物聯網在當今是非常重要的應用，其在近年來的發展使得無線感測網路與感測器的議題越來越受重視。在無線通訊的研究領域中，我們特別關注無線感測器的能源消耗問題，因為網路中通常有著大量的感測器數目但能源供應卻是相對有限的(大部分感測器由電池提供能源)。除此之外，頻繁地為耗盡電量的感測器更換電池或為其充電在目前是相當消耗人力成本的。因此本研究希望能利用資料分析技術，來為感測器進行有效的排程工作，也就是在一個特定的時間內，我們只啟動部分的感測器，同時又能有效的監控周圍的環境變數，並不會因為未啟動的那些感測器導致嚴重的疏忽或誤差。

在本文中，我們提出一個基於哈爾小波轉換的貪婪演算法，並以此作為選擇感測器在一段時間內決定是否啟動的優先度依據。哈爾小波轉換具有低複雜度與多解析度等特性，配合我們節省能源消耗的需求，並可根據情況觀察到不同尺度的資料變化和特性，讓提取特徵更為方便。另外，我們也嘗試運用其他特徵來作為優先度的依據，並且和我們提出的演算法結合，發現到我們的方法在選擇關閉一些感測器的情況，比起隨機選擇或是其他方法能更有效地降低誤差使其更接近有最低誤差之最佳感測器組合

The Internet of Things (IoT) is an essential application today. Its development in recent years has made the topic of wireless sensing networks and sensors more and more prevalent. In the field of wireless communication research, we pay great attention to the energy consumption of wireless sensors, especially. Because there are usually a large number of sensors in the network, but the energy supply is relatively limited (sensors are mostly powered by replaceable batteries). Also, the action of frequent battery replacement or charging batteries for depleted sensors is currently quite labor-intensive. Therefore, this study hopes to use data analysis techniques to schedule sensors effectively for reducing power consumption by only activating some of the sensors while it still effectively monitoring the surrounding environmental variables without causing severe negligence or error.

In this thesis, we proposed a greedy algorithm based on Haar wavelet transform and use this as a priority basis for selecting whether the sensor will be active or not within a certain period of duration. Haar wavelet transform has the characteristics of low complexity and multi-resolution, combining with our need to solving power-saving consumption issue, and can observe data changes and properties of different scales according to the situation in the time, making the feature extraction more convenient. Besides, we also try to use other features as the basis for priority and combine with our proposed algorithm. We found that our method is more effective than random selection or other methods when choosing to turn off some sensors. This method makes it more similar to the best sensor set with the lowest error.

[1] Y. J. Jung, Y. K. Lee, D. G. Lee, K. H. Ryu, and S. Nittel, “Air pollution monitoring system based on geosensor network,” IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium, vol. 3, pp. III – 1370–III – 1373, 2008.
[2] S. Kumar, T. H. Lai, and J. Balogh, “On kcoverage in a mostly sleeping sensor network,” Wireless Networks, vol. 14, no. 3, pp. 277–294, Jun 2008.
[3] D. S. G. Pollock, R. C. Green, and T. Nguyen, Handbook of time series analysis, signal processing, and dynamics. Elsevier, 1999.
[4] Chong Liu, Kui Wu, and Min Tsao, “Energy efficient information collection with the arima model in wireless sensor networks,” in GLOBECOM ’05. IEEE Global Telecommunications Conference, 2005., vol. 5, Nov 2005, pp. 5 pp.–2474.
[5] S. Pravilovic, A. Appice, and D. Malerba, “Integrating cluster analysis to the arima model for forecasting geosensor data,” in Foundations of Intelligent Systems, T. Andreasen, H. Christiansen, J.-C. Cubero, and Z. W. Raś, Eds. Cham: Springer International Publishing, 2014, pp. 234–243.
[6] W. T. Cochran, J. W. Cooley, D. L. Favin, H. D. Helms, R. A. Kaenel, W. W. Lang, G. C. Maling, D. E. Nelson, C. M. Rader, and P. D. Welch, “What is the fast fourier transform?” Proceedings of the IEEE, vol. 55, no. 10, pp. 1664–1674, Oct 1967.
[7] Kin-Pong Chan and Ada Wai-Chee Fu, “Efficient time series matching by wavelets,” in Proceedings 15th International Conference on Data Engineering (Cat. No.99CB36337), March 1999, pp. 126–133.
[8] C. Zhang, Y. Zheng, X. Ma, and J. Han, “Assembler: Efficient discovery of spatial coevolving patterns in massive geo-sensory data,” in Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ser. KDD ’15. New York, NY, USA: ACM, 2015, pp. 1415–1424.
[9] S. Kumar, T.-H. Lai, and A. Arora, “Barrier coverage with wireless sensors,” Wireless Networks, vol. 13, pp. 817–834, 2007.
[10] S. Kumar, T.-H. Lai, M. E. Posner, and P. Sinha, “Optimal sleep-wakeup algorithms for barriers of wireless sensors,” 2007 Fourth International Conference on Broadband Communications, Networks and Systems (BROADNETS ’07), pp. 327–336, 2007.
[11] C. Liu, K. Wu, and V. King, “Randomized coverage-preserving scheduling schemes for wireless sensor networks,” in NETWORKING, 2005.
[12] C. Liu, K. Wu, Y. Xiao, and B. Sun, “Random coverage with guaranteed connectivity: joint scheduling for wireless sensor networks,” IEEE Transactions on Parallel and Distributed Systems, vol. 17, pp. 562–575, 2006.
[13] J.-W. Lin and Y.-T. Chen, “Improving the coverage of randomized scheduling in wireless sensor networks,” IEEE Transactions on Wireless Communications, vol. 7, 2008.
[14] D. Tian and N. D. Georganas, “A coverage-preserving node scheduling scheme for large wireless sensor networks,” in Proceedings of the 1st ACM International Workshop on Wireless Sensor Networks and Applications, ser. WSNA ’02. New York, NY, USA: ACM, 2002, pp. 32–41.
[15] P. Berman, G. Calinescu, C. Shah, and A. Zelikovsky, “Efficient energy management in sensor networks,” Ad. Hoc. Sensor Netw., vol. 2, 11 2004.
[16] S. Joshi and S. P. Boyd, “Sensor selection via convex optimization,” IEEE Transactions on Signal Processing, vol. 57, pp. 451–462, 2009.
[17] F. Bian, D. Kempe, and R. Govindan, “Utility based sensor selection,” in IPSN, 2006.
[18] E. L. Lawler and D. E. Wood, “Branch-and-bound methods: A survey,” Operations Research, vol. 14, pp. 699–719, 1966.
[19] T. Rault, A. Bouabdallah, and Y. Challal, “Energy efficiency in wireless sensor networks: A top-down survey,” Computer Networks, vol. 67, pp. 104–122, 2014.
[20] G. Anastasi, M. Conti, M. D. Francesco, and A. Passarella, “Energy conservation in wireless sensor networks: A survey,” Ad Hoc Networks, vol. 7, pp. 537–568, 2009.
[21] D. Kumar, T. C. Aseri, and R. B. Patel, “Eehc: Energy efficient heterogeneous clustered scheme for wireless sensor networks,” Computer Communications, vol. 32, pp. 662–667, 2009.
[22] H. Li, Y. Liu, W. Chen, W. Jia, B. Li, and J. Xiong, “Coca: Constructing optimal clustering architecture to maximize sensor network lifetime,” Computer Communications, vol. 36, pp. 256–268, 2013.
[23] S. Sudevalayam and P. Kulkarni, “Energy harvesting sensor nodes: Survey and implications,” IEEE Communications Surveys & Tutorials, vol. 13, pp. 443–461, 2011.
[24] D. Trihinas, G. Pallis, and M. D. Dikaiakos, “Adam: An adaptive monitoring framework for sampling and filtering on iot devices,” 2015 IEEE International Conference on Big Data (Big Data), pp. 717–726, 2015.
[25] S. M. Preum, J. A. Stankovic, and Y. Qi, “Maper: A multi-scale adaptive personalized model for temporal human behavior prediction,” in CIKM, 2015.