跳到主要內容

臺灣博碩士論文加值系統

(35.175.191.36) 您好!臺灣時間:2021/08/02 14:41
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:葉振山
研究生(外文):Jehn-shan Yeh
論文名稱:以階層式軟計算方法診斷小血球性貧血
論文名稱(外文):Differential microcyte anemia diagnosis with hierarchical soft computing
指導教授:鄭景俗鄭景俗引用關係
指導教授(外文):C.H. Cheng
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:資訊管理系碩士班
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2004
畢業學年度:92
語文別:中文
論文頁數:42
中文關鍵詞:缺鐵型貧血小血球性貧血地中海型貧血軟計算自適應類神經-模糊推論系統
外文關鍵詞:Soft computingANFISThalassemiamicrocyte anemiaIron deficiency anemia
相關次數:
  • 被引用被引用:7
  • 點閱點閱:244
  • 評分評分:
  • 下載下載:33
  • 收藏至我的研究室書目清單書目收藏:1
貧血是一般常見的血液疾病,而最常見的地中海型貧血 型與缺鐵型貧血都是小血球性貧血,臨床上依據完整血液檢查(Completely Blood Checks, CBCs) 來診斷貧血,而小血球性貧血的特徴在CBCs表現上都由平均血球容積(Mean Blood Cell Volume ,MCV)表現出低於標準值 80fL(fL 計量單位約為29.57ml),由於有相同的表現,使得臨床醫生根據個人主觀經驗做診斷,因此極有機會將二種不同的貧血做相同的診斷,對患者之日後治療影有相當的影響。

軟計算的方法,如模糊分群(Fuzzy C-means ,FCM)、競爭學習網路(Competitive Learning Network ,CLN)和自適應神經網路模糊推論(Adaptive Neural-Fuzzy Inference System ,ANFIS),模仿人類心智來推論及學習環境中不確定或不精確的事物。而貧血診斷在性質上具有此種不精確的特性,極適合以軟計算方法,來輔助醫生在臨床的疾病診斷上。過去區別函數方法以Mantzer指標區別地中海型貧血只有82%的正確率,而區別缺鐵型貧血只有90%,而以England指標區別地中海型貧血正確率為91%。本研究主要利用CBCs之患者血液樣本,透過階層式的軟計算方法來輔助臨床醫生針對小血球性貧血之地中海型貧血 與缺血型貧血診斷的鑑別。然後以ANFIS對小血球性貧血找出13條規則其正確率為92%,其次對ANFIS的推論值做評估,當值為13.6時正確率為95.3%,改善區別函數應用在小血球性貧血的鑑別的正確率。本研究以軟計算方法明顯改善過去區別函數方法與臨床醫生經驗診斷,尤其在多個指標同時使用的情形下的時間與成本的降低是顯然的。
Anemia is the common hematological disorder. It’s difficult to differential both of thalassemia (THA) and Iron deficiency anemia (IDA) often seen belongs to microcyte anemia. The CBCs is objective clinically that physician diagnoses anemia in proportion 1:4 between Iron deficiency anemia with thalassemia because of two anemia express the feature similarly with MCV less than 80 fL (fluid ounces). It will be more serious to the therapy of the patient when physicians do the same diagnosis.

It’s novel to use soft computing that include FCM, Competitive learning, and ANFIS that parallels the human mind to process imprecision and uncertain in circumstance. It suit for to assist with physicians to diagnose clinically of the anemia that with the imprecision and uncertain. There are 98% accurate rate inferred in 50 cases refer with documented diagnosis of hospital, it’s more accurate than diagnose by experienced. There are 92% of accurate rate employ ANFIS with 13 rules and 95.3% of accuracy rate when the inference value is 13.6. It improve the discriminant function to differential microcyte that Mantzer index only have accuracy rate 82% to identity THA and only have 90.6% accuracy rate to identity IDA and England index have accuracy rate 91.5% to identity THA. It’s obvious the hierarchical soft computing cut-off the time and cost than cooperate some of discriminate functions to differential microcyte.
中文摘要 ………………………………………………………………… i
英文摘要 ………………………………………………………………… ii
誌謝 ………………………………………………………………… iii
目錄 ………………………………………………………………… iv
表目錄 ………………………………………………………………… V
圖目錄 ………………………………………………………………… Vi


一、 緒論…………………………………………………………… 1
1.1 研究背景與動機……………………………………………… 1
1.2 研究限制……………………………………………………… 1
1.3 研究目的……………………………………………………… 1
1.4 論文架構……………………………………………………… 2
二、 文獻探討……………………………………………………… 3
2.1 軟計算………………………………………………………… 3
2.2 貧血疾病相關研究…………………………………………… 3
三、 研究方法……………………………………………………… 8
3.1 階層式軟計算方法…………………………………………… 8
3.2 階層式軟計算演算法演算步驟……………………………… 11
3.2.1 ANFIS ………………………………………………………… 11
3.2.2 Fuzzy C-means……………………………………………… 15
3.3.3 Competitive Learning……………………………………… 17
四、 小血球性貧血診診斷驗證與比較…………………………… 19
4.1 小血球性貧血資料庫簡介…………………………………… 19
4.2 Fuzzy C-means.區分血球性貧血之實驗結果……………… 21
4.3 Competitive Learning.實驗結果………………………… 22
4.4 ANFIS 實驗結果……………………………………………… 25
4.5 各種分群方法之效益與比較………………………………… 34
4.6 臨床常用指標驗證推論之結果……………………………… 35
五、 結論…………………………………………………………… 37
參考文獻 ………………………………………………………………… 39

圖目錄
圖1 論文架構圖…………………………………………………… 2
圖2 貧血診斷鑑別………………………………………………… 4
圖3 研究流程示意圖……………………………………………… 8
圖4 自適應神經網路-模糊推論系統 架構圖…………………… 11
圖5 競爭學習網路 架構圖 ……………………………………… 17
圖6 模糊分群以MCV/RBC與HGB/RBC為分群變數之結果……… 21
圖7 重覆尋找分群中心之目標函數曲線………………………… 22
圖8 MCV隸屬函數 (訓練 前 後) ……………………………… 26
圖9 HCT隸屬函數 (訓練 前 後) ……………………………… 26
圖10 RDW隸屬函數 (訓練 前 後) ……………………………… 26
圖11 ANFIS架構圖 ………………………………………………… 27
圖12 模糊推論系統 架構圖 ……………………………………… 27
圖13 簡化規則後之模擬…………………………………………… 31
圖14 簡化後之ANFIS架構圖……………………………………… 32
圖15 MCV,HCT,RDW之Surface …………………………………… 32
表目錄
表1 CBCs標準值…………………………………………………… 4
表2 血球型貧血分類……………………………………………… 6
表3 資料庫欄位內容……………………………………………… 19
表4 資料庫內容片斷……………………………………………… 20
表5 競爭學習結果第一群………………………………………… 23
表6 競爭學習結果第二群………………………………………… 24
表7 競爭學習結果第三群………………………………………… 24
表8 模糊隸屬程度語意表達……………………………………… 25
表9 ANFIS驗證輸出結果………………………………………… 29
表10 推論之全部規則……………………………………………… 30
表11 語意變數……………………………………………………… 30
表12 簡併後之規則………………………………………………… 30
表13 簡併規則之驗證結果………………………………………… 33
表14 簡併規則後之推論結果原始資料…………………………… 34
表15 各種分群方法在CBCs之正確率比較 ……………………… 35
表16 分群檢測基準………………………………………………… 35
表17 文獻提出之貧血推論之驗證指標…………………………… 36
表18 推論值之正確率表…………………………………………… 36
英文部份
[1].Arpad Kelemen, Robert Kozma, Yulan Liang, 2001,“Neuro-Fuzzy classification for the job assignment problem” University of Memphis.

[2].Ana Lucia, Dai Pra* 2003, “A study about dimensional change of industrial parts using fuzzy rules” Fuzzy Sets and Systems 139 (2003) 227-237.

[3].Ben Krose, Patrick van der Smagt , 1996 ,”An introduction to Neural Network” University of Amsterdam.

[4].Bruno M, et al.”Relevance of red cell distribution width in the differential diagnosis of microcytic anemias.”, Clin lab Haematol, 13:141-151, 1991.

[5].E. McLaren,I. V. Cadez, P.Smyth and G. J. McLachlan, 2001, “ Classification Of Disorders Of Anemia On The Basis Of Mixture Model Parameters”,Technical Report No. 01-56, Information and Computer Science Department, University of California, Irvine.

[6].England JM. , Fraser P. “ Discrimination between iron-deficiency and heterozygous-thalassemia syndromes in differential diagnosis of microcytosis.”, Lancet, 1:145-148, 1979.

[7].Fred Rosner, Hans W. Gunwald 1997, “The Patient with Anemia” Hematology Update.

[8].Igor V. Cadez, Geoff J. McLachlan, Christine E. McLaren 2000,”Maximum Likelihood Estimation of Mixture Densities for Binned and Truncated Multivariate Data”Kluwer Academic Publishers.

[9].J.-S.R. Jang,C.-T. Sun, E. Mizutani 1993, “Neuro-Fuzzy and Soft Computing” Matlab curriculum series.


[10].L. A. Zadeh 1975, “The concepts of a linguistic variable and it’s application to approximate reasoning”, Information Science, Vol. 8, pp. 199-249(I).

[11].L.A. Zadeh 1975, “The concepts of a linguistic variable and it’s application to approximate reasoning”, Information Science, Vol. 8, pp. 301-357(II).

[12].L.A. Zadeh 1976, “The concepts of a linguistic variable and it’s application to approximate reasoning”, Information Science, Vol. 9, pp. 43-80(III).

[13].L.A. Zadeh. “Fuzzy logic, neural networks and soft computing.” One-page course announcement of CS 294-4, Spring 1993, the University of California at Berkeley, November 1992.

[14].L. Van Hove, T.Schisano, L. Brace 1999, “Anemia Diagnosis Classification, and Monitoring Using Cell-Dyn Technology Reviewed for the Mew Millennium”,Laoratory Hematology 6:93-108.

[15].Mentzer WG “ Differentiation of iron deficiency from thalassemia trait.”, Lancet, 1:882, 1973.

[16].Norman I. Birndorf, Jeffrey O. Pentecost, James R. Coakley, 1995,“An Expert System to Diagnose Anemia and Report Results Directly on Hematology Forms” Academic Press.

[17].Rashmi Malhotra, D.K. Malhotra 2002,“Differentiating between good credits and bad credits using neuro-fuzzy systems”,Computing, Artifical Intelligence and Information Technology. European Journal of Operation Research 136 (2002) 190-211.

[18].Raid A. Al-Iman “Neuro-Fuzzy Model for classifying and Monitoring Multivariate Attribute Processes”, Agilent Technologies.


[19].Reed E. Drews 2003, “A Primer on anemia evaluation with case presentations” Cardiovascular update.

[20].Srivastava PC, Bevington JM “ Iron deficiency and-or thalassemia trait.”, Lancet, 1:832, 1973

[21].Ho S.Y., K. C. Lee, S. S. Chen, S. J. Ho. “Accurate Modeling and prediction of surface roughness by computer vision in turning operations using an adaptive neuro-fuzzy inference system” International Journal of Machine Tools & Manufacture 42 1441-1446.

[22].S. M. Chen 2001, “A New method for generating fuzzy rules from numerical data for handing classification problems” Artifical Intelligence, 15:645-664, 2001.

[23].Virant-Klun, J. Virant 1999,“Fuzzy Logic Alternative for Analysis in the Biomedical Sciences”,Computers and Biomedical Research 32, 305-321.

[24].Yasumasa A.,Fumio K., Sunil K. B., Niriksha B.M.,Prakash,R.P.,Vijay P.,Hiroyuki N.,Tokuhiro O. 1998. “A Study of B Thalassemia Screening using an Automated Hematology Analyzer.”, Sysmex Journal Interational Vol.8 No.2(1998).

-中文部份
[1].林幸玟, 李宇芬 2003 “缺鐵性貧血的鑑別診斷與治療”Community medicine 基層醫學第十一卷第十期。

[2].林東燦 2003, “孩童貧血的診斷及治療” 醫學繼續教育2卷6期。
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top