https://spl.ics.forth.gr en-gb Sun, 05 Apr 2026 21:48:42 +0000 Sun, 05 Apr 2026 21:48:42 +0000 Elxis 5.6 240 https://spl.ics.forth.gr/media/images/logo_rss.png https://spl.ics.forth.gr Title: Data Science Mini Symposium Date: 2026-02-27 Time: 09:00 – 17:00 (Athens) Location: Pagiatakis Seminar Room, Forth Main Building 1st floor Hosts: A. Stamatakis, G. Tzagarakis, P. Tsakalides, D. Plexousakis Symposium Agenda We are pleased to invite you to an internal mini-symposium on Data Science, taking place on Friday, February 27 (09:00–17:00) in the Payatakes Seminar Room, at the premises of FORTH. The event aims to bring together researchers to share ongoing work, exchange ideas, and strengthen growing data-science and AI community at FORTH across institutes. We look forward to your participation and to a stimulating day of discussion and collaboration. Format: 10 minutes for respective PIs to provide an overview of activities + 10 to max. 15 minutes for one group member (PhD/PostDoc) to present a project in more detail, i.e., 30 minutes per group including questions. The mini-symposium is supported by the ERA Chair project "Comp-Biodiv-GR" and the Twinning project "TwinODIS". ]]> https://spl.ics.forth.gr/news-announcements/data-science-mini-symposium-forth.html https://spl.ics.forth.gr/news-announcements/data-science-mini-symposium-forth.html Tue, 17 Feb 2026 08:17:00 +0000 https://spl.ics.forth.gr/files/file2.html https://spl.ics.forth.gr/files/file2.html Mon, 19 Jan 2026 11:08:00 +0000 FORTH SmartWater Demo Ready to Transform Water Management? Water is precious but often mismanaged. Traditional systems struggle with leaks and inefficiency. Transforms how you monitor & manage water infrastructure with real-time insights Real-time Real-time data collection & processing addressing network anomalies Plug-and-play Seamless integration with advanced visualization tools (e.g. Grafana) Cost-efficient Cost-efficient communication between sensors/actuators and the central system FORTH SmartWater Video Demo Improved leak detection & water loss prevention reducing unbilled water Enhanced AI-driven decision-making Modular design for optimal adaptation to water utility companies needs Supports both wired and wireless sensors ]]> https://spl.ics.forth.gr/services/forth-smartwater2.html https://spl.ics.forth.gr/services/forth-smartwater2.html Mon, 19 Jan 2026 11:05:00 +0000 TRIERES: Towards the development of a hydRogen valley demonstratIng applications in an intEgRated EcoSystem in Greece Dates: 07/2023 – 04/2028 Funded by: European Commission, Horizon JU Innovation Actions, HORIZON-JTI-CLEANH2-2022-2 PI for FORTH: Georgios Tzagkarakis Funding: total funding: € 10,492,431.25 , FORTH-ICS cost/ funding: € 118,750 Summary: TRIĒRĒS is Greece’s first Hydrogen Valley brings together business, knowledge and regional interests. The TRIĒRĒS Valley starts as a small scale Valley but has a tremendous upward perspective over a large part of the Balkans, South-Eastern Europe and the wider area of Eastern Mediterranean. The Valley will be built around the nucleus of MOH’s Corinth Refinery complex. From a business perspective the project has strong transeuropean interest as 80% of the refinery sales are generated outside of Greece, rendering it internationally oriented by default. Creating and building a Valley using the refinery as Hydrogen generator accelerates the transition, with an annual production of 2,410 tons of Green Hydrogen that will be utilised in the production of low and no Carbon footprint energy and industrial products and will be injected in the natural gas grid creating a Hydrogen Backbone of full EU interest. High visibility actions in mobility will include one (1) short-sea ferry ship, three (3) public transport buses, and at least (two) 2 cars. Knowledge and innovations are spurred through the intensive collaboration with knowledge institutes and SME’s. The participation of the local and regional governments assures the component of public acceptance, understanding and advocacy, generating interest to many parties supporting regional economic growth. The learnings from HEAVENN and WIGA P&G Valleys will be replicated with the specific knowledge of the Greek and broader connected geographies. TRIĒRĒS entails an investment of 115 mil EUR (initially by project partners) up to 408 million EUR (potential direct/indirect leverage of investments). Several thousand people will be employed during the realisation of the valley project, which will promote new skills development. The consortium partners are creating a true new perspective in the region, transitioning from a traditional refinery complex to a state-of-the art future oriented energy and hydrogen ecosystem in the region. Visit Website ]]> https://spl.ics.forth.gr/research/projects/ongoing/trieres.html https://spl.ics.forth.gr/research/projects/ongoing/trieres.html Tue, 09 Sep 2025 17:20:00 +0000 TwinODIS: Twinning for Optimized Decision Intelligence in Data-Intensive Dates: 10/2024 – 09/2027 Funded by: European Commission, Horizon Europe, HORIZON-WIDERA-2023-ACCESS-02 Project Coordinator: Georgios Tzagkarakis (Intistute of Computer Science, FORTH) PI for FORTH: Georgios Tzagkarakis Funding: total Funding: € 1,488,125 , FORTH-ICS cost/ funding € 739,375 Summary: Dynamic decision-making in large-scale uncertain systems poses significant challenges in modern data-rich operational environments. Traditional decision support systems struggle to manage vast and complex datasets in real time, while handling multiple conflicting objectives of high-dimensional problems and ensuring fairness and transparency in decision-making. A fundamentally new perspective is necessary to address these challenges by adopting a holistic, cross-disciplinary approach that bridges the realms of Artificial Intelligence (AI) and Operations Research (OR). This approach will pave the way for the next-generation Decision Intelligence systems, driving sustainable development and economic growth. TwinODIS is a transformative project aimed to revolutionize data-driven large-scale decision optimization through the integration of AI technologies and OR analytical methods. A group of excellence will be established in the emerging field of Large-Scale Decision Intelligence, by twinning the Institute of Computer Science at the Foundation for Research & Technology-Hellas (FORTH, Greece) with two internationally-leading research institutions, namely, the Laboratory of Informatics Paris Descartes, Université Paris Cité (UPC, France) and the Erasmus School of Economics, Erasmus University Rotterdam (EUR, Netherlands). The project leverages comprehensive knowledge transfer, training and networking programmes to elevate FORTH's scientific profile and research capacity, foster an innovation culture to attract industrial investments, engage in competitive EU projects, and enrich the skills ofseniorscientistsin administrative and management aspects, positioning FORTH as a prominent AI-driven Decision Science Hub in Greece and South-Eastern Europe. Visit Website ]]> https://spl.ics.forth.gr/research/projects/ongoing/twinodis.html https://spl.ics.forth.gr/research/projects/ongoing/twinodis.html Tue, 09 Sep 2025 17:02:00 +0000 BrainCode: Brain-inspired Intelligence for Semantic Video Compression Dates: 01/2025 – 12/2027 Funded by: European Commission, Horizon Europe, HORIZON-MSCA-2023-PF-01 Project Coordinator: P. Tsakalides and I. Katsavounidis (Meta) PI for FORTH: E. Doutsi Funding: total cost/funding: € 279,227 Summary: The BrainCode project proposes novel compression techniques for extended reality (XR) data which are energy efficient while ensuring a reconstruction quality that satisfies the human visual semantic perception. There are several challenges concerning the complexity and the power consumption of the latest video compression standards which have not yet taken into account by the signal processing community. We propose that these challenges can be addressed by machine learning based architectures in order to avoid the exhaustive comparisons between sequential frames. We aim at releasing a semantic video compression algorithm that uses Convolutional Neural Networks (CNNs) and drives the bit allocation with respect to the content of the visual scene. Another goal of BrainCode is to mimic the visual system as an intelligent mechanism that processes the visual stimulus. This can be claimed as it consumes low power, it deals with high resolution dynamic signals and the dynamic way it transforms and encodes the visual stimulus is beyond the current compression standards. During the last decades, a lot of effort has been made to understand how the visual system works, what is the structure and role of each layer and individual cell that lies along the visual pathway, and how the huge visual information is propagated and compacted through the nerve cells before it reaches the visual cortex. There are very interesting mathematical models which approximate the neural behaviour and they have been widely used for image processing applications including compression. The BrainCode project searches the latest neuroscience models for the design of a groundbreaking XR video compression architecture. The efficiency of the above approaches is expected to improve several image processing applications like computer vision, virtual reality, and video compression among other, where the real-time processing of the visual scene plays a substantial role. Visit Website ]]> https://spl.ics.forth.gr/research/projects/ongoing/braincode.html https://spl.ics.forth.gr/research/projects/ongoing/braincode.html Tue, 09 Sep 2025 16:53:00 +0000 ARGOS Conceptual Design Study: Designing a next-generation radio facility for multi-messenger astronomy Dates: 01/2023 – 06/2026 Funded by: European Commission, Horizon Europe, HORIZON-INFRA-2022-DEV-01 Project Coordinator: Ioannis Antoniadis (Intistute of Astrophysics, FORTH) PI for FORTH: Stefanos Papadakis Funding: total cost/funding: € 3,000,000 , FORTH-ICS funding: € 737,750. Summary: Astronomy is being transformed by surveys performed with instruments capable of searching the sky for multi-messenger signals with high speed and sensitivity, while delivering science-read datasets to the community. While radio astronomy is not yet fully participating in this revolution, an instrument following the same philosophy that would finally open the dynamic radio sky for exploration is not only urgent but inevitable. ARGOS is a concept TRL2 for a leading-edge, low-cost, sustainable “small-D, big-N” radio interferometer that will realize this ambition, directly addressing multiple fundamental scientific questions, from the nature of dark matter and dark energy to the origin of fast radio bursts. ARGOS Conceptual Design Study: Designing a Next-Generation Radio Facility For Multi-Messenger Astronomy is funded by the European Comission under the HORIZON-INFRA-2022-DEV-01 call Grant Agreement number: 101094354 Visit Website ]]> https://spl.ics.forth.gr/research/projects/ongoing/argos.html https://spl.ics.forth.gr/research/projects/ongoing/argos.html Tue, 09 Sep 2025 16:36:00 +0000 BrainSIM: Brain-like Semantic Video coMpression Dates: 10/2021 – 03/2025 Funded by: 2nd Call for H.F.R.I. Research Projects to support Post-doctoral Researchers PI for FORTH: Effrosyni Doutsi Funding: € 82,080 Summary:The BrainSIM proposes some novel brain-inspired video compression techniques, which are energy efficient while ensuring a reconstruction quality that satisfies the human visual perception. There are several challenges concerning the complexity and the power consumption of the latest video compression standards which have not yet taken into account by the signal processing community. We propose that these challenges can be addressed by artificial intelligence in order to avoid the exhaustive comparisons between sequential frames. We aim to release a semantic video compression algorithm based on Convolutional Neural Networks (CNNs) that detect multiple moving objects in order to do semantic bit-allocation. Another goal is to mimic the visual system as an intelligent mechanism that processes the visual stimulus. This can be claimed as it consumes low power, it deals with high resolution dynamic signals and the dynamic way it transforms and encodes the visual stimulus is beyond the current compression standards. There have been a lot of efforts to understand the structure and functions of the visual system and especially how the huge visual information is propagated and compacted through the nerve cells into a sequence of electrical impulses, called spikes, before it reaches the visual cortex. There are very interesting neuroscience models which approximate the neural behaviour and they have been widely used for image processing applications including compression. The BrainSIM project searches the latest and more efficient neuroscience models to design a groundbreaking video compression architecture that transforms the input signal into spikes. Last but not least, we aim to analyse the spikes using the Recurrence Quantification Analysis; for the analysis of complex dynamic structures. The BrainSIM is expected to improve the performance of the latest stateof- the-art and draw new horizons for image processing community. Visit Website ]]> https://spl.ics.forth.gr/research/projects/completed/brainsim.html https://spl.ics.forth.gr/research/projects/completed/brainsim.html Tue, 09 Sep 2025 16:15:00 +0000 POLAR: Computational Intelligence for Multimodal Astrophysical Tomography Dates: 07/2021 – 12/2024 Funded by: 3rd Call for FORTH Synergy Grants proposals Project Coordinator: Georgios Tzagkarakis (FORTH-ICS) PI for FORTH: Georgios Tzagkarakis Funding: total cost/funding: € 73,600, FORTH-ICS funding: € 50,300. Summary: A detailed mapping of the Galactic magnetic field would revolutionize our understanding for a wide range of astrophysical processes, including star formation, high-energy astrophysics, and cosmology. Typically, our diagnostics of astrophysical magnetic fields are few, hard to obtain, and difficult to process. The main method exploits starlight polarization, induced by the magnetic field that permeates interstellar dust clouds between the stars and the Earth, as a major diagnostic of the Galactic magnetic field properties. The polarization of stars that are distributed at different, but known (thanks to ESA’s Gaia mission) distances along the line of sight, encode information on the 3D geometry of the magnetic field of the Milky Way. The problem is knowing the distance to the stars and their polarization to create a tomographic map of the magnetic field of the Galaxy. A second major problem in such studies is that the observed starlight polarization does not always encode the magnetic field of the Galaxy, but instead, an appreciable fraction of stars emits polarized light themselves. These intrinsic polarizations are a nuisance for Galactic magnetic field studies, but also a real treasure for stellar astrophysics. POLAR aspires to pave the way for the upcoming Big Astrophysical Data era by providing a solid computational intelligence framework for unsupervised (or semi-supervised) multimodal data analysis and learning in astrophysical tomography. Visit Website ]]> https://spl.ics.forth.gr/research/projects/completed/polar-computational-intelligence-for.html https://spl.ics.forth.gr/research/projects/completed/polar-computational-intelligence-for.html Tue, 09 Sep 2025 15:56:00 +0000 We were honored to host Dr. Ioannis Katsavounidis (Meta Platforms, IEEE Distinguished Industry Speaker 2025) at ICS-FORTH for his talk on Video Quality Optimization in Adaptive Streaming. The event saw exceptional participation, with attendees from: Students of all levels of the University of Crete. Members of the FORTH community — including participants from multiple Institutes. Professionals from companies based in the Science & Technology Park of Crete. Download Presentation The talk exceeded the planned two hours, concluding with an extensive and dynamic Q&A session, reflecting the high level of interest and interaction from the audience. A special thank you to Prof. Panagiotis Tsakalides and the SPL team for organizing this inspiring event! ]]> https://spl.ics.forth.gr/news-announcements/ioannis-katsavounidis-meta-platforms.html https://spl.ics.forth.gr/news-announcements/ioannis-katsavounidis-meta-platforms.html Fri, 23 May 2025 12:08:00 +0000