October 9, Anchorage, USA
8:30 Opening remarks
8:45 Invited talk: HASC Corpus: Large Scale Human Activity Corpus for the Real-World Activity Understandings. Prof. Nobuo Kawaguchi, Nagoya University (pdf)
9:30 Exploring and Extending the Boundaries of Physical Activity Recognition. Reiss, DFKI
9:55 Unsupervised Model Generation for Motion Monitoring. Weber, DFKI
10:20 Coffee break
10:40 (Featured video) A Framework for Opportunistic Context and Activity Recognition. Hölz, JKU (pdf)
10:55 Collection and Curation of a Large Reference Dataset for Activity Recognition. Calatroni , ETHZ
11:20 Benchmarking classification techniques using the Opportunity human activity dataset. Sagha, EPFL
14:00 Invited talk: TBA. Dr. Kamil Kloch (Prof. Dr. Paul Lukowicz), U. Passau
14:45 Benchmarking ‘Radio Exercises’ Recognition with a Three-axis Accelerometer. Terumoto, Kyushu IT
15:10 FEOGARM: A Framework to Evaluate and Optimize Gesture Acquisition and Recognition Methods. Ruffieux, EIA-FR (pdf)
15:35 Coffee break
16:00 Opportunity challenge: Results and conclusions. Chavarriaga, EPFL (Slides)(Challenge contributions)
16:45 Conclusive remarks & discussion
Prof. Nobuo Kawaguchi received the B.E, M.E and Ph.D. in Computer Science from Nagoya University, Japan, in 1990, 1992, and 1997 respectively. From 1995 he was with Department of Electrical and Electronic Engineering and Information Engineering, School of Engineering, Nagoya University at the levels of assistant and associate professor. Since 2009, he has been a Professor of Department of Computational Science and Engineering, Graduate School of Engineering, Nagoya University. During 1999-2004, he was working with CIAIR (Center for Integrated Acoustic Information Research), and made a major contribution on its large scale in-car speech database which includes speech dialog with car-driving information for more than 500 subjects in the real-world driving environment. He also developed a location based timetable information system named "TimeTable.Locky" as a iPhone Application. The series of the system was downloaded more than a million times. Prof. Nobuo Kawaguchi has his research interest in the areas of Human Activity Recognition, Smart Environmental System and Ubiquitous Communication Systems. He is now serving a chair person of the Human Activity Sensing Consortium (HASC), Japan.
Dr. Kristof Van Laerhoven leads the Embedded Sensing Systems (ESS) group at Technische Universität Darmstädt. The ESS group investigates the topic of Long-term Activity Recognition with Wearable Sensors. In this project they develop both hardware and algorithms for small-scale activity sensors that recognize the type of activities that the user wearing the sensor performs. They collaborate closely with psychiatrists from King's College's Institute of Psychiatry to test their work in the field of bipolar patient monitoring, and have several long-term platform trials planned over the next five years. After several works on robotics and neural networks at Luc Steels' VUB AI lab, Dr. Van Laerhoven got a Ph.D. at the Embedded Interactive Systems group at the University of Lancaster in the United Kingdom with Hans Gellersen. Then he moved to the TU Darmstädt for a postdoc position with Bernt Schiele's Multimodal Interactive Systems group. After this, he was granted an Emmy Noether Research Group by the German Research Foundation (DFG), on the theme of Long-Term Activity Recognition with Wearable Sensors, which started in 2010.
Dr. Kamil Kloch received his M.S. in 2003 and Ph.D. in Computer Science in 2008, both from the Jagiellonian University in Kraków, Poland. In his Ph.D. he investigated algorithms for the on-line scheduling problem. Since 2009 he is a senior researcher and a deputy coordinator of the EU FP7 ICT project SOCIONICAL in the Embedded Systems Lab, University of Passau, Germany. His current research is focused on software tools and collaborative sensing on mobile devices.
Prof. Dr. Paul Lukowicz has a Ph.D. in Computer Science from the University of Karlsruhe in Germany. After his Ph.D., he went to ETH Zurich and then to a Professorship in Computer Engineering at the University of Medical Informatics and Technology in Hall in Tirol, Austria (UMIT) where his group worked on health related applications of pervasive and wearable computing and context recognition. Paul Lukowicz is Associate Editor in Chief, IEEE Pervasive Magazine and member of the Editorial Board Member Hindawi Advances in Human Computer Interaction. Between 2008 and 2010 he has been in charge of the Wearable Computing Department of the IEEE Pervasive Magazine. His research is devoted to adaptive, intelligent systems seamlessly integrated in the environment. This includes wearable computing, sensors and sensor networks, activity and context recognition, software tools, system models, and a wide range of pervasive computing applications. With particular interest in large-scale systems that self organize to cooperate in dynamic, opportunistic configurations. In the application area his group has a strong emphasis on health and wellness related systems.
Do not hesitate to contact the consortium.
We develop opportunistic activity recognition systems: goal-oriented sensor assemblies spontaneously arise and self-organize to achieve a common activity and context recognition. We develop algorithms and architectures underlying context recognition in opportunistic systems.
Subscribe to our newsletter for regular project updates.