Panteion University of Social and Political Sciences, Greece
Title: “What would Aristotle say? The Importance of Interpretability and Explainability in High Risk/High Reward Contexts”
Kostas Karpouzis is an Assistant Professor at the Department of Communication, Media and Culture. In his research, he’s looking for ways to make computer systems more aware of and responsive to the way people interact with each other. He is also investigating how gamification and digital games can be used in classroom and informal settings to assist conventional teaching and help teach social issues and STEAM subjects to children and adults. Since 1998, he has participated in more than twenty research projects funded by Greek and European bodies; most notably the Humaine Network of Excellence, leading research efforts in emotion modelling and recognition, the FP6 IP CALLAS project, where he served as Area Leader of Affective applications, the FP7 TeL Siren project (Technical Manager), which was voted Best Learning Game in Europe for 2013 by the Games and Learning Alliance Network of Excellence, the H2020 iRead project, which produced Navigo, the winner of the GALA Serious Games competition for 2018 and the H2020 ECoWeB project which builds engaging and personalized mobile applications to promote emotional wellbeing and prevent mental health problems in adolescents and young adults.
He is a member of the BoD for the gi-Cluster of Corallia, which consists of industrial and academic members of the game and creative ecosystem in Greece, a member of the Hellenic Bioethics and Technoethics committee and Chairman of the Board of the Hellenic Association of Computer Engineers. He co-edited a book on “Emotion in Games: Theory and Practice” published by Springer in late 2016. His Google Scholar profile is available at https://scholar.google.gr/citations?user=12olpHgAAAAJ.Besides this, he is involved in a number of science communication activities, most notably Famelab Greece and openscience.gr. He’s also an advocate for technology and CS in primary schools, participating in the Girls Go Coding initiative and serving as an Ambassador of EU Code Week in Greece (until 2018). He has participated as a speaker in 3 TEDx events, including TEDxAthens in 2019, while in 2016, he authored a lesson on the TED-ed platform titled “Can machines read your emotions?”; the lesson surpassed 300.000 views in its first week.
Noroff University College, Norway · Department of Applied Data Science
Prof. Kadry has a bachelor’s degree in 1999 from Lebanese University, an MS degree in 2002 from Reims University (France) and EPFL (Lausanne), Ph.D. in 2007 from Blaise Pascal University (France), an HDR degree in 2017 from Rouen University (France). His research currently focuses on Data Science, medical image recognition using AI, education using technology, and applied mathematics. He is an IET Fellow and IETE Fellow, member of European Academy of Sciences and Arts.
Professor Kadry’s most significant contribution to medical image analysis and processing is his thorough and rigorous approach to developing and documenting different Deep Learning models to analyze medical images for various diseases. He was one of the first researchers to develop a classification methodology to classify Focal and Non-Focal EEG by combining optimized entropy features towards classification. Therefore, he showed that entropy features are very good concerning EEG classification for better classification accuracy.
In this approach, the maximum computation time of the selected features is 0.054 seconds,
opening the window for real-time processing. Furthermore, Prof. Kadry was the first to introduce a heart rate measuring strategy using LAB color facial video. RGB videos are used by most of the nonintrusive-based systems as it is appropriate for experiments. Still, they must be developed extensively before being implemented in real-time applications. Furthermore, heart rate monitoring using RGB videos is inefficient outdoors because light significantly contributes to RGB videos. The proposed algorithm using LAB, The presented algorithm seems to be very powerful, quite practical, and easy to use in the regular observation of home care patients.
His work on developing machine learning and deep learning models to analyze medical images has encouraged the development of AI models for the Covid-19 pandemic. His team proposes a deep learning framework for classifying COVID-19 pneumonia infection from normal chest CT scans. In this regard, a 15-layered convolutional neural network architecture is developed, which extracts deep features from the selected image samples – collected from the Radiopeadia. Deep features are collected from two different layers, the average global pool and fully connected layers, which are later combined using the max-layer detail (MLD) approach. Subsequently, a Correntropy technique is embedded in the main design to select the most discriminant features from the features pool. Finally, a one-class kernel extreme learning machine classifier is utilized for the final classification to achieve an average accuracy of 95.1% and sensitivity, specificity & precision rate of 95.1%, 95%, & 94%, respectively.
Prof. Mouloud Adel
Aix-Marseille University, Marseille, France · Professor of Computer Science and Electrical Engineering
TITLE: Computer-Aided Diagnosis systems on medical images using image processing and machine learning techniques.
ABSTRACT: Computer-Aided Diagnostic (CAD) is the elaboration and development of any digital technique capable of helping doctors to establish the best diagnosis including assistance with representation and classification of biomedical signals and images but also helping them to estimate parameters of interest. Diagnosis is not just considering that a medical region on interest in an image is benign or malignant but all the tools that help better visualise, segment, detect, denoise, extract, follow up, classify,…. This speech gives an overview of the main steps on a computer-aided diagnosis system including data acquisition, image preprocessing, feature extraction, selection and ranking and classification into healthy and diseased subjects. The course will focus on general concepts of such systems and then present some case studies including different medical imaging modalities as well as different low, intermediate and high levels image processing and classification techniques using classical techniques as well as machine learning based on neural network architectures.
BIOGRAPHY: Mouloud Adel is a Professor in Computer Science and Electrical Engineering at Aix-Marseille University, Marseille, France. He is currently a visiting Professor at Galatasaray University, Istanbul, Turkey. His research areas concern signal, image processing and machine learning applied to biomedical and industrial images. He obtained his PhD degree from the Institut National Polytechnique de Lorraine (INPL) of Nancy in 1994 in image processing. He is a member of Institut Fresnel Lab UMR-CNRS 7249, Marseille, France. He has been the supervisor of more than fifteen PhD students and has been involved in many international research programs (Germany, Algeria, United Kingdom, Vietnam). He is a member of the editorial board of Journal of Biomedical Engineering and Informatics. He has been the co-organizer of various international conferences and workshops. He also served as a regular reviewer, associate and guest editor for a number of journals and conferences. He is the author or co-author of 80 journal and conference papers.
Prof. Nizamettin AYDIN
İstanbul Technical University, Computer Engineering Department,
TITLE: AI and Computer Vision Approach for Assessment of Male Dependent Infertility
Today, infertility is a common health concern that affects approximately 15%–20% of the world population. The evaluation of male patients with infertility includes diverse examination and laboratory tests in comparison to female patients. In the evaluation of male infertility, sperm specimens are examined in terms of morphometry, concentration, and motility. Detection of sperm is the critical step to determine the concentration and motility parameters. In this talk, a number of research studies towards a low cost automatic sperm analysis system based on AI and computer vision will be presented.
BIOGRAPHY: Prof. Aydin received B.Sc. (1984) and M.Sc. (1987) degrees in Electronics and Communication Engineering at Yildiz Technical University, Turkiye, and Ph.D. degree in Medical Physics (1994) at the University of Leicester, UK. He worked in the Department of Clinical Neuroscionces at Kings College London and the Division of Clinical Neuroscience at St George’s Hospital Medical School as a Research Fellow between 1998 and 2001. He was a Senior Research Fellow in the Institute for Integrated Micro and Nano Systems at the University of Edinburgh from 2001 to 2004. In 2004, he was appointed as head of Computer Engineering Department and in 2006 he founded Software Engineering Department, both at Bahcesehir University, Turkiye. Between 2009 and 2023, he was professor in Computer Engineering Department at Yildiz Technical University and served as the head of the department between 2011 and 2023. He is now with the Computer Engineering Department at Istanbul Technical University. His research interests and contributions cover a wide range of subkects including biomedical signal/image processing, bioinformatics, system-on-chip, AI, data science, and computer science. He was awarded the IEE the Institute Premium Award for 2000/2001 for his contributions in coplex wavelet transform for processing Doppler ultrasound signals. He is a senior member of IEEE and acts as Sponsored Events Coordinator of IEEE Turkiye chapter.