Centre for Research and Technology-Hellas / Information Technologies Institute (CERTH/ITI)
The Centre for Research and Technology-Hellas (CERTH, www.certh.gr) is the only research centre in Northern Greece and one of the largest in the country and it was founded in 2000. It is a legal entity governed by private law with non-profit status, supervised by the General Secretariat for Research and Technology (GSRT) of the Greek Ministry of Education and Religious Affairs. CERTH has important scientific and technological achievements in many areas including: Energy, Environment, Industry, Mechatronics, Information & Communication, Transportation & Sustainable Mobility, Health, Agro-biotechnology, Safety & Security, Cybersecurity, as well as several cross-disciplinary scientific areas.
CERTH has received numerous awards and distinctions such as the European Descartes Prize, the European Research Council (ERC) Advanced Grant, Microsoft International Contest Prize, the Trading Agents Competition Award and many more and is listed among the Top-25 of the EU’s Organisations with the highest participation in H2020 competitive research grants. CERTH has participated successfully in more than 1.200 competitive research projects (involving more than 4.410 international partner organizations) financed by the European Union (EU), leading industries from USA, Japan and Europe and the Greek Government via the General Secretariat of Research and Technology (GSRT). More specifically, CERTH has been involved in 613 EU funded research projects (318 H2020, 259 FP7, 14 RFCS, 1 EMFF, 3 3HP, 11 CIP, 6 EPLUS, 1 JUST) acting as Project Coordinator in 136 , beneficiary in 443 and 3rd party in 6 of them. CERTH’s research results (more than 350 publications/year) have significant scientific impact (about 7.100 heterocitations/year).
The Information Technologies Institute (ITI, www.iti.gr) was founded in 1998 as a non-profit organisation under the auspices of the General Secretariat for Research and Technology of the Greek Ministry of Development, with its head office located in Thessaloniki, Greece. Since 10/03/2000, it is a founding member of the Centre for Research and Technology Hellas (CERTH) also supervised by the General Secretariat for Research and Technology (GSRT).
CERTH/ITI is one of the leading Institutions of Greece in the fields of Informatics, Telematics and Telecommunications, with long experience in numerous European and national R&D projects. It is active in a large number of research domains such as Security and Surveillance, Image and Signal Processing, Artificial Intelligence, 5G/6G Smart Networking, Computer & Cognitive Vision, Human Computer Interaction, Virtual and Augmented Reality, Multimedia, Database and Information Systems and Social Media Analysis.
CERTH/ITI has participated in more than 525 research projects and R&D contracts with the Private Sector (Industry). More specifically, it has been involved in 304 EU funded research projects (167 FP7 & 137 H2020) and in 221 projects funded by Greek National Research Programmes and Consulting Subcontracts with the industry (87 National; 8 Interreg and 126 R&D contracts). The current ITI projects consist of 116 ongoing projects (including EU and national projects, contracts and services).
For the last 10 years, the publication record of ITI includes more than 330 scientific publications in international journals, more than 780 publications in conferences and 100 books and book chapters. These works have been cited in more than 7.500 times.
Role within TeamAware
CERTH/ITI primarily participates in WP6 (“Acoustic Detection System”) with developing algorithms for the detection and localisation of emergency events such as explosions, gunshots and snipers, as well as human voices (e.g., screams asking for help) and whistling in the operations, using an acoustic vector sensor. In particular, CERTH/ITI is the Task Leader of T6.2 (“Overlapping acoustic event detection”) which aims to provide recognition of overlapping acoustic events and participates in Task 6.1 (“Acoustic event analysis and detection”) which focuses primarily on the design of the ADS architecture and the implementation of algorithms for Single-event detection (SED) and Task 6.3 (“System validation”) which evaluates the final system in the tested environment.
Moreover, CERTH/ITI participates in WP2 (“System Architecture Specification and Design”) which provides the requirements and architectural design for the ADS. This information will be the basis for the development of each of the components and algorithms in WP6. Also, WP6 will feed the platform software in WP10 (“TeamAware AI Platform Software”) and will help to increase the confidence of the detected events, by performing fusion with the other modalities (T10.1). Furthermore, WP6 will also feed the user interface in WP11 (“TeamAware AR/Mobile Interfaces”). Moreover, WP6 will have an interface with communication and network infrastructure from WP9 (“Secure and Standardised Communication Network") (T9.4). Finally, WP6 will take part in WP12 (“Integration and Test”) (T12.1) for integration, testing and in WP13 (“Demonstration and Validation”) (T13.4) for demonstration. CERTH/ITI also participates in horizontal activities of the project in WP1 (“Project Management and Coordination”) and WP14 (“Dissemination, Exploitation and Communication”).
Acoustic Detection System
The stages of an audio-based event detection system consist of two phases: training and testing as it is illustrated in Figure 1 .
During the training phase, the raw audio recording is obtained, usually in wav format, it is annotated as a string regarding the events that it contains and then it is encoded into an array of zeros and ones. Following this step, audio characteristics (also known as features) are extracted from the raw recording, they are processed, usually by normalizing them in terms of their mean and standard deviation and finally, they are stored in a two-dimensional matrix. The first dimension of this matrix (rows) is usually the number of features and the other one, the time-step at which each feature is calculated. The annotation and feature extraction complete the acoustic model that is stored in order to perform the classification.
For the acoustic model, deep learning methods can be applied such as Convolutional Neural Networks (CNNs). The classification process, from the input magnitude spectrogram representation to the final Softmax layer that outputs the probability score of each class is shown in Figure 2.
During the testing phase, similarly, features are calculated from the raw audio recording, they are processed and stored in a two-dimensional matrix. This matrix is compared to the one created during the training to find the closest match. Finally, once the match is found the system outputs the corresponding class, related to the audio event.
For the detection of overlapping acoustic events noise reduction and echo cancellation techniques should be applied. The stages of a sound event detection system where overlapping sound events are occurring are illustrated in Figure 3. In polyphonic sound event detection, a multi-level segmentation of the audio is provided based on the number of the targets and the temporal timestamp of the events.
Dr. Dimitrios Tzovaras
Dr. Dimitrios Tzovaras is the President of CERTH (and Senior Researcher Grade A’) of the Information Technologies Institute. He received the Diploma in Electrical Engineering and the Ph.D. in 2D and 3D Image Compression from the Aristotle University of Thessaloniki, Greece in 1992 and 1997, respectively. Prior to his current position, he was a Senior Researcher in the Information Processing Laboratory at the Electrical and Computer Engineering Department of the Aristotle University of Thessaloniki. His main research interests include network and visual analytics for network security, computer security, data fusion, biometric security, virtual reality, machine learning and artificial intelligence. Dr. Tzovaras has participated and is also participating actively with his research group in more than 136 European Commission and 45 nationally funded Research and Development Projects. Dr. Tzovaras has conducted very important scientific and research work (843 publications in total), which is summarized in 3 books, 217 publications in International Journals with Referees, 54 book chapters, and 569 presentations in International Conferences with Referees. Dr. Tzovaras has also acted as a reviewer of a large number of submitted scientific papers for a plethora of International Journals and Magazines, such as IEEE, ACM, Elsevier and EURASIP, as well as International Scientific Conferences (ICIP, EUSIPCO, CVPR, etc.). Since 2004, he has been the Associate Editor in the following International journals: Journal of Applied Signal Processing (JASP) and Journal on Advances in Multimedia of EURASΙP. He is also an Associate Editor in the IEEE Signal Processing Letters Journal (since 2009) and a Senior Associate Editor in the IEEE Signal Processing Letters journal (since 2012), while since mid 2012 he has been also an Associate Editor in the IEEE Transactions on Image Processing journal. During the period 2007-2009, he was elected to participate in the group of National Representatives of Greece in the European Commission for the FP7 Programme of International Cooperation. Since 2000, Dr. Tzovaras has been leading the Virtual & Augmented Reality Lab of ITI, whereas he is the main responsible for the Digital Innovation Hub, namely nZEB (http://smarthome.iti.gr). He has participated with his team in more than 200 Research and Development projects of ITI. During the last 5 years, he has a very large management record having been the project coordinator of more than 22 projects and the technical/ scientific manager of 18 projects. He has been a lecturer of the Department of Electrical and Computer Engineering, Polytechnic School, Aristotle University of Thessaloniki since 1992.
Dr. Konstantinos Votis
Dr. Konstantinos Votis is a computer engineer and a senior researcher (Researcher Grade B’) at Centre for Research and Technologies Hellas/ Information Technologies Institute (CERTH/ITI) and Director of the Visual Analytics Laboratory of CERTH/ITI. He is also a Visiting professor at the De-montfort University in UK in the field of Human Computer Interaction, Virtual and Augmented Reality (VR), Augmented Reality (AR). He received an MSc and a Ph.D. degree in computer science and service-oriented architectures from Computer Engineering and Informatics department, University of Patras, Greece. Also, he holds an MBA from the Business School department in the University of Patras. His research interests include Human Computer Interaction (HCI), information visualisation and management of big data, knowledge engineering and decision support systems, Internet of Things, cybersecurity and blockchain technologies as well as pervasive computing, with major application areas such as mHealth, eHealth, and personalized healthcare. His PhD was in the domain of service Oriented Architecture and Information management systems in the inclusion and healthcare. Since 2012 he was appointed by the Corallia cluster (Hellenic Technology Clusters initiative) as a technical and administrative evaluator for some of the activities of the projects Innovative sensor systems offering distributed intelligence (MEMSENSE), Next Generation Millimeter Wave Backhaul Radio (NexGenMiliWave), Microelectronics Components for Lab -On-Chip Instruments in Molecular Diagnostics for Genetics and Environmental Applications (Lab-On-Chip). Since 2001 he has published more than 139 international scientific articles on eHealth, mhealth, human-technology interaction visualisation (AR, VR, information visualisation with visual analytics), mobile and ambient technologies as well as human-centred design, etc. Since 2001, Dr. Votis has participated in 29 Research and Development projects in the fields of HCI, IoT, information Visualisation and data analytics, personal health systems, cybersecurity, blockchain, Ambient Assisted Living, e-Inclusion and big data: of which 24 are funded by the EC (6 H2020, 11 FP7 ICT, 1 FP6 IST STREP, 4 FP5 IST, 2 structural/cross border), 2 are funded by the General Secretariat for Research and Technology, 2 are cross border, and 1 is subcontract from the industry), acting both as Scientific Responsible and as the Technical Coordinator of the whole European consortium (technical coordinator of the project in 3 projects - 1 FP7 ICT, 1 H2020, and 1 Greek National project). Dr. Votis has strong expertise in managing EU and national projects especially in the era of IoT, cybersecutiy, mHealth, as he was the technical coordinator of FP7 NoTremor, CaregiversPROMMD H2020, deputy coordinator myAirCoach H2020 (mHealth and self management), Greek pilot Leader and WP leader in Large scale IoT project ACTIVAGE in the Active and Healthy Ageing.
Dr. Antonios Lalas
Dr. Antonios Lalas is a postdoctoral researcher in Centre for Research and Technology – Hellas / Information Technologies Institute (CERTH/ITI). He received the Diploma and Ph.D. degrees from the Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki (AUTH), Thessaloniki, Greece, in 2006 and 2012, respectively. During the period 2020-2021, he has served as an adjunct lecturer at the Department of Electrical and Computer Engineering, University of Western Macedonia (ECE/UOWM), while during the period 2012-2018, he has served as an adjunct lecturer at the Department of Informatics and Telecommunications Engineering, UOWM. He has also served as postdoctoral research fellow at the Department of Electrical and Computer Engineering, AUTH, during the period 2013-2015. His research interests include artificial intelligence, deep neural networks, sensor fusion, acoustics, wireless power transfer, computational fluid dynamics, computational electromagnetics, visualization of physical information, IoT and 5G/6G in relation to autonomous vehicles, counter-UAV, security, and cybersecurity, as well as eHealth domains. In addition, his research interests include sensors and RF circuits design, radio frequency microelectromechanical systems (RF-MEMS), metamaterials, THz technology and graphene for various applications. He has authored twenty three (23) papers in international scientific peer review journals and more than forty eight (48) papers in international conferences and events. He has also been involved in several research projects, such as AVENUE, SHOW, SANCUS, TeamAware, NEoteRIC, INCISIVE, ALADDIN, myAirCoach, BADGER, ACMIMS funded by the EC and the Greek secretariat of Research and Technology.
Dr. Anastasios Vafeiadis
Dr. Anastasios Vafeiadis is a postdoctoral researcher at CERTH/ITI. He received the Master of Science in Electrical & Computer Engineering from Northeastern University, Boston in 2014. He received the PhD in Computer Science for the thesis, Machine Learning for Human Activity Detection in Smart Homes, as a Marie-Curie fellow, having studied at De Montfort University, Leicester, England. He has been working as a research assistant at the Information Technologies Institute of CERTH, since October 2016. Prior to joining CERTH he has worked as a research assistant intern at Toyota InfoTechnology Center, USA and as an advance development engineer at Bose Corporation, USA. His research interests include digital signal processing, machine learning, acoustics, speech recognition and speech synthesis.
Ms. Theoktisti Marinopoulou
Ms. Theoktisti Marinopoulou is a Research Associate in the Information Technologies Institute (ITI) of the Centre for Research and Technology-Hellas (CERTH) since June 2019. She graduated as Computer Engineer from the Department of Information Technology of Alexander Technological Institute of Thessaloniki in September 2017. She received her Master’s degree in «Data and Web Science» from the Department of Informatics of Aristotle University of Thessaloniki in February 2019. Since June 2019 she has been working as a research assistant at the Institute of Information Technology and Communications of CERTH. As a research associate at CERTH/ITI she has been involved in the ALADDIN, AVENUE and TeamAware H2020 European projects, in the fields of audio-based UAV detection, traffic flow prediction for Autonomous Vehicles and overlapping acoustic events detection. Her research interests include data science, machine learning, deep learning and audio signal processing.
