Exploiting indoor location and mobile information for context-awareness service
Highlights
► To propose a simple, yet powerful, technique for indoor localization specific to context awareness. ► To propose new techniques for localization in a building using decision tree and wireless LAN signal. ► To develop a system to infer user’s context by adopting Bayesian network and the indoor localization technique together.
Introduction
Mobile devices in the early generation played a role in calling only, providing limited services and functions. Those equipments have advanced significantly in the past decade, and now provide various functions including not only calling, but also camera, MP3 player, and the connection to Internet. In addition, various sensors in mobile devices enable to collect more information concerning our daily life. That information collected in mobile devices triggered in-depth investigation on user-context awareness (Abowd et al., 2002, Dey, 2001, Dey and Abowd, 1999, Gemmell et al., 2006, Gemmell et al., 2004, Ljungstand, 2001, Loke, 2006, Raento et al., 2005; Nokia LifeBlog, http://www.nokia.com/lifeblog).
Many researchers on context awareness especially focused on the inference of user’s hidden information which cannot be obtained explicitly. They usually used users’ location information as one of the major clues, which is collected from a GPS receiver. However, GPS receivers cannot work in buildings, so indoor-location information is unavailable in existing works on context awareness. The lack of indoor-location information prevents the accurate inference of hidden information because most people usually perform a certain activity in a building. In addition, a building has many areas which are closely linked to a user’s context.
Consider a building which has various areas such as cloth stores, a theater, restaurants, a bookstore, a workplace and so on. GPS devices cannot recognize the exact area in a building, which is closely linked to his context. For example, if the user stays in a workplace, we can infer that he/she works. In contrast, we can imagine that the user is having a lunch if he/she stays in a restaurant. However, GPS devices cannot provide those valuable evidences.
In order to overcome this drawback of traditional context awareness using GPS, this paper proposes a simple, yet powerful, technique for indoor localization specific to context awareness. In addition, this paper deals with an entire system to infer user’s context by adopting the Bayesian network and proposed indoor localization technique together.
Section snippets
Related works
There are many works on the life log and context awareness. In this section, we describe them briefly by dividing them into two groups: information collection and management, and inference of hidden information (see Table 1).
The proposed system
In this section, we describe the logical structure of the proposed system (see Fig. 1). The system works through five phases: collection, data manipulation, localization, inference and visualization.
Experiments
Three experiments are conducted to verify the performance and the usability of the system we develop: The performance of the decision tree for localization, the Bayesian network to infer users’ hidden information and poll to measure the system usability.
Experiments were carried out on the laptop with Intel® PRO/Wireless 3945ABG Network connection and Marvell Yukon 88E8055 PCI-E Gigabit Ethernet Controller. NetStumbler v.0.4.0 is used to collect SSIDs and SSs from APs, and WEKA 3.4.13 serves as
Concluding remarks
Location information is a major evidence to recognize user context. However, a GPS receiver cannot work in a building, so it is impossible to recognize user context in a building. Furthermore, existing indoor localization techniques seem inappropriate for context awareness because they cannot recognize the role of the place where a user stays. For these reasons, this paper proposes a new indoor localization technique specific to context awareness.
In addition, we develop a system to infer user’s
Acknowledgment
This research was supported by the Converging Research Center Program through the Converging Research Headquarter for Human, Cognition and Environment funded by the Ministry of Education, Science and Technology (2010K001173).
H.Y. Noh is a researcher in the Department of Computer Science at Yonsei University. His research interests include context awareness using Bayesian networks and localization technique.
References (21)
- et al.
Landmark detection from mobile life log using a modular bayesian network model
Expert Systems with Application
(2009) - et al.
Context-aware computing
IEEE Pervasive Computing
(2002) - Bahl, P., & Padmanabham, V.N., 2000. RADAR an in-building RF-based user location and tracking system. In Proc. IEEE...
- Brooke, J., 1996. SUS: A “quick and dirty” usability scale. In P.W. Jordan, B. Weerdmeester, & A. L. McClelland (Ed.),...
- Castelli, G., Mamei, M., & Rosi, A. (2007). The whereabouts diary. In Proc. LoCA 2007 (pp....
- Chen, Q., Lee, D. L., & Lee, W. C., 2008. Rule-based WiFi localization methods. In Proc. of IEEE int. conf. on embedded...
- et al.
AniDiary: Daily cartoon-style diary exploits bayesian networks
IEEE Pervasive Computing
(2007) - Coppola, P., Della Mea, V., Di Gaspero, L., Mizzaro, S., Scagnetto, I., Selva, A., et al. (2005). MoBe: Context-aware...
- et al.
A probabilistic theory of pattern recognition
(1996) Understanding and using context
Personal and Ubiquitous Computing
(2001)
Cited by (0)
H.Y. Noh is a researcher in the Department of Computer Science at Yonsei University. His research interests include context awareness using Bayesian networks and localization technique.
J.H. Lee received his B.S. degree in the Department of Computer Science at Yonsei University. His research interests include Bayesian network, and context-awareness computing.
S.W. Oh is a researcher in the Department of Computer Science at Yonsei University. His research interests include the Bayesian network and context awareness.
K.-S. Hwang is a researcher at the LG Electronics, Inc. and the Softcomputing Laboratory in computer science at Yonsei University. His research interests include Bayesian networks and evolutionary algorithms for context-aware computing and intelligent agents. He received his M.S. and Ph.D. degrees in computer science from Yonsei University.
S.-B. Cho received the B.S. degree in computer science from Yonsei University, Seoul, Korea and the M.S. and Ph.D. degrees in computer science from KAIST (Korea Advanced Institute of Science and Technology), Taejeon, Korea. He was an Invited Researcher of Human Information Processing Research Laboratories at ATR (Advanced Telecommunications Research) Institute, Kyoto, Japan from 1993 to 1995, and a Visiting Scholar at University of New South Wales, Canberra, Australia in 1998. He was also a Visiting Professor at University of British Columbia, Vancouver, Canada from 2005 to 2006. Since 1995, he has been a Professor in the Department of Computer Science, Yonsei University. His research interests include neural networks, pattern recognition, intelligent man-machine interfaces, evolutionary computation, and artificial life. Dr. Cho was awarded outstanding paper prizes from the IEEE Korea Section in 1989 and 1992, and another one from the Korea Information Science Society in 1990. He was also the recipient of the Richard E. Merwin prize from the IEEE Computer Society in 1993. He was listed in Who’s Who in Pattern Recognition from the International Association for Pattern Recognition in 1994, and received the best paper awards at International Conference on Soft Computing in 1996 and 1998. Also, he received the best paper award at World Automation Congress in 1998, and listed in Marquis Who’s Who in Science and Engineering in 2000 and in Marquis Who’s Who in the World in 2001. He is a Senior Member of IEEE and a Member of the Korea Information Science Society, INNS, the IEEE Computational Intelligence Society, and the IEEE Systems, Man, and Cybernetics Society.