HPC-Cloud environment instead of using a local PC. The goal was to reduce the number of computing hours to minutes even for large-scale optimizations. An additional goal was to develop a graphical user interface to guide the optimizations. The modified software would serve…
-
Success Story: Optimal positioning of mini wind turbines
This challenge needs to develop an application that combines GIS (Geographic Information System), NWP (Numerical Weather Prediction), CFD (Computational Fluid Dynamics) and analytical software, NWP (Numerical Weather Prediction), CFD (Computational Fluid Dynamics) and analytical software in a cloud environment. The company needs a cloud environment, to provide detailed information about wind flow in urban environments…
-
Success Story: Deep Code: Deep Learning system for customer characterisation, prediction and decision making in the insurance industry
The challenge is to develop a Deep Learning system for the insurance sector to improve the data analysis needed in the actuarial process. Insurance companies use complex statistical and mathematical models to estimate the different types of risk associated with an insurance policy and therefore to determine the possible premiums, with a whole science behind…
-
Success Story: Smart Test – Failure forecast for zero defects
The aim of this challenge is to predict failures in the electronic board manufacturing chain, based on the patterns and correlations detection between the multiple sensor measurements. These measurements can lead to failures in electrical and functional tests, which can be detected to prevent possible failures in early stages, to correct or rectify the causes…
-
Success Story: Public Transport Analysis on HPC Infrastructure
Parabol has been developing a PT analysis platform (cermoni.app) to analyze the passengers’ boarding data and the vehicles’ GPS location data collected from a PT system. Currently, it performs spatiotemporal processing and analysis on the PT data, around 10M rows per month. Moreover, the PT accessibility analysis should be performed by finding activity regions for…
-
Success Story: Large-Scale Real-Time Image Content Moderation
This project addresses the problem of large-scale real-time image-based content moderation. The system is deployed to a production environment where tens of thousands of users browse the internet daily. The system must be both accurate and run in real-time to meet the business requirements. Moreover, the model size must be small so that multiple copies…
-
Success Story: The multiphysics experiments of the Weather Research and Forecasting Model (WRF) on precipitation patterns of Turkey
The reliable weather research and forecast heavily rely on the choice of the model physics options. There are multiple physics options in the WRF model that should be tested in a combinational manner to improve the forecasts. The weather events are chaotic by nature, and any physic option may be time and domain-specific thus have…
-
Success Story: Simulation-Optimisation of a Patented Design with Parallel Computing on TRUBA cluster – Design-Optimisation of a Disinfection System
Dynamic systems should be optimised using a simulation and optimisation framework to find out design parameters without using a blind-search approach. DSTECH intended to optimise geometrical specifications of a previously patented slot-baffle design for the enhancement of the efficiency of a disinfection contact system. Specifications of the slot-baffle design need to be optimised considering single…
-
Success Story: Improving the Efficiency of the Graphene-Enhanced Polymer Composite Production via Classical Molecular Dynamics
One of the most popular products that Nanografi specializes in is graphene- and graphene oxide-enhanced polymer composites. Their protocol is based on a “synthesize-test-improve” with a lot of the human resources spent in the trial-and-error stages to develop the composite with the best mechanical properties. Since there are a large number of parameters that potentially…
-
Success Story: HPC as Industry Enabler
Considering the wide portfolio of products and services built and developed by Leonardo, HPC has proven to be useful in different scenarios and sectors. Those, HPC has a dual function: on one hand, it provides a large proprietary computing power, by removing limits on the processing power used by the internal algorithms and codes; on…
-
Success Story: The most advanced center of competence aimed at fighting the coronavirus by combining the best supercomputing resources, and AI up to clinical validation.
The E4C project addresses a globally unmet societal and medical need: is there an infrastructure/operating workflow which might help in quickly identifying existing drugs or novel NCE in case of a pandemic outbreak? We think that E4C had a high societal importance, under these premises. The project addressed the issues related to public health…
-
Success Story: Predict the damage to infrastructures caused by storms and map more precisely the risks of claims for insurance
Because of the recurrence of intense weather disturbances in France, Risk Weather Tech has developed, thanks to the Criann’s Myria supercomputer, a vast catalogue of storms physically and statistically plausible. Main objectives: to anticipate potential damage to infrastructures and to map more precisely the risks of claims for insurance…
-
Success Story: Decision support tool combining artificial intelligence and behavioural finance adapted to trading and portfolio management
Horae Technology is an entrepreneurial and independent investment management company, founded in 2021, and approved by the French financial market Authority (AMF). Our mission: Enhance the value of our clients’ savings. Horae Technology addresses both private clients and institutional investors through the mutual fund « Horae Opportunities » and the management of customised mandates. We offer…
-
Success Story: Multi-scale and multiphysics simulation of a dam
CEVAA specialized in acoustics and mechanics, offers its test equipment and its expertise to Industry. Numerical simulation by finite elements is a major tool, with various specialized software and a dedicated team of engineers. In 2021, CEVAA was asked to study the mechanical strength of a dam. With scales ranging from centimeters to several tens…
-
Success Story: AI medical device software to quantify brain damage and clinical prognosis
BrainTale is an innovative company opening a new era in medicine by providing physicians with clinically validated prognostic solutions for the management of brain injured patients through sensitive and reliable measurements of brain white-matter microstructure alterations. Building on more than 15 years in clinical development, BrainTale’s products are developed collaboratively to address medical need and…
-
Success Story: Launch of the vaccination centre
IT4Innovations was invited to participate in the project to build a large-scale vaccination centre in Ostrava. The centre at Černá louka became operational in March 2021. During the planning of the vaccination centre, many different aspects had to be considered, such as personnel, space organisation, number of other stations, etc. The main point was…
-
Success Story: Medical Image Processing as a Service
The main goal of our cooperation with University Hospital Ostrava was to deploy and test a tool providing remote automatic tissue segmentation from patient image data obtained from computed tomography (CT) or magnetic resonance imaging (MRI) on HPC infrastructure at IT4Innovations. The methods used to enable tissue segmentation were based on deep learning (DL). The…
-
Success Story: Machine learning can help with weed detection
The vision of the Ullmanna company is to boost the efficiency and eco-friendliness of farming in conventional, organic, and sustainable farms. Nevertheless, it comes with the complex challenge of growing more organic crops without an enormous increase in the required workforce for weed control. Therefore, the Ullmanna company is developing an agricultural weeding machine that…
-
Success Story: Computational Fluid Dynamics of Selective Catalytic Reaction
The main objective of the proof-of-concept was to determine whether Computational Fluid Dynamics simulations could be used for the fast and efficient description of the catalysis process of the selective catalytic reduction technology (SCR), and therefore can be used as a tool for the design of this technology, which belongs to the group of DeNOx…
-
Success Story: Numerical simulation of exoskeleton
The objective of this proof-of-concept was to demonstrate the use of numerical modelling and simulation in the design process of an innovative UNILEXA exoskeleton for gait assistance designed for people with partial or complete loss of lower limb function…
-
Success Story: Using bulk simulation in the development of a railway freight car
Advanced Engineering carried out a pilot project to simulate the emptying of a newly developed truck; a 103 m³ Tagnpps model designed primarily for grain transport. Because clients expected a guarantee for the time required to empty each wagon during unloading, the development team needed to assure that the designed geometry of the bins and…
-
Success Story: Numerical analysis and assessment of a conceptual dam proposal
SME partner has been developing a small river dam that should meet energy production requirements so as to be a viable option while also integrating into the surrounding environment with minimal disturbance/changes. NCC’s goal in this project was the assessment of the feasibility of such a dam, assessment of potential flooding and overall integration into…
-
Success Story: Software development and comparative assessment
IB-Nujić j.d.o.o. is a specialized office for flow modelling with numerous projects over the past 20 years. The Office has worked on various models for use in water management, including Hydro_AS-2D, Hydro_GS-2D, Hydro_FT-2D, Laser_AS-2D, flow network generator, etc. More than 400 hundred institutions worldwide have successfully implemented the models.
-
Success Story: Francis turbine draft tube modernization
Industrial partner sought a technical solution to improve the efficiency of a hydroelectric power plant with minimal investment / alterations. Although the obvious solution would be to modernize the runner of the turbine, it was questionable whether the long-term gains would justify the expenses. Solution was seen in the modernization of the draft tube which…
-
Success Story: Pipe flow measurements, analysis and analytics
SME partner required help with ultrasonic pipe measurements, general sensing and automation. Therefore, a series of experimental test measurements had to be conducted, obtained experimental data had to be analysed, and subsequently used to improve current systems that integrate different sensing technologies.
-
Success Story: Traffic Events and Alerts: Data Integration and Analytics to Support Managerial Decisions
The considerable technical challenge is to accurately identify, extract, transfer and integrate reliable and fast changing data from traffic events and alerts to be followed by sophisticated and exhaustive analysis (descriptive and predictive). On one hand, the large volumes of data being transferred, the enormous diversity of traffic sensors, events, and alerts to be encompassed…
-
Success Story: Environmental Data – From Transferring and Analytics to Decision Making
Reliable, fast, and accurate transferring of environmental (meteorological) data, followed by its computational analysis (descriptive and predictive), is a considerable technical challenge. On one hand, it is difficult to methodologically organise the large volumes of data being transferred, the enormous diversity of environmental sensors used, and the proliferation of the transmission protocols. On the other…
-
Success Story: Low-latency AI-based gesture recognition HMI running on edge platforms
Implement a low-cost, low-latency, high-accuracy gesture recognition solution that can be deployed on different edge platforms such as the NVIDIA Jetson Nano.
-
Success Story: Supercomputer Applications in Biomedical Engineering
To develop a supercomputer model of the processes of Radio-Frequency (RF) Liver Ablation (a treatment based on RF alternating current flow, delivered by a needle-like probe, that destroys the undesired tumor tissue via heating). Up to O(109) unknowns with respect to space variables and O(104) time steps are needed to resolve the complex geometry…
-
Success Story: Optimizing industrial particle processes through simulation
More particles can only be simulated in shorter time spans by making use of the parallel resources available. For ‘shared memory’ parallelism such as TBB or GP-GPU, the bottleneck for this type of simulation is typically memory bandwidth and memory latency. When switching to an MPI parallel acceleration, across multiple compute nodes, the main challenge…
-
Success Story: Airinnova Successful Prace Type-A Application
Within the proposed project Airinnova will focus on a very high altitude and long endurance solar-electronic aircraft, using the designed models by Conceptual Design Corporate (CRC), simulate the given models, and optimize to find out the best design regarding lift-to-drag ratio. The tasks mainly consist of…
-
Success Story: Successful application of Compular to the FF4EuroHPC program
we are happy to announce the successful application of Compular to the FF4EuroHPC program. Compular is a Swedish SME, based in Gothenburg, that develops cutting-edge analysis tools for molecular dynamics simulations. Compular’s new and innovative technology automatically detects, identifies, and analyses the emergent structures and dynamics within materials that give rise to their technologically relevant…
-
Success Story: Creo Dynamics Successful Application PRACE DECI17
Computational Fluid Dynamics (CFD) study of high-pressure hydrogen (H2). The overall aim of the project is to derive a best practice recommendation for transient CFD simulations of H2 high pressurized tanks. State-of-the-art commercial and open-source CFD software will be used within the project…
-
Success Story: Icarus Simulations AB Accesses EuroHPC JU system Vega
With the support of ENCCS the Swedish SME Icarus Digital Math (http://icarusmath.com, Icarus Simulation AB), a spin-off from KTH, received access to the EuroHPC JU system Vega at Izum, Slovenia. In the project, Icarus aims to focus on development for industrial and commercial applications in the aviation, marine and, automotive industry…
-
Success Story: National Library of Sweden Has Now Access to VEGA
The National Library of Sweden has been awarded development access to the Vega EuroHPC JU system making it the first public administration actor in Sweden to access the system. The successful application was a joint effort between KB expert Dr. Love Börjeson and his group, and ENCCS expert Dr. Hossein Ehteshami…
-
Success Story: Drug Research and HPC. Moroxite AB & Forcelab AB Access VEGA System
It is thrilling to announce that Moroxite AB (https://moroxite.net/) and Forcelab AB (www.force-lab.eu) have been awarded EuroHPC Joint Undertaking development-type access allocation on the VEGA petascale supercomputer hosted at the Institute for Information Science (IZUM) in Maribor, Slovenia. The application process benefitted from input by dr. Roberto Di Remigio, research software engineer at ENCCS…
-
Success Story: RISE Accesses VEGA
RISE NLU Group will train English BERT model using multiple GPUs on the EuroHPC JU system Vega. With the help of ENCCS, Evangelia Gogoulou from RISE NLU Group, Digital Systems got access to the EuroHPC JU system Vega at Izum, Slovenia. She will be training from scratch an English BERT model using multiple GPUs and…
-
Success Story: Thermo-Calc Software AB to access VEGA
Thermo-Calc Software AB (TCSAB) has been awarded the development access to EuroHPC JU petascale system Vega at Izum, Slovenia with the help of ENCCS research software engineer Dr. Hossen Ehteshami…
-
Success Story: Traffic Flow and Deep Neural Networks
Most inter-and intra-city transportations occur via vehicles. Managing the traffic caused by such vehicles is of great importance for several primary reasons. Proper traffic control saves plenty of time and resources, assures the safety of drivers and passengers, and last but not least could help mitigate the issue of air pollution…
-
Success Story: Vinnova to Use Vega EuroHPC JU System
Vinnova, Sweden’s innovation agency, has been awarded development access to the Vega EuroHPC JU system. The successful application was a joint effort between Vinnova Data Scientist Dr. Leonora Vesterbacka Olsson and ENCCS…
-
Success Story: Voxo AB SHAPE Access to Improve Swedish Text-to-Speech Algorithms
Voxo AB (https://www.voxo.ai/) is a Stockholm-based startup that specializes in extracting, analysing, and visualising voice data. Their services are used in multiple industries to provide insights and enable data-driven business development.
-
Success Story: Austria, the Czech Republic and Germany introduce EuroCC to the international community
The workshop on High-Performance Computing attracted 60 participants from more than ten countries and facilitated productive networking with the b2b sector. In essence, it became a great platform for promoting the uptake of HPC, explaining the European HPC landscape to the international audience and offering access to the technical know-how available in AT/CZ/DE in particular.
-
Success Story: EnginZyme PRACE DECI17 Access
A EnginZyme project has been allocated 1.2 million core-hours after the PRACE DECI17 call for a molecular dynamics study to evaluate how the wild-type proteins behave in solution, and how different mutations influence the structure and properties of the enzyme. The overall goal is to increase the stability of enzymes in EnginZyme’s cascades for sustainable…
-
Success Story: DigitalSmart and DunavNET to provide AI edge solution for poultry industry, done in context of FF4EuroHPC experiments
DigitalSmart is a coordinator of a new H2020 project: called AIMHiGH that is implemented in the context of HPC Fortissimo project. The title of the project is AI/ML Enabled by HPC for Edge Camera Devices for the Next Generation Hen Farms and it is funded as an application experiment within Horizon 2020 FF4EuroHPC project.