Fraunhofer Institute for Computer Graphics Research IGD, Germany
Applications of machine learning in physiological signal and exercise monitoring
Artificial Intelligence and Machine Learning have been significant drivers in computer science for the past years. Growing computational capabilities and increasingly powerful sensors enable applications in physiological monitoring and exercise tracking that were not feasible just a few years ago.
Of particular interest in our research are smart objects – typical objects that we use in our daily lives with added sensing and communication capabilities. Using invisible sensing technologies and sophisticated machine learning methods, we are able to monitor certain physiological parameters, and even track exercises that the user performs on or around those smart objects.
In this talk, I will present an overview of our research in smart objects, systems & methods in use, as well as recent applications. Some of the presented projects include an exercise-tracking chair, using the smartphone as an exercise tracker, and a car seat that monitors various physiological parameters.
Dr. Andreas Braun is the head of the department for Smart Living & Biometric Technologies at the Fraunhofer Institute for Computer Graphics Research IGD in Darmstadt, Germany. The department conducts research in the domains of Smart Environments, Identification and Biometrics, Capacitive Systems, as well as Embedded Sensing and Perception. Dr. Braun is the deputy spokesperson of the Fraunhofer AAL Alliance, a thematic network of ten Fraunhofer institutes in the areas of Active & Assisted Living and Personal Health. He is also a principal investigator at the Center for Research in Security and Privacy CRISP in Darmstadt. Dr. Braun is the representative of Fraunhofer IGD in the CAST-Forum, the European Association of Biometrics, and the TeleTrusT. He has been active for many years in various European research initiatives, including the Knowledge and Innovation Communities EIT Health and EIT Digital, of the European Institute of Innovation and Technology. He published more than 70 scientific papers and is holding several patents.
University of Maribor, Slovenia
Brain training – does it work?
The “Nürnberger Trichter” – a magic funnel used to pour knowledge, expertise and wisdom into students – demonstrates that the idea of effortless learning and the power of intelligence was “cool” even 500 years ago. Today noninvasive brain stimulation (NIBS), which involves transcranial direct and alternating current stimulation (tDCS and tACS), as well as random noise (tRNS) and transcranial magnetic stimulation (TMS), could be regarded as a contemporary replacement for the magic funnel. They represent and extension to the more classical methods for cognitive enhancement, such as behavioral training and computer games. On the other hand, there is still a number of alternative approaches that can affect cognitive function. Among the most prominent are: nutrition, drugs, exercise, meditation-related reduction in psychological stress and neurofeedback. The presentation will provide a concise overview of methods claiming to improve cognitive functioning – psychological constructs such as intelligence and working memory. Discussed will be changes in behavior and brain activation patterns observed with the electroencephalogram (EEG), functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI). Examined will be the usefulness of brain training for the man/woman in the street, as well as an additional device that can verify and bring causation into the relations between brain activity and cognition. Modulating brain plasticity and by that changing network dynamics crucial for intelligent behavior can be a powerful research tool that can elucidate the neurobiological background of intelligence, working memory and other psychological constructs.
Norbert Jaušovec holds a PhD in Psychology from the University of Ljubljana. He is a professor at the department of psychology University of Maribor. His research interest are in neurobiological underpinning of cognition, mainly intelligence, creativity and working memory. His work has been published in many referred journals, volumes and conference proceedings (details on this and additional information can be found at the ResearchGate website: https://www.researchgate.net/home).
University of Aveiro, Portugal
The environments where we all live are increasingly populated by devices. Our houses, buildings and cities are becoming more “intelligent” and the way we interact with these devices, in our daily life, is changing constantly, consequence of the emergence of new technologies and methods. Interaction is becoming more complex and, if nothing is done, will contribute to more exclusion. It is crucial do have interaction and design for all.
How can we face these challenges creating new services and applications that are easily usable by all, despite contextual, temporary or permanent limitations of capabilities?
In this presentation, the use of multimodal interaction will be analyzed and defended as having great potential to contribute to the needed Design and Development for All. The set of commonly used modalities is increasing, with touch and classic text and graphics being complemented by body gestures and speech, a major current trend, due to recent evolution of devices and technologies such as speech recognition and conversational assistants.
The talk will start by a brief overview of motivations for Multimodal Interaction, and recent trends and developments, including the recommendations of the W3C Multimodal User Interaction Working Group (with a particular focus on their architectural proposals).
The second part of the talk will illustrate the potential of Multimodal Interaction, side-by-side with a user-centered approach, to tackle different audiences and needs, with examples of conceptual visions and applications for Autism Spectrum Disorders, older adults, Smart Homes, and Human Building Interaction, developed in projects such as Living Usability Lab, AAL PaeLife, AAL4ALL, IRIS and the ongoing Smart Green Homes. For example, recent work in Silent Speech Interaction and interaction for an Accessible Smart Home will be presented.
The talk is the direct continuation of the DSAI 2009 position paper “Speech as the Basic Interface for Assistive Technology” and the talk “Towards Speech-Based Interaction with Machines”, part of Microsoft Workshop “Natural User Interaction: Current Challenges and Future Perspectives” at DSAI 2012.
Dr. António Teixeira holds a Master in Electronics and Telecommunications Engineering and a Ph.D. in Electrical Engineering, both from the University of Aveiro (Portugal). He is Associate Professor at University of Aveiro Department of Electronics, Telecommunications and Informatics (DETI) and a researcher at the Institute of Electronics and Telematics Engineering of Aveiro – IEETA.
He is the Chair of the Special Interest Group on Iberian Languages (SIG-IL) of the International Speech Communication Association (ISCA), since 2008. His main research activity is in the areas of Multimodal Human-Machine Interaction and Speech Processing.
He was General Chair of several international conferences on Processing of Speech and Language: IberSpeech 2016 (Lisboa, Portugal) IberSpeech 2014 (Las Palmas, Spain), IberSpeech 2012 (Madrid, Spain), FALA 2010 (Vigo, Spain), 1st Iberian SLTech (2009), PROPOR 2008 (Aveiro, Portugal). Was co-organizer of the DSAI 2013 Special Track “New Applications and Services for Ambient Assisted Living and Older Adults”.
Professor Teixeira has been project principle investigator or responsible for University of Aveiro participation in several national and European research projects in speech science and technology, Interaction and AAL (Heron II, LUL, AAL4ALL, Smartphones for Seniors, AAL PaeLIFE, IAPP IRIS) and has supervised 12 concluded PhDs and more than 50 Masters’ thesis.
He is co-author of more than two hundred publications (books, book chapters, international journals and proceedings of international conferences). He is a reviewer for several international journals.