MKLab

The Lab has extensive experience and expertise in semantic multimedia analysis, indexing and retrieval, social media and big data analytics, knowledge structures, reasoning and personalization for multimedia applications, eHealth and environmental applications

Bridging the gap between Copernicus data providers and end users through Artificial Intelligence solutions

Feb 02, 2021

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”. 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.

Kicking off i4Q - New project to pave the way towards Industry 4.0

Jan 28, 2021

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.

MKLab presents the Oil Spill Detection Dataset to the research community

Jan 15, 2021

(a) Sample of a SAR image and (b) Corresponding annotated image. Cyan color corresponds to oil spills, red to look-alikes, brown to ships, green to land and black is for sea surface. Aiming to enhance the research activity in the field of oil spill detection, the Multimedia Knowledge and Social Media Analytics Laboratory (MKLab) has developed the Oil Spill Detection Dataset, a dataset containing Synthetic Aperture Radar (SAR) images depicting oil spills and other relevant instances.

Resting-State High-Density EEG using EGI GES 300 with 256 Channels of Healthy Elders, People with Subjective and Mild Cognitive Impairment and Alzheimer's Disease

Jan 05, 2021

This repository contains Matlab files including 4 samples of 15 minutes resting-state EEG recording for Alzheimer's Disease (AD), Mild Cognitive Impairment (MCI), Subjective Cognitive Decline (SCD), and Healthy Controls (HC) using the HD-EEG EGI 300 Geodesic EEG system (GES 300, CERTH-ITI, Thessaloniki, Greece) with a 256-channel HydroCel Geodesic Sensor Net (HCGSN). In total 230 participants have been recruited from the memory and dementia clinic of the Greek Association of Alzheimer's Disease and Related Disorders (GAADRD) and the 1st Department of Neurology, U.

Joint EOPEN-BETTER exercise in the H2020 BETTER Project Hackathon

Oct 14, 2020

A joint exercise will be supported by Fraunhofer IAIS (BETTER project) and 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

Flood-Related Multimedia Task at MediaEval 2020

Sep 22, 2020

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.

Visualisation Tool for monitoring Italian tweets concerning COVID19

May 22, 2020

The Multimedia Knowledge and Social Media Analytics Laboratory (MKLab) of the Centre for Research & Technology Hellas (CERTH) 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.

Η εκπαίδευση στα χρόνια του κορονοϊού μέσω τρισδιάστατων εμπειριών

Apr 06, 2020

Tο εργαστήριο «Γνώσης, Πολυμέσων και Κοινωνικών Δικτύων» (MKlab) του Εθνικού Κέντρου Έρευνας και Τεχνολογικής Ανάπτυξης (ΕΚΕΤΑ) αναπτύσσει τρισδιάστατες εφαρμογές και εκπαιδευτικά παιχνίδια που παρέχονται δωρεάν και μπορούν να αποτελέσουν μια δημιουργική, εναλλακτική απασχόληση στις δύσκολες αυτές στιγμές που όλοι βιώνουμε. 1. Πάρκο της Αιολικής Ενέργειας “Wind Energy Lab” Μια εφαρμογή προσομοίωσης για την κατασκευή και διαχείριση πάρκων αιολικής ενέργειας που απευθύνεται σε παιδιά του δημοτικού σχολείου. Το εικονικό εργαστήριο δίνει στα παιδιά τη δυνατότητα να φτιάξουν και να διαχειριστούν το δικό τους πάρκο αιολικής ενέργειας μελετώντας τους παράγοντες που επηρεάζουν το κόστος και το κέρδος που έχει ένα τέτοιο πάρκο κατά τη διάρκεια ενός χρόνου.

Best Paper Award at MMM 2020

Jan 13, 2020

The MKLab paper on "Unsupervised Video Summarization via Attention-Driven Adversarial Learning", authored by E. Apostolidis, E. Adamantidou, A. Metsai, V. Mezaris, I. Patras, and supported by the ReTV H2020 project (https://retv-project.eu), was presented at the 26th Int. Conf. on Multimedia Modeling (MMM2020), Daejeon, Korea, in January 2020, and received the MMM 2020 Best Paper Award. The full-text paper, presentation slides, and open-sourced software are available from the following links: Paper: https://www.