News ...

PhD Opening @ VUB - Multimodal Fake Media Detection

PhD Researcher in Multimodal Fake Media Detection

The rise of fake news has brought with it many different modalities of misinformation. Images can be falsified or taken out of context, videos can be edited to be misleading and deep-fake video can make and portray events that have never happened. The complexity of this manipulated or generated content requires new fake media detection methods that can combine different modalities (e.g., image and text, video and audio) and can aggregate supporting evidence from multiple sources (e.g., news websites, fact-checking websites, social media).

This fully funded PhD position will design novel deep-learning models to detect fake media from multimodal content (images/video and text/audio). The research will also investigate (graph) deep learning models for multidomain and multilingual automated fact-checking, which can reason on the veracity of content using evidence from multiple sources. The research will also focus on innovative post-hoc interpretation and explanation algorithms that analyze the behavior of the (multimodal) deep learning models.

The position is available within the team of Prof. Nikos Deligiannis at the Department of Electronics and Informatics (www.etrovub.be) at Vrije Universiteit Brussel, Belgium, which specializes in interpretable and explainable machine learning, signal processing, and federated learning for computer vision and data processing. The team is affiliated with imec, an international R&D and innovation hub in nanoelectronics and digital technologies (www.imec-int.com/).

Responsibilities:

  • Design and implement innovative models and algorithms within the aforementioned research,
  • Publish at top-tier journals and conferences in computer vision (e.g., CVPR, ICCV, ICIP, TIP, PAMI) and
  • machine learning (e.g., AAAI, TNNLS, TSP);
  • Prepare a doctoral dissertation and support in teaching.

Profile and requirements:

  • An MSc degree focusing on computer science, electrical engineering, mathematics or related field;
  • Prior experience with natural language processing, image processing and/or computer vision is
  • considered as a strong asset;
  • An excellent academic record;
  • Proven programming experience (e.g., Python, C++);
  • Prior experience with state-of-the-art machine learning frameworks (e.g., Tensorflow, PyTorch) is a
  • plus;
  • Excellent oral and written communication skills in English (experience in publishing at international
  • conferences/journals is a plus).

What we offer:

  • A fully funded PhD position;
  • A competitive salary and benefits,
  • An international scientific environment driven by excellence in research,
  • Opportunities for travelling to conferences and research visits to international partner research groups.

Interested candidates can send via email: (i) a detailed curriculum vitae; (ii) a motivation letter related to the position’s profile; (iii) academic transcripts (undergraduate and graduate), and (iv) the names of two potential referees by May 27, 2024 to the following contact person:

Prof. Dr. Nikos Deligiannis
Vrije Universiteit Brussel – imec
Pleinlaan 2, Brussels 1050, Belgium
https://www.etrovub.be/people/member/about-bio/ndeligia/
Tel.: +32 2 629 1683
Email: ndeligia@etrovub.be

PhD Opening @ VUB - Multimodal Explainable AI for Multimodal Sensing

PhD Researcher in Multimodal Explainable AI for Multimodal Sensing

We are seeking a highly motivated and talented individual to join our research team as a PhD student in the exciting field of Multimodal Explainable AI for Multimodal Sensing. This position offers a unique opportunity to contribute to cutting-edge research at the intersection of artificial intelligence and sensory technologies.

The successful candidate will work on developing novel methods and algorithms that integrate multiple sensory modalities (including radar and LiDar sensors, cameras, and joint communication and sensing systems) in the primary prediction models and multiple data modalities in generating explanations for their behavior (including visual, textual and speech). By leveraging multiple modalities, these approaches enhance the system's understanding of complex data and provide transparent explanations that users can trust. This research will have applications in various domains, including healthcare diagnostics, autonomous systems, and human- computer interaction in agricultural and industrial environments.

The position is available within the team of Prof. Nikos Deligiannis at the Department of Electronics and Informatics (www.etrovub.be) at Vrije Universiteit Brussel, Belgium, which specializes in interpretable and explainable machine learning, signal processing, and federated learning for computer vision and data processing. The team is affiliated with imec, an international R&D and innovation hub in nanoelectronics and digital technologies (www.imec-int.com/).

Responsibilities:

  • Conduct research to advance the state-of-the-art in multimodal explainable AI.
  • Designing and implementing algorithms for integrating multiple modalities in prediction models.
  • Developing methods for generating transparent and interpretable explanations for AI decisions.
  • Collaborate with interdisciplinary teams to apply research findings to real-world problems.
  • Publish at top-tier journals and conferences.
  • Prepare a doctoral dissertation and support in teaching.

Profile and requirements:

  • An MSc degree focusing on computer science, electrical engineering, mathematics or related field;
  • Bachelor's or Master's degree in computer science, engineering, or a related field.
  • Strong background in artificial intelligence, machine learning, and/or computer vision.
  • Experience with one or more programming languages such as Python, C++, or Java.
  • Familiarity with deep learning frameworks (e.g., TensorFlow, PyTorch) is desirable.
  • Excellent analytical and problem-solving skills.
  • Effective communication skills and ability to work both independently and collaboratively.

What we offer:

  • A fully funded PhD position;
  • A competitive salary and benefits,
  • An international scientific environment driven by excellence in research,
  • Opportunities for travelling to conferences and research visits to international partner research groups.

Interested candidates can send via email: (i) a detailed curriculum vitae; (ii) a motivation letter related to the position’s profile; (iii) academic transcripts (undergraduate and graduate), and (iv) the names of two potential referees by May 27, 2024 to the following contact person:

Prof. Dr. Nikos Deligiannis
Vrije Universiteit Brussel – imec
Pleinlaan 2, Brussels 1050, Belgium
https://www.etrovub.be/people/member/about-bio/ndeligia/
Tel.: +32 2 629 1683
Email: ndeligia@etrovub.be

PhD Opening @ VUB - Task-oriented Sensing, Compression and Communication

PhD Researcher in task-oriented sensing, compression, and communication

We are seeking a highly motivated and talented individual to join our research team as a PhD student in the exciting field of task-oriented sensing, compression, and communication. Task-oriented sensing and compression refers to a new paradigm in data acquisition and compression, where sensors and signal processing pipelines are designed, optimized, and deployed specifically to fulfill predefined tasks or objectives. Unlike traditional sensing approaches focusing on capturing raw data without specific context or purpose, task-oriented sensing systems are tailored to collect information relevant to particular tasks. Moreover, semantic communication is anticipated to be a cornerstone of next-generation AI-based communication systems. Central to this evolution is the capacity for semantic compression, wherein data (including images, videos, and radar and LiDar signals) equivalent in meaning to the transmitted ones can be reconstructed at the receiving end without necessarily recovering the transmitted sequence of bits. This approach holds promise for revolutionizing various domains, including environmental and infrastructure monitoring, healthcare, and autonomous systems.

The position is available within the team of Prof. Nikos Deligiannis at the Department of Electronics and Informatics (www.etrovub.be) at Vrije Universiteit Brussel, Belgium, which specializes in interpretable and explainable machine learning, signal processing, and federated learning for computer vision and data processing. The team is affiliated with imec, an international R&D and innovation hub in nanoelectronics and digital technologies (www.imec-int.com/).

Responsibilities:

  • Conduct research to advance the state-of-the-art in task-oriented sensing, compression, and
  • communication.
  • Collaborate with interdisciplinary teams to apply research findings to real-world problems.
  • Publish at top-tier journals and conferences.
  • Prepare a doctoral dissertation and support in teaching.

Profile and requirements:

  • An MSc degree focusing on computer science, electrical engineering, mathematics or related field;
  • Bachelor's or Master's degree in computer science, engineering, or a related field.
  • Strong background in artificial intelligence, machine learning, and/or computer vision.
  • Experience with one or more programming languages such as Python, C++, or Java.
  • Familiarity with deep learning frameworks (e.g., TensorFlow, PyTorch) is desirable.
  • Excellent analytical and problem-solving skills.
  • Effective communication skills and ability to work both independently and collaboratively.

What we offer:

  • A fully funded PhD position;
  • A competitive salary and benefits,
  • An international scientific environment driven by excellence in research,
  • Opportunities for travelling to conferences and research visits to international partner research groups.

Interested candidates can send via email: (i) a detailed curriculum vitae; (ii) a motivation letter related to the position’s profile; (iii) academic transcripts (undergraduate and graduate), and (iv) the names of two potential referees by May 27, 2024 to the following contact person:

Prof. Dr. Nikos Deligiannis

Vrije Universiteit Brussel – imec
Pleinlaan 2, Brussels 1050, Belgium
https://www.etrovub.be/people/member/about-bio/ndeligia/
Tel.: +32 2 629 1683
Email: ndeligia@etrovub.be

 

PhD Opening @ WPI

https://cchamzas.com/news/phd_call/

November 22, 2023

The Efficient Learning and Planning for Intelligent Systems (ELPIS) Lab invites applications for two fully funded Ph.D. positions starting in Fall 2024.

Lab Focus: The ELPIS Lab has a broad interest in autonomous robotic system capable of reasoning about and interacting with the physical world. The primary goal is to develop agents that are efficient, robust, and capable of learning from real-world interactions. Current research projects focus on the integration of classical planning algorithms and state-of-the-art machine learning techniques, aiming to advance 1) planning efficiency, 2) planning robustness, and 3) planning from visual inputs. The lab concentrates on real-world applications in robotic manipulation, including tasks such as object manipulation, mobile manipulation, and multi-arm manipulation.

What we are looking for: Prospective applicants should have a background in CS, EE, ME, or a related field, and a passion for robotics! Preference will be given to those with relevant research experience, and a significant emphasis is placed on programming and/or hardware skills.

If you are interested: Interested students should submit their applications through the WPI application portal at the Robotics Engineering Department. Applicants are also encouraged to directly contact Dr. Chamzas at cchamzas at wpi dot edu. In the email, please attach your CV, transcript, and a short cover letter describing research interests, and any relevant experience.

Ph.D. in Robotics at WPI: WPI is located in Worcester, Massachusetts. WPI is one of the few places, worldwide, that has a dedicated Robotics Department and students can earn a doctorate in the field. There is a serious emphasis on robotics as well as on creativity and innovation. It also offers one of the most competitive stipends in the U.S. with at least 39.000$ per year.

 

Lecture by Prof. Pantelis Georgiou, DEEE, ICL @ 25 Oct 2023

Prof. Pantelis Georgiou from the Department of Electrical and Electronic Engineering, Centre for Bio-inspired Technology, Imperial College London, UK will deliver a lecture entitled

"Microchip Technology enabling Rapid Diagnostics for Infectious Diseases - From AMR to COVID-19"

on Wednesday 25 Oct 2023 at 11:00 (Athens time).

The event will be held in the Conference Hall of the ECE Department of the University of Patras.

Remote participation will be possible via the link: 

https://upatras-gr.zoom.us/j/97733095454?pwd=UXd4am1qWENxRGRBZGVpRlFaakNwdz09

The lecture will be given in English and is open to all interested.

For more information you can contact Prof. A. Skodras [ skodras at upatras.gr ]

Abstract

In the last decade, we have seen a convergence of microelectronics into the world of healthcare providing novel solutions for early detection, diagnosis and therapy of disease. This has been made possible due to the emergence of CMOS technology, allowing fabrication of advanced systems with complete integration of sensors, instrumentation and processing, enabling design of miniaturised medical devices which operate with low-power. This has been specifically beneficial for the application areas of DNA based diagnostics and full genome sequencing, where the implementation of chemical sensors known as Ion-Sensitive Field Effect Transistors (ISFETs) directly in CMOS has enabled the design of large-scale arrays of millions of sensors that can conduct in-parallel detection of nucleic acids. Furthermore, the scaling of CMOS with Moore’s law and the integration capability with microfluidics has enabled the creation of hand-held and portable rapid diagnostic systems for infectious diseases.

In this talk, I present how my lab is advancing the areas of DNA and RNA detection for rapid diagnostics of infectious diseases and Antimicrobial Resistance (AMR) through the design of CMOS based Lab-on-Chip systems using ISFETs. I will showcase Lacewing, our latest handheld diagnostic system which is able to rapidly identify bacterial and viral infections in under 30 minutes, communicating results in real-time to the cloud for epidemiological surveillance. Results from our latest trials for detection of Malaria and bacterial resistant infections will be shown in addition to our most recent efforts in tackling the COVID-19 outbreak.

Biographical Note

Prof. Pantelis Georgiou received the M.Eng. degree in electrical and electronic engineering and the Ph.D. degree from Imperial College London (ICL), London, U.K., in 2004 and 2008, respectively.
He is currently a Professor of Biomedical Electronics with the Department of Electrical and Electronic Engineering, ICL, where he is also the Head of the Bio- Inspired Metabolic Technology Laboratory, Centre for Bio-Inspired Technology. His research includes bio-inspired circuits and systems, CMOS based Lab-on-Chip technologies, and application of microelectronic technology to create novel medical devices. He has made significant contributions to integrated chemical-sensing systems in CMOS, conducting pioneering work on the development of ISFET sensors, which has enabled applications, such as point-of-care diagnostics and semiconductor genetic sequencing and has also developed the first bio-inspired artificial pancreas for treatment of Type I diabetes using the silicon-beta cell. He received the IET Mike Sergeant Medal of Outstanding Contribution to Engineering in 2013. In 2017, he was also awarded the IEEE Sensors Council Technical Achievement award. He is a member of the IET and serves on the BioCAS and Sensory Systems technical committees of the IEEE CAS Society. He is also on the IEEE Sensors council as a member at large and an IEEE Distinguished Lecturer. He is Co-founder and CEO of ProtonDx, commercialising technologies for rapid diagnostics for infectious diseases.

ENF of Mainland Greece in Real-Time

At DSIP Lab (Digital Signal Processing Laboratory, ECE, University of Patras) we are recording the Electrical Network Frequency (ENF) of Mainland Greece since July 2016. We make all data available for free.

As of April 2023 a new system has been added that makes the ENF measures available in Real-Time, along with the Min, Max, Avarage and Variance of the last 12000 measures. See http://enf4gr.ece.upatras.gr/

The Electrical Network Frequency (ENF) Criterion is a forensic technique used to identify the authenticity of a digital recording. Since the power line signal interferes with all kinds of recordings (telephone, video, biosignals, …), the availability of the ENF signal data for Greece could facilitate the authenticity of a recording, and the time and place that this recording has taken place. This is made possible by comparing the frequency pattern between the background utility hum in the evidence and long-term records of the ENF.

To obtain such a long term record of the ENF fluctuations at national level, we have ported the power line frequency recording system to a Raspberry Pi 3 Model B. This has rendered the whole system small in size, portable, and of low cost. The system captures the power line signal and extracts the ENF signal for mainland Greece, 24/7. The ENF data are uploaded to the cloud for free download by all those who are using the ENF in their research. More info can be found at the followig links:

http://www.ece.upatras.gr/skodras/index.php?id=research

http://dsip.ece.upatras.gr/projects/

 

 

Data and code are made available for free download. (http://www.ece.upatras.gr/skodras/index.php?id=research)

Fully funded PhD @ Technical University of Denmark

Technical University of Denmark

Fully funded PhD position in:

AI based High Quality Image and Video Processing and Coding

https://efzu.fa.em2.oraclecloud.com/hcmUI/CandidateExperience/en/sites/CX_1/job/1564/

 

Prof. Søren Forchhammer

Head of Coding and Visual Communications

DTU Electro

Technical University of Denmark

Tel: (45) 71 69 80 01

Email: sofo@dtu.dk

 

Post-doctoral Research Associate @ Delaware State University

Post-doctoral Research Associate - 100% GRANT FUNDED

Delaware State University

https://www.higheredjobs.com/region/details.cfm?JobCode=178344958&Title=Post%2Ddoctoral%20Research%20Associate%20%2D%20100%25%20GRANT%20FUNDED
 

 

Workshop on Cutting Edge Smart Technologies in Building: Smart Home Environment

ICR’23: The 2023 International Conference on Innovations in Computing Research, Madrid, Spain, September 4-6, 2023
Indexed by SCOPUS, DBLP, INSPEC, Norwegian Register for Scientific Journals and Series, SCImago, WTI Frankfurt eG, and zbMATH
https://iicser.org/icr23

Workshop Chairs

Eleftheria Katsiri, Democritus University of Thrace, Greece, ekatsiri@ee.duth.gr Theofilos Papadopoulos, Democritus University of Thrace, Greece, thpapad@ee.duth.gr

Workshop Objective

Despite technological advances, even in developed economies, seniors who continue to live at home require, more than anyone else need a friendly and safe smart home environment that is protective during their various activities. Yet the world and much more so the home equipment/tools are not yet prepared for the needs of this segment of the world's population. The evolution of technology and in particular of electronic, electrical, inter-networked devices and systems, combined with modern monitoring, prediction and assistance techniques can make a significant contribution to improving the quality of life of elderlies, so that they can enjoy a greater degree of safety and independence, at least at home. Although there have been important initiatives such as the Energy Performance of Buildings Directive (EPBD) and the Smart Readiness Indicator (SRI) scheme to encourage the integration of smart technologies to enhance buildings energy performance, there are still a number of barriers and gaps related to smart buildings and technologies identified. The main technological barriers are the lack of interoperability of the existing solutions, the lack of standardization and numerous legacy standards at the building side, the security of the solutions.

The aim of this workshop is to support technology innovation in the building sector and create an incentive for the integration of cutting-edge smart technologies in buildings. In this respect, its core objective is to raise awareness of the benefits of smarter building technologies and functionalities and make their added value more tangible for building users, owners, tenants, and smart service providers. Interesting and relevant research includes interoperable and cybersecure-by-design software and hardware solutions fully enabling the three functionalities required for a building to become “smart”: optimization of operation of technical building systems, adaption to the external environment, changing conditions in relation to demands from building occupants.

Call for Papers

The workshop invites submissions with methodology structured amongst, but not restricted to the technical domains of Heating, DHW, Cooling, Ventilation, Lighting, Electricity, Electrical Vehicles, Dynamic Envelopes, and Monitoring & Control. The impact criteria are Energy savings, Maintenance and Fault Prediction, Comfort, Convenience, Information to occupants, Health and wellbeing, Energy Flexibility and Storage, Safety, Sustainability.

Indicative areas for workshop submission are:

  • Accessibility to the building information
  • Energy & indoor environment performance of buildings
  • One-stop, replicable and interoperable solutions
  • Advanced edge computers, multi-protocol data gateways
  • Smart sensors and actuators for the integrated control of TBS
  • Wireless sensor networks and toolkits
  • M2M interfaces and multi-protocol
  • Low-power communication pro-tools
  • Cloud-based middleware providing building services
  • IoTs platforms in smart building
  • Thermal comfort solutions
  • Indoor environmental monitoring using low-cost sensors
  • Indoor localization systems
  • Daily observation and real-time vital measurements of the elderly
  • Optimized physical rehabilitation mechanisms for the elderly in the home
  • Robotic assistant
  • Energy flexibility solutions
  • Indoor risk assessment solutions

Workshop Committee

Eiko Yoneki , University of Cambridge, UK
Dimitris Kalogeras, National Technical University of Athens (NTUA)
Aggelos Bouhouras, University of Western Macedonia, Greece
Levente Czumbil, Technical University of Cluj-Napoca, Romania
Emrullah Fatih Yetkin, Kadir Has University, Turkey

Deep Learning Opening @ ELLAB - University of Patras

Το Εργαστήριο Ηλεκτρονικής (ELLAB) ενδιαφέρεται για μια αμειβόμενη θέση ερευνητή στα πλαίσια του ερευνητικού έργου DeepSky (ΕΔΚ Β’ ΚΥΚΛΟΣ).

➢  Το έργο DeepSky (https://deepsky-project.com/index.php/en/) βασίζεται στην ταυτόχρονη χρήση και ανάλυση δεδομένων από κάμερες στο ορατό και το θερμικό υπέρυθρο, με αποτέλεσμα την ταυτόχρονη εκτίμηση πολλών γεωφυσικών παραμέτρων (ηλιακή ακτινοβολία, ποσοστό και είδος νέφωσης, οπτικές ιδιότητες νεφών και αιωρούμενων σωματιδίων κ.α.). Έτσι, θα συνδυαστούν οι πληροφορίες των εικόνων, οι εκτιμήσεις από μοντέλα διάδοσης της ακτινοβολίας αλλά και οι τεχνικές υπολογιστικής όρασης και βαθείας εκμάθησης για την εκτίμηση γεωφυσικών μεταβλητών, τόσο για την ημέρα όσο και για τη νύχτα.

➢  Το Εργαστήριο Ηλεκτρονικής (ELLAB) στο έργο ασχολείται με την ανάπτυξη του λογισμικού βαθείας εκμάθησης και υπολογιστικής όρασης για την ανάλυση των νεφών και των χαρακτηριστικών τους με χρήση εικόνων στο ορατό και το μακρινό υπέρυθρο.

Θέμα: Ανάπτυξη αλγορίθμων βαθείας μηχανικής εκμάθησης (Deep Learning – CNN) για ταξινόμηση και τμηματοποίηση εικόνας στο πρόβλημα της αναγνώρισης τύπου νεφών (cloud type classification and cloud segmentation with Deep Convolutional Neural Networks using visible and thermal cameras).

➢ Χρήση εικόνων από κάμερες στο ορατό και στο υπέρυθρο φάσμα.
➢ Δημιουργία βάσης δεδομένων με annotated εικόνες με βάση τον τύπο νεφους
➢ Εκπαίδευση μοντέλων βαθέων συνελικτικών νευρωνικών δικτύων (CNN)
➢ Συγγραφή επιστημονικών εργασιών με τα αποτελέσματα των παραπάνω μεθόδων

▪ Κύριος στόχος: Εκπαίδευση μοντέλων βαθέων συνελικτικών νευρωνικών δικτύων και δημιουργία βάσης δεδομένων για την αναγνώριση ή/και τμηματοποίηση του τύπου των νεφών από all-sky- view fisheye κάμερα στο ορατό φάσμα αλλά και από θερμική wide-angle κάμερα. Οι κάμερες αυτές είναι σεταρισμένες και λειτουργούν ήδη λαμβάνοντας εικόνες ενώ το βασικό τμήμα της βάσης δεδομένων έχει δημιουργηθεί στο ορατό. Επίσης, έχουν εκπαιδευτεί CNNs στο classification πρόβλημα.

Επόμενοι στόχοι: Επίλυση προβλήματος τμηματοποίησης εικόνας για την αναγνώρισης τύπου νεφών (cloud segmentatio using CNN), Χρήση αναπαραστάσεων από θερμικές κάμερες για το πρόβλημα αναγνώρισης τύπου νεφών. Δημιουργία βάσης δεδομένων με επιπρόσθετες πληροφορίας πέραν της εικόνας (π.χ. θερμοκρασία, υγρασία, θερμική εικόνα, κτλ) για χρήση στην εκπαίδευση CNN. Συγγραφή τουλάχιστον 3 εργασιών σε περιοδικά ή συνέδρια.

Προϋποθέσεις:
• Υποψήφιος Διδάκτορας ή Μεταδιδάκτορας με αντικείμενο σχετικό με την επεξεργασία σήματος και εικόνας (ενδεικτικά αναφέρονται η ειδικότητα Μηχανικού Η/Υ και εξειδίκευση στην επιστήμη των Η/Υ ή η ειδικότητα Φυσικού και εξειδίκευση στην Ηλεκτρονική).

• Γνώσεις λειτουργίας βαθέων συνελικτικών νευρωνικών δικτύων και ανάπτυξης λογισμικού βαθείας εκμάθησης (σε matlab ή Pytorch ή Tensorflow), δηλαδή υλοποίηση δικτύων για image classification και segmentation.

• Εμπειρία στη συγγραφή επιστημονικών εργασιών (papers).

▪  Η διάρκεια της σύμβασης θα είναι περίπου 9 μήνες (μέχρι 15/10/2023) και οι μηνιαίες απολαβές θα είναι 1000 Ευρώ υπό μορφή χορήγησης υποτροφίας από τον ΕΛΚΕ Πανεπιστημίου Πατρών είτε με μπλοκάκι με αντίστοιχη καθαρή αμοιβή και μπορεί να ξεκινήσει άμεσα βγάζοντας την προκήρυξη της θέσης.

▪  Η δουλειά μπορεί να γίνεται και εξ αποστάσεως, με remote πρόσβαση στα υπολογιστικά συστήματα (PC with GPUs for deep learning) του Εργαστηρίου Ηλεκτρονικής.

▪  Ο ερευνητής θα συνεργάζεται με έναν Μεταδιδάκτορα και έναν Υποψήφιο Διδάκτορα του Εργαστηρίου Ηλεκτρονικής που ήδη απασχολούνται στο έργο υπό την επίβλεψη του καθηγητή κ. Γ. Οικονόμου.

-----------------------------------------------------------------------------------------------------------------------------------------

Το Εργαστήριο Ηλεκτρονικής (ELLAB), με επιστημονικό υπεύθυνο τον κ. Οικονόμου, συμμετέχει στο ερευνητικό έργο

με τίτλο:
ΑΝΆΠΤΥΞΗ ΕΝΌΣ ΚΑΙΝΟΤΟΜΟΥ ΚΑΙ ΕΥΈΛΙΚΤΟΥ ΣΥΣΤΉΜΑΤΟΣ ΕΠΊΓΕΙΩΝ ΜΕΤΕΩΡΟΛΟΓΙΚΩΝ, ΑΤΜΟΣΦΑΙΡΙΚΩΝ ΚΑΙ ΗΛΙΑΚΩΝ ΜΕΤΡΉΣΕΩΝ ΜΕ ΤΗ ΣΥΝΕΡΓΕΙΑ ΦΥΣΙΚΩΝ ΜΟΝΤΕΛΩΝ ΚΑΙ ΜΕΘΟΔΩΝ ΥΠΟΛΟΓΙΣΤΙΚΗΣ ΟΡΑΣΗΣ ΚΑΙ ΒΑΘΙΑΣ ΜΑΘΗΣΗΣ, DEEPSKY.

(https://deepsky-project.com/index.php/en/)

που χρηματοδοτείται στο πλαίσιο της δράσης: «ΕΡΕΥΝΩ-ΔΗΜΙΟΥΡΓΩ-ΚΑΙΝΟΤΟΜΩ Β’ ΚΥΚΛΟΣ» και στο οποίο συμμετέχουν ακόμα το Εργαστήριο Φυσικής της Ατμόσφαιρας του τμήματος Φυσικής Πανεπιστημίου Πατρών (https://www.atmosphere-upatras.gr/) και η εταιρία Irida Labs (https://iridalabs.com/).

------------------------------------------------------------------------------------------------------------------------------------------

DSP 2023 - 24th International Conference on Digital Signal Processing

===============================================================================
DSP 2023

24th International Conference on Digital Signal Processing

11-13 June 2023, Island of Rhodes, Greece

https://2023.ic-dsp.org/

===============================================================================

IMPORTANT DATES

•    Submission of full papers – March 11, 2023
•    Notification of acceptance – April 11, 2023
•    Author advance registration – April 22, 2023
•    Camera-ready paper submission – May 11, 2023

===============================================================================

The 24th International Conference on Digital Signal Processing (DSP 2023) will be held in June 11-13, 2023 on the island of Rhodes, Greece. It is the longest in existence Conference in the area of DSP and belongs to a series of events that commenced from London in 1967 and continued to Florence, Nicosia, Limassol, Santorini, Cardiff, Corfu, Hong-Kong, Singapore, Beijing, and Shanghai. It returns back to Greece after ten years; DSP 2013 took place on Santorini island. It will bring together leading experts from academia and industry to share the most recent and exciting advances in the general area of digital signal processing and analysis.

DSP 2023 addresses the theory and application of filtering, coding, transmitting, estimating, detecting, analysing, recognising, synthesising, recording, and reproducing signals by means of digital devices or techniques. The term "signal" includes audio, video, speech, image, communication, geophysical, sonar, radar, medical, musical, and any other type of signal. This includes primarily those areas listed under all EDICS categories of the IEEE Transactions on Signal Processing and IEEE Transactions on Image Processing.

The program will include presentations of novel research theories / applications / results in lecture, poster and plenary sessions. Special Sessions organised by internationally recognised experts in the area constitute the basis of DSP conferences


Topics of interest include, but are not limited to:

Biomedical Signal Processing
• Biomedical Signal and Image Processing
• Brain-Computer Interface
• Genomic Signal Processing
• Signal Processing in Genomics and Proteomics

Digital and Multirate Signal Processing
• Adaptive Signal Processing
• Digital and Multirate Signal Processing
• Digital Filter Design and Implementation
• Multidimensional Filters and Transforms
• Multiresolution Signal Processing
• Multiway Signal Processing
• Theory and Applications of Transforms
• Time-Frequency Analysis and Representation
• Statistical Signal Processing

Sensor Array and Multichannel Processing
• Array Signal Processing
• Signal Processing for Smart Sensors and Systems
• Compressive Sensing

Signal Processing for Communications
• Geophysical/Radar/Sonar Signal Processing
• MIMO Signal Processing

Signal Processing for Audio/Image/Video
• Audio/Speech/Music Processing & Coding
• Digital Photography
• HDR Imaging
• Image and Multidimensional Signal Processing
• Image/Video Indexing, Search and Retrieval
• Image/Video Compression and Coding Standards
• Image/Video Content Analysis
• Image/Video Processing Techniques
• 3D Image Processing and Applications
• Mobile Imaging and Image Quality
• Real-Time Signal/Image/Video Processing
• Video Surveillance and Transportation Imaging
• Digital Watermarking and Data Hiding

Other Areas and Applications
• Big Data
• Cognitive Signal Processing
• DSP Education
• Nonlinear Signals and Systems
• Information Forensics and Security
• Internet of Things (IoT)
• Social Signal Processing & Affective Computing
• Signal and System Modelling
• Signal Processing of Financial Data
• VLSI Architectures and Implementations for DSP

===============================================================================

PAPER SUBMISSION

The language of the Conference is English. Prospective authors are invited to submit full-length papers (up to 4 pages for technical content including figures, tables, references and one optional 5th page containing references only). IEEE templates for the paper format, and “no show” policy apply. Authors should indicate one or more of the above listed categories that best describe the topic of the paper, as well as their preference (if any) regarding lecture or poster sessions. Lecture and poster sessions will be treated equally in terms of the review process. Submitted papers will be peer-reviewed by at least two experts in the field. All accepted papers that have been presented, will be published in IEEE Xplore. In addition to the technical program, a social program will be offered to the participants and their companions. It will provide an opportunity to meet colleagues and friends against a backdrop of outstanding natural beauty and rich cultural heritage in one of the best-known international tourist destinations, the Island of Sun, Rhodes.

===============================================================================

ORGANISING COMMITTEE

Honorary Chair
Anthony G. Constantinides, UK

General Chair
Athanassios N. Skodras, GR

General Co-Chair
Danilo Mandic, UK

Constantinides Track Chair
fred harris, US

Technical Program Chair
Adrian Munteanu, BE

Awards Chairs
Constantinos S. Pattichis, CY
Saeid Sanei, UK

Plenary Sessions Chairs
Marc Antonini, FR
Jonathon Chambers, UK

Special Sessions Chairs
Angelo Genovese, IT
Marios S. Pattichis, USA

Early Career Researcher Chair
Stefan Vlaski, UK

DSP Challenge Chair
Ayush Bhandari, UK

Women in SP Chair
Tania Stathaki, UK

Publicity Chairs
Efe Bozkir, DE
Dimitris Ampeliotis, GR
Melpomeni Dimopoulou, FR

Publications Chair
Vassilis Fotopoulos, GR

Industrial Liaisons
Ioannis Katsavounidis, US
George Lambropoulos, CA
Béatrice Pesquet-Popescu, FR
Mahsa Pourazad, UK
Andreas Spanias, US
Christian Timmerer, AT

International Liaisons
Jing Dong, CN
Alex Kot, SG
Vincenzo Piuri, IT
W. C. Siu, HK

Advisory Board
Moncef Gabbouj, FI
Kin K. Leung, UK
Thrasos Pappas, US

===============================================================================

IMPORTANT DATES

•    Submission of full papers – March 11, 2023
•    Notification of acceptance – April 11, 2023
•    Author advance registration – April 22, 2023
•    Camera-ready paper submission – May 11, 2023

===============================================================================

DNA-based Digital Data Storage

Digital sobriety? DNA might be the solution | Melpomeni Dimopoulou | TEDxCannes
https://www.youtube.com/watch?v=NG9x03DQ7CI&ab_channel=TEDxTalks

EMG-based Hand Gesture Recognition for Rehabilitation (ENHANCE)

The purpose of this research project is the development of a serious game controlled by a surface electromyography (sEMG) interface for rehabilitation purposes. The processing of the sEMG signals and the gesture recognition is performed in an end-to-end fashion by deep learning (DL) methods. Specifically, convolutional neural network (CNN) architectures are utilised for the classification of signal segments to one of the target gestures. The interface is based on a sEMG armband placed around the user’s forearm. Using sEMG sensors allows the developed system to reject unwanted compensatory movements which are difficult to filter out with typical game controllers such as cameras. The evaluation of this serious game involves patients with upper limb impairments and neurological diseases, such as multiple sclerosis. The outcomes of this research project will contribute to the development of motivational serious games for the motion improvement of physically impaired people.

More on ERT3 O3 at https://www.youtube.com/watch?v=ILVMkHddUvY (in Greek)

 

ENF 4 GR

At DSIP Lab (Digital Signal and Image Processing Laboratory) of the ECE Dept, Univ of Patras, Greece, we are recording the Electrical Network Frequency (ENF) since July 2016. Data and code are made available for free download.

The Electrical Network Frequency (ENF) Criterion is a forensic technique used to identify the authenticity of a digital recording. Since the power line signal interferes with all kinds of recordings (telephone, video, biosignals, ...), the availability of the ENF signal data for Greece could facilitate the authenticity of a recording, and the time & place that this recording has taken place. This is made possible by comparing the frequency pattern between the background utility hum in the evidence and long-term records of the ENF. 

We have ported the power line frequency recording system to a Raspberry Pi 3 Model B. This has rendered the whole system small in size, portable, and of low cost. The system captures the power line signal and extracts the ENF signal for mainland Greece, 24/7. The ENF data are uploaded every midnight to the cloud for free download. The recordings are in .csv file format.

More details about the system and the Python code for the Raspberry, can be found at http://dsip.ece.upatras.gr/projects/
 

JICT will continue for another three years … 2021 - 2023

JICT stands for the VUB-UPatras International Joint Research Group on ICT. It is a strategic collaboration that enables both partners to strengthen their position in the individual core competence domains and deliver cross-disciplinary research contributions to the vast domain of E2E ICT systems. Moreover, joint European projects, publications and MSc/PhD students are pursued. The collaboration acts as a platform that seeds student mobility to reach the European goals of exchange of human capital. Moreover, another goal is to connect to the companies in local incubation ecosystems and as such also boost the local economies by an increased knowledge transfer both at academic and at B2B level.

For more info please visit

http://dsip.ece.upatras.gr/projects/

https://www.vub.be/en/nieuws/2013/12/02/university-patras-and-vrije-universiteit-brussel-merge-their-competences