Abstract: Over the past decade, my team has developed probabilistic, decision-theoretic, and vision-based technologies that can assist persons with cognitive disabilities with a range of activities using monitoring and cueing (prompting). Although these technologies are reasonably effective, the interventions (e.g. audio-visual cues or prompts) are rendered (mostly) independently of users and context. In this talk, I will discuss how this is a significant barrier to adoption, and how this barrier can be lifted by automated reasoning about the personal (socio-cultural and affective) identities of users, and about the affective and emotional delivery of interventions. I will introduce a socio-cultural reasoning engine called "Bayesact" that can be used to provide this level of affective reasoning. Bayesact is based on 25 years of research in sociology and cognitive psychology. Bayesact can learn the affective identity of a user during an interaction, and can tailor prompts/cues/treatments/interventions to specific individuals in a way that ensures smoother and more effective uptake and response. I will give an introduction to this reasoning engine, and will discuss how affective reasoning could be used to create truly adaptive treatment and therapeutic technologies.
Dr. Jesse Hoey is an associate professor in the David R. Cheriton School of Computer Science at the University of Waterloo, where he leads the Computational Health Informatics Laboratory (CHIL). He is also an adjunct scientist at the Toronto Rehabilitation Institute in Toronto, Canada, where he is co-leader of the AI and Robotics Research Team. He is currently a visiting professor at the Institut National de Recherche en Informatique et en Automatique (INRIA) in Sophia-Antipolis, France. He has published over twenty peer reviewed scientific papers in highly visible journals, and over fifty conference and workshop papers. His research focuses on probabilistic and decision theoretic planning in large scale real-world uncertain domains. He also works on computational social science, affective computing, computer vision and ubiquitous computing. He applies these ideas primarily in the development of systems that help persons with a cognitive disability (e.g. Alzheimer's disease) to perform activities of daily living. More information on Dr. Hoey can be found at his website ( http://www.cs.uwaterloo.ca/~jhoey ).
Abstract: Physical rehabilitation for neurologically impaired people is crucial to improving or maintaining motor skills and can aid in muscle education and restoring or improving gait. For rehabilitation to be effective, it must be early, intensive and repetitive. However, adherence to therapy regimes can be a challenge for the individual. Recently the use of computer games in physical therapy has demonstrated potential for a more enjoyable and immersive experience than traditional therapy. A consequence of people being more engaged is that they are more likely to adhere to their exercise programmes. In this talk I will present research undertaken by our group at Ulster, which is addressing issues of motivation, adherence, adaptivity and personalisation with regard to rehabilitation therapy regimes. The underlying hypothesis is that the motivating qualities of computer games and virtual/augmented reality may be harnessed and embedded into a game-based rehabilitation system to improve the quality of user participation. Our early work considered stroke rehabilitation and used natural user interfaces (webcams) to control interaction with computer games designed to mimic specific traditional rehabilitation exercises. The games adapted to user performance to ensure appropriate difficulty levels were maintained. Subsequently the group investigated a more participatory design framework for the gamification of rehabilitation systems where inclusive participation from the beginning of a rehabilitation design process is seen as an increasingly important experimental methodology. Providing an engaging and motivating experience that takes account of an individual’s capability, opportunities, and motivation, to ensure adherence to exercise can be challenging. Due to the difference in patients’ profiles, rehabilitation games should be adaptive by embedding dynamic difficulty, containing variation in gameplay styles, and having personalised feedback/rewards systems for motivating individuals based on their psychology or temperament. We are currently investigating the limitations and benefits of user perception on game design, and the benefits of game adaptation towards patient skill levels for a more personalised experience. Examples of our work will be presented and future work using a combination of recent natural input technologies will be outlined.
Prof. Philip Morrow is currently Professor of Computer Vision in the School of Computing and Information Engineering at the University of Ulster, Northern Ireland and is a member of the University's Computer Science Research Institute (CSRI). His main research interests lie in image processing / computer vision and distributed / cloud computing. He has been involved in a range of research projects including, using image processing in rehabilitation (adaptive and personalised game development to improve motivation and engagement); medical imaging and analysis (3D wound analysis, retinal analysis, artefact detection in 3D medical surface data, iris biometrics, 4D facial mobility analysis); remote sensing (fusing elevation / satellite data for improved classification accuracy, image analysis for UAV safe landing zone detection); smart environments (video and sensor analytics for activity recognition); classification and clustering algorithms; 3D/4D image capture and analysis; biomedical image analysis (active contours for segmentation); and cloud computing (cloud content delivery networks, resource management, adaptive video distribution). He has over 140 peer-reviewed publications across these areas of research and has been involved as a Co-Investigator (CI) and Principal Investigator (PI) in a number of funded research projects concerned with the development of software tools and application solutions. He has (co-)supervised twenty PhD students to successful completion and is currently (co-)supervising a further seven students. He regularly acts as reviewer for a number of journals and has served on the programme committee for numerous national and international conferences.