跳到主要內容

臺灣博碩士論文加值系統

(44.222.64.76) 您好!臺灣時間:2024/06/15 05:09
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

我願授權國圖
: 
twitterline
研究生:伍志翔
研究生(外文):Chi-Hsiang Wu
論文名稱:近紅外光光譜標準化模式建立之研究
論文名稱(外文):Study on the Development of the Standardization of Near-Infrared Spectra
指導教授:陳世銘陳世銘引用關係
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:生物產業機電工程學研究所
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2006
畢業學年度:94
語文別:中文
論文頁數:157
中文關鍵詞:標準化近紅外光多變數迴歸分析支援向量迴歸
外文關鍵詞:StandardizationNear InfraredMultivariate AnalysisSupport Vector Regression
相關次數:
  • 被引用被引用:2
  • 點閱點閱:389
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本研究以PDS (Piecewise Direct Standardization)、DPDS (Differential Piecewise Direct Standardization)及SVS(Support Vector Standardization)三種方法針對因為儀器的不同造成光譜在強度上的差異作標準化,並且討論標準化後光譜應用於已建立之資料庫的準確度。標準化方法PDS及DPDS是以PLSR為基礎之線性標準化的方法,而SVS是以SVR為基礎非線性標準化方法,另外為提升標準化光譜預測標準參考值(如水果糖度)之能力,以KS所選別之標準化校正樣本,少量但是差異性較大之樣本對已建立之資料庫作Model Adaptation,使標準化光譜可用性更高。蔗糖(Sucrose)與鹽(NaCl)的混合物為本研究之實驗樣本,以其作光譜量測並以蔗糖含量作為標準參考值,分佈範圍為0%~100%。採用PDS、DPDS及SVS三種方法對不同時間量測、相同儀器不同配件、不同儀器之光譜作標準化,分別討論光譜誤差與標準參考值之預測誤差。分析結果發現以SVS作標準化後之結果最佳。不同時間量測之光譜標準化其光譜誤差SEPw=0.044,既有資料庫經過Model Adaptation後,標準參考值預測之誤差SEPc=6.464。相同儀器不同設備的實驗,NIRS 6500之樣本夾具mini cup與fiber配件量測後標準化之光譜誤差SEPw =0.050,以既有之資料庫作預測,標準參考值誤差SEPc=12.911,資料庫經過Model Adaptation後SEPc=6.471。不同儀器的實驗,Online 6500與NIRS 6500標準化後之光譜誤差SEPw = 0.040,以既有之資料庫作預測,標準參考值誤差SEPc=8.482,Model Adaptation後,標準參考值預測之誤差SEPc=7.318;N-400與NIRS 6500兩台儀器標準化後之光譜誤差SEPw=0.042,資料庫經過Model Adaptation後標準參考值預測之誤差為SEPc = 5.623。Online 6500與N-400兩台儀器波長範圍及間距不等,若不作光譜前處理(波段選擇及波長間距調整),標準化後之光譜誤差SEPw = 0.034,既有資料庫經過Model Adaptation後誤差SEPc=6.03,而經過波段選擇1100~2000nm後光譜誤差SEPw=0.02,已既有之資料庫作預測誤差SEPc=7.800。另外本研究亦討論當儀器標準化主副關係互換,結果發現當誤差較大精確度較差之儀器轉換到精確度較高的儀器時,光譜誤差較大,標準參考值之預測精準度也隨之降低,Online 6500及NIRS 6500互換後標準化光譜誤差SEPw=0.072,已既有之資料庫作預測SEPc=15.338,若選擇波段以1100~2000nm作標準化,可提升標準化能力,光譜誤差SEPw=0.016,已既有之資料庫作預測SEPc=12.470。由結果來看,本研究所研發出之光譜標準化方法可成功地將不同時間測量、兩台不同設備或不同儀器量測光譜所造成的差異降低,並且透過Model Adaptation的方法提升標準化光譜應用於既有資料庫的預測能力。
This research used PDS (Piecewise Direct Standardization), DPDS (Differential Piecewise Direct Standardization) and SVS (Support Vector Standardization) to standardize spectra, which were obtained by using different instruments. Among them, PDS and DPDS are linear standardization methods based on PLSR (Partial Least Square Regression), while SVS is a nonlinear standardization method based on SVR (Support Vector Regression). Besides, to improve the use of standardized spectra on established database and models, Model Adaptation was introduced with samples were selected by KS (Kennard-Stone algorithm). The mixture of sucrose and NaCl was used as samples in this study, in which the content of sucrose was served as the reference data. Three models of PDS, DPDS and SVS were adopted to investigate the spectra standardization for the cases of different time, attachments and instruments. The results indicated that SVS was the best model. Regarding the effect of measurements at different time, spectra error SEPw was 0.044 after standardization, and standard refrence value error SEPc was 6.464 after Model Adaptation. Regarding the measurements by using different attachments on the same instrument, SEPw and SEPc were 0.050 and 12.911 respectively after standardization, and SEPc was 6.471 after Model Adaptation. As of the measurements by using different instruments (Online 6500 and NIRS 6500), SEPw and SEPc were 0.040 and 8.842 respectively after standardization, and SEPc was 7.318 after Model Adaptation. As of the measurements by using different instruments (N-400 and NIRS 6500), spectra error SEPw was 0.042 after standardization, and standard refrence value error SEPc was 5.623 after Model Adaptation. As of the measurements by using different instruments (N-400 and Online 6500), spectra error SEPw was 0.034 after standardization, and standard refrence value error SEPc was 6.03 after Model Adaptation; however, if same wavelength range (1100~2000nm) was selected, standard error of spectra SEPw was 0.02 and SEPc was 7.800 without Model Adaptation. In this study, the investigation was also conducted by exchanging the relation of Master and Slave in the standardization. The results revealed that when a less precise instrument was standardized to a more precise instrument, both SEPw and SEPc increased. After exchanging of Online 6500 and NIRS 6500, SEPw and SEPc were 0.072 and 15.338 respectively after standardization; if same wavelength range (1100~2000nm) was selected, standard error of spectra SEPw was 0.016 and SEPc was 12.470. Spectra standardization methods with Model Adaptation were successfully developed in this study, it allowed to transfer spectra among different attachments and instruments, and to reduce the spectra difference due to different measurement time.
誌謝 i
摘要 ii
Abstract iv
目錄 vi
圖目錄 viii
表目錄 xiii
第一章 前言 1
1.1前言 1
1.2研究目的 3
第二章 文獻探討 4
2.1光譜差異程度之比較 4
2.2光譜標準化方法探討 7
2.3光譜標準化校正樣本選擇方法探討 19
2.4 光譜標準化計算轉換矩陣之理論 22
2.4.1 Partial Least Square Regression (PLSR)理論 23
2.4.2 Support Vector Machine (SVM)理論 26
第三章 材料與方法 37
3.1實驗儀器與分析軟體 37
3.2量測設備與實驗規劃 44
3.2.1相同儀器配件不同時間之光譜標準化 46
3.2.2相同儀器不同配件之光譜標準化 48
3.2.3不同儀器之光譜標準化 49
3.3光譜標準化理論分析 50
3.3.1 Piecewise Direct Standardization (PDS) 52
3.3.2 Differential Peicewise Direct Standardization (DPDS) 53
3.3.3 Support Vector Standardization (SVS) 56
3.3.4 Calibration Model Adaptation 58
第四章 結果與討論 59
4.1 相同儀器配件不同時間 61
4.2相同儀器不同配件 75
4.3 不同儀器 89
4.3.1 光譜標準化之準確性 89
4.4標準化光譜之預測能力 118
4.5 M與S關係互換以及波段選擇後之標準化及其預測結果 134
第五章 結論與建議 140
5-1結論 140
5-2建議 145
參考文獻 146
符號表及名詞解釋 155
附錄A 157
上泰儀器股份有限公司。2006。產品介紹。台北:上泰儀器股份有限公司。網址:http://www.suntex.com.tw/index.asp。上網日期:2006-04-21。
伍志翔、陳世銘、楊宜璋、陳加增、葉冠宏。2005。近紅外光光譜儀標準化模式建立之研究。出自“2005農機與生機論文發表會論文摘要集”,333-334。台北:中華農業機械學會。
邱鶴圍。1999。近紅外光應用於芒果內部品質分析之研究。碩士論文。台北:國立台灣大學生物產業機電工程學系研究所。
林育菁。2003。蓮霧及木瓜內部品質之近紅外光檢測。碩士論文。台北:國立台灣大學生物產業機電工程學系研究所。
張嘉麟。1999。近紅外光與核磁共振應用於乳粉脂肪含量之檢測。碩士論文。台北:國立台灣大學生物產業機電工程學系研究所。
張智星。2001。MATLAB程式設計與應用。初版三刷。台北:全華科技。
陳世銘、張文宏、謝廣文。1998。果汁糖度檢測模式之研究。農業機械學刊7(3):41-60。
陳加增。2001。近紅外光應用於水果糖酸度線上檢測之研究。碩士論文。台北:國立台灣大學生物產業機電工程學系研究所。
陳寬裕、何嘉惠、蕭宏誠。2004。應用支援向量迴歸於國際旅遊需求之預測。博士論文。台南:遠東技術學院企業管理系。
楊宜璋。2001a。近紅外光技術應用於柑桔類水果果汁糖酸度之測定。學士論文。台北:國立台灣大學生物產業機電工程學系研究所。
葉冠宏。2005。以小波理論與非線性演算法建構光譜分析法。碩士論文。台北:國立台灣大學生物產業機電工程學系研究所。
葉冠宏、陳世銘、楊宜璋、陳加增、伍志翔。2005。以小波理論與類神經網路建構光譜分析法。出自“2005農機與生機論文發表會論文摘要集”,335-336。台北:中華農業機械學會。
蔡志成。2004。以近紅外光檢測幾丁類物質去乙醯率之研究。碩士論文。台北:國立台灣大學生物產業機電工程學系研究所。
Adhihetty, I.S., J.A. McGuire., B. Wangmannerat., T.M.Niemczyk., D.M. Haaland. 1991. Achieving Transferable Multivariate Spectral Calibration Models:Demonstration with Infrared Spectra of Thin-Film Dielectrics on Silicon. American Chemical Society 63:2329-2338.

Avidan, S. 2003. Subset Selection for Effcient SVM Tracking. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition 03:1063-6919.

Barring, H.K., H. F.Boelens., O. E. DE Noord., and A. K. Smilde. 2001. Optimizing Meta-parameters in Continuous Piecewise Direct Standardization. Applied Spectroscopy 55(4):458-466.
Bi, J., and K.P. Bennett. 2003. A geometric approach to Support Vector Regression. Neurocomputing 55:79-108.
Bouveresse, E., D.L. Massart, P. Dardenne. 1994. Calibration transfer across near-infrared spectrometric instruments using Shenk’s algorithm:effects of different Standardization samples. Analytica Chemica Acta 297:405-416.
Bouveresse, E. and D.L. Massart. 1995. Standardization of near-infrared spectrometric instrument:A review. Vibrational Spectroscopy 11:3-15.
Bouveresse, E. and D.L. Massart. 1996. Improvement of the piecewise direct Standardization procedure for the transfer of NIR spectra for multivariate calibration. Chemometrics and Intelligent laboratory systems 32:201-213.
Bouveresse, E., C. Hartmann, D.L. Massart, I.R. Last, and K.A. Prebble. 1996. Standardization of Near-Infrared Spectrometric Instruments. Analytical Chemistry 68:982-990.
Bouveresse, E., C. Casolino, C. de la Pezuela. 1998. Application of Standardization methods to correct the spectral differences induced by the a fibre optic probe used for the near-infrared analysis of pharmaceutical tablets. Journal of Pharmaceutical and Biomedical Analysis 18:35-42.
Chen, K.Y., C.H. Ho., H.C. Shiau. 2004. Application of support vector regression in forecasting international tourism demand. Tourism Management Research 4:81-97.
Chen, N. 2004. Support vector machine in chemistry. Singapore ; Hackensack, NJ : World Scientific Pub.

Cherkassky, V., and Y. Ma. 2002. Selection of Meta-parameters for Support Vector Regression. Proc. Int. Conf. Artificial Neural Networks:687-693.

Cherkassky, V., and Y. Ma. 2005. Multiple Model Regression Estimation. IEEE TRANSACTIONS ON NEURAL NETWORKS 16(4):785-798.
Cogdill, R.P. and P. Dardenne. 2004. Least-square support vector machines for chemometrics:an introduction and evaluation. Near Infrared Spectrosc 12:93-100.

Cogdill, R.P., L.R. Schimleck, P.D. Jones, G.F. Peter, R.F. Daniels, and A. Clark, III. 2004. Estimation of the physical wood properties of Pinus taeda L. radial strips using least squares support vector machines. Near Infrared Spectrosc 12:263-269.

Despagne, F., B. Walczak,. D.Massart. 1998. Transfer of Calibration of Near-Infrared using Neural Networks. Applied Spectroscopy 52(5):732-745.

Despagne, F., D.L. Massart., M. Jansen., H.V. Daalen. 2000. Intersite transfer of industrial calibration models. Analytica Chimica Acta 406:233-245.
Duponchel, L., C. Ruckebusch, J.P. Huvenne, P. Legrand. 1999. Standardisation of near-IR spectrometers using artificial neural networks. Journal of Molecular Structure 480–481:551–556.
Feudale, R.N., H. Tan., and S.D. Brown. 2002. Peicewise orthogonal signal correction. Chemometrics and Intelligent Laboratory Systems 63:129-138.
Forina , M., G. Drava, C. Armanino, R. Boggia, S. Lanteri, R. Leardi, P. Corti, P. Conti, R. Giangiacomo, C. Galliena, R. Bigoni, I. Quartari, C. Serra, D. Ferri, O. Leoni, L. Lazzeri. 1995. Transfer of calibration function in near-infrared spectroscopy. Chemometrics and Intelligent laboratory systems 27:189-203.
Gemperline, P.J., J.H. Cho., P.K. Aldridge and S.S Sekulic. 1996. Appearance of Discontinities in Spectra Transfomed by the Piecewise Direct Instrument Standardization Procedure. Analytical Chemistry 68:2913-2915.

Herriro, A. and M.C. Ortiz. 1997.Multivariate calibration transfer applied to the routine polarographic determination of cooper, lead, cadmium and zinc. Analytica Chimica Acta 348:51-59.

Kecman, V. (Vojislav). 2001. Learning and soft computing : support vector machines, neural networks, and fuzzy logic models / Vojislav Kecman。Cambridge, Mass : MIT Press.
Larrechi, M.S., and M.P. Callao. 2003. Strategy for introducing NIR spectroscopy and multivariate calibration techniques in industry. Trends in Analytical Chemistry Vol. 22 No. 10:634-640
Leion,H., F. Staffan., M. Josefson., A. Sparen. 2005. Evaluation of basic algorithms for transferring quantitative multivariate calibrations between scanning grating and FT NIR spectrometers. Journal of Pharmaceutical and Biomedical Analysis 37:47-55.

Lin, J., S.C. Lo., C.W. Brown. 1997. Calibration transfer from a scanning near-IR spectrophotometer to a FT-near-IR spectrophotometer. Analytica Chimica Acta 349:263-269.

Liu, J.J., M.H. Bharati, and K.G. Dunn. 2005. Automatic masking in multivariate image analysis using support vector machines. Chemometrics and Intelligent Laboratory Systems 79:42-54
Norgaard, L. 1995. Direct Standardization in multi wavelength fluorescence Spectroscopy. Chemometrics and Intelligent laboratory systems 29:283-293.
Park, K.S., Y.H. Ko, H. Lee, C.H. Jun, H. Chung, and M.S. Ku. 2001. Near-infrared spectral transfer using independent standization samples:a case study on the trans-alkylation process. Chemometrics and Intelligent laboratory systems 55:53-65.
Pierna, J.A.F., P. Volery, R.Besson, V.Baeten, and P. Dardenne. 2005. Classification of Modified Starches by Fourier Transform Infrared Spectroscopy Using Support Vector Machine. Journal of Agricultural and food chemistry 53:6581-6585.
Puigdomenech, A., R. Tauler, E. Casassas, M. Aragay. 1997. Modelling near infrared instrument differences by chemometric methods:testing for near infrared forage analysis. Analytica Chimica Acta 355:181-193.
Quang, H.N., M. Jouan, and N.Q. Dao. 1999. A simplified calibration model of spectra data for quantitative analysis with different Raman spectrometers. Analytica Chimica Acta 379:159-167.
Sahni, N.S., T. Isaksson., and T. NAES. 2005. Comparison of Methods for Transfer of Calibration Models in Near-Infared Spectroscopy:A Case Study Based on Correcting Path Length Differences Using Near-Infarared Spectroscopy. Applied Spectroscopy 59(4):487-495.
Sjoblom, J., O. Svensson, M. Josefson, H. Kullberg, and S. Wold. 1998. An evaluation of orthogonal signal correction applied to calibration transfer of near infrared spectra. Chemometrics and Intelligent laboratory systems 44:229-244.
Swierenga, H., P.J. Groot, A.P. de Weijer, M.W.J. Derksen, and L.M.C. Buydens. 1998. Improve of PLS model transferability by robust wavelength selection. Chemometrics and Intelligent laboratory systems 41:237-248.
Swierenga, H., F. Wulfert., O.E. de Noord., A.P. de Weijer., A.K. Smilde., L.M.C. Buydens. 2000. Development of robust calibration models in near infra-red spectrometric applications. Analytica Chimica ACTA 411;121-135.

Thissen, U., B. Űstűn, W.J. Melssen, and L.M.C. Buydens. 2004. Multivariate Calibration with Least-Squares Support Vector Machines. Analytical Chemistry 76:3099-3105.

Thissan, U., M. Pepers, B. U stun, W.J. Melssena, and L.M.C. Buydens. 2004. Comparing support vector machines to PLS for spectral regression applications. Chemometrics and Intelligent laboratory systems 73:169-179.

Űstűn, B., W.J. Melssen., M. Oudenhuijzen., L.M.C. Buydens. 2005. Determination of optimal support vector regression parameters by genetic algorithms and simplex optimization. Analytica Chimica Acta 544:292-305.
Vapnic, V.N. 1995. The Nature of Statistical Learning Theory. New York:Springer-Verlag.
Walczak, B., E. Bouveresse, D.L. Massart. 1997. Standardization of near-infrared spectra in the wavelet domain. Chemometrics and Intelligent laboratory systems 36:41-51.
Wang , Y., David J. Veltkamp, and Bruise R. Kowalski. 1991. Multivariate Instrument Standardization. Analytical Chemistry 63:2750-2756.
Wang, Y., M.J. Lysaght., and B.R. Kowalski. 1992. Improvement of Multivariate Calibration through Instrument Standardization. Analytical Chemistry 64:562-564.

Wang, Z., T. Dean, and B.R. Kowaiski. 1995. Additive Background Correction in Multivariate Dnstrument Standardization. Analytical Chemistry 67:2379-2385.
Wold, S.vante, M. Sjostrom, and L. Eriksson. 2001. PLS-regression: a basic tool of chemometrics. Chemometrics and Intelligent laboratory systems 58:109-130.
Wold, S. and M. Sjostrom. 1998. Chemometrics, present and future success. Chemometrics and Intelligent laboratory systems 44:3-14.
Wűlfert, F., W.T. Kok, and A. K. Smilde. 1998. Influence of Temperature on Vibreational Spectra and Consequences for the predictive Ability of Multivariate Models. Analytical Chemistry 70:1761-1767.

Wűlfert, F., W.T. Kok, O.E.D. Noord, and A.K. Smilde. 2000. Correction of Temperature-Induced Spectral Variation by Continuous Piecewise Direct Standardization. Analytical Chemistry 72:1639-1944.

Yoon, J., B. Lee, and C. Han. 2002. Calibration transfer of near-infrared spectra based on compression of wavelet coefficients. Chemometrics and Intelligent laboratory systems 64:1-14.
Zue, Y., C. Li., and Y. Zhang. 2004. A Practical Parameter Selection for SVM. ISNN 2004, LNCS 3173, pp. 518–523.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top