Time and Place: Day 1 (June 21), Room 1 @ 9:30am
Title: RADIO Home: an integrated smart home and assistant robot clinical monitoring environment
The RADIO Home is, effectively, a robot operating inside a Smart Home. In this environment, Smart Home and robot functionalities accommodate the user’s needs. At the same time, robot sensing monitors Activities of Daily Living (ADL) and mood. RADIO pursues a novel approach to user acceptance and unobtrusiveness at all levels. The medical observation sensors become an obvious, yet discrete and accepted part of the user’s daily life. Monitoring a person via static sensors installed all over a house is cumbersome. What RADIO does instead is to remove static sensors and place them on the robot. This clearly solves the problem of having to install sensors everywhere. You only have a few sensors in the right place, at the right angle. Using a robot also raises the awareness of the users about when they are being monitored and practically allows them to choose when to be monitored. Moreover, a robot has a dynamic presence in the user’s space, which can increase the feeling of safety by being in the right place at the right time. RADIO Home is implemented in the context of the EC- funded H2020 RADIO project. The talk will present the project outcomes so far, focusing on the real-environment piloting in the premises of our clinical partners. RADIO pilot studies take place at various stages of the project in order to evaluate the usability of the system, its fitness for its medical purpose and the compliance with unobtrusiveness.
Dr. Vangelis Karkaletsis is the head of the Software and Knowledge Engineering Laboratory (SKEL) of the Institute of Informatics and Telecommunications at NCSR "Demokritos", and responsible for the Institute's educational activities. His research interests are in the areas of Language and Knowledge Engineering, as applied to content analysis, natural language interfaces, ontology engineering. He has extensive experience in the coordination and technical management of European and national projects. He is currently coordinator of the H2020 Radio project on the use of robots in assisted living environments. He has organised international workshops, conferences, summer schools. He teaches for many years at ost-graduate courses on language and knowledge technologies.
Time and Place: Day 1 (June 21), Room 2 @ 10:50am
Title: Human in the Loop Robot Control Applications
There has been significant research and development effort on assistive robot applications in the past decade, such as smart mobility systems, wearable robots, and rehabilitation assistants. Personalized human-in-the-loop robot control remains to be a challenging research question. This talk will provide an overview of our recent research results from human-in-the-loop control of assistive robots. We will reflect on our lessons learned in this field in the past five years and identify future research directions. We introduce the concept of science of personalization with three main thrusts on flexible interaction, reconfigurable controllers, and adaptive feedback.
Dr. Taşkın Padır is the Director of the Robotics and Intelligent Vehicles Research Laboratory (RIVeR Lab) at Northeastern University. He is an Associate Professor of Electrical and Computer Engineering at Northeastern. He holds Ph.D. and M.S. degrees from Purdue University. His research interests include human-in-the-loop robot control, medical cyber-physical systems, and intelligent vehicles.
Time and Place: Day 2 (June 22), Room 1 @ 9:00am
Title: Supporting elderly in their homes: the role of Assistive Technology
Assistive Technology (AT) is an umbrella term to define any item or system aimed to maintain, increase, or improve working, learning, and activities of daily living of persons with special needs. We focus on AT products aimed at providing solutions to support the elderly in their daily life at home, to reduce the burden of their caregivers and the cost of healthcare services. The aim of this research is both to develop cutting-edge and effective solutions, as well as to investigate the effectiveness and the acceptability and usability of these products. We will present a review of AT solutions developed and, more specifically, solutions that can overcome typical issues shown by the target population of “frail elderly”, namely seniors with motor impairments (e.g., Parkinson’s disease), cognitive impairments or mild dementia (e.g., Mild Cognitive Impairment, mild Alzheimer’s disease), or at risk of falling. We will present some innovative AT solutions studied within projects funded by the European Community. Our work confirms the usefulness and effectiveness of AT solutions that show an optimal level of acceptability and usability. Especially when targeting such a population, several parameters beyond usefulness and effectiveness must be taken into account, such as the non tech-savvy end-users, the unobtrusiveness, and the possible psychosocial impact of such devices.
Roberta Annicchiarico, Ph.D., is a geriatrician, medical assistant at Fondazione S. Lucia, Rome since 2002. She is the director of the Technology-assisted neuro-rehabilitation Laboratory at Fondazione Santa Lucia. Her main research interests are the disability correlates of chronic diseases, and possible clinical applications of new technologies. She has been the principal investigator in several international European Union (EU) funded projects (VI FP, VII FP and Horizon 2020). She is Professor of Geriatrics at the School of Physiotherapy, University “Tor Vergata” in Rome and Professor of Internal Medicine at the School of Speech Therapy, at the University “Tor Vergata” in Rome.
Time and Place: Day 2 (June 22), Room 1 @ 10:20am
Title: Improving disaster response through the eyes of social media
Tornadoes, hurricanes, earthquakes, plane crashes, epidemics, bombings, terrorist attacks - deadly disasters happen at all times. Social media platforms such as Twitter and Facebook have emerged as an effective tool for broad- casting messages worldwide during disaster events. With millions of messages posted through these services during such events, it has become imperative to extract valuable information that can help emergency responders to develop efficient relief efforts and aid victims. In this talk, I will present models of social media data that explore the following questions: ”In a social media stream of messages, what is the useful information to be extracted that can help emergency response organizations to become more situationally aware during and following a disaster? What are the features (or patterns) that can help to automatically identify messages that are useful during disasters?” I will describe domain adaptation al- gorithms to automatically predict the relevance and informativeness of messages posted during emergency events in Twitter.
Cornelia Caragea is an Assistant Professor at the University of North Texas in the Computer Science and Engineering department, where she directs the Machine Learning group. She received her Ph.D. in Computer Science from Iowa State University and her B.S. in Computer Science and Mathematics from the University of Bucharest. Her research interests are in machine learning, information retrieval, and natural language processing, with applications to text and image analysis, and social media. Caragea’s work has been recognized with several NSF research awards, including an NSF CAREER award. Caragea has published research papers in prestigious venues such as AAAI, IJCAI, EMNLP, and ACM Transactions on the Web. She reviewed for many journals including Nature, JAIR, TACL, and IEEE TKDE, served on several NSF panels, and was a program committee member for top conferences such as AAAI, IJCAI, ACL, EMNLP, SIGIR. Caragea also organized several workshops on scholarly big data co-located with IJCAI, AAAI, and IEEE Big Data.
Time and Place: Day 2 (June 22), Room 1 @ 1:30pm
Title: Intelligent Transportation Systems for a safe, smooth and less polluted road environment – Research Challenges
The most direct impacts of road transport relate to traffic congestion, road safety, fuel consumption, greenhouse gases emissions, local pollutants emissions and noise levels. The implementation of environmental policies in the transportation sector should consider the level of contribution of each externality and its geographical scale. Thus, in a context of increasing data availability, a relevant research topic is to explore the potentialities of the use of ICT in the transportation sector, in order to efficiently manage current road networks and decrease negative impacts, according to each region’s characteristics. In this presentation the results of some R&D projects will be presented as well as the research needs on this topic.
Dr. Margarida Coelho is an Assistant Professor at the Department of Mechanical Engineering of the University of Aveiro. She is also the Coordinator of the R&D Group on Transportation Technology at the Centre for Mechanical Technology and Automation. She is developing research in the field of mechanical engineering - energy and transportation since 2000, namely in the numerical modeling of road traffic, fuel consumption and pollutant emissions. She completed her PhD in Instituto Superior Técnico – Technical University of Lisbon, within a partnership with the Institute for Transportation Research and Education of North Carolina State University, USA. She started working at UA in 2005.
Time and Place: Day 3 (June 23), Room 1 @ 9:00am
Title: Self Calibrating Protocols for Wearables and Personalized Machine Learning
Interactive environments whether in the VR/AR/MR or sensing settings are becoming commonplace in both research and industry and will soon be appearing as integrated consumer product solutions to human performance enhancement and therapeutic intervention.. This talk will explore the confluence of wearables with novel biosensors (such as machine olfactors) and the emerging framework of personalized machine learning from the standpoint of SCP (Self-Calibrating Protocols). As case studies we will examine the recent progress with consumer-grade Electro-Encephalography (EEG) neurofeedback applied to sensory deprivation tank simulation and characterization of neurofeedback performance when running on cellphones.
Dr. Andreas Mershin is a Research Scientist at the MIT Center for Bits and Atoms. He leads the Label Free research group with a wide portfolio of research directions including projects directly relevant to wearable biosensing such as machine olfaction, bioenergy harvesting, EEG pain sensing, neurofeedback and synthetic cell microfluidics. His research and the technologies it has spawned are used by industry and government, exhibited at the Boston Museum of Science and Designer Open Exhibition, he holds over a dozen US patents and his work is globally covered by media including CNN, BBC, NYT, Discovery Channel, Wired, New Scientist, Nature and Science. He is the co-founder and director emeritus of the international Molecular Frontiers Inquiry Prize (MFIP) a.k.a Kid Nobel open to anyone under 18 years old and awarded annually at the Royal Swedish Academy of Sciences in Stockholm (home of the science Nobels) to the most intriguing scientific questions posed by children. Winners are determined by a jury selected from a panel of eminent scientists including thirteen Nobel laureates. The MFIP is the world's first ever prize awarded for asking good questions. He is a scuba dive master and a private pilot and occasionally teaches the “hard" MIT Experimental Study Group physics and the "Making Sense of Scent" classes at MIT as well as the "From Lab to Market the MIT Way" for the Executive Education Program of the MIT Sloan School of Business.