台灣四面環海，海洋運輸因此成為台灣重要的經濟命脈。有鑑於此，本文研究一透過雲端運算與分散式儲存的系統，可用於收集散佈於海面上的監測感
應器所提供的大量資料進行運算、分析，進而判斷是否有會造成磁場異常擾動的帶磁性入侵物出現與其所在方位與運動方向的辨識。
我們利用Apache基金會所提供的Hadoop平台進行可分散處理的K-Means分群運算、收集搭載磁場感應器與DGPS定位裝置的海面感應器節點所獲得的資料，並判斷入侵物的有無與可能的移動方向，並將此結果回傳到遠端的監控終端。除了K-Means分群演算法相當適合處理磁場異常的偵測以外、本系統也透過Hadoop平台獲得優秀的可靠性與效率。

Taiwan is surrounded by ocean, thus the ocean transportation has become the necessary support of Taiwan's economy. Due to this fact, this research provides a system based on cloud computing and distributed storage which is applied to compute large amount of data provided by many sensors on the sea in order to diagnose the existence of possible magnetized invaders.
We use Hadoop platform from Apache Foundation to proceed distributable K-means clustering computation to process the data collected f
rom many sensor nodes containing DGPS and magnetic sensors. With these data, it is possible to diagnose the existence and the moving direction of the possible invader. And the result can be return to remote monitoring terminal. Not only K-means can detect the irregularity of any axis of the magnetic field well, but also this system obtain good reliability and performance by Hadoop platform.
The goal system can detect the irregularity of any axis of the magnetic field well enough by deploying K-Means clustering and obtain good reliability and performance by Hadoop platform.

致謝 iv
中文摘要 v
Abstract vi
第一章 緒論 1
1.1 研究動機 1
1.2 問題定義 3
1.3 論文架構 4
第二章 文獻探討 5
2.1 磁場量測相關 5
2.2 機器學習相關 7
2.3 雲端運算相關 8
第三章 研究方法 12
3.1 系統概觀 12
3.2 訓練流程 13
3.3 訓練方法 14
第四章 實驗範例與結果 20
4.1 實驗器材與環境 20
4.2 磁場偵測入侵物相對位置方向實驗數據 26
4.3 磁場入侵物運動方向實驗數據 36
4.4 磁場入侵物實驗數據歸納 46
4.5 K-means實作效能比較 47
第五章 結論與未來展望 50
5.1 結論 50
5.2 未來展望 50
Bibliography 52

[1] http://commons.apache.org/logging/guide.html.
[2] http://www.streetdirectory.com/travel_guide/115541/
technology/understanding_electric_motors_and_their_
uses.html.
[3] http://www.top500.org/.
[4] U. B. Angadi and M. Venkatesulu. Structural scop superfamily level classification
using unsupervised machine learning. IEEE/ACM Trans. Comput. Biol. Bioinfor-
matics, 9(2):601–608, Mar. 2012.
[5] D. Arnold. Age of Discovery, 1400-1600. Routledge, 2002.
[6] D. Arthur and S. Vassilvitskii. k-means++: the advantages of careful seeding. In
Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algo-
rithms, SODA ’07, pages 1027–1035, Philadelphia, PA, USA, 2007. Society for
Industrial and Applied Mathematics.
[7] D. Cai, C. Zhang, and X. He. Unsupervised feature selection for multi-cluster data.
In Proceedings of the 16th ACM SIGKDD international conference on Knowledge
discovery and data mining, KDD ’10, pages 333–342, New York, NY, USA, 2010.
ACM.
[8] J. L. Castro, M. Delgado, J. Medina, and M. D. Ruiz-Lozano. Intelligent surveillance
system with integration of heterogeneous information for intrusion detection. Expert
Syst. Appl., 38(9):11182–11192, Sept. 2011.
[9] A. Clement, M. Kapritsos, S. Lee, Y. Wang, L. Alvisi, M. Dahlin, and T. Riche.
Upright cluster services. In Proceedings of the ACM SIGOPS 22nd symposium on
Operating systems principles, SOSP ’09, pages 277–290, New York, NY, USA,
2009. ACM.
[10] D. A. Fleisch. A Student’s Guide to Maxwell’s Equations. Cambridge University
Press, 2008.
[11] S. Ghemawat, H. Gobioff, and S.-T. Leung. The google file system. SIGOPS Oper.
Syst. Rev., 37(5):29–43, Oct. 2003.
[12] D. J. Griffiths. Introduction to Electrodynamics. Prentice Hall, 1998.
52
Collier and Sons New York, 1902.
[16] S. Y. Ko, I. Hoque, B. Cho, and I. Gupta. Making cloud intermediate data fault-
tolerant. In Proceedings of the 1st ACM symposium on Cloud computing, SoCC ’10,
pages 181–192, New York, NY, USA, 2010. ACM.
[17] S.-N. Lim, G. Doretto, and J. Rittscher. Multi-class object layout with unsupervised
image classification and object localization. In Proceedings of the 7th international
conference on Advances in visual computing - Volume Part I, ISVC’11, pages 573–
585, Berlin, Heidelberg, 2011. Springer-Verlag.
[18] T. M. Mitchell. Machine Learning. McGraw-Hill, 1997.
[19] L. S. Monteiro, T. Moore, and C. Hill. What is the accuracy of dgps? The Journal
of Navigation, 58(02):207–225, 2005.
[20] E. S. Raymond. The Cathedral and the Bazaar. O’Reilly & Associates, Inc., Se-
bastopol, CA, USA, 1st edition, 1999.
[21] USGS. National geomagnetism program.
[22] S. I. K. U. J. Yamaguchi Takashi, Kashima Hirotoshi. Two-dimensional position
detection method using linear gradient magnetic fields. Papers of Technical Meeting
on Magnetics, IEE Japan, MAG-06(11-18):7–10, 2006.
[23] N. Youngblood. The Development of Mine Warfare: A Most Murderous And Bar-
barous Conduct War, Technology, And History. Greenwood Publishing Group, 2006.
[13] N. Gruzling. Linear Separability of the Vertices of an N-dimensional Hypercube.
[14] Z. Guo, G. Fox, and M. Zhou. Investigation of data locality and fairness in mapre-
duce. In Proceedings of third international workshop on MapReduce and its Appli-
cations Date, MapReduce ’12, pages 25–32, New York, NY, USA, 2012. ACM.
[15] E. J. Houston and A. Kennelly. Recent Types of Dynamo-Electric Machinery. P.F.