本論文提出三種現存類神經形式對無線感測模組測量作品質的監測實驗，有十個感測器佈置在一個區域進行感測，收集到的數據需要進行數位轉換和權重的調整，用這方式使得估測的數據更加精確，本篇使用類神經的方式對感測數據進行校正，第一種方法是常見的倒傳遞神經網路(BPN)，使用這個方法雖然收斂很快，但是卻無法收斂到期望值，而訓練出來的數據，輸出結果無法能精確的對感測數據進行校正，本篇使用第二種方法叫做徑向基神經網路(RBF)，它能有效對收集感測數據進行校正，輸出訓練數據會更符合實際溫度量測，本篇最後使用廣義迴歸類神經網路(GRNN)，廣義迴歸類神經網路和徑向基神經網路都是概率神經網路，從本篇論文的實驗分析來看，廣義迴歸類神經網路對感測數據更能精確且快速的計算出實際情況。

In this thesis, We proposed three types of neural form we for measuring the quality of monitoring wireless sensor modules. Ten sensors are deployed in a sensing region.These data be collected and need to hex conversion and weight adjustment. In this study， we employed neural method to ensor Data for Calibration data . The first method is a common back-propagation neural network (BPN). While this study using this method converges very quickly. Output can not be precise calibration for the sensor data. Another method , called radial basis function network (RBF), it can effectively collect sensor data on the correction. Output training data are more consistent with actual temperature measurements. In this study, the third way is General Regression Neural Network (GRNN), it and RBF network are probabilistic neural network. According to experimental results, GRNN is better at processing of sensor data and it
more realistic environmental conditions.

目錄
中文摘要...................................................i
英文摘要..................................................ii
誌謝.....................................................iii
目錄......................................................iv
圖目錄....................................................vi
表目錄..................................................viii
第一章緒論.................................................1
1.1 研究背景.............................................. 1
1.2 研究目的.............................................. 3
1.3 研究方法.............................................. 3
1.4 本文架構.............................................. 4
第二章文獻回顧............................................ 5
2.1 ZigBee 介紹........................................... 5
2.1.1 ZigBee／IEEE 802.15.4 簡介ZigBee 介紹............... 5
2.1.2 ZigBee／IEEE 802.15.4 簡介.......................... 6
2.1.3 IEEE 802.15.4 標準.................................. 8
2.2 資料融合............................................. 10
2.3 類神經網路........................................... 12
2.3.1 類神經網路之基本架構與原理......................... 13
2.4 倒傳遞神經網路架構....................................15
2.5 徑向基函數網路簡介................................... 18
2.6 廣義迴歸類神經網路................................... 23
第三章整體架構............................................29
3.1 硬體說明..............................................29
3.1.3 溫度感測器..........................................32
3.1.4 T1 CC2430/31 模擬器.................................33
3.2 架構內容..............................................34
第四章實驗模擬............................................41
第五章結論與未來研究方向..................................52
5.1 結論..................................................52
5.2 未來研究方向..........................................53
參考文獻..................................................54
附錄......................................................65

[1] L.Yu,N. Wang,X. Meng, Real-time Forest Fire Detection with Wireless Sensor Networks,IEEE preceedings of WCNM2005 , Wuhan,china,pp.1214-1217.
[2] ZigBee Specification [S/OL]. ZigBee Alliance. Hhtp://www.zigbee.com.
[3] IEEE Std 802.15.4 IEEE Standard for Part 15.4 : Wireless Medium Access Control(MAC) and Physical Layer(PHY) Specifications for Low-Rate Wireless Personal Area Network(LR-WPANs)[S].New York:IEEE,2003
[4] IEEE Std 802 ． 15 ． 4 ， IEEE Standard for Wireless Medium Access Control(MAC)and Physical Layer(PHY)Speci fications for Low—Rate Wireless Personal Area Networks(LR—WPANs)，2003．
[5] S. Bhattacharyya, T. Srikanthan, and Pramod Krishnamurthy, “Ideal GMM parameters & posterior log likelihood for speaker verification”,Proceedings of
IEEE Signal Processing Society Workshop, pp.471-480,10-12 Sept. 2001
[6] Z. Chair and P. K. Varshney, “Optimal data fusion in multiple sensor detection systems,” IEEE Trans. Aerosp. Electron. Syst., vol. AES-22, pp. 98 - 101, January
1986.
[7] Welstead, S.T., Neural Network and Fuzzy Logic Applications in C/C++, John Wiley & Sons, New York, 1994.
[8] Zurada, L., Introduction to Artificial Neural Systems, West Publ. Co., USA, 1992.
[9]宋文財、劉宇豐、陳家豪、陳瑞和,＂以倒傳遞神經網路改進無線感測網路中之 資料融合計算＂ , 第四屆智慧生活科技研討會(ILT 2009),June5,2009,台中pp.
1083-1088.
[10] Wen-Tsai Sung, Yu-Feng Liu , Jui-Ho Chen , Chia-Hao Chen ,”Enhance the Efficient of WSN data fusion by Neural Networks Training Process ”, 2010 Department of Electrical Engineering, National Chin-Yi University of Technology,
Taiwan ，pp.373-376
[11]Fausset, L., Fundamental of Neural Networks, Prentia Hall, 1994.
[12]Dayhoff, J., Neural networks architecture, New York: Van Nostrand Reinhold,
1990.
[13]朱凱、王正林，“精通MATLAB神經網路”，電子工業出版社，北京，2010。
[14] D.F. Specht. A general regression neural network. IEEE Trans Neural Networks,
1991, 2(6):568-576.
[15] G.J. Bowden et al. Forecasting chlorine residuals in a water distribution system using a general regression neural network. Mathematical and Computer Modeling, 2006, 44: 469-484.
[16] P. Zhang*, S.X. Ding", P.M. Frank*and M. Sader” Fault detection of networked control systems iwith missing measurements” Control Conference, 2004. 5th Asian pp.1258-1263
[17]薛文彬、劉建源，“ZIGBEE感測與定位實戰”，橋高科技有限公司，2009.04。
[18]叢爽，“面向MATLAB工具箱的神經網路與應用”，中國科學技術大學出版社，
2009.04。