Are you a scientist or developer dealing with HPC applications? Are you interested in developing, optimizing or testing applications on EuroHPC Pre-exascale and/or Petascale systems? Take advantage of the great opportunity to gain access to Pre-exascale or Petascale systems. Applications can be submitted at any time as the call is open continuously.
Access is guaranteed within two weeks of the application deadline (application deadlines are usually set once a month). The evaluation of submitted projects will take place on a fixed date at monthly intervals. The objectives of the individual modes of access within this proposal are:
Benchmark calls are designed for code scalability tests, the outcome of which is to be included in the proposal in a future EuroHPC Extreme Scale and Regular call. Users receive a limited number of node hours; the maximum allocation period is three (3) months.
Development calls are designed for projects focusing on code and algorithm development and optimisation. This can be in the context of research projects from academia or industry, or as part of large public or private funded initiatives as for instance Centres of Excellence or Competence Centres. Users will typically be allocated a small number of node hours; the allocation period is one (1) year and is renewable up to 2 times.
Various systems will be available in each cut-off for the different Benchmark & Development Access modes. The exact amount of available node hours is subject to the EuroHPC systems participating in a given call and will be announced prior to the cut-off dates. For the first cut-off period the VEGA system resources (Slovenia) are available.
Small and medium-sized businesses that do not embrace the digital age will be at a competitive disadvantage to those that do. However, this move into a modern and innovative future also has its challenges. How, then, to protect your business in the digital world and ensure its continuity?
Unfortunately, small and medium-sized businesses in Slovakia and the Czech Republic often do not address the risks associated with their online presence. This opens the door to hacker attacks, which can lead not only to damage to a company's reputation, but also to problems that can ultimately lead to the collapse of the business. And that's certainly something you don't want. Fortunately, there is also someone on the home front who can lend a helping hand.
Cybersecurity without stress – FREE webinar
Qubit Conference® is organizing a FREE webinar called Cybersecurity without stressin cooperation with Edenred Slovakia. The webinar will take place on September 13, 2023 at 2:00 PM. This online webinar is intended for small and medium-sized businesses that want to improve their cybersecurity standards, protect their businesses, and ensure their continuity in the years to come.
The webinar Cybersecurity without stress will provide up-to-date insights from the world of cybersecurity and present effective strategies that can protect businesses from hacker attacks, password breaches, and data leaks. Their subsequent implementation will lead to more efficient and secure business operations, as well as a significant improvement in the company's reputation.
The number of places is limited. So don't hesitate to register for the FREE webinar Cybersecurity without stress todays!
Small and medium-sized businesses are at risk
Až 43% of all cyberattacks are targeted at small and medium-sized businesses. Why are these businesses so vulnerable?
There are several reasons. Hackers target them primarily because they are vulnerable and exploit their cybersecurity ignorance. Such companies often do not have the resources – both financial and human – to pay enough attention to cybersecurity.
Many business owners, especially in Slovakia and the Czech Republic, do not even perceive the threats of cyberattacks. They do not see it as a problem and therefore carelessly neglect cybersecurity. Unfortunately, if a risk does occur, it is usually too late.
Cyberattacks on small and medium-sized businesses often have a fatal impact on their operations and in many cases such companies end up. The result is financial losses, laid-off employees, and in the worst cases even legal problems. However, this can be prevented when you invest time and energy into cybersecurity awareness.
Viruses, stolen passwords, and leaks of sensitive data
Neglecting cybersecurity opens the door to viruses, trojans, stolen passwords, and leaks of sensitive data. In many cases, there is nothing that can be done about it. For example, with ransomware, hackers will encrypt all of your files on your storage device and demand a ransom that often does not even help. This is how many companies have lost all of their data, especially if they did not back it up.
Stolen passwords and leaks of customer data are especially sensitive. These increase customer outrage, damage the company's reputation, and can even lead to legal consequences.
The truth is that the best defense is prevention. And the first step can be the online webinar . Cybersecurity without stressSo don't hesitate, register for FREE and protect your business.
EuroHPC Summit 2025: Three Days Full of Innovation, Discussion, and Inspiration24 Mar-V dňoch 18. – 20. marca sme sa zúčastnili prestížneho EuroHPC Summitu 2025, ktorý sa tento rok konal v Krakove. Počas troch nabitých dní sa na jednom mieste stretli odborníci, výskumníci, inovátori a zástupcovia inštitúcií z celej Európy, aby diskutovali o budúcnosti vysokovýkonného počítania (HPC), umelej inteligencie (AI) a kvantových technológií. Prvý deň bol zameraný na strategické smerovanie európskeho HPC ekosystému. Veľmi zaujímavou bola aj diskusia o tzv. AI Factories – iniciatívach, ktoré majú posilniť európske postavenie v oblasti umelej inteligencie.
Supercomputers and Agriculture: Starting a Partnership with SPU21 Mar-Tento týždeň sme absolvovali pracovné rokovanie na Slovenskej poľnohospodárskej univerzite (SPU) v Nitre, počas ktorého sme spolu s odborníkmi z rôznych oblastí diskutovali o možnostiach spolupráce v oblasti výskumu, inovácií a vzdelávania. Hlavným cieľom stretnutia bolo preskúmať potenciál prepojenia odborných kapacít univerzity s výpočtovým výkonom a expertízou Národného superpočítačového centra (NSCC) a Národného kompetenčého centra pre HPC (NCC pre HPC).
When Energy Meets Supercomputing: Collaboration with IPEEK20 Mar-Dňa 20. marca sme v Nitre rokovali so zástupcami Ipeľského energetického a environmentálneho klastra (IPEEK). Cieľom stretnutia bolo identifikovať možnosti spolupráce pri využití vysokovýkonnej výpočtovej infraštruktúry (HPC) na podporu projektov v oblasti energetiky, obnoviteľných zdrojov a environmentálnych inovácií.
Inno4scale: Innovative Algorithms For Applications On European Exascale Supercomputers
Inno4scale is a European initiative, which was started to support the development of innovative algorithms for exascale supercomputers, so their efficient use can be fully exploited. Currently existing codes for high-performance computing will not be able to function efficiently on upcoming exascale systems in the future. Therefore, the project will identify and support the development of applications that have the potential to fully exploit the new upcoming EuroHPC exascale systems. The most successful application will be taken up by science and industry after the project.
The objective of Inno4scale is to support the EuroHPC Joint Undertaking, whose goal it is to achieve the deployment of Exascale supercomputers in Europe. As part of the project, the development of novel algorithms for applications on upcoming European Exascale supercomputers will be efficiently exploited. Used in public administration or industry these supercomputers will be able to solve previously unaffordable computational challenges. Industry, science, as well as public administration will then be able to reduce their time-to-solution for computational simulations and approach larger problems with novel solutions.
The Inno4scale project started in the beginning of July 2023 and will run for 21 months. Financial support is guaranteed to the project by the use of cascade funding. The project is coordinated by the Barcelona Supercomputing Center. Project partners: SCAPOS, the High-Performance Computing Center of the University of Stuttgart and the PRACE network. A total budget of EUR 4.5 Mio. is available to the project.
You can apply for the Inno4scale Open Call and submit your proposals for the upcoming innovation studies!
After last year's successful event, you can already look forward to the Qubit Conference® Košice 2023
On November 8-9, 2023 in Košice, interesting speakers and panel discussions, sharing of practical experience of professionals in the field of information and cyber security, interactive training and popular networking await you. Come and share valuable knowledge and experience in the area of development, current regulations and trends in IT security and digital transformation, taking into account the key ways of managing organizations.
Do not miss:
Inspirational panel discussions and presentations by leading speakers.
Training for small and medium enterprises.
Networking events.
Tak part at the Qubit Conference® Košice 2023 and don't miss a unique opportunity for education, presentation of your company and establishing new partnership and professional relationships on the Slovak and Czech cybersec market.
The mission of Qubit Conference is to build a professional community of experts in the cybersecurity industry through networking and partnerships through highly professional educational events characterized by a professional approach and a friendly atmosphere.
EuroHPC Summit 2025: Three Days Full of Innovation, Discussion, and Inspiration24 Mar-V dňoch 18. – 20. marca sme sa zúčastnili prestížneho EuroHPC Summitu 2025, ktorý sa tento rok konal v Krakove. Počas troch nabitých dní sa na jednom mieste stretli odborníci, výskumníci, inovátori a zástupcovia inštitúcií z celej Európy, aby diskutovali o budúcnosti vysokovýkonného počítania (HPC), umelej inteligencie (AI) a kvantových technológií. Prvý deň bol zameraný na strategické smerovanie európskeho HPC ekosystému. Veľmi zaujímavou bola aj diskusia o tzv. AI Factories – iniciatívach, ktoré majú posilniť európske postavenie v oblasti umelej inteligencie.
Supercomputers and Agriculture: Starting a Partnership with SPU21 Mar-Tento týždeň sme absolvovali pracovné rokovanie na Slovenskej poľnohospodárskej univerzite (SPU) v Nitre, počas ktorého sme spolu s odborníkmi z rôznych oblastí diskutovali o možnostiach spolupráce v oblasti výskumu, inovácií a vzdelávania. Hlavným cieľom stretnutia bolo preskúmať potenciál prepojenia odborných kapacít univerzity s výpočtovým výkonom a expertízou Národného superpočítačového centra (NSCC) a Národného kompetenčého centra pre HPC (NCC pre HPC).
When Energy Meets Supercomputing: Collaboration with IPEEK20 Mar-Dňa 20. marca sme v Nitre rokovali so zástupcami Ipeľského energetického a environmentálneho klastra (IPEEK). Cieľom stretnutia bolo identifikovať možnosti spolupráce pri využití vysokovýkonnej výpočtovej infraštruktúry (HPC) na podporu projektov v oblasti energetiky, obnoviteľných zdrojov a environmentálnych inovácií.
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 an
unsupervised deep learning method with an objective to identify players showing signs of problem gambling
based on available data in a form of time series. We compare the transformer-based autoencoder architecture for
anomaly detection proposed by us with recurrent neural network and convolutional neural network autoencoder
architectures and highlight its advantages. Due to the fact that the players’ clinical diagnosis was not part of
the data at hand, we evaluated the outcome of our study by analyzing correlation of anomaly scores obtained
from the autoencoder and several proxy indicators associated with the problem gambling reported in the
literature.
illustrative image
Gambling prevention of players with problem
or pathological gambling, currently conceptualized
as a behavioural pattern where individuals
stake an object of value (typically money) on the
uncertain prospect of a larger reward [1], [2], is
of high societal importance. Research over the
past decade has revealed multiple similarities between
pathological gambling and the substance
use disorders [3]. With the high accessibility of
the Internet, the incidence of pathological gambling
has increased. This disorder can result
in significant negative consequences for the affected
individual and his/her family too. Therefore
detecting early warning signs of problem
gambling is crucial for maintaining player’s wellbeing. This work is a joint effort of Slovak National
Competence Center for High-performance
Computing, DOXXbet, ltd. – sports betting
and online casino, and Codium, ltd. – software
developer of the DOXXbet sports betting and
iGaming platform, with the goal to enhance
customer service and players’ engagement
via identification and prevention of gambling
behaviour. This proof of concept is a foundation for future tools, which will help casino mitigate
negative consequences for players, even for a
price of less provision for the provider, as in
line with European trends in risk management
related to problem gambling.
In our study we propose a completely
unsupervised deep learning approach using
transformer-based AE architecture to detect
anomalies in the dataset - players with anomalous
behaviour. The dataset at hand does not
comprehend the clinical diagnosis, and amongst
other proxy indicators mentioned before only
few are available - requests to increase spending
limits, chasing losses by gambling more (referred
to as chasing episodes later in this article), usage
of multiple payment methods, frequent withdrawals
of small amount of money and other
mentioned later in the text. Clearly, not all the
anomalous users must necessarily have problem
gambling, hence the proxy indicators are
used in combination with AE results, namely the
anomaly score. The foundation of our approach
rests on the idea that a compulsive gambler is an
anomaly within the active casino players, with
the literature mentioning their fraction amongst
all players being between 0.5% to 5% for chancebased
games.
Data
The data acquired for this research consist of sequences
of data points collected over time, tracking
multiple aspects of player’s behaviour such
as frequency and timing of their gaming activities,
frequency and amount of cash deposits,
payment methods used when depositing cash,
information about the bets, wins, losses, withdrawals
and requests for change of deposit limit.
Feature engineering resulted in 19 features in
a form of time series (TS), so that each feature consists of multiple time stamps. These features
can be classified into three categories - ”time”,
”money” and ”despair”, as inspired by Seth et
al. [7]. Table 1 summarizes the full set of TS
features with a short explanation.
Each feature is a sequence of N values, where
each value stands for one out of N consecutive
time windows. This value was produced by
aggregating daily data in the respective time
window, with the time window length being
specified in the Table 1 together with the information
about the time window being sliding or
not. Hence, for each sample we needed a history
of N time windows. Feature engineering procedure
is displayed in Figure 1 and the final data
shape is depicted in Figure 2.
Figure 1: Visualization of the data aggregation from daily basis into time windows, and eventually to TS features.
t1, …, t450 represent time stamps for daily data x1, ..., x450. Daily data points from a time window are aggregated into a
single value zi for all i ∈ (1, . . . , 8).1, …, x450. Denné záznamy z časového okna sú agregované do jednej hodnoty zi pre všetky i ∈ (1, . . . , 8).
Figure 2: Final data shape obtained after feature engineering.
Each sample is represented by 19 features consisting
of 8 time windows.
AE models comparison
Autoencoder is a "self-supervised" deep learning method suitable for anomaly detection in the Czech Republic. The idea behind using this type of neural network for anomaly detection is based on the model's reconstruction capability. AE learns to reconstruct the data in the training set and since the training set should ideally only contain "normal" observations, the model learns to reconstruct only such observations correctly. Therefore, when the input observation is anomalous, the trained AE model cannot reconstruct this input sufficiently correctly, resulting in a high reconstruction error. This reconstruction error can be used as an anomaly score for the given observation, where a higher score means a higher probability that the observation deviates from the general trend.
In the study, we trained an AE model based on transformers, where both the encoder and decoder contain a layer called "Multi Head Attention" with four "heads" and 32-dimensional key and value vectors. This layer is followed by a classical neural network with so-called "dropout" layers and residual connections. The entire AE model has just over 100k trainable parameters.
Reconstruction loss and Prediction ability
We performed a 3-fold
cross-validation by splitting the data into training,
validation, and test sets, and trained the
models for each split to assess their stability. Resulting
average loss values and their variances
are displayed in the Table 3. The average reconstruction
error of Transformer model is significantly
lower than all the other models. LSTM B
model comes second in the reconstruction performance
and CNN model seems to have the
worst prediction performance. Generally, the
test loss is observed to be always higher than
train and validation losses. The reason for this
is that those 211 data points that were removed
from the training set in the data cleaning process,
were moved to the test set. Without moving these samples, the test loss for transformer-based
model would be as low as 0.012, for CNN model
0.33, for LSTM A model 0.27, and for LSTM B
model 0.13. More detailed overview of the models’ performance
is displayed on the Figure 6 as histograms
of loss values of the test set. All histograms have
heavy right tail, which is expected for datasets
containing anomalies.
Figure 3: Reconstruction error histograms of the transformer-based AE model for the test set. On the x-axis is the value of the anomaly score and on the y-axis is the frequency of the corresponding value.
To demonstrate the quality of the CR reconstruction, the original (blue line) and predicted (red line) values for a randomly selected anomalous observation of one player are shown in Figure 4. The value of the anomaly score for the respective models is given in the caption of the graphs.
Figure 4: Comparison of the predictive ability of AE models. All models reconstructed the same observation coming from the test set. Predictive ability: the blue line represents the input data, the red reconstruction obtained using the transformer-based AE model. The number shown in the graph header represents the anomaly score for that data sample.
Results
Since clinical diagnosis was not part of the data we had, we can only rely on auxiliary indicators to identify players with potentially problem gambling. We approached this task by detecting anomalies in the data, but we are aware that not all anomalies necessarily indicate a gambling problem. Therefore, we will correlate the results of the AE model with the following auxiliary indicators:
Mean number of logins in a time window.
Mean number of withdrawals in a time window.
Mean number of small and frequent withdrawals
in a time window.
Mean number of requests for the change of
the deposit limit in a time window.
Sum of the chasing episodes in the time slot
of N time window
Figure 5 depicts the correlation of the anomaly
score with the proxy indicators. Each subplot contains 10 bars, each bar representing one
decile of the data samples (i.e. each bar represents
10% of data samples sorted by anomaly
score). The bar colors represent the category
value of the respective proxy indicator.
(a)
(b)
(c)
(d)
(e) Figure 5: Each bar in the graphs represents one decile of the anomaly score (MSE). The colors represent the categories of the relevant auxiliary indicators, with category values specified in the legend.
A distinctive pattern in players’ behavior can
be observed, where players with larger anomaly
scores tend to exhibit high values for all the indicators
evaluated. Higher frequency of logins
is proportionate to higher anomaly score with
more than half of the players in the last decile of
reconstruction error having a mean number of logins
in a time window greater than 50. The same
applies for mean number of cash withdrawals
in a time window. Players with low anomaly
score have almost none or very few withdrawals,
whilst more than one fourth of players in the
last anomaly score decile have two or more withdrawals
in a time window on average. Another
secondary indicator we utilize is the number of
small and frequent withdrawals. Most of the
players with at least one of these events is in
10% of players with the highest MSE. When analyzing
another indicator, namely the number
of requests for a deposit limit change, we observe
a more subtle pattern. It is evident that
players in the first five deciles generally have no
requests for a limit change (with very few exceptions),
while as the anomaly score increases,
the frequency of limit change requests also tends
to rise. The last proxy indicator depicted is the
number of chasing episodes. A rising frequency
of these events proportionate to their anomaly
score can be observed. More than half of the
players in the last decile have at least one chasing
episode in the time window.
If these plots are overlapped in order to identify
the portion of players fulfilling multiple
proxy indicators, following observations result:
in the last five percentiles of the anomaly scores
98.6% of players satisfy at least one proxy indicator,
and 77.3% satisfy at least three indicators.
As for the last two percentiles, so 2% of players
with the highest reconstruction error, almost
90% of them satisfy at least three indicators. The
thresholds used to calculate these proportion are
>= 1 chasing episode, >= 1 limit change, >= 1
small and frequent withdrawal, >= 31 logins
and >= 1.25 withdrawal on average per time
window.
Conclusion
In this work, we successfully applied a
transformer-based autoencoder (AE) to detect
anomalies in the dataset of online casino players.
The aim was to detect problem gamblers
in dataset at hand in an unsupervised manner.
19 features were derived from the raw time series
(TS) data reflecting players’ behavior in the
context of time, money and despair.
We compared the performance of this architecture
with three other AE architectures based on
LSTM and convolutional layers and found that
the transformer-based AE achieved the best results
amongst the four models in terms of reconstruction capability. This model also showcases
high correlation with proxy indicators such as
the number of logins, number of player’s withdrawals,
number of chasing episodes and other,
that are commonly mentioned in literature in relation
to the gambling disorder. This alignment of AE’s anomaly score with proxy indicators
enables us to gain insights into prediction’s effectiveness
in identifying players with potential
problem gambling.
Even though these proxy indicators were also
used as predictors, we suggest to use them as a secondary check when detecting players with potential
problem gambling in order to avoid false
positives, as not all anomalies must be linked to
the condition of gambling disorder.
Our findings demonstrate the potential
of transformer-based AEs for unsupervised
anomaly detection tasks in TS data, particularly
in the context of online casino player behavior.
[1] Alex Blaszczynski and Lia Nower. “A Pathways Model of Problem and Pathological Gambling”. In: Addiction (Abingdon, England) 97 (June 2002), pp. 487–99. doi: 10.1046/j.1360-0443.2002.00015.x.
[2] National Research Council. Pathological Gambling: A Critical Review. Washington, DC: The National Academies Press, 1999. isbn: 978-0-309-06571-9. doi: 10 . 17226 / 6329. url: https ://nap .nationalacademies.org/catalog/6329/pathological – gambling – a – critical -review.
[3] Luke Clark et al. “Pathological Choice: The Neuroscience of Gambling and Gambling Addiction”. In: Journal of Neuroscience 33.45 (2013), pp. 17617–17623. issn: 0270-6474. doi: 0.1523/JNEUROSCI.3231-13.2013.eprint: https : / / www . jneurosci . org /content / 33 / 45 / 17617 . full . pdf. url: https://www.jneurosci.org/content/33/45/17617.
[4] Deepanshi Seth et al. “A Deep Learning Framework for Ensuring Responsible Play in Skill-based Cash Gaming”. In: 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA) (2020), pp. 454–459.
Intent Classification for Bank Chatbots through LLM Fine-Tuning12 Sep-Tento článok hodnotí použitie veľkých jazykových modelov na klasifikáciu intentov v chatbote s preddefinovanými odpoveďami, určenom pre webové stránky bankového sektora. Zameriavame sa na efektivitu modelu SlovakBERT a porovnávame ho s použitím multilingválnych generatívnych modelov, ako sú Llama 8b instruct a Gemma 7b instruct, v ich predtrénovaných aj fine-tunovaných verziách. Výsledky naznačujú, že SlovakBERT dosahuje lepšie výsledky než ostatné modely, a to v presnosti klasifikácie ako aj v miere falošne pozitívnych predikcií.
Leveraging LLMs for Efficient Religious Text Analysis5 Aug-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. These technologies can be leveraged to reveal various insights and nuances contained in religious texts — interpreting their symbolism and uncovering their meanings. This acceleration of the analytical process allows researchers to focus on specific aspects of texts relevant to their studies.
Mapping Tree Positions and Heights Using PointCloud Data Obtained Using LiDAR Technology25 Jul-Cieľom spolupráce medzi Národným superpočítačovým centrom (NSCC) a firmou SKYMOVE, v rámci projektu Národného kompetenčného centra pre HPC, bol návrh a implementácia pilotného softvérového riešenia pre spracovanie dát získaných technológiou LiDAR (Light Detection and Ranging) umiestnených na dronoch.
We are pleased to announce that the Devana supercomputer is now available for your computations and projects. The Computing Centre of the Slovak Academy of Sciences and the National Supercomputing Center have opened the first call for proposals for testing and benchmarking The call is continuously open, the project is possible repeatedly during the year and can be used through the register.nscc.sk .
A comprehensible website with practical instructions and documentation is also available at userdocs.nscc.sk, where you can find information about logging in, projects, SSH keys, software and development equipment, and running computing tasks. Access to Devana is possible through a terminal with a command line, but also through a web interface with the possibility of interactive calculation.
Currently, it is possible to apply for access for testing and benchmarking within a continuously open call s možnosťou využitia získaných údajov (vhodnosť aplikácie, paralelizácia, škálovanie, potrebná veľkosť dátového úložiska a pod.) na podanie žiadosti v pripravovanej výzve pre štandardné projekty.
Scientists and researchers from Slovak public universities and the Slovak Academy of Sciences, as well as from public and state administration organizations and private enterprises registered in the Slovak Republic, can apply for access for testing and benchmarking. Access is provided exclusively for civil and non-commercial open-science research and development. Interested parties from private companies are advised to contact the National Competence Centre for HPC.
We believe that with our professional support, working with Devana will be a benefit for your research and that the new system will allow the realization of many high-quality projects.
EuroHPC Summit 2025: Three Days Full of Innovation, Discussion, and Inspiration24 Mar-V dňoch 18. – 20. marca sme sa zúčastnili prestížneho EuroHPC Summitu 2025, ktorý sa tento rok konal v Krakove. Počas troch nabitých dní sa na jednom mieste stretli odborníci, výskumníci, inovátori a zástupcovia inštitúcií z celej Európy, aby diskutovali o budúcnosti vysokovýkonného počítania (HPC), umelej inteligencie (AI) a kvantových technológií. Prvý deň bol zameraný na strategické smerovanie európskeho HPC ekosystému. Veľmi zaujímavou bola aj diskusia o tzv. AI Factories – iniciatívach, ktoré majú posilniť európske postavenie v oblasti umelej inteligencie.
Supercomputers and Agriculture: Starting a Partnership with SPU21 Mar-Tento týždeň sme absolvovali pracovné rokovanie na Slovenskej poľnohospodárskej univerzite (SPU) v Nitre, počas ktorého sme spolu s odborníkmi z rôznych oblastí diskutovali o možnostiach spolupráce v oblasti výskumu, inovácií a vzdelávania. Hlavným cieľom stretnutia bolo preskúmať potenciál prepojenia odborných kapacít univerzity s výpočtovým výkonom a expertízou Národného superpočítačového centra (NSCC) a Národného kompetenčého centra pre HPC (NCC pre HPC).
When Energy Meets Supercomputing: Collaboration with IPEEK20 Mar-Dňa 20. marca sme v Nitre rokovali so zástupcami Ipeľského energetického a environmentálneho klastra (IPEEK). Cieľom stretnutia bolo identifikovať možnosti spolupráce pri využití vysokovýkonnej výpočtovej infraštruktúry (HPC) na podporu projektov v oblasti energetiky, obnoviteľných zdrojov a environmentálnych inovácií.
Devana: Výzva na podávanie projektov pre testovanie a benchmarking
The Computing Center of the SAS and the National Supercomputing Centre are opening the first call for proposals for testing and benchmarking The call is continuously open, the project is possible repeatedly during the year and can be used through the register.nscc.sk user portal. The testing and benchmarking approach serves primarily to obtain data on application performance parameters, parallelization, utilization, and scaling of data storage size requirements for subsequent standard access requests. However, it can be used for less time- and computationally intensive projects.
Superpočítač Devana
Access is free of charge, provided that all requirements defined in the Terms of reference The application must clearly define the need for use and testing in an HPC environment. Submitted projects are evaluated by the internal team of VS SAV and NSCC.
Call opening date: 19.7.2023
Call closing date: The call is open continuously
Termín pre notifikácie o schválení projektu: Within 2 weeks of project submission.
Eligible Researchers Scientists and researchers from Slovak public universities and the Slovak Academy of Sciences, as well as from public and state administration organizations and private enterprises registered in the Slovak Republic, can apply for access for testing and benchmarking. Access is provided exclusively for civil and non-commercial open-science research and development. Interested parties from private companies are advised to contact the National Competence Centre for HPC.
Allocation period: 4 months
Allocation available per project: 50,000 CPU core-hours and 12,500 GPU core-hours
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 software solution for automatic processing of polymer microcapsules images using artificial intelligence (AI) and machine learning (ML) approach. The microcapsules consist of semi-permeable polymeric membrane which was developed at the IP SAV.
illustrative image
Automatic image processing has several benefits for IP SAV. It will save time since manual measurement of microcapsule structural parameters is time-consuming due to a huge number of images produced during the process. In addition, the automatic image processing will minimize the errors which are inevitably connected with manual measurements. The images from optical microscope obtained with 4.0 zoom usually contain one or more microcapsules, and they represent an input for AI/ML process. On the other hand, the images from optical microscope obtained with 2.5 zoom usually contain (three to seven) microcapsules. Herein, a detection of the particular microcapsule is essential.
The images from optical microscope are processed in two steps. The first one is a localization and detection of the microcapsule, the second one consists of a series of operations leading to obtaining structural parameters of the microcapsules.
Microcapsule detection
YOLOv5 model with pre-trained weights from COCO128 dataset was employed for microcapsule detection. Training set consisted of 96 images, which were manually annotated using graphical image annotation tool LabelImg [3]. Training unit consisted of 300 epochs, images were subdivided into 6 batches per 16 images and the image size was set to 640 pixels. Computational time of one training unit on the NVIDIA GeForce GTX 1650 GPU was approximately 3.5 hours.
The detection using the trained YOLOv5 model is presented in Figure 1. The reliability of the trained model, verified on 12 images, was 96%, with the throughput on the same graphics card being approximately 40 frames per second.
Figure 1: (a) microcapsule image from optical microscope (b) detected microcapsule (c) cropped detected microcapsule for 4.0 zoom, (d) microcapsule image from optical microscope (e) detected microcapsule (f) cropped detected microcapsule for 2.5 zoom.
Measurement of microcapsule structural parameters using AI/ML
The binary masks of inner and outer membrane of the microcapsules are created individually, as an output from the deep-learning neural network of the U-Net architecture [4]. This neural network was developed for image processing in biomedicine applications. The first training set for the U-Net neural network consisted of 140 images obtained from 4.0 zoom with the corresponding masks and the second set consisted of 140 images obtained from 2.5 zoom with the corresponding masks. The training unit consisted of 200 epochs, images were subdivided into 7 batches per 20 images and the image size was set to 1280 pixels (4.0 zoom) or 640 pixels (2.5 zoom). The 10% of the images were used for validation. Reliability of the trained model, verified on 20 images, exceeded 96%. Training process lasted less than 2 hours on the HPC system with IBM Power 7 type nodes, and it had to be repeated several times. Obtained binary masks were subsequently post-processed using fill-holes [5] and watershed [6] operations, to get rid of the unwanted residues. Subsequently, the binary masks were fitted with an ellipse using scikit-image measure library [7]. First and second principal axis of the fitted ellipse are used for the calculation of the microcapsule structural parameters. An example of inner and outer binary masks, and the fitted ellipses is shown in Figure 2.
Structural parameters obtained by our AI/ML approach (denoted as “U-Net“) were compared to the ones obtained by manual measurements performed at the IP SAV. A different model (denoted as “Retinex”) was used as another independent source of reference data. The Retinex approach was implemented by RNDR. Andrej Lúčny, PhD. from the Department of Applied Informatics of the Faculty of Mathematics, Physics and Informatics in Bratislava. This approach is not based on the AI/ML, the ellipse fitting is performed by the aggregation of line elements with low curvature using so-called retinex filler [8]. The Retinex approach is a good reference due to its relatively high precision, but it is not fully automatic, especially for the inner membrane of the microcapsule.
Figure 3 summarizes a comparison between the three approaches (U-Net, Retinex, UP SAV) to obtain the 4.0 zoom microcapsule structural parameters.
(a)
(b)
(c)
Figure 3: (a) microcapsule diameter for different batches (b) difference between the diameters of the fitted ellipse (first principal axis) and microcapsule (c) difference between the diameters of the fitted ellipse (second principal axis) and microcapsule. Red lines in (b) and (c) represents the threshold given by IP SAV. The images were obtained using 4.0 zoom.
All obtained results, except 4 images of batch 194 (ca 1.5%), are within the threshold defined by the IP SAV. As can be seen from Figure 3(a), the microcapsule diameters calculated using U-net and Retinex are in a good agreement to each other. The U-Net model performance can be significantly improved in future, either by the training set expansion or by additional post-processing. The agreement between the manual measurement and the U-Net/Retinex may be further improved by unifying the method of obtaining microcapsule structural parameters from binary masks.
The AI/ML model will be available as a cloud solution on the HPC systems of CSČ SAV. Additional investment into the HPC infrastructure of IP SAV will not be necessary. Production phase, which goes beyond the scope of the pilot solution, accounts for an integration of this approach into the desktop application.
Intent Classification for Bank Chatbots through LLM Fine-Tuning12 Sep-Tento článok hodnotí použitie veľkých jazykových modelov na klasifikáciu intentov v chatbote s preddefinovanými odpoveďami, určenom pre webové stránky bankového sektora. Zameriavame sa na efektivitu modelu SlovakBERT a porovnávame ho s použitím multilingválnych generatívnych modelov, ako sú Llama 8b instruct a Gemma 7b instruct, v ich predtrénovaných aj fine-tunovaných verziách. Výsledky naznačujú, že SlovakBERT dosahuje lepšie výsledky než ostatné modely, a to v presnosti klasifikácie ako aj v miere falošne pozitívnych predikcií.
Leveraging LLMs for Efficient Religious Text Analysis5 Aug-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. These technologies can be leveraged to reveal various insights and nuances contained in religious texts — interpreting their symbolism and uncovering their meanings. This acceleration of the analytical process allows researchers to focus on specific aspects of texts relevant to their studies.
Mapping Tree Positions and Heights Using PointCloud Data Obtained Using LiDAR Technology25 Jul-Cieľom spolupráce medzi Národným superpočítačovým centrom (NSCC) a firmou SKYMOVE, v rámci projektu Národného kompetenčného centra pre HPC, bol návrh a implementácia pilotného softvérového riešenia pre spracovanie dát získaných technológiou LiDAR (Light Detection and Ranging) umiestnených na dronoch.
On June 27, 2023 an event "CHEMSHOW" took place in the premises of the Faculty of Chemical and Food Technology (FCHPT) of the Slovak Technical University (STU). During the event, they also had the opportunity to learn more about the National Competence Centre for HPC and its activities. Experts presented services NCC for HPC. Through an interactive demonstration of simulations of potential drugs against the Covid-19 disease, we brought the participants closer to what calculations supercomputers can be used for. Participants could watch the simulations on a screen and through 3D glasses.
At the chemshow, we presented the results of calculations of the interaction of potential drugs with the active part of the spike-protein unit, which forms tetramers present on the surface of the SARS-CoV2 virus, which causes the disease COVID19. Calculations were carried out using molecular mechanics methods using the GROMACS software. Six potential drugs were tested in the study. In this presentation, we mainly showed the trajectory of one of them. High school students had the opportunity to view the results on a projection with 3D glasses, where they could interactively change their view and protein display settings.
EuroHPC Summit 2025: Three Days Full of Innovation, Discussion, and Inspiration24 Mar-V dňoch 18. – 20. marca sme sa zúčastnili prestížneho EuroHPC Summitu 2025, ktorý sa tento rok konal v Krakove. Počas troch nabitých dní sa na jednom mieste stretli odborníci, výskumníci, inovátori a zástupcovia inštitúcií z celej Európy, aby diskutovali o budúcnosti vysokovýkonného počítania (HPC), umelej inteligencie (AI) a kvantových technológií. Prvý deň bol zameraný na strategické smerovanie európskeho HPC ekosystému. Veľmi zaujímavou bola aj diskusia o tzv. AI Factories – iniciatívach, ktoré majú posilniť európske postavenie v oblasti umelej inteligencie.
Supercomputers and Agriculture: Starting a Partnership with SPU21 Mar-Tento týždeň sme absolvovali pracovné rokovanie na Slovenskej poľnohospodárskej univerzite (SPU) v Nitre, počas ktorého sme spolu s odborníkmi z rôznych oblastí diskutovali o možnostiach spolupráce v oblasti výskumu, inovácií a vzdelávania. Hlavným cieľom stretnutia bolo preskúmať potenciál prepojenia odborných kapacít univerzity s výpočtovým výkonom a expertízou Národného superpočítačového centra (NSCC) a Národného kompetenčého centra pre HPC (NCC pre HPC).
When Energy Meets Supercomputing: Collaboration with IPEEK20 Mar-Dňa 20. marca sme v Nitre rokovali so zástupcami Ipeľského energetického a environmentálneho klastra (IPEEK). Cieľom stretnutia bolo identifikovať možnosti spolupráce pri využití vysokovýkonnej výpočtovej infraštruktúry (HPC) na podporu projektov v oblasti energetiky, obnoviteľných zdrojov a environmentálnych inovácií.
We would like to invite you to the webinar to present the outputs and results through business benefits organisations gained while implementing HPC, AI and other advanced technologies for business in various industrial sectors.
When: 23th of June 2023 from 9:00 to 13:15 CET
Where online
You can find a detailed program and more information HERE.
EuroHPC Summit 2025: Three Days Full of Innovation, Discussion, and Inspiration24 Mar-V dňoch 18. – 20. marca sme sa zúčastnili prestížneho EuroHPC Summitu 2025, ktorý sa tento rok konal v Krakove. Počas troch nabitých dní sa na jednom mieste stretli odborníci, výskumníci, inovátori a zástupcovia inštitúcií z celej Európy, aby diskutovali o budúcnosti vysokovýkonného počítania (HPC), umelej inteligencie (AI) a kvantových technológií. Prvý deň bol zameraný na strategické smerovanie európskeho HPC ekosystému. Veľmi zaujímavou bola aj diskusia o tzv. AI Factories – iniciatívach, ktoré majú posilniť európske postavenie v oblasti umelej inteligencie.
Supercomputers and Agriculture: Starting a Partnership with SPU21 Mar-Tento týždeň sme absolvovali pracovné rokovanie na Slovenskej poľnohospodárskej univerzite (SPU) v Nitre, počas ktorého sme spolu s odborníkmi z rôznych oblastí diskutovali o možnostiach spolupráce v oblasti výskumu, inovácií a vzdelávania. Hlavným cieľom stretnutia bolo preskúmať potenciál prepojenia odborných kapacít univerzity s výpočtovým výkonom a expertízou Národného superpočítačového centra (NSCC) a Národného kompetenčého centra pre HPC (NCC pre HPC).
When Energy Meets Supercomputing: Collaboration with IPEEK20 Mar-Dňa 20. marca sme v Nitre rokovali so zástupcami Ipeľského energetického a environmentálneho klastra (IPEEK). Cieľom stretnutia bolo identifikovať možnosti spolupráce pri využití vysokovýkonnej výpočtovej infraštruktúry (HPC) na podporu projektov v oblasti energetiky, obnoviteľných zdrojov a environmentálnych inovácií.