IT-Ecosystems subproject “LocCom”

November 5th, 2012  |  Published in Research

Classical approaches of computer science do not scale well for today’s large and complex software-intensive systems. Software systems cannot be considered in isolation, since they are connected among each other and interact massively. Instead they are to be designed as parts of a larger IT Ecosystem. In analogy to biological ecosystems, IT Ecosystems are based on the balance between individuals (autonomy) and sets of rules (control) defining equilibria within an IT Ecosystem. Maintaining and continuously evolving IT Ecosystems requires deep understanding of this balance.
In the IT Ecosystems subproject LocCom (local communities) we develop methods, concepts, and tools for decentralized IT Ecosystems. Our part is especially the resaerch of context detection, handling and pattern recognition.

One example is smart phones, that have become a powerful platform for wearable context recognition. We present a service/cloud-based recognition architecture which creates an evolving classification system using feedback from the user community. The approach utilizes classifiers based on fuzzy inference systems which use live annotation to personalize the classifier instance on the device. Our recognition system is designed for everyday use: it allows flexible placement of the device
(no assumed or fixed position), requires only minimal personalization effort from the user (1–3 minutes per activity) and is capable of detecting a high number of activities. The components of the service are shown in an evaluation scenario, in which recognition rates up to 97% can be achieved for ten activity classes.

 

External links:

Start/End:

2009-2011

Partners:

Technische Universität Clausthal, Leibniz Universität Hannover

Research Topics:

Context detection and handling, pattern recognition

Publications

2013

Dawud Gordon, Jan-Hendrik Hanne, Martin Berchtold, Ali Asghar Nazari Shirehjini, Michael Beigl (2013) Towards Collaborative Group Activity Recognition Using Mobile Devices, Mobile Networks and Applications 18(3), p. 326-340, url, doi:10.1007/s11036-012-0415-x

2011

Dawud Gordon, Jan-Hendrik Hanne, Martin Berchtold, Takashi Miyaki, Michael Beigl (2011) Recognizing Group Activities using Wearable Sensors, 8th International ICST Conference on Mobile and Ubiquitous Systems (MobiQuitous 2011), p. 350 - 361, Copenhagen, Denmark: Springer Berlin Heidelberg, url

Dawud Gordon, Jan-Hendrik Hanne, Martin Berchtold, Takashi Miyaki, Michael Beigl (2011) An Experiment in Hierarchical Recognition of Group Activities Using Wearable Sensors, The 7th International and Interdisciplinary Conference on Modeling and Using Context 6967, Michael Beigl, Henning Christiansen, Thomas R. Roth-Berghofer, Anders Kofod-Petersen, Kenny R. Coventry, Hedda R. Schmidtke (ed.), p. 104-107, Karlsruhe, Germany: Springer Berlin Heidelberg, url, doi:10.1007/978-3-642-24279-3

Matthias Budde, Martin Berchtold, Michael Beigl (2011) Activity Recognition on Mobile Phones - Why do we need it and how can it be done?, The 9th International Conference on Pervasive Computing (Pervasive 2011), Best Video Nominee, watch on youtube [expand]

Martin Berchtold, Henning Günther, Matthias Budde, Michael Beigl (2011) Scheduling for a Modular Activity Recognition System to Reduce Energy Consumption on SmartPhones, 24th International Conference on Architecture of Computing Systems (ARCS 2011), Second Workshop on Context-Systems Design, Evaluation and Optimisation (CoSDEO 2011), VDE Verlag, pdf

2010

Henning Günther, Firas El Simrany, Martin Berchtold, Michael Beigl (2010) A Tool Chain for a Lightweight , Robust and Uncertainty-based Context Classification System ( CCS ), 23rd International Conference on Architecture of Computing Systems (ARCS), 1st Workshop on Context-Systems Design, Evaluation and Optimization (CoSDEO), pdf

Martin Berchtold, G Henning, Michael Beigl (2010) A Demonstration of a Robust Context Classification System ( CCS ) and its Context ToolChain ( CTC ), Demonstration on the Eighth International Conference on Pervasive Computing (Pervasive'10), pdf

Martin Berchtold, Matthias Budde, Hedda R. Schmidtke, Michael Beigl (2010) An Extensible Modular Recognition Concept that Makes Activity Recognition Practical, 33rd Annual German Conference on Advances in Artificial Intelligence (KI 2010, p. 400-409, Springer Berlin / Heidelberg

Martin Berchtold, Matthias Budde, Dawud Gordon, Hedda R. Schmidtke, Michael Beigl (2010) ActiServ: Activity Recognition Service for mobile phones, International Symposium on Wearable Computers (ISWC) 2010 i, p. 1-8, IEEE, Best Paper Nominee, url, doi:10.1109/ISWC.2010.5665868

2009

Leonardo Weiss F. Chaves, Martin Berchtold, Christian Decker, Till Riedel (2009) Enhanced item tracking using selective querying, url

Martin Berchtold, Michael Beigl (2009) Increased Robustness in Context Detection and Reasoning Using Uncertainty Measures: Concept and Application, AmI '09: Proceedings of the European Conference on Ambient Intelligence, p. 256-266, Berlin, Heidelberg: Springer-Verlag, doi:10.1007/978-3-642-05408-2_30

2008

Martin Berchtold, Till Riedel, Michael Beigl, Christian Decker, Christian Bittel (2008) Quality of Location: Estimation, System Integration and Application, Fifth International Conference on Networked Sensing Systems, doi:10.1109/INSS.2008.4610924

Martin Berchtold, Till Riedel, Christian Decker, Kristof Van Laerhoven (2008) Gath-Geva specification and genetic generalization of Takagi-Sugeno-Kang fuzzy models, 2008 IEEE International Conference on Systems Man and Cybernetics, p. 595-600, Ieee, url, doi:10.1109/ICSMC.2008.4811342

Martin Berchtold, Till Riedel, Michael Beigl, Christian Decker (2008) AwarePen - Classification Probability and Fuzziness in a Context Aware Application, UIC 08 Proceedings of the 5th international conference on Ubiquitous Intelligence and Computing, p. 647-661, Springer-Verlag, url, doi:10.1007/978-3-540-69293-5_51

Christian Decker, Martin Berchtold, Leonardo Weiss F Chaves, Michael Beigl, Daniel Roehr, Till Riedel, Monty Beuster, Thomas Herzog, Daniel Herzig (2008) Cost-Benefit Model for Smart Items in the Supply Chain, The Internet of Things 4952, p. 155-172, Springer Berlin Heidelberg, pdf, doi:10.1007/978-3-540-78731-0_10

Till Riedel, Philipp Scholl, Christian Decker, Martin Berchtold, Michael Beigl (2008) Pluggable real world interfaces Physically enabled code deployment for networked sensors, Networked Sensing Systems, 2008. {INSS} 2008. 5th International Conference on, p. 111-114, doi:10.1109/INSS.2008.4610909

Monty Beuster, Michael Beigl, Daniel Röhr, Till Riedel, Christian Decker, Martin Berchtold (2008) Matrix Routing -- An Interference Range Insensitive Routing Protocol for Wireless Sensor Networks, 2008 International Symposium on Applications and the Internet, p. 137-140, Washington, DC, USA: IEEE, url, doi:10.1109/SAINT.2008.47

Daniel Röhr, Michael Beigl, Monty Beuster, Stephan Sigg, Christian Decker, Till Riedel, Martin Berchtold (2008) Developing a Virtual Environment for better Sensory Perception, Fifth International Conference on Networked Sensing Systems. June 17 - 19, 2008, Kanazawa, Japan, pdf

Till Riedel, Michael Beigl, Martin Berchtold, Christian Decker, A Puder (2008) Implicit Middleware - A Ubiquitous Abstract Machine, On the Move to Meaningful Internet Systems: OTM 2008 Workshops (Persys 2008), LNCS Volume 5333/2008, p. 830-840, Springer Berlin / Heidelberg, pdf, doi:10.1007/978-3-540-88875-8_108

2007

Christian Decker, Till Riedel, Martin Berchtold, Philipp Scholl, Albert Krohn, Michael Beigl, Monty Beuster, Daniel Röhr, Manabu Isomura (2007) Collaborative Business Items. 5th International Conference on Pervasive Computing, Toronto, Canada, In Advances in Pervasive Computing, Late Breaking Results, Austrian Computer Society, ISBN 978-3-85403-219-9, pp 33-36, 2007

Till Riedel, Christian Decker, Martin Berchtold, Michael Beigl (2007) Life Cycle Management of Pervasive Services, 5th International Conference on Pervasive Computing, Toronto, Canada, In Advances in Pervasive Computing (Late Breaking Results), p. 58-65, Austrian Computer Society

T Riedel, C Decker, M Berchtold, A Krohn, M Beigl (2007) Autoannotated Skating Maps, Networked Sensing Systems, 2007. {INSS} '07. Fourth International Conference on, p. 302, url, doi:10.1109/INSS.2007.4297444

Christian Decker, Emilian Peev, Till Riedel, Martin Berchtold, Michael Beigl, Daniel Roehr, Monty Beuster (2007) Using auction based group formation for collaborative networking in Ubicomp, UCS07 Proceedings of the 4th international conference on Ubiquitous computing systems, p. 134-149, Springer-Verlag, doi:10.1007/978-3-540-76772-5_11

Christian Decker, Till Riedel, Martin Berchtold, Philipp Scholl, Albert Krohn, Michael Beigl, Monty Beuster, Daniel Röhr, Manabu Isomura (2007) Geo-Coding of Sensors with Logic on the Map, 5th International Conference on Pervasive Computing (Late Breaking Results), Canada In Advances in Pervasive Computing Late Breaking Results on Pervasive Computing Toronto (ed.), p. 29-32, Austrian Computer Society

Martin Berchtold, Christian Decker, Till Riedel, Tobias Zimmer, Michael Beigl (2007) Using a Context Quality Measure for Improving Smart Appliances, 27th International Conference on Distributed Computing Systems Workshops ICDCSW07, p. 52-52, IEEE, url, doi:10.1109/ICDCSW.2007.87

2005

Martin Berchtold, K van Laerhoven (2005) Real-time Analysis of Correlations Between On-Body Sensor Nodes (with Topological Map Architectures), Proceedings of the International Workshop on Wearable and Implantable Body Sensor Networks (BSN 2005), Imperial College London, United Kingdom: IEE, pdf

Martin Berchtold-buschle () A Modular Classifier Concept for Activity Recognition on Mobile Phones Ein modulares Konzept von Klassifikatoren f ur Aktivit ¨ atserkennung auf Mobiltelefonen(August 2011), url

Comments are closed.