Abstract
Multiple sensor-based context inference systems can perceive users’ tasks in detail while it requires complicated recognition models with larger resources. Such limitations make the systems difficult to be used for the mobile environment where the context-awareness would be most needed. In order to design and operate the complex models efficiently, this paper proposes an evolutionary process for generating the context models and a selective inference method. Dynamic Bayesian networks are employed as the context models to cope with the uncertain and noisy time-series sensor data, where the operations are managed by using the semantic network which describes the hierarchical and semantic relations of the contexts. The proposed method was validated on a wearable system with variable sensors including accelerometers, gyroscopes, physiological sensors, and data gloves.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Roy, N., Gu, T., Das, S.K.: Supporting Pervasive Computing Applications with Active Context Fusion and Semantic Context Delivery. Perv. and Mobile Comp. 6, 21–42 (2010)
Laerhoven, K.V., Aidoo, K.A., Lowette, S.: Real-time Analysis of Data from Many Sensors with Neural Networks. In: Proc. of the 5th Int. Symposium on Wearable Computers, pp. 115–123 (2001)
Wang, Y., Lin, J., Annavaram, M.: A Framework of Energy Efficient Mobile Sensing for Automatic User State Recognition. In: Proc. of MobiSys., pp. 179–192 (2009)
Krause, A., Ihmiq, M., Rankin, E., Leong, D., Smriti, G., Siewiorek, D., Smailaqic, A., Deisher, M., Senqupta, U.: Trading off Prediction Accuracy and Power Consumption for Context-aware Wearable Computing. In: ISWC 2005, pp. 20–26 (2005)
Hwang, K.-S., Cho, S.-B.: Landmark Detection from Mobile Life Log using a Modular Bayesian Network Model. Expert Syst. Appl. 36, 12065–12076 (2009)
Hong, J.-H., Yang, S.-I., Cho, S.-B.: ConaMSN: A Context-aware Messenger using Dynamic Bayesian Networks with Wearable Sensors. Expert Syst. Appl. 37, 4680–4686 (2010)
Blum, M., Pentland, A., Troster, G.: InSense: Interest-based Life Logging. IEEE Multimedia 13, 40–48 (2006)
Oliver, N., Garg, A., Horvitz, E.: Layered Representations for Learning and Inferring Office Activity from Multiple Sensory Channels. Comput. Vis. Image Understand. 96, 163–180 (2004)
Ermes, M., Parkka, J., Mantyjarvi, J., Korhonen, I.: Detecting of Daily Activities and Sports with Wearable Sensors in Controlled and Uncontrolled Conditions. IEEE T. Inf. Technol. B. 12, 20–26 (2008)
Schmidt, A., Aidoo, K.A., Takaluoma, A., Tuomela, U., Laerhoven, K.V., Velde, W.V.D.: Advanced Interaction in Context. In: 1st Int. Symposium on Handheld and Ubiquitous Computing, pp. 89–101 (1999)
Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley, Reading (1989)
Marinov, M., Zheliazkova, I.: An Interactive Tool based on Priority Semantic Networks. Knowledge-Based Systems 18, 71–77 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Min, JK., Cho, SB. (2011). A Hybrid Context-Aware Wearable System with Evolutionary Optimization and Selective Inference of Dynamic Bayesian Networks. In: Corchado, E., Kurzyński, M., Woźniak, M. (eds) Hybrid Artificial Intelligent Systems. HAIS 2011. Lecture Notes in Computer Science(), vol 6678. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21219-2_56
Download citation
DOI: https://doi.org/10.1007/978-3-642-21219-2_56
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21218-5
Online ISBN: 978-3-642-21219-2
eBook Packages: Computer ScienceComputer Science (R0)