在此碩士論文中，我們提出了情境感測系統之生命週期預測模組。此模組為一機率模組，它能夠描述在智慧型手機上情境感測資訊維持在同一生命週期的時間。若能精確預測，則我們便能在其生命週期內關閉智慧型手機上相應的感測器。如此一來，便能減少感測器週期性及期多餘的感測行為，藉此達到省電的效果。另外，也分析了許多不同生命週期預測策略，使其能夠在猜測精確度及省電量之間做出權衡。同時也指出猜測錯誤所會造成的後果並提出將其修正解決的方案。最後，在實驗中，我們以從真實使用者身上所取得的情境感測資料來實行情境感測系統之生命週期預測，並藉此證明此模組能夠適應各種種類的情境感測資訊並且得到大量的節電效果。

This thesis presents the Life Cycle Prediction Model (LCPM), a probabilistic model that models the time when a context of a smartphone will remain the same as a life cycle. A correct prediction allows the corresponding sensors on the smartphone to be turned off during the life time of the context. Thus, it is possible to eliminate periodic and redundant sampling of the sensors, resulting in energy saving. Different ways of building the probabilistic LCPM for a given context are discussed, which try to trade off between miss predictions and energy consumption. We also address the issues resulting from miss predictions by identifying possible causes and proposing feasible solutions. Our experiments using data collected from real users on various contexts show that LCPM can adapts to different kinds of contexts and results in significant power saving.

Abstract i
Contents i
1 INTRODUCTION 1
2 RELATED WORK 3
3 SYSTEM ARCHITECTURE 5
3.1 A General Context Framework . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
3.2 Model of Contexts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3.3 Duration Service . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
4 METHODOLOGY 9
4.1 Life Cycle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
4.2 Life Cycle Prediction Strategy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
4.3 Life Cycle Prediction Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
4.3.1 Lifetime Decision . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
4.3.2 Bias Accumulation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
5 EVALUATION 16
5.1 Experiment setting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
5.1.1 Experiment Platform and Implemented services . . . . . . . . . . . . . . . . 16
5.2 Evaluation Result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
5.2.1 Accuracy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
5.2.2 Recession Probability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
5.2.3 Life Cycle Prediction vs Polling Service . . . . . . . . . . . . . . . . . . . . 21
6 CONCLUSION 22

[1] CHUN-LIN LIN, CHUNG-TA KING, C.-H. H. An energy/accuracy-optimized framework for
context sensing on smartphones.
[2] CONSTANDACHE, I., GAONKAR, S., SAYLER, M., CHOUDHURY, R., AND COX, L. Enloc:
Energy-efficient localization for mobile phones. In INFOCOM 2009, IEEE (April 2009),
pp. 2716–2720.
[3] FRENCH, B., SIEWIOREK, D., SMAILAGIC, A., AND DEISHER, M. Selective sampling strategies
to conserve power in context aware devices. In Wearable Computers, 2007 11th IEEE International
Symposium on (Oct 2007), pp. 77–80.
[4] KANG, S., LEE, J., JANG, H., LEE, H., LEE, Y., PARK, S., PARK, T., AND SONG, J. Seemon:
Scalable and energy-efficient context monitoring framework for sensor-rich mobile environments.
In Proceedings of the 6th International Conference on Mobile Systems, Applications, and Services
(New York, NY, USA, 2008), MobiSys ’08, ACM, pp. 267–280.
[5] KRAUSE, A., IHMIG, M., RANKIN, E., LEONG, D., GUPTA, S., SIEWIOREK, D., SMAILAGIC,
A., DEISHER, M., AND SENGUPTA, U. Trading off prediction accuracy and power consumption
for context-aware wearable computing. In Wearable Computers, 2005. Proceedings. Ninth IEEE
International Symposium on (Oct 2005), pp. 20–26.
[6] LIN, K., KANSAL, A., LYMBEROPOULOS, D., AND ZHAO, F. Energy-accuracy trade-off for
continuous mobile device location. In Proceedings of the 8th International Conference on Mobile
Systems, Applications, and Services (New York, NY, USA, 2010), MobiSys ’10, ACM, pp. 285–
298.
[7] NATH, S. Ace: Exploiting correlation for energy-efficient and continuous context sensing. In
Proceedings of the 10th International Conference on Mobile Systems, Applications, and Services
(New York, NY, USA, 2012), MobiSys ’12, ACM, pp. 29–42.