Mobile activity recognition using contextual reasoning and ubiquitous data stream processing

Activity recognition has become one of the emerging applications in the area of ubiquitous computing. This research aims at leveraging ubiquitous data stream mining and context reasoning for mobile activity recognition. The novel system allows dynamic adaptation and personalisation of the learning model to reflect the realistic activity changes emerged over time. Sensors fusion to attain a context aware activity recognition is also a key contribution in this project.

[1]  Mohamed Medhat Gaber,et al.  KB-CB-N classification: Towards unsupervised approach for supervised learning , 2011, 2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).

[2]  Arkady B. Zaslavsky,et al.  ECSTRA - Distributed Context Reasoning Framework for Pervasive Computing Systems , 2011, NEW2AN.

[3]  Angelo M. Sabatini,et al.  Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers , 2010, Sensors.

[4]  Paul Lukowicz,et al.  OPPORTUNITY: Towards opportunistic activity and context recognition systems , 2009, 2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks & Workshops.

[5]  Juha Pärkkä,et al.  Personalization Algorithm for Real-Time Activity Recognition Using PDA, Wireless Motion Bands, and Binary Decision Tree , 2010, IEEE Transactions on Information Technology in Biomedicine.

[6]  Jun Yang,et al.  Toward physical activity diary: motion recognition using simple acceleration features with mobile phones , 2009, IMCE '09.

[7]  Mirco Musolesi,et al.  Sensing meets mobile social networks: the design, implementation and evaluation of the CenceMe application , 2008, SenSys '08.

[8]  Norbert Gyorbíró,et al.  An Activity Recognition System For Mobile Phones , 2009, Mob. Networks Appl..

[9]  Pedro José Marrón,et al.  Challenges in ubiquitous context recognition with personal mobile devices , 2010, CASEMANS '10.

[10]  Kenneth Meijer,et al.  Activity identification using body-mounted sensors—a review of classification techniques , 2009, Physiological measurement.