-
Touradj Ebrahimi, Professor, EPFL [bio] [abstract]
Touradj EBRAHIMI received his M.Sc. and Ph.D., both in Electrical Engineering, from the Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland, in 1989 and 1992 respectively. In 1993, he was a research engineer at the Corporate Research Laboratories of Sony Corporation in Tokyo, where he conducted research on advanced video compression techniques for storage applications. In 1994, he served as a research consultant at AT&T Bell Laboratories working on very low bitrate video coding. He is currently Professor at EPFL heading its Multimedia Signal Processing Group. He is also the Convenor of JPEG standardization Committee. He was also adjunct Professor with the Center of Quantifiable Quality of Service at Norwegian University of Science and Technology (NTNU)between 2008 and 2012. Prof. Ebrahimi has been the recipient of various distinctions and awards, such as the IEEE and Swiss national ASE award, the SNF-PROFILE grant for advanced researchers, Four ISO-Certificates for key contributions to MPEG-4 and JPEG 2000, and the best paper award of IEEE Trans. on Consumer Electronics . He became a Fellow of the international society for optical engineering (SPIE) in 2003. Prof. Ebrahimi has initiated more than two dozen National, European and International cooperation projects with leading companies and research institutes around the world. He is a co-founder of Genista SA, a high-tech start-up company in the field of multimedia quality metrics. In 2002, he founded Emitall SA, start-up active in the area of media security and surveillance. In 2005, he founded EMITALL Surveillance SA, a start-up active in the field of privacy and protection. He is or has been associate Editor with various IEEE, SPIE, and EURASIP journals, such as IEEE Signal Processing Magazine, IEEE Trans. on Image Processing, IEEE Trans. on Multimedia, EURASIP Image Communication Journal, EURASIP Journal of Applied Signal Processing, SPIE Optical Engineering Magazine. Prof. Ebrahimi is a member of Scientific Advisory Board of various start-up and established companies in the general field of Information Technology. He has served as Scientific Expert and Evaluator for Research Funding Agencies such as those of European Commission, The Greek Ministry of Development, The Austrian National Foundation for Scientific Research, The Portuguese Science Foundation, as well as a number of Venture Capital Companies active in the field of Information Technologies and Communication Systems. His research interests include still, moving, and 3D image processing and coding, visual information security (rights protection, watermarking, authentication, data integrity, steganography), new media, and human computer interfaces (smart vision, brain computer interface). He is the author or the co-author of more than 200 research publications, and holds 14 patents. Prof. Ebrahimi is a member of IEEE, SPIE, ACM and IS&T.
Wearable Computing – an Overview
Together with Internet of Things, Wearable Computing is becoming an important focus of interest to the point that it is being foreseen by some as the next step in the (r)evolution of ICT beyond mobile phones. In this talk we give an overview of the state of the art in wearable technologies from past to near future by examining a number of concrete cases as illustrative examples. Beyond this, we will attempt to better understand the potential features wearable computing can offer in addition to those already brought by mobile computing and communications in recent years. The impact of such wearable technologies, both good and less positive, as well as challenges, obstacles and future trends will also be discussed. The complex emerging ecosystem of wearable computing is then explored and a few conclusions are drawn along with potential avenues in future where efforts need to be concentrated in order to make wearable computing leap beyond the hype it represents today, to finally result in more mature, more reliable and more dependable products and services.
-
Ramesh Jain, Professor, University of California, Irvine [bio] [abstract]
Ramesh Jain is an entrepreneur, researcher, and educator.
He is a Donald Bren Professor in Information & Computer Sciences at University of California, Irvine where he is doing research in Event Web and experiential computing. Earlier he served on faculty of Georgia Tech, University of California at San Diego, The university of Michigan, Ann Arbor, Wayne State University, and Indian Institute of Technology, Kharagpur. He is a Fellow of ACM, IEEE, AAAI, IAPR, and SPIE. His current research interests are in processing massive number of geo-spatial heterogeneous data streams for building Smart Social System. He is the recipient of several awards including the ACM SIGMM Technical Achievement Award 2010.
Ramesh co-founded several companies, managed them in initial stages, and then turned them over to professional management. These companies include PRAJA, Virage, and ImageWare. Currently he is working with Krumbs, a situation aware computing company. He has also been advisor to several other companies including some of the largest companies in media and search space.
Personal Lifestyle and Health
A person’s lifestyle is the most controllable factor affecting her health. Advances in technology have made it now possible to analyze and understand an individual’s life style from passively collected objective data streams to build her model and predict important events in her life. Wearable/mobile sensors, smart homes, social networks, e-mail, calendar systems, and environmental sensors continuously generate data streams that can be used as lifestyle data. By assimilating and aggregating these multi-sensory data streams, we create an accurate chronicle of a person’s life. By correlating life events with other events, and using a novel causality exploration framework, one can build model of the person. Such a model, that we call objective self, is the objective characterization of a person’s health, social life, and other aspects. We illustrate how to build an objective personal chronicle, called personicle, for a person. By building personicle for a long period and applying pattern recognition, it is possible to build a model of the person that could result in actionable insights and alerts in everyday life. We will present our ideas related to objective self its impact on societal health, and its use in making decisions.
-
Edward J. Delp, Professor, Purdue University [bio] [abstract]
Edward J. Delp was born in Cincinnati, Ohio. He received the B.S.E.E. (cum laude) and M.S. degrees from the University of Cincinnati, and the Ph.D. degree from Purdue University. In May 2002 he received an Honorary Doctor of Technology from the Tampere University of Technology in Tampere, Finland. In 2008 he was named a Distinguished Professor and is currently The Charles William Harrison Distinguished Professor of Electrical and Computer Engineering and Professor of Biomedical Engineering and Professor of Psychological Sciences (Courtesy) at Purdue University His research interests include image and video processing, image analysis, computer vision, image and video compression, multimedia security, medical imaging, multimedia systems, communication and information theory.
Dr. Delp is a Fellow of the IEEE, a Fellow of the SPIE, a Fellow of the Society for Imaging Science and Technology (IS&T), and a Fellow of the American Institute of Medical and Biological Engineering.
Food Image Analysis:The Big Data Problem You Can Eat!
Six of the ten leading causes of death in the United States can be directly linked to diet. Dietary intake, the process of determining what someone eats during the course of a day, provides valuable insights for mounting intervention programs for prevention of many of the above chronic diseases. Measuring accurate dietary intake is considered to be an open research problem in the nutrition and health fields. In the Technology Assisted Dietary Assessment (TADA) project at Purdue University, we are developing imaging based tools in order to automatically obtain accurate estimates of what foods a user consumes. We have developed a novel food record method using a mobile device and the embedded camera. This is known as Mobile Food Record (mFR). Images acquired before and after foods are eaten can be used to estimate the amount of food consumed. This project is the result of a large collaboration between various departments at Purdue University, the University of Hawaii, and the Curtin University of Technology in Australia. This paper will describe the current status of the TADA project and overview problems that still need to be addressed.
-
Lin Yuan, PhD student, EPFL [bio] [abstract]
Lin Yuan received his B.S. and M.Sc. degrees in both Electronic Engineering from University of Electronic Science and Technology of China (UESTC) and Swiss Federal Institute of Technology in Lausanne (EPFL), in 2011 and 2013 respectively. Since then he has been working as a Ph.D. candidate in the Multimedia Signal Processing Group of EPFL, supervised by Prof. Touradj Ebrahimi. He was with Technicolor R&I in Hannover for one-year internship between 2012-2013. His work has been focused on image privacy protection, image context and emotion analysis.
A Smart Phone Demonstrator for Food Recognition Based on Deep Learning
Well-being is becoming a topic of great interest and an essential factor linked to improvements in the quality of life. Modern information technologies have brought a new dimension to this topic. It is now possible, thanks to various wearable devices (health bands, smart watches, smart clothes, etc.), to gather a wide range of information from subjects such as number of steps walked, heart rate, skin temperature, skin conductivity, transpiration, respiration, etc. and analyze this information in terms of the amount of calories spent, level of stress, duration and quality of sleep, etc. An accurate estimation of daily nutritional intake provides a useful solution for keeping healthy and to prevent diseases. However, it is not easy to assess the nutritional value of food and beverage consumed by subjects in an au- tomatic and accurate way. This presentation reports experiments on food/non-food clas-sification and food recognition using a GoogLeNet model based on deep convolutional neural network. The experiments were conducted on two image datasets created by our own, where the images were collected from existing image datasets, social media, and imaging devices such as smart phone and wearable cameras. Experimental results show a high accuracy of 99.2% on the food/non-food classification and 83.6% on the food category recognition.
-
Xavier Comtesse, Former Director, Think Tank Avenir Suisse [bio] [abstract]
Xavier Comtesse received his Master of Science in Mathematics and Ph.D. in Computer Science from University of Geneva. From seventies, he has been involved in Communications and Computer Science. Since then he has been behind various initiatives in publishing (created Editions Zoé), in communications (initiated one of the local radio stations: Tonic) and in telecommunications (founded a start-up: le Concept Moderne). He joined the Swiss government in 1992 as personal assistant to the Secretary of State in Science, Research and Education. In 1995 he was nominated as a scientific diplomat to the Swiss Embassy in Washington, DC, USA. He became the first Science Consul for Switzerland in Boston, MA, USA, in 2000, where he created the Swissnex. In 2002 he became the first Director of the Think Tank Avenir Suisse based in French part of Switzerland, focusing mainly on metropolitan and innovation issues. In 2012, he co-founded the Swiss Creative Center for the Chamber of Commerce and Industry of Neuchatel dedicated to new industrial revolution (FabLab, Design Thinking and Think Tank). He created together with Elmas Mock (co-inventor of Swatch) a discussion group called Watch Thinking, in 2014, which is considered as the first industrial think thank addressing the future of watch industry.
Smartwatches: More Smart than Watch!
“Smart” watches are referred to as “connected” watches in French. One could wonder why such a different choice in the naming. This could be the result of a subconscious focus on the “connectivity” as opposed to “smartness” feature such devices offer. Although, this observation may seem too trivial, it could also be the indication of a symptomatically divergent vision of the future evolution of the good old watch as envisioned by different actors. The French naming hints into the fact that the future of the watch resides in its connectivity with the world of the Internet of Things via a plethora of sensors they are enhanced with. The Anglo-Saxons however, especially Californians, are betting on Artificial Intelligence, Big Data, Machine Learning, etc. as intrinsic features which should also be included in the future of the watch. In other words, they see a connected and smart watch multiplying our intellectual and sensory abilities several fold. If we start thinking like them, would that change our perspective on the future of the watch? The connected and smart watch, we know now, is here to stay and will continue to challenge the well-established Swiss watch industry. By opening this new path to an alternative future for watches, the current generations of watches may well be supplanted for good and forever. This has been the case in other industries! Remember the music industry: vinyl first, then magnetic tapes, followed by audio cassettes, MP3, and finally the streaming, which taking turns, each cannibalized its predecessor … in some cases even leading to their complete extinction. The history of the watch is not immune to similar industrial (r)evolutions! For if the smart watches are potentially able to bring such superior values that they could eventually do away with the traditional watches or at least have a significant impact in their global market shares as once happened with audio cassettes mentioned above. Once this happens, the pressure of desire for “smartness” from consumers will become so strong that even tomorrow’s luxury watches will have to submit to it. Look at Ferrari! They gave into the change from their consumers, to bring just another example! No doubt, tomorrow’s luxury will have to be smart too. Leaving an increasingly shrinking niche for vintage to satisfy the minds of a few collectors. A clear and tragic example of such an evolution can be found in the toy industry with the advent of video games that pushed aside many brands such as “Märklin” which are nothing more than vintage today! The arrival of smart watches coincides with a parallel trend in Big Data, Data Mining, Machine Learning and all the apparatus of artificial intelligence in the digital economy. More than one million jobs will be created in this area in the US alone in the next two to three years. This is what is called “Revolution 4.0”. Americans prefer to speak of “smart industry revolution”. Again, the emphasis is on the “smart”! Why such an insistence on a word? Is it just marketing? Or is it hiding an important economic reality behind it? The answer to the last question seems to be yes. Artificial Intelligence has found a second life thanks to an efficient analysis of large amounts of unstructured data, allowing for extraction of efficient models to predict and to anticipate. Here resides the real game changing revolution behind smartness of a connected watch…
-
Panos Nasiopoulos, Professor, The University of British Columbia [bio] [abstract]
Panos Nasiopoulos earned his bachelor’s degree in physics from the Aristotle University of Thessaloniki (1980), Greece, and his bachelor’s (1985), master’s (1988), and Ph.D. (1994) degrees in electrical and computer engineering from the University of British Columbia (UBC), Canada. He is a professor with the Department of Electrical and Computer Engineering and the former Director of ICICS and the Master of Software Systems at UBC. Before joining UBC, he was the President of Daikin Comtec US and Executive Vice President of Sonic Solutions. He is a registered professional engineer in British Columbia, a fellow of the Canadian Academy of Engineering, and has been an active member of the Standards Council of Canada, MPEG, ACM and IEEE.
Watches that Help You Make Better Sense of Your Wearable and Personal Health Data
We add missing intelligence to sensor captured bio-signals (blood pressure, heart rate, activity, sleeping quality), leveraging analytics to predict health risks. Our “engine” performs big data analysis to provide personalized health recommendations to the users, improving their quality of life and helping them live healthier lives. All this without changing the look of the oldest wearable device, the classic WATCH!
-
Silvano Freti, Director, Laboratoire Dubois [bio] [abstract]
Silvano Freti graduated in Material Science at EPFL in 1981. After more than 20 years in various R&D positions within the industry in Switzerland and overseas, he completed is academic cursus with the EPFL/UNIL EMBA in Management of Technology in 2004 and 2007. He joined Laboratoire Dubois in 2008 and is managing this Service Lab since the end of 2011. Active in the watch standardisation from 2012 on, he was appointed this year as chairman of both the Swiss Watch Industry Standards (NIHS) and the ISO/TC 114 dedicated to Horology.
Laboratoire Dubois – Testing Watches and More
Although traditional watches and modern wearables of any kind are objects originated by dissimilar technologies, with different historical background and industries with different degree of maturity, many basic or implicit requirements converge to fulfil the expectations of customers. For instance, reliability and water resistance are two typical examples of properties which need to be ensured before placing a product on the market. Another example is the presence or the release of substances regulated by the same legislations.
The presentation will cover the test range routinely performed for the traditional watch industry and on some of the common customer’s expectations form the standardization standpoint. Similarities or divergences on watch standard requirements compared with the wearable ones will be outlined -
Masahito Kawamori, Project Professor, Keio University, Japan [bio] [abstract]
Masahito KAWAMORI is a Project Professor at the Graduate School of Media and Governance, Keio University, Japan. Before joining Keio University, he worked for 25 years as a senior research engineer at NTT (Nippon Telegraph and Telephone) R&D, Japan, where he did research and development in artificial intelligence, multimedia, convergence of fixed/mobile telecommunication, etc. Since 1998 until 2002, he was a research member of the “Creating the Brain” Research Project of the JST (Japan Science and Technology Agency)’s CREST (“Core Research for Evolutional Science and Technology”) Program, and in 2004, he led the development with the University of Tokyo, Japan, on a health information system using wearable sensors that measured the hippocampal function in the brain to detect early signs of dementia. He is currently the Rapporteur of Question 28 “Multimedia Framework for e-Health Applications” in the Study Group 16 (Multimedia), of ITU-T.
Textile Wearables – the Japanese Landscape
Textile manufacturers are now introducing “smart textiles” into the market. These smart textiles can be used as sensor devices to collect bio-data such as body temperature, heart-rate, etc. Smart textiles are expected to enable textile wearable sensor devices and open many new applications and services. Some of them are already in use in the market, especially for monitoring health level and workplace safety. This situation was even emphasized at an event on smart textile during the recent CEATEC (Combined Exhibition of Advanced Technologies) held near Tokyo, Japan, on 4-7 October 2016, where use cases and services using wearable sensors with smart textile were introduced. In this presentation, I will introduce and describe two examples of textile wearable systems, and discuss some issues related to standardization.
-
Satomi Michitsuta, Senior Wearable Technology Manager, Development Timepiece, Casio, Japan [bio] [abstract]
Satomi has experience in Product development and Project management. Satomi has good knowledge of low power wireless technology and its applications to wearables and he has experience in managing Application development. Satomi has over 30 years’ experience in development of Watches as consumer electronics devices with global perspective. Satomi has led the development of “Smart Watch” functionally. Satomi has skills in product development (initial product idea to development) and, launch of new products. Satomi lead Specification working group to develop Bluetooth profiles. Satomi have ability to manage several projects. Satomi has good knowledge of low power Bluetooth as a IoT technology. Over 15 years’ experience working in an international role.
Smartwatch — New user Experience
Description of the Background of Casio’s technology development. Description of Casio wearable strategy. Issues raised for the next generation wearable technology.
-
Frédérique de Waresquiel, Project Manager – Connected Devices, TAG Heuer [bio] [abstract]
Joined TAG Heuer early 2016 as Project Manager for Connected Technology. She is in charge of defining and developing new wearable products with a focus on the hardware part. Formerly spent 10 years at L’Oréal in Paris, where she held several functions in Packaging Research, Product Development for Lancôme, and Point of sale Furniture Sourcing for various luxury brands of the group (Yves Saint-Laurent, Giorgio Armani, Biotherm…). She is a graduate from Ecole des Mines de Paris, in Innovation and Product Design.
TAG Heuer Connected: how TAG Heuer innovated to adapt to the smartwatch world
Since its creation in 1860, TAG Heuer, a Swiss luxury watch making company, has always been driven by innovation and avant-garde spirit. With the recent advent of smartwatches, there was an opportunity that TAG Heuer couldn’t miss: their first smartwatch, the TAG Heuer Connected, was launched in November 2015 in record time. How was this made possible ? What were the innovations attached to this product ? What were the main challenges ? The presentation will give feedback on this experience.
-
Kiyoharu Aizawa, Professor, The University of Tokyo [bio] [abstract]
Prof. Kiyoharu Aizawa, received the B.E., the M.E., and the Dr.Eng. degrees in Electrical Engineering all from the University of Tokyo, in 1983, 1985, 1988, respectively. He is currently a Professor at the Department of Information and Communication Engineering of the University of Tokyo. He was a Visiting Assistant Professor at University of Illinois from 1990 to 1992.
His research interest is in image processing and multimedia applications. He is one of the pioneers of life logging fields, and recently he is focusing on multimedia food logging for dietary assessment. The outcome of his research, FoodLog, is made available to general public.
He received the 1987 Young Engineer Award and the 1990, 1998 Best Paper Awards, the 1991 Achievement Award, 1999 Electronics Society Award from IEICE Japan, and the 1998 Fujio Frontier Award, the 2002 and 2009 Best Paper Award, and 2013 Achievement award from ITE Japan. He received the IBM Japan Science Prize in 2002.
He is an IEEE Fellow. He is currently a Senior Associate Editor of IEEE Trans. Image Processng, and Associate Editor of ACM TOM, APSIPA Transactions on Signal and Information Processing, and International Journal of Multimedia Information Retrieval. He served as the Editor in Chief of Journal of ITE Japan, an Associate Editor of IEEE Tans. Image Processing, IEEE Trans. CSVT and IEEE Trans. Multimedia. He has served a number of international and domestic conferences; he was a General co-Chair of ACM Multimedia 2012.
Practice of FoodLog, a Multimedia Food Recording Tool
Our daily food is an emerging target for multimedia. Health care field is paying considerable attention on dietary control, which requires that individuals record what they eat. We developed and made publicly available a novel smartphone application, that is, FoodLog, a multimedia food recording tool that allows users to take photos of their meals and to produce textual food records. Unlike conventional smartphone-based food recording tools, it allows users to employ meal photos to help them to input textual descriptions assisted by image recognition and retrieval. We have been operating FoodLog for general public and collected more than 4M food records for three years. In this talk, we will talk about the outline of FoodLog, and share our findings in the large amount of data about natures of food recording data produced by general public users.
-
István Sebestyén, Secretary General, Ecma International [bio] [abstract]
Dr. István Sebestyén has been Secretary General of Ecma International in Geneva since 2007. Before joining Ecma he has been Director of Standards in Siemens, Munich for 21 years, mostly in the areas of telecommunication terminals and protocols, multimedia and enterprise networks. He has been doing standardization for more than 30 years in various SDO and For a, like ITU, ISO, ETSI, DIN, IMTC, where he has hold several leading positions. For over 20 years he has been also lecturing at the University of Klagenfurt in Austria and the Technical University of Graz. Before that between 1978-1984 he has been Research Scholar at the International Institute for Applied Systems Analysis in Laxenburg, Austria and was involved in early international computer networking projects and many interdisciplinary ICT technology related studies.
Ecma and “Wearable” Standardization
The presentation is just a short welcome to the summit on behalf of Ecma International. Then very brief introduction to Ecma (most just for reading) and some thoughts about what Ecma may do in the future in the area of “Wearables” standardization based on the lessons learned from the Wearbale 2016 workshop.
-
David Atienza Alonso, Professor, EPFL [bio] [abstract]
David Atienza Alonso is Associate Professor of Electrical and Computer Engineering and Director of the Embedded Systems Laboratory (ESL) at EPFL, Switzerland. He received his MSc and PhD degrees in Computer Science and Engineering from UCM in Spain, and IMEC in Belgium in 2001 and 2005, respectively. His research interests focus on system-level design methodologies for multi-core system-on-chip architectures (MPSoC) and embedded systems. In these fields, he is co-author of more than 200 publications, and six US patents, and received several best paper awards in top conferences. He received the IEEE CEDA Early Career Award in 2013, the ACM SIGDA Outstanding New Faculty Award in 2012 and a Faculty Award from Sun Labs at Oracle in 2011. He was Distinguished Lecturer of IEEE CASS in 2014 and 2015. He is senior member of ACM and an IEEE Fellow.
Designing Ultra-Low Power Wearable Systems for the Internet-of-Things Era
Latest progress of manufacturing technologies has enabled the design of low cost, compact and high-performance wearable embedded systems. These new wearable devices are multi-parametric sensing devices that can be deployed ubiquitously in order to enable the rise of the Internet-of-Things (IoT) Era. Nonetheless, the power requirements and resource-constrained nature of wearable systems can result in degraded performance or a global energy crisis if they are massively deployed in the new IoT context. In this presentation I will introduce how the future generation of ultra-low power wearable systems needs to adopt a new system-level approach to synergistically design both hardware and software components. These new systems will need to learn from living organisms and include subsequently more onboard intelligence, include specialization in architecture and gracefully adapt their energy consumption for their possible different working conditions.
-
Michele Nitti, Assistant Professor, University of Cagliari, Italy [bio] [abstract]
Michele Nitti is an Assistant Professor at the University of Cagliari, Italy. He received a M.Sc. degree in Telecommunication Engineering with full marks in 2009. In 2010 he worked for a year as a researcher at the National Interuniversity Consortium for Telecommunications (CNIT) at Cagliari, on the development of models for network connectivity in mobile ad hoc network. From February to August 2013, he was a visiting PhD student at the Department of Management, Technology and Economics at ETH Zurich, Switzerland. In 2014, he was awarded with the Ph.D. degree in Electronic and Computer Engineering with Doctor Europaeus mention. His main research interests are on Internet of Things (IoT), particularly on the creation of a network infrastructure to allow the objects to organize themselves according to a social structure.
Can the Wearables be Social?
Wearable devices are at the heart of every discussion related to the Internet of Things (IoT) and of the full range of new pervasive capabilities they can bring, since they represent the first point of contact between people and the IoT. Nevertheless, the complexity derived from the ever-increasing variety of wearable devices and technologies involved, and the even more rapid increase of the range of possible applications calls for new paradigms of interaction among objects. In this presentation, I will introduce the Social Internet of Things (SIoT) concept, which is intended as a social network where every node is an object capable of establishing social relationships with other things in an autonomous way according to the rules set by the owner. This new paradigm focuses on the needs of individuals by leveraging on objects with a certain degree of social awareness, virtualized in the network and cloud and that can establish trustworthy relations among things that are friends.