NEWS

M4D will actively participate to the Artificial Intelligence for Big Satellite Data workshop (Feb 25, 2021) with Dr. Stefanos Vrochidis giving a talk on “Multimodal fusion of EO and non-EO data for Big Data analytics” presenting the research of the group relevant to Artificial Intelligence and Earth Observation. Six leading Greek research institutions (including ITI-CERTH) join forces to showcase how Artificial Intelligence can unlock the potential of Big Earth Observation Data for socio-environmental good in AI4EO workshop on February 25th, 2021. Join us on our Workshop on AI for EO (25th of February 9:00-12:45 CET) to learn about: The main research trends and challenges in AI4EO, proposed by excellent European scientists The leading role of the Greek research community in addressing scientific questions with direct socio-environmental implications How Artificial Intelligence…

M4D/MKLab of the Information Technologies Institute of CERTH is contributing to the research and development of novel AI technologies for health as part of the consortium of ALAMEDA under the European’s Research and Innovation Programme Horizon 2020. ALAMEDA’s vision is to research and prototype the next generation of personalized AI healthcare support systems for people with brain diseases and disorders, specifically focusing on the needs of patients with Parkinson’s, Multiple Sclerosis and Stroke (PMSS). The project’s innovations will take advantage of new machine learning models, built upon lifestyle retrospective data as well as new streams of patient data that involve the monitoring of everyday activities, such as sleep behaviour and emotional status. M4D/MKLab will coordinate activities relevant to Artificial Intelligence approaches, aiming the reinvention of the modern healthcare in order…

M4D/MKLab of ITI-CERTH is delighted to participate in the newly launched, EU-funded H2020 project CALLISTO - “Copernicus Artificial Intelligence (AI) Services and data fusion with other distributed data sources and processing at the edge to support DIAS and HPC infrastructures”. M4D/MKLab has a significant role in CALLISTO, being the scientific and technical coordinator, as well as leading one Work Package and several tasks, including social media data collection, change detection on satellite and UAV images, data fusion, and information retrieval. The EU-funded H2020 project CALLISTO aims to bridge the gap between the DIAS providers and the users of the above-mentioned data through dedicated AI solutions that add value to the large volumes of satellite data frequently coming to Earth from the Copernicus Sentinel constellation. CALLISTO has the ambition to enable…

Journal: Sustainability Deadline: 31 May 2021 This special issue aims to publish high-quality research papers on the inter-disciplinary field of real-time water quality and quantity monitoring, flood mapping and risk assessment, using low-cost sensors, satellite images, UAVs, CCTVs, photonic technologies and community-based in-situ observations from social media and crowdsourcing platforms. Big data analytics aim to extract meaningful insights and patterns from very large and heterogeneous data sources in water resource monitoring. Multimodal data fusion aims to effectively combine data and information from the abovementioned technologies. Semantic technologies may also offer novel mitigation strategies through the enrichment of extracted knowledge, interlinking and reasoning for decision-making. Moreover, model-based and simulation-based approaches can be considered to optimize the operation and reduce the risk of an unforeseen event. Novel methodologies, frameworks and tools should…

M4D/MKLab coordinates the H2020 project i4Q on Industrial Data Services for Quality Control in Smart Manufacturing. The project had its Kick off Meeting on Tue. 19/01/2021 - Wed. 20/01/2021 and it aims at providing the industry with a complete solution that will consist of sustainable IoT-based Reliable Industrial Data Services (RIDS) which will be able to manage huge amounts of industrial data. This data will come from cost-effective, smart, and small-size interconnected factory devices and will be supported by i4Q throughout their complete flow, meaning from data collection to data analysis, simulation and prediction. In this way, the industry can aim towards zero-defect manufacturing and a smart and fully-digitized factory. i4Q involves 24 partners from 11 different European countries that bring to the table various expertise and experience in the…

Aiming to enhance the research activity in the field of oil spill detection, the Multimodal Data Fusion and Analytics Group (M4D) has developed the Oil Spill Detection Dataset, a dataset containing Synthetic Aperture Radar (SAR) images depicting oil spills and other relevant instances. Current dataset is part of our research work presented in the paper entitled as “Oil spill identification from satellite images using deep neural networks” and could be beneficial for remote sensing applications mostly. The dataset is available to the research community through a specific access request  process. Currently, more than 50 institutions and organizations have utilized the Oil Spill Detection Dataset in research projects, which among of them are: Greenpeace UK – Development of an automatic oil spill detection tool based on SAR data with a web…

M4D/MKLAB announces the kick off of PathoCERT project that aims to the timely and precise identification of pathogen contamination events in areas that water is present in order to inform the first responders and warn the public. The project’s main mission is to ensure the quality of surface water. To this end, a unified solution will be adopted that combines (i) Remote sensing techniques applied on Satellite Data (ii) Artificial intelligence technologies paired with UAV material (iii) social media analysis on the most relative tweets (iv) early detection of threats to minimize any potential danger, detect incidents and most important to inform the first responders of any potential contaminations. The contamination of water systems with pathogens is a major public health issue in both developing and developed countries across the…

M4D/MKLAB is happy to announce the kick off of our exciting new project ISOLA aiming at fighting piracy, protect cruise lines on voyage, safeguard on board passengers and ensure that ships are well equipped to handle challenging situations. The project’s main mission is to optimize the security of cruise ships. This will be achieved with the adoption of a holistic solution that combines (i) AI and computer vision (ii) intelligent monitoring (iii) UAVs and chemical detectors  (iv) early detection of threats to minimize any potential danger, detect incidents, abate thefts and episodes due to alcohol or drugs consumption and last but not least effectively mitigate cyber security dangers. Cruise ships today can carry more than 5500 passengers and 2200 crew members for an average time of seven days per trip…

  A joint exercise will be supported by Fraunhofer IAIS (BETTER project) and M4D/MKLab ITI-CERTH (EOPEN project) in the final BETTER Hackathon. This step-by-step exercise will involve the conversion of Tweets to RDF for ingestion by SANSA for semantic geo-clustering and visualization. We invite students, software developers, data scientists, EO-developers, or anyone with interest in EO and semantic interoperability topics to participate. Date & Time:  29 October 1:30pm – 5:30pm CET Register for this exercise here

  M4D/MKLab in cooperation with the Alto Adriatico Water Authority (AAWA) is organizing the Flood-related Multimedia task at the MediaEval Multimedia Evaluation benchmark, an initiative that is dedicated to evaluating new algorithms for multimedia access and retrieval. The task requires participants to build an information retrieval system or a classifier that is able to distinguish whether or not a tweet is relevant to a flooding event in an area of interest, in order to support flood disaster management. Participants can tackle the challenge using text features, image features, or a combination of both. The dataset of the task, collected and annotated in the frame of H2020 beAWARE, H2020 EOPEN and H2020 aqua3S projects, consists of Italian-language tweets, motivated by the common flood events in the cities of the Eastern Alps partition in North-East Italy. Find…

  M4D/MKLab participates and contributes actively in the Security Research Rapid Response Platform (sec3r.com) and the efforts to combat COVID19 by developing a web-based application to monitor, analyse and visualise social media posts related to the Coronavirus pandemic. The Social Media Visualisation Tool (beaware-server.mklab.iti.gr:3000) collects tweets with the hashtags #covid19Italy and #covid19italia, focusing on the region of Italy. The advanced analytical processes enable to geo-localise the captured tweets, extract the visual content from their images as well as estimate their severity. The outcomes of the analysis are propagated and visualised to a user-friendly and interactive interface facilitating civil protection authorities and other stakeholders from the health sector to monitor and extract valuable and actionable information concerning the evolution of COVID19 outbreak. This in-house application is motivated by the basic ideas and aspects of various EU funded…

  We are proud to announce that our team, consisted of S. Andreadis, M. Mpakratsas, A. Moumtzidou, I. Gialampoukidis, S. Vrochidis and I. Kompatsiaris, has succeeded to place second out of thirteen teams in the first Copernicus Thessaloniki Hackathon! The hackathon was organized by Draxis environmental company and was held in Thessaloniki, Greece from 29/11 till 01/12/2019. Using the motto "Sustainable solutions for a sustainable way of living", the Copernicus Thessaloniki Hackathon invited participants to think and build a prototype using Space Data & Earth Observation Services. The MKLab team proposed a decision support system, named "Sack of Sand", which monitors floods by analysing satellite images and social media data. The idea, which was praised for its clear concept, and the live demonstration of a Web application developed during the Hackathon…