Prof. Pétia Georgieva
Title: Explainable Artificial Intelligence (AI) in Healthcare applications
Petia Georgieva is Professor of Machine Learning in the Department of Electronics Telecommunications and Informatics (DETI) at University of Aveiro, Portugal and senior researcher in the Institute of Electronics Engineering and Telematics of Aveiro (IEETA), Portugal. Her research interests include machine learning, deep learning and data mining with strong application focus on brain computer interface, medical imaging, robotics, optical and wireless communications. She holds Master and PhD degrees in Control System Engineering from Technical University of Sofia (TUS) and PhD degree in Computer Science from Faculty of Engineering of University of Porto (FEUP), Portugal in 2003. She has held several visiting positions. In particular, she was a visiting faculty at Carnegie Mellon University (CMU) – Silicon Valley in 2019 (Fall Semester), CMU-Pittsburg in 2012 (Fall Semester), an invited professor at Rowan University, Glassboro, New Jersey, USA in 2016 (Spring Semester), an invited researcher at the School of Computing and Communications, University of Lancaster, UK in 2010 (Spring Semester). Dr. Georgieva is a Senior member of IEEE and a Senior Member of International Neural Network Society (INNS).
Current artificial intelligence (AI) advances and progress in medicine created a new challenge for medical AI. The” black-box” nature of AI methods has created a discussion on the use of explainability techniques to build trust and provide transparency in the AI decision-making process. This talk will give an overview of current explainable AI (XAI) techniques such as Class Activation Mapping (CAM), Gradient-weighted CAM, Guided Grad CAM. Typical architectures for medical imaging will be introduced (e.g. CNN DenseNet) and challenges related with image processing (unbalanced data, patient overlap) will be discussed.
Prof. Francisco Flórez-Revuelta
Title: Trustworthy video-based solutions for active and healthy ageing
Francisco Florez-Revuelta is a Professor at the Department of Computer Technology, University of Alicante (Spain), where he leads the Research Group on Ambient Intelligence for Active and Healthy Ageing (AmI4AHA). His main research work is focused on active assisted living: intelligent environments, computer vision, and support to older and/or disabled people. He is currently the coordinator of visuAAL – Privacy-Aware and Acceptable Video-Based Technologies and Services for Active and Assisted Living, a Marie Sklodowska-Curie Innovative Training Network. He is also the Chair of the GoodBrother COST Action – International Network on Privacy-Aware Audio- and Video-Based Applications for Active and Assisted Living.
Europe is facing crucial health and social care challenges due to the demographic shift towards an ageing population and related economic impact from increased provision of care. Innovation in Active and Assisted Living (AAL) solutions has the potential to address these healthcare and social demands while profiting from the economic opportunities driven by the Silver Economy. Advances in computer vision have given video cameras the ability of ‘seeing’, evolving their functionality to become ‘smart cameras’. However, the monitoring using cameras can be seen as intrusive and violating rights to privacy, because of the concern that raw video images could be observed by unauthorised viewers or stored for inappropriate use. Acceptance of such technologies is also low because they create a sense of Orwellian “Big Brother” surveillance. This talk will present the latest developments in two international research projects, visuAAL and GoodBrother, on the design of trustworthy solutions to support older, impaired, and frail people in their daily life as well as on the ethical, legal, social, and privacy issues associated to video-based monitoring in private spaces.
Title: AI-tools and citizen science come together towards OneHealth in the cities
Carina Dantas has a degree in Law, she is a PhD candidate on Biomedical Sciences (AI ethics) and is the CEO of SHINE 2Europe with over 20 years-experience in areas related to health, social aspects and ICT. She is the Chair of the COST Action NET4Age-Friendly, Coordinator of the Stakeholders Network on SHAFE – Smart Healthy Age-friendly Environments and Vice-President of the European Covenant on Demographic Change. Carina is evaluator/reviewer for the European Commission, Eureka, AAL, EIT Climate and EIT Digital; Committee Member of CEN/CENELEC TC 428, Advisory and Ethics Board Member of several Horizon and AAL projects, and reviewer of ICF Journal, Geriatrics and MDPI. She manages several international projects such as SIRENE | Social Innovation Responsive Environments NETwork, an HORIZON Europe CSA, where she is the Project Coordinator; or RadioVal | International Clinical Validation of Radiomics Artificial Intelligence for Breast Cancer Treatment Planning, an Horizon Europe RIA where she leads WP1 – Multi-stakeholder engagement and social innovation.
Urban aquatic ecosystems make cities more biodiverse and sustainable. Yet, they are often confronted with urbanisation processes that degrades them, leading to emerging pathogens, decreasing disease resistance, climate change impacts and other health concerns in cities. Based on the experience of the ongoing Horizon Europe OneAquaHealth project, we are investigating the interconnection of ecosystem health and human wellbeing, to identify early warning indicators and enhance environmental monitoring with AI-assisted tools. As a result, the project will support decision-makers in finding adequate and timely decisions as well as effective measures to promote OneHealth. The project is developing an Environmental Surveillance System, a Decision & Support System and a CitizenScience App to raise awareness and to engage all relevant stakeholders to jointly achieve thriving ecosystems and healthier communities for the future.
Prof. Radu-Ioan Ciobanu
Title: Mobile Computing for Smart Object Applications
Radu-Ioan Ciobanu is an associate professor and researcher at the Computer Science department of the Faculty of Automatic Control and Computers at the National University of Science and Technology POLITEHNICA Bucharest, Romania. He obtained his B.S., M.S. and Ph.D. (Summa Cum Laude) from the same faculty in 2010, 2012 and 2016, respectively. He has worked in the area of mobile devices for more than 10 years, having experience in both startups (VirtualMetrix) as well as corporations (Luxoft). His research interests include pervasive and mobile networks, DTNs, opportunistic networks, cloud computing, etc. During his career, he has been involved in several national and international research projects in the area of mobile and cloud computing, as well as IoT and Ambient Assisted Living.
Smart objects nowadays form the basis of a multitude of applications that attempt to improve society’s wellbeing. However, the amount of data that these applications need to store, as well as the quantity of computations that need to be performed, can become real bottlenecks, due to the limited capabilities of the smart objects and other mobile devices. Most modern solutions try to alleviate these issues by employing a cloud backend to offload computations and data, but this usage model leads to high costs for developing the applications (since a cloud infrastructure that should scale to the number of users must be maintained), and to a potentially bad user experience (if the latency is high or the users employ mobile broadband they pay for). Thus, we introduce the Drop Computing paradigm, which proposes the concept of decentralized computing over multilayered networks, combining cloud and wireless technologies over a social crowd formed between mobile and edge devices. Mobile devices and people interconnect to form ad-hoc dynamic collaborations to support the equivalent of a crowd-based edge multilayered cloud of clouds, where the capabilities of any mobile device are extended beyond the local technology barriers, to accommodate external resources available in the crowd of other devices. Thus, instead of every data or computation request going directly to the cloud, Drop Computing employs the mobile crowd formed of devices in close proximity for quicker and more efficient access. Devices in the mobile crowd are leveraged for requesting already downloaded data or performing computations, and the cloud acts as the second (or even third) option. On top of the Drop Computing framework, multiple smart object-based use cases can be implemented, taking advantage of the benefits brought by social mobile collaboration.