{"id":14870,"date":"2024-06-10T15:51:37","date_gmt":"2024-06-10T13:51:37","guid":{"rendered":"https:\/\/www.sling.si\/repository\/"},"modified":"2026-04-01T14:50:08","modified_gmt":"2026-04-01T12:50:08","slug":"repository","status":"publish","type":"page","link":"https:\/\/www.sling.si\/en\/repository\/","title":{"rendered":"Repository"},"content":{"rendered":"
\n
\n
\n \n NCC SLING Success Stories: Gostol\n <\/a>\n
\n

NCC SLING Success Stories: Gostol<\/a><\/h3>\n
<\/i> 384.67 KB <\/i> 20 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

The article presents a case of collaboration between NCC SLING and the company GOSTOL \u2013 GOPAN, a global provider of integrated industrial solutions for medium-sized and large industrial bakeries, including equipment for dough mixing, forming, proofing, baking, and cooling. The result of the collaboration is an interactive table that serves as a dynamic platform for presenting Gostol\u2019s product portfolio in an engaging, intuitive, and informative way. Through interactive 3D models, customers can explore not only detailed technical specifications but also real-time data on economic efficiency.<\/p>\n

With HPC they wanted to achieve the following goals.
\n\u2022 Real-time CFD simulations to prepare visualisations of the airflow and steam distribution within machines, providing deep insights into thermal efficiency and process optimization.
\n\u2022 Interactive exploration of 3D models, allowing users to rotate, zoom, and dissect components to understand design and functionality.
\n\u2022 Access to live sensor data and performance analytics, including current readings from various monitoring systems.<\/p>\n

More examples of successful collaborations between National Competence Centres (NCCs) and Centres of Excellence (CoEs) with companies are presented in the online publication \u201cSuccess Stories 2025<\/a>\u201d.<\/p>\n

Download the entire article<\/p>\n

\"Download<\/a><\/p>\n

Authors: NCC SLING and GOSTOL \u2013 GOPAN<\/p>\n\n

<\/i> 1. April 2026 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n NCC SLING Success Stories: A Case of Collaboration with the R&D Company PRIOT Digital\n <\/a>\n
\n

NCC SLING Success Stories: A Case of Collaboration with the R&D Company PRIOT Digital<\/a><\/h3>\n
<\/i> 611.40 KB <\/i> 30 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

The article describes a case of collaboration between NCC SLING and the company PRIOT Digital in the development of a system for the early detection of bark beetle outbreaks using Sentinel-2 satellite data, deep learning, and high-performance computing (HPC). The solution enables faster analysis of large volumes of data and early detection of tree stress, helping forestry services take timely action and reduce economic and ecological damage. PRIOT Digital is a Slovenian research and development company founded in 2019, operating in the fields of Industry 4.0, the Internet of Things (IoT), and remote sensing.<\/p>\n

More examples of successful collaborations between National Competence Centres (NCCs) and Centres of Excellence (CoEs) with companies are presented in the online publication \u201cSuccess Stories 2025<\/a>\u201d.<\/p>\n

Download the entire article<\/p>\n

\"Download<\/a><\/p>\n

Authors: NCC SLING and PRIOT Digital Systems<\/p>\n\n

<\/i> 13. March 2026 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Updates to the ARNES HPC Cluster in 2025 and Plans for 2026\n <\/a>\n
\n

Updates to the ARNES HPC Cluster in 2025 and Plans for 2026<\/a><\/h3>\n
<\/i> 374.44 KB <\/i> 48 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

In 2025, ARNES continued the intensive development and upgrade of its high-performance computing (HPC) infrastructure, further strengthening the capabilities of the national environment for advanced computing. The ARNES computing cluster, in operation since 2009, represents one of the key processing resources for the Slovenian research and education community. With a total computing power of approximately 2.3 petaFLOPS, it is the second most powerful supercomputer in Slovenia and the only one accessible both to beginners and to more advanced users.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: ARNES<\/p>\n\n

<\/i> 12. February 2026 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Using High-Performance Computing for Engineering Innovation: The HPCFS Infrastructure and 2025 Upgrade\n <\/a>\n
\n

Using High-Performance Computing for Engineering Innovation: The HPCFS Infrastructure and 2025 Upgrade<\/a><\/h3>\n
<\/i> 295.15 KB <\/i> 72 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

High Performance Computing has become a key enabler of innovation in modern engineering. At the Faculty of Mechanical Engineering, University of Ljubljana, the HPCFS infrastructure provides researchers and students with the computational power necessary for advanced simulations, modelling, and data analysis. This paper presents the motivation for using HPC in engineering, an overview of the HPCFS system, and the planned 2025 upgrade. The selected projects demonstrate how HPC supports complex analyses ranging from plasma simulations to AI-driven modelling.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Authors: Pavel Tom\u0161i\u010d, Leon Kos, Matja\u017e \u0160ubelj, University of Ljubljana<\/p>\n\n

<\/i> 5. January 2026 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Summer School: Gray\u2013Scott School 2025 \u2013 Revolutions\n <\/a>\n
\n

Summer School: Gray\u2013Scott School 2025 \u2013 Revolutions<\/a><\/h3>\n
<\/i> 320.04 KB <\/i> 91 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

The Gray\u2013Scott School 2025 \u2013 Revolutions offered an intensive introduction to modern high-performance computing, with a focus on optimization, profiling, and software engineering across CPE and GPE architectures. The Slovenian satellite school, hosted at the Faculty of Engineering and on the VEGA supercomputer, provided hands-on exercises and discussions based on the Gray\u2013Scott reaction\u2013diffusion model \u2014 a pedagogical system well suited for parallelization. Participants explored advanced programming in C++, Rust, Fortran, and Python, applying concepts such as vectorization, cache blocking, GPE offloading, and numerical precision. The event exemplified the active role of Slovenian HPC infrastructure and SLING in European HPC education and open science.<\/p>\n

Download the entire article (in Slovenian language):<\/p>\n

\"Download<\/a><\/p>\n

Author: Luka Leskovec, University of Ljubljana<\/p>\n\n

<\/i> 4. December 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Privacy-by-design AIoT vision for intelligent urban environments\n <\/a>\n
\n

Privacy-by-design AIoT vision for intelligent urban environments<\/a><\/h3>\n
<\/i> 0.00 KB <\/i> 2 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

The recent advancements in AI (Artificial Intelligence) have been instrumental in fostering the development of AIoT (Artificial Intelligence of Things)-enabled urban environments. Machine vision and image analysis, in particular, have become integral to a wide array of AI applications within the field of urban planning and monitoring. Yet, the rapid adoption of AI algorithms in public areas has significantly heightened privacy concerns. In this paper, we introduce a privacy-by-design approach tailored for intelligent urban systems, presenting a holistic approach to the development and deployment of AI-driven systems for privacy-preserving image acquisition and analysis. Specifically, we design an embedded vision system that acquires privacy-protected data, safeguarding sensitive information against unauthorized access and potential misuse. Furthermore, we propose a strategy for developing AI vision methods using data that has been anonymized, ensuring that privacy is maintained throughout the AI application building process. Through experiments on a real-world AIoT-enabled urban environment use case - traffic flow monitoring at a city intersection - we demonstrate that our approach upholds strong privacy guarantees while maintaining the operational performance of modern AI vision systems<\/p>\n

Marija Ivanovska, Jakob Kreft, Vitomir \u0160truc, Janez Per\u0161, University of Ljubljana<\/p>\n

Privacy-by-design AIoT vision for intelligent urban environments<\/strong>, Journal of Systems Architecture<\/em>, 2025, 103586, ISSN 1383-7621<\/p>\n

Read the whole article here: https:\/\/doi.org\/10.1016\/j.sysarc.2025.103586<\/a><\/p>\n\n

<\/i> 3. November 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Using Artificial Intelligence to Generate 3D Models\n <\/a>\n
\n

Using Artificial Intelligence to Generate 3D Models<\/a><\/h3>\n
<\/i> 342.85 KB <\/i> 160 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

In recent years, AI has become a driving force of technological progress, transforming the way we create, communicate, and design digital content. Originally known primarily as a tool for generating text, AI algorithms are now expanding into images, videos, and 3D models. AI is reshaping 3D modeling into a faster, more accessible, and more automated process. What was once the exclusive domain of experienced designers using software such as Blender, Maya, or ZBrush is now accessible to those without a technical background. Just a few lines of description are enough for AI to generate a preliminary 3D model. These models form the foundation of modern product development, video games, animations, architectural visualizations, and medical diagnostics. The core idea behind using AI for 3D modeling is simple: The user provides a concept, and the AI turns it into a three-dimensional object. Rather than using complex polygon-by-polygon modeling, one can now use a text description, a sketch, or a reference image. Machine learning algorithms, often powered by deep neural networks, then generate a mesh or voxel-based representation that designers can refine as needed.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Authors: Domen Verber, Jani Dugonik; University of Maribor<\/p>\n\n

<\/i> 8. October 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Classica: The future of AI-assisted cancer surgery\n <\/a>\n
\n

Classica: The future of AI-assisted cancer surgery<\/a><\/h3>\n
<\/i> 297.23 KB <\/i> 152 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

Artificial Intelligence (AI) is becoming an indispensable tool in healthcare, improving diagnostics, treatment planning, and patient outcomes. As AI systems handle sensitive health data and make critical decisions, ethical considerations, including patient privacy, data security, and the transparency of AI decision-making processes, are paramount. The CLASSICA project (Horizon Europe Programme) is at the forefront of integrating AI with medical technology to tackle colorectal cancer, the third most common type of cancer worldwide. CLASSICA transforms a research prototype into a vital tool for surgeons, utilising tissue fluorescence dynamics to effectively distinguish between cancerous and non-cancerous tissues. The technology leverages the differential fluorescence intensity of tissues when exposed to indocyanine green (ICG), a fluorescent dye, and excited by near-infrared (NIR) light. This method captures and analyses the intensity curves from video frames, allowing for real-time AI-based classification of tissues during colorectal cancer surgery.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Authors: Samo Er\u017een, Jernej Cucek, Jan Rojc; Arctur<\/p>\n\n

<\/i> 10. September 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n ARNES Data Center: Connecting Open Science and Supercomputing\n <\/a>\n
\n

ARNES Data Center: Connecting Open Science and Supercomputing<\/a><\/h3>\n
<\/i> 392.23 KB <\/i> 189 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

The ARNES data center will integrate the capabilities of the new Slovenian supercomputer, the Slovenian Artificial Intelligence Factory (SLAIF), permanent storage of research data, and infrastructure to support open science. This strategic investment will establish a central Slovenian hub for open science and supercomputing.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: ARNES<\/p>\n\n

<\/i> 19. August 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n How AI Text Detection Tools Work\n <\/a>\n
\n

How AI Text Detection Tools Work<\/a><\/h3>\n
<\/i> 326.68 KB <\/i> 191 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

In recent years, generative artificial intelligence has transformed the way texts are created. Tools like ChatGPT can now write essays, school papers, advertisements, and even articles like this one in just a few clicks. These tools can mimic different writing styles, draw on massive amounts of data, and sound increasingly \"human.\" However, the rapid development of this technology also raises an important question: Who is the real author of the text we\u2019re reading? In an era when a convincing essay or article can be generated in seconds, the need to verify content authenticity is growing.This has led to the development of detectors, which are tools designed to determine whether a text was written by a human or by AI. Most of these detectors measure perplexity. Large language models produce text that is smooth and orderly, following a kind of statistical logic. In contrast, human writing is often imperfect, riddled with errors, stylistic quirks, and even contradictions.<\/p>\n

Download the entire article (in Slovenian language):<\/p>\n

\"Download<\/a><\/p>\n

Authors: Jani Dugonik, Domen Verber; University of Maribor<\/p>\n\n

<\/i> 16. July 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Slovenian Supercomputing for Artificial Intelligence\n <\/a>\n
\n

Slovenian Supercomputing for Artificial Intelligence<\/a><\/h3>\n
<\/i> 429.86 KB <\/i> 177 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

Technological innovations with flashy names often receive a lot of media attention, but they often amount to nothing more than passing trends. Interest in artificial intelligence, however, will not fade so easily. The rise of generative models\u2014including today's popular large language models, such as Claude and ChatGPT; image models, such as DeepAI and DALL\u00b7E; and lesser-known or proprietary industrial and development-specific models\u2014has firmly placed AI at the core of modern society's developmental, technological, administrative, user interface, and artistic and creative foundations.<\/p>\n

To ensure our researchers and technology developers have access to powerful enough tools to meet the increasingly demanding technological and skill-related challenges brought about by the rise of artificial intelligence, numerous AI factories are being established across the shared European research space. One such AI factory is being developed in Slovenia. The project will include support mechanisms to guide and assist users, as well as educational activities. At its core is the development of a new supercomputer specifically designed for AI tasks.<\/p>\n

Download the entire article (in Slovenian language):<\/p>\n

\"Download<\/a><\/p>\n

Authors: Jan Jona Javor\u0161ek, Florian Klauser; Jo\u017eef Stefan Institute<\/p>\n\n

<\/i> 27. June 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Using ChatGPT as a Coding Assistant\n <\/a>\n
\n

Using ChatGPT as a Coding Assistant<\/a><\/h3>\n
<\/i> 830.83 KB <\/i> 223 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

ChatGPT has become a valuable tool in software development, capable of generating code quickly and providing useful insights. However, directly copying large code snippets into a project without review can introduce unintended bugs, often leading to time-consuming debugging. In some cases, manually writing code from scratch may be more efficient.<\/p>\n

Despite these challenges, there are several scenarios where ChatGPT adds significant value to coding workflows. Below are some practical examples, focusing on Python, though the same concepts can be applied to other programming languages. The goal is not just to solve problems but to demonstrate how to use ChatGPT effectively as a development assistant.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: Mark Balti\u010d; Arctur<\/p>\n\n

<\/i> 27. May 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n When Students Solve Global Challenges with Supercomputers: The Arnes Hackathon 2025\n <\/a>\n
\n

When Students Solve Global Challenges with Supercomputers: The Arnes Hackathon 2025<\/a><\/h3>\n
<\/i> 186.62 KB <\/i> 249 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

This year's Arnes Hackathon 2025 has once again shown that open science and supercomputing are key tools to tackle the challenges of modern society. Under the slogan \u201cFly into the future with open science and supercomputing\u201d, more than a hundred participants from all over Slovenia took part in finding innovative solutions to the challenges set by the HackathON. The Hackathon took place in two rounds with a clear focus on sustainable development, the use of digital twins, and HPC technologies.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: ARNES<\/p>\n\n

<\/i> 24. April 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n The Research Revolution: How Deep Research is Transforming the Future of Search and Discovery\n <\/a>\n
\n

The Research Revolution: How Deep Research is Transforming the Future of Search and Discovery<\/a><\/h3>\n
<\/i> 662.91 KB <\/i> 266 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

The past year has seen the continued rapid advancement of large language models, yet training them has become increasingly complex. Even companies with vast financial and computational resources are encountering significant limitations that slow progress in enhancing these models\u2019 capabilities.<\/p>\n

One notable example is OpenAI\u2019s development of its new Orion model, which has faced several challenges. While Orion has shown some improvements in language tasks, its overall progress\u2014particularly in programming\u2014has been modest compared to the leap from GPT-3 to GPT-4. Testing has revealed that the model struggles to handle coding tasks as efficiently as its predecessor, raising serious concerns within the development team.<\/p>\n

The whole article is available here (in Slovene language only).<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: Jenz Per\u0161; University of Ljubljana<\/p>\n\n

<\/i> 3. March 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Leveraging LLMs for Parametric 3D Modeling\n <\/a>\n
\n

Leveraging LLMs for Parametric 3D Modeling<\/a><\/h3>\n
<\/i> 594.27 KB <\/i> 254 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

Artificial Intelligence (AI) has made rapid progress in recent years, especially in the field of generative and large language models (LLMs). Its growing capabilities are making it increasingly important across various industries, including engineering. To integrate AI into mechanical engineering more effectively, they explored how and where its potential can be best utilized. This study presents a methodology that incorporates AI into computer-aided design (CAD), enabling a simple and efficient conversion of text descriptions into parametric 3D models written in the STEP format.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Authors: Luka Samsa, Nikola Vuka\u0161inovi\u0107, Miha Brojan; University of Ljubljana<\/p>\n

 <\/p>\n

 <\/p>\n\n

<\/i> 25. February 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Scientific Software Challenges in Supercomputing\n <\/a>\n
\n

Scientific Software Challenges in Supercomputing<\/a><\/h3>\n
<\/i> 426.32 KB <\/i> 268 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

To overcome the many problems of compiling software on supercomputers, a few solutions are emerging. The first are package managers like EasyBuild, Spack, Conda, Nix or GuixHPC. At the same time, European projects have been funded over the last few years to help with this problem. It is also worth mentioning containers, which provide users with an isolated environment in which to run their software.<\/p>\n

Download the entire article (in Slovenian language):<\/p>\n

\"Download<\/a><\/p>\n

Author: Alja Prah; Jo\u017eef Stefan Institute<\/p>\n\n

<\/i> 13. January 2025 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Genetic Algoritms Explained\n <\/a>\n
\n

Genetic Algoritms Explained<\/a><\/h3>\n
<\/i> 282.00 KB <\/i> 282 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

Optimization problems are everywhere in today's world. From minimizing costs to maximizing efficiency, the goal is often to find the most effective solution for a given task. These challenges typically involve identifying the maximum and minimum values\u2014such as reducing fuel costs for a transportation company. One of the most powerful and valuable methods for tackling these problems is the use of genetic algorithms, a technique inspired by Darwin's theory of evolution.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: Nejc Ho\u010devar; Arctur<\/p>\n\n

<\/i> 11. December 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Why Containers on HPC\n <\/a>\n
\n

Why Containers on HPC<\/a><\/h3>\n
<\/i> 157.23 KB <\/i> 282 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

Containers in high-performance computing (HPC) offer a flexible and efficient alternative to traditional modular software. Containers permit researchers and engineers to package applications and their dependencies into a single file, thereby ensuring portability, reproducibility and consistent performance across different computing environments.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: Barbara Kra\u0161ovec; Jo\u017eef Stefan Institute<\/p>\n

 <\/p>\n\n

<\/i> 27. November 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Plasma power deposition to first wall of ITER reactor with focus on ray-tracing\n <\/a>\n
\n

Plasma power deposition to first wall of ITER reactor with focus on ray-tracing<\/a><\/h3>\n
<\/i> 498.91 KB <\/i> 354 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

The work by UL focuses on the optimization of ray-tracing techniques, commonly used in simulation of nuclear fusion phenomena, especially estimation of radiation on plasma facing surfaces, signal calculation of diagnostic systems to arrive at synthetic diagnostic signal.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: Matic Brank; University of Ljubljana<\/p>\n

 <\/p>\n

 <\/p>\n\n

<\/i> 9. October 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n How high-performance computing and artificial intelligence are shaping the future of tourism\n <\/a>\n
\n

How high-performance computing and artificial intelligence are shaping the future of tourism<\/a><\/h3>\n
<\/i> 115.10 KB <\/i> 328 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

In recent years, artificial intelligence (AI) has dramatically changed various industries, including tourism. The integration of advanced technologies such as high-performance computing (HPC) and machine learning has enabled tourism companies to improve user experience, optimize processes and adapt marketing strategies.<\/p>\n

The tourism industry faces many challenges that can be addressed by advanced technologies. One of the main problems is processing the huge amounts of data generated by tourism providers such as hotels, airlines and travel agencies. Managing this data requires powerful systems that can analyze and predict customer behavior and optimize operational processes in real time. In addition, the tourism sector faces the need to improve the user experience at all customer touch points, from travel planning to post-service feedback. The key is for companies to understand customer preferences and behavior, which is no easy task in such a dynamic environment.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Authors: Domen Verber, Jani Dugonik; University of Maribor<\/p>\n\n

<\/i> 13. September 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Super-resolution\n <\/a>\n
\n

Super-resolution<\/a><\/h3>\n
<\/i> 1.01 MB <\/i> 387 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

Many breakthroughs in speed and accuracy of single image super-resolution (SISR) have been achieved. One of the biggest challenges is how to recover finer texture details when super-resolution is applied at large upscaling factors. A typical solution to SISR involves using a convolutional neural network (CNN), however new approaches using a generative adversarial network (GAN) are now also popular. The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. In this work, we present an evaluation of SRResNet and SRGAN. SRResNet is a deep residual network and SRGAN is a generative adversarial network for image super-resolution (SR). SRResNet is able to recover reasonable quality photo-realistic textures from heavily downsampled images. SRGAN is capable of inferring photo-realistic natural images with high upscaling factors. This is achieved using a perceptual loss function which consists of an adversarial loss and a content loss. The adversarial loss pushes the solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images. The content loss is motivated by perceptual similarity instead of similarity in pixel space.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: Sebastien Strban; University of Ljubljana<\/p>\n\n

<\/i> 9. August 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n New low-shot object counting methods developed on EuroHPC Vega and the Arnes computing cluster\n <\/a>\n
\n

New low-shot object counting methods developed on EuroHPC Vega and the Arnes computing cluster<\/a><\/h3>\n
<\/i> 636.97 KB <\/i> 346 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

Object counting is crucial in applications ranging from cell growth analysis, to crowd estimation in video surveillance systems, to product counting on production lines. Classical methods are not applicable in these cases because they require large annotated training sets and struggle in dense scenarios. On the other hand, the methods developed at the Visual Cognitive Systems Laboratory at the Faculty of Computer Science and Information Science, University of Ljubljana, develop accurate counting with just a few training examples and represent a methodological leap in computer vision.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Authors: Matej Kristan; University of Ljubljana, Ur\u0161a Vodopivec; ARNES<\/p>\n\n

<\/i> 8. July 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Slovenia Celebrates Over Two Years with Two European Digital Innovation Hubs and a DIH with a Certificate of Excellence\n <\/a>\n
\n

Slovenia Celebrates Over Two Years with Two European Digital Innovation Hubs and a DIH with a Certificate of Excellence<\/a><\/h3>\n
<\/i> 163.25 KB <\/i> 331 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

The digital transformation of organizations represents a necessary process for achieving competitiveness in both the economic and public sectors, thereby contributing to the development of the entire society. To encourage and accelerate this process, the European Commission has adopted two multi-annual work programs for the Digital Europe Program (DIGITAL) to support digital transformation and strengthen cybersecurity.<\/p>\n

In the framework of the call for proposals for European Digital Innovation Hubs (EDIH), published by the European Commission in 2021, two Slovenian candidates were selected, the DIGI-SI consortium and SRC-EDIH, while 4PDIH obtained a Certificate of Excellence.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: University of Maribor<\/p>\n\n

<\/i> 25. June 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Advancing Maritime Design: HPC-Enhanced Hull Optimization in Wave Dynamics\n <\/a>\n
\n

Advancing Maritime Design: HPC-Enhanced Hull Optimization in Wave Dynamics<\/a><\/h3>\n
<\/i> 620.67 KB <\/i> 351 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

Optimizing a container ship's hull for both calm water and added resistance in waves is a complex technical challenge. In calm water, the focus is on reducing resistance to enhance fuel efficiency and speed. This often involves streamlining the hull shape to minimize resistance. However, in wave conditions, additional factors like wave-induced motions, wave reflection and refraction come into play. This demands an iterative approach by employing CFD simulations and HPC resources to balance streamlined shapes for calm water efficiency hull geometry features that reduce added wave resistance.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Author: Arctur<\/p>\n\n

<\/i> 26. May 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Drug discovery with a supercomputer\n <\/a>\n
\n

Drug discovery with a supercomputer<\/a><\/h3>\n
<\/i> 1.33 MB <\/i> 296 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

In the development of new medicinal compounds, research laboratories employ robotic equipment for high-throughput screening (HTS), which enables automated experimental in vitro biological evaluation of various compounds with a capacity of several hundred thousand compounds [1]. With the rapid advancement of computer science, this relatively expensive and complex process is complemented and being replaced by computational tools for molecular modelling.\u00a0 Similar to experiments conducted in vivo<\/em> or in vitro<\/em>, we can also refer to experiments conducted in silico<\/em>, which\u00a0literally\u00a0means in silicon, essentially referring to computer simulation.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Authors: Davor Sluga, Ratko Pilipovi\u0107, Nejc Ilc; University of Ljubljana<\/p>\n\n

<\/i> 27. March 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Upgrade of the Arnes Supercomputer Cluster\n <\/a>\n
\n

Upgrade of the Arnes Supercomputer Cluster<\/a><\/h3>\n
<\/i> 211.62 KB <\/i> 194 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

We have recently upgraded our computing cluster at Arnes, and it is now much more powerful.<\/p>\n

Download the entire article (in Slovene language):<\/p>\n

\"Download<\/a><\/p>\n

Author: ARNES<\/p>\n\n

<\/i> 15. February 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n\n\n
\n
\n
\n \n Heritage+: Digital Innovation of Cultural Heritage\n <\/a>\n
\n

Heritage+: Digital Innovation of Cultural Heritage<\/a><\/h3>\n
<\/i> 0.02 KB <\/i> 295 Downloads<\/div>\n <\/div>\n <\/div>\n <\/div>\n
\n

The main result is 100 digitised units of cultural heritage and 30 5-star tourist products - AR app at the Russian Chapel, re-created world of sunken villages, exploring local stories with the help of a web app, e-Castles digital room, interpretation of 7 castles, Winegrowing and winemaking interpretation, etc.<\/p>\n

Download the entire article:<\/p>\n

\"Download<\/a><\/p>\n

Athor: Arctur<\/p>\n\n

<\/i> 12. January 2024 <\/i> <\/span><\/div>
Download<\/a><\/div>
<\/div><\/div><\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":13,"featured_media":15549,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"footnotes":""},"class_list":["post-14870","page","type-page","status-publish","has-post-thumbnail","hentry"],"acf":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.sling.si\/en\/wp-json\/wp\/v2\/pages\/14870","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.sling.si\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.sling.si\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.sling.si\/en\/wp-json\/wp\/v2\/users\/13"}],"replies":[{"embeddable":true,"href":"https:\/\/www.sling.si\/en\/wp-json\/wp\/v2\/comments?post=14870"}],"version-history":[{"count":37,"href":"https:\/\/www.sling.si\/en\/wp-json\/wp\/v2\/pages\/14870\/revisions"}],"predecessor-version":[{"id":20092,"href":"https:\/\/www.sling.si\/en\/wp-json\/wp\/v2\/pages\/14870\/revisions\/20092"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.sling.si\/en\/wp-json\/wp\/v2\/media\/15549"}],"wp:attachment":[{"href":"https:\/\/www.sling.si\/en\/wp-json\/wp\/v2\/media?parent=14870"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}