臺灣博碩士論文加值系統

哮喘是一種常見的慢性呼吸道疾病，隨著工業的進步，空氣污染日益嚴重，國內哮喘患者患者已達人口總數的2%，而突發性的哮喘更是足以造成致命的危機。由於哮喘尚無根治的辦法，因此如何有效的診斷出哮喘並加以預防，是一個值得重視的議題。
類神經網路是人工智慧中相當重要的一員，它最重要的特色莫過於強大的學習能力，其中倒傳遞類神經網路更是廣泛被應用的一種類神經網路方法。如果可以結合中醫師的診斷資料，並對網路加以訓練勢必可以建構出一套有效的診療輔助系統。
本研究在由長庚醫院中醫內科沈建中醫生的協助之下，對哮喘病患進行各項病徵的蒐集與整理，並且採用數種常見的倒傳遞類神經網路演算法加以測試，經由測試結果評估各種演算法的準確度與效能差異，作為未來建構中醫專家系統的參考。

Asthma is a common chronic disease. Because the air pollution becomes more serious, the number of the infected people have come up to 2%. Asthma still can''t be healed today and the acute asthma is lethal. So it is important to find a way preventing from getting it.
Artificial Neural Networks is an important member of the Artificial Intelligence and it is famous for its learning ability. Especially, the Back-propagation Neural Network has been applied to many different areas. If we can obtain the diagnosis data form the doctor and train the network. It will be a great help to establish a diagnosis system to help the doctor.
In this research we got the help form the Mr.Shen a great doctor of Cheng Cung Momorial Hospital. He helped us to obtain the diagnosis data and taught us some professional knowledge of asthma. We used the data to train some kinds of neural network algorithm. Finally, we compared the performance and accuracy of different neural network algorithm.

目錄
第一章 緒論 1
1.1 研究動機與背景 1
1.2 研究目的 2
1.3 研究流程 3
1.4 本文架構 4
第二章 文獻回顧 5
2.1 前言 5
2.2 類神經網路簡介 6
2.3 FEED-FORWARD 架構 10
2.4 類神經網路簡介 11
2.4.1 BP (Back-Propagation Network) 11
2.4.2 MOBP (Momentum modification to back-propagation)
and VLBP(Variable learning rate back-propagation
algorithm) 13
2.4.3 CGBP (Conjugate gradient back-propagation) 14
2.5.4 LMBP(Levenberg-Marquardt back-propagation) 14
2.5哮喘病理分析 15
第三章 研究方法 19
3.1 BP (BACK-PROPAGATION NETWORK) 20
3.1.1 基本原理與概念 20
3.1.2 演算法說明 21
3.1.3 學習程序 24
3.2 MOBP (VOGL, ET AL., 1988) (MOMENTUM MODIFICATION TO BACK-
PROPAGATION) 24
3.3 VLBP (VOGL, ET AL., 1988) (VARIABLE LEARNING RATE BACK-
PROPAGATION ALGORITHM) 25
3.4 CGBP (CHARALAMBOUS, 1992) (CONJUGATE GRADIENT BACK-
PROPAGATION) 25
3.4.1 基本原理與概念 25
3.4.2 演算法說明 26
3.4.3 學習程序 27
3.5 LMBP (HAGAN, MENHAJ, 1994) (LEVENBERG-MARQUARDT BACK-
　　PROPAGATION) 30
　　3.5.1 基本原理與概念 30
　　3.5.2 演算法說明 31
　　3.5.3 學習程序 34
第四章 研究結果分析 35
　4.1 前言 35
　4.2 測試環境說明 35
　4.3 XOR PROBLEM 36
　　4.3.1 測試結果 37
　　4.3.2 小結 44
　4.3 中醫氣喘資料測試 45
　　4.3.1 問卷資料說明 45
　　4.3.2 資料測試說明 46
　　4.3.3 測試結果 47
　　4.3.3小結 66
第五章 結論與建議 68
　5.1研究貢獻與結論 68
　5.2後續研究建議 68
參考文獻 70
附錄 73
附錄一 人體試驗申請書 73
附錄二 問卷資料 74
附錄三 受測者同意書 79
附錄四 調查人員手冊 80
附錄五 樣本資料 81

1.C.Charalambous, “Conjugate gradient algorithm can training of artificial neural networks”, IEEE Proceedings, vol. 139, on. 3, pp. 301-310, 1992.
2.Eun-Jung Song , Min-Jea Tahk , “ Three-dimensional midcourse guidance using neural networks for interception of ballistic targets ” , IEEE Trans. Aerospace and Electronic Systems , Vol. 38 , No. 2 , April , 2002
3.Meng Joo Er , Shiqian Wu , Juwei Lu , and Hock Lye Toh , “ Face recognition with radial basis function (rbf) neural networks ,” IEEE Trans. Neural Networks , Vol. 13 , No. 3 , May , 2002
4.M.T.Hangan and M.Menhaj, “Training feed-forward networks with the Marquardt algorithm”, IEEE Transactions on Neural Networks, vol. 5, no. 6, 1994.
5.Paul Sajda , Clay Spence , and John Pearson , “ Learning contextual relationships in mammograms using a hierarchical pyramid neural network ,” IEEE Trans. Medical Imaging , Vol. 21 , No. 3 , March , 2002
6.P. Arena , M. Bucolo , L. Fortuna , L. Occhipinti , “ Cellular neural networks for real-time DNA microarray analysis ,” IEEE Engineering in Medicine and Biology , March/April , 2002
7.R.Battiti, “First- and second-order methods for learning: Between steepest decent and Newton’s method”, Neural Computation, vol. 4, on. 2, pp. 141- 166,1992.
8.Rao ,“Engineering Optimization Theory and Practice” John Wiley and Sons, Inc, 1996
9.T.P.Vogl, J.K.Mangis, A.K.Zigler, W.T.Zink and D.L.Alkon, “Accelerating the convergence of the backpropagation method”, Biological Cybernetics, vol. 59, pp.256-264, 1988
10.T.Hagan, B.Demuth and Mark Beale, “Neural Network Design”, PWS Publishing Inc. 1996
11.Xicai Yue , Datian Ye , Chongxun Zheng , and Xiaoyu Wu , “ Neural networks for improved text-independent speaker identification ,” IEEE Engineering in Medicine and Biology , March/April , 2002
12.X. Yao and Y. Liu , “ A New Evolutionary System for Evolving Artificial Neural Networks ,” IEEE Trans. Neural Networks , Vol 8. , pp. 694-713 , May , 1997
13.「氣喘、氣喘200問答集」http://ntuh.mc.ntu.edu.tw/med/sections/chest/asthma_200q/，臺大醫院胸腔內科，最後查閱2004/05/13
14.周鵬程，「類神經網路入門-活用Matlab」，全華科技圖書股份有限公司，2002
15.林暉慶，「中醫師氣喘支氣管過敏性鼻炎處方選輯」，武陵出版社，1997
16.馬斌榮，「中醫專家系統與中醫知識庫」，北京醫學文庫，1998
17.葉怡成，「類神經網路模式應用與實作」，第六版，儒林圖書有限公司，1999