Dipl.-Ing. Marc Kurz
|
|
Universitätsassistent (Univ.-Ass.) Institut für Pervasive Computing Office Hour: Mo 10:00 - 11:00 Phone: +43-732-2468-8527 Fax: +43-732-2468-8426 E-Mail: kurz ät pervasive döt jku döt at |
Curriculum Vitae: download cv_kurz.pdf
| Lectures in 2011WS | ||
| 340.024 | UE G1 | Algorithmen und Datenstrukturen 2 |
| 340.025 | UE G2 | Algorithmen und Datenstrukturen 2 |
| 340.026 | UE G3 | Algorithmen und Datenstrukturen 2 |
| Projects |
| OPPORTUNITY: FP7-ICT-2007-C, FET open Goals: The project aims at developing mobile systems to recognize human activity with dynamically varying sensor setups. We refer to such systems as opportunistic, since they take advantage of sensing modalities that just happen to be available, rather than forcing to deploy specific, application dependent sensor systems. Partners: ETH Zurich, UoPassau, IDIAP Status: started February 1st, 2009 |
| PowerIT: FFG Call: FIT-IT Embedded Systems & Semiconductors, 2nd Call Goals: This project will investigate on potentials to reduce energy inefficiency by the development of methods and solutions based on implicit user interaction. Methodologically, it will attempt to exploit opportunistic sensor configurations to establish context information, in order to avoid standby losses of electronic equipment, machines and appliances. |
| Betreute Bakk-/Masterarbeiten |
| On the Evolution of Wearable Sensors Systems in an opportunistic Activity Recognition System: Problem Definition: This Master’s Thesis investigates how new sensors can be used in a recognition chain by training them with the existing ones. Thereby, the focus shall be the question how sufficient the dynamic transfer learning approach from a sensor jacket (or alternatively from one or more smart phones) to more unobtrusive sensors (e.g., wrist worn watch, sensor on the shoe), is. |
| Porting and Executing Activity Recognition Algorithms on the Sensing Platform: Description: General purpose of the work is to find out which parts of the activity recognition chain (i.e., sensor signal acquisition, signal processing, feature extraction, classification) can be executed directly on the sensing platform. The platform that has to be used within this master thesis is the so-called Token, which will be provided by the Institute for Pervasive Computing. Details of the hardware can be found below, in the corresponding section. |
| Distributed Activity Recognition: Beschreibung Im Rahmen dieser Arbeit soll ein bestehendes Aktivitätserkennungssystem, welches mit Java/OSGi implementiert wurde, weiterentwickelt werden, um auf mehreren physischen Knoten verteilt lauffähig zu sein. Dies beinhaltet zunächst die Einarbeitung in das bestehende System, um anschließend die bestehenden Komponenten zu erweitern, um in einer verteilten Umgebung zu operieren. |
| Bipedale Aktivitätserkennung mit Beschleunigungssensoren: Beschreibung Im Rahmen dieser Arbeit soll untersucht werden wie und zu welchem Maß bipedale Aktivitätserkennung anhand von an den Beinen angebrachten Beschleunigungssensoren (zB in und an den Schuhen integriert) möglich ist. Dazu soll ein System entwickelt und implementiert werden, welches geeignete Trainings-, Klassifikations- und Feature Extraktions-Methoden integriert, um Aktivitäten von Personen mithilfe von Beschleunigungssensoren zu erkennen. |
| Arm-Sensor-Based Activity Recognition: Beschreibung Im Rahmen dieser Arbeit soll ein Aktivtätserkennungssystem entwickelt werden, welches Aktivitäten von Personen mithilfe von an den Händen und Armen angebrachten Beschleungigungssensoren erkennt. Dazu soll ein System entwickelt und implementiert werden, welches geeignete Trainings-, Klassifikations- und Feature Extraktions-Methoden integriert, um Aktivitäten von Personen mithilfe von Beschleunigungssensoren zu erkennen. |
Publications (13)
| 2011 |
The OPPORTUNITY Framework and Data Processing Ecosystem for Opportunistic Activity and Context Recognition International Journal of Sensors, Wireless Communications and Control, Special Issue on Autonomic and Opportunistic Communications, Bentham Science Publishers, ISSN: 2210-3279, 2011.
to appear December 2011
|
Activity Recognition in Opportunistic Sensor Environments Proceedings of the 2nd European Future Technologies Conference and Exhibition 2011 (FET 11), Procedia Computer Science, Editors: Elisabeth Giacobino, Rolf Pfeifer, Elsevier, Vol. 7, pp. 173-174, 2011.
|
Real-Time Transfer and Evaluation of Activity Recognition Capabilities in an Opportunistic System Third International Conference on Adaptive and Self-Adaptive Systems and Applications (ADAPTIVE2011), September 25-30, Rome, Italy, ISBN: 978-1-61208-156-4, pp. 73-78, 2011.
|
A Framework for Opportunistic Context and Activity Recognition 9th International Conference on Pervasive Computing (Pervasive2011), June 12-15, San Francisco, CA, USA, 2011.
Conferences: 9th International Conference on Pervasive Computing (Pervasive2011)
Projects: OPPORTUNITY Master Thesis: Distributed Activity Recognition Videos: View A Framework for Opportunistic Context and Activity Recognition stream |
Dynamic Quantification of Activity Recognition Capabilities in Opportunistic Systems Fourth Conference on Context Awareness for Proactive Systems: CAPS2011, 15-16 May 2011, Budapest, Hungary, 2011.
Conferences: Fourth Conference on Context Awareness for Proactive Systems: CAPS2011
Projects: OPPORTUNITY Master Thesis: Distributed Activity Recognition |
Activity recognition in opportunistic sensor environments The European Future Technologies Conference and Exhibition (FET11), 4-6 May, Budapest, Hungary, pp. 2, 2011.
Projects: OPPORTUNITY
|
| 2010 |
Robust activity recognition for assistive technologies: Benchmarking ML techniques Workshop on Machine Learning for Assistive Technologies at the Twenty-Fourth Annual Conference on Neural Information Processing Systems (NIPS-2010), 2010.
Projects: OPPORTUNITY
|
Sensor Abstractions for Opportunistic Activity and Context Recognition Systems 5th European Conference on Smart Sensing and Context (EuroSSC 2010), November 14-16, Passau Germany, Editors: Lukowicz, Paul; Kunze, Kai; Kortuem, Gerd, Springer LNCS, Berlin-Heidelberg, ISBN: 978-3-642-16981-6, pp. 135-149, 2010.
Conferences: The 5th European Conference on Smart Sensing and Context (EuroSSC)
Projects: OPPORTUNITY |
Goal-Driven opportunistic Sensing 12th ACM International Conference on Ubiquitous Computing (Ubicomp 2010), Doctoral Colloquium, Copenhagen, Denmark, September 26 - 29, 2010, Adjunct Proceedings, 2010.
|
Towards a Framework for opportunistic Activity and Context Recognition 12th ACM International Conference on Ubiquitous Computing (Ubicomp 2010), Workshop on Context awareness and information processing in opportunistic ubiquitous systems, Copenhagen, Denmark, September 26 - 29, 2010, 2010.
|
Collecting complex activity data sets in highly rich networked sensor environments Proceedings of the Seventh International Conference on Networked Sensing Systems (INSS), Kassel, Germany, IEEE Computer Society Press, 2010.
Projects: OPPORTUNITY
|
Walk-through the OPPORTUNITY dataset for activity recognition in sensor rich environments Adjunct Proceedings of the Eighth International Conference on Pervasive Computing, Helsinki, Finland, 2010.
|
| Teaching History | ||
ST 2011 |
Praktische Informatik I
|
|
ST 2011 |
Praktikum Pervasive Computing
|
|
WT 2010/2011 |
Algorithmen und Datenstrukturen 2
|
|
ST 2010 |
Praktische Informatik I
|
|
|
Last update: June 25th, 2011 |