本文選題：近紅外光譜　切入點：波長選擇算法　出處：《中國農(nóng)業(yè)大學(xué)》2017年博士論文

【摘要】：近紅外光譜作為一種快速無損檢測技術(shù)在農(nóng)產(chǎn)品品質(zhì)分析領(lǐng)域發(fā)揮著越來越重要的作用。然而近紅外光譜中往往存在著大量無信息波長甚至是噪聲波長,因此波長選擇已經(jīng)成為近紅外光譜分析中一個關(guān)鍵的環(huán)節(jié),目前已有多達(dá)幾十種波長選擇算法。本文系統(tǒng)分析和研究了現(xiàn)有波長選擇算法原理的差異,并將近紅外光譜分析中常用波長選擇算法大體上劃分為基于偏最小二乘模型參數(shù)、智能優(yōu)化算法、連續(xù)投影策略、模型集群分析策略和波長區(qū)間選擇等五類。為了解決現(xiàn)有方法存在的可靠性和穩(wěn)定性問題,本文在近紅外光譜譜學(xué)特點的基礎(chǔ)上,分別借鑒模型集成、模型集群分析和串聯(lián)等三種新思路開展了以下幾項研究,并采用玉米、土壤、藥片等三種代表性樣品體系進(jìn)行了算法驗證。(1)首次采用移動窗口平滑集成策略(MWWS)對競爭性自適應(yīng)加權(quán)采樣算法(CARS)進(jìn)行了改造,得到了一種名為MWWS-ECARS的新型波長選擇算法。實驗結(jié)果表明,MWS-ECARS算法通過移動窗口對CARS算法重復(fù)運行后各波長的累積被選頻率進(jìn)行平滑處理,不僅克服了 CARS算法選擇波長的不穩(wěn)定性,而且還可以通過調(diào)節(jié)移動窗口寬度和閾值的大小對最終選中波長區(qū)間的寬度進(jìn)行優(yōu)化。(2)在模型集群分析(MPA)的框架下提出了一種新型波長區(qū)間組合優(yōu)化算法(ICO)。ICO算法首先采用軟收縮的方式對波長區(qū)間組合進(jìn)行優(yōu)化,然后采用局部搜索的方式對最終入選區(qū)間的寬度進(jìn)行自動優(yōu)化。實驗結(jié)果表明ICO算法不僅具有軟收縮的特點,還具有收斂速度更快,參數(shù)設(shè)置較少等優(yōu)點;ICO算法中采用波長區(qū)間替換波長點作為優(yōu)化對象,既可以較好地降低軟收縮策略在尋優(yōu)過程中的計算負(fù)擔(dān),又可以降低優(yōu)化算法出現(xiàn)過擬合的風(fēng)險;其中采用的WBS方法被證明比WBMS方法更適合用于在模型集群分析框架下開發(fā)新型波長選擇算法,因為其可以通過在MPA的隨機(jī)采樣環(huán)節(jié)引入更合適水平的隨機(jī)因素來克服WBMS方法存在的缺陷。(3)基于算法串聯(lián)的思路采用連續(xù)投影算法(SPA)對MWWS-ECARS和ICO算法選中的波長進(jìn)行簡化,結(jié)果表明SPA算法可以在保證所建模型的預(yù)測能力不出現(xiàn)顯著下降的同時,進(jìn)一步簡化上述兩種算法選中的波長點,但是樣品體系越復(fù)雜,簡化的力度就越小。(4)通過實驗考察了不同預(yù)處理方法對ICO算法選擇波長分布和建模效果的影響情況。結(jié)果表明,不同光譜預(yù)處理方法對于ICO算法選擇波長的分布情況和建模效果均有著較強(qiáng)的影響。
[Abstract]:Near infrared spectroscopy as a rapid nondestructive detection technology plays an increasingly important role in the quality of agricultural products. However, the domain analysis in near infrared spectroscopy is the existence of a large number of information without wavelength even noise wavelength, therefore the wavelength selection has become a key link in near infrared spectroscopy analysis, there are dozens of wavelength selection research on the existing algorithm. The wavelength selection algorithm principle and difference analysis of this system, and the analysis of near infrared spectroscopy was used in wavelength selection algorithm is generally divided into partial least squares model parameters based on intelligent optimization algorithm, continuous projection strategy, model cluster analysis strategy and wavelength interval selection of five. In order to solve the problem of reliability and stability the existing methods, this paper in the near infrared spectrum based on the characteristics, respectively referring to the model integration, model and cluster analysis on With three new ideas in the following study, and the use of corn, soil, pills and other three kinds of representative sample system to verify the algorithm. (1) for the first time using moving window smoothing integration strategy (MWWS) sampling algorithm for competitive adaptive weighted (CARS) to get a choice of transformation a new algorithm for wavelength of MWWS-ECARS. The experimental results show that the MWS-ECARS algorithm by moving the window on the accumulation of each wavelength CARS algorithm was repeated after running smooth frequency rate, not only to overcome the CARS algorithm to select the wavelength of the instability, but also can be optimized by adjusting the window width and the width of the mobile threshold on the size of the final selected wavelength interval. (2) analysis in cluster model (MPA) framework proposed a new wavelength interval optimization algorithm (ICO).ICO algorithm adopts soft contraction on wavelength interval Combined optimum width and then uses a local search method was chosen to optimize the interval. The experimental results show that the ICO algorithm not only has soft shrinkage, but also has faster convergence speed, less parameter settings etc.; the ICO algorithm uses the wavelength interval to replace wavelength as the optimization object, which can reduce the computational burden in the optimization process of the soft contraction strategy, but also can reduce the risk of over fitting optimization algorithm; the WBS method proved more suitable for the development of new wavelength selection algorithm analysis framework in the model cluster than WBMS method, because it can overcome the defects of WBMS method by random factors into more appropriate level random sampling part of MPA. (3) the idea of using a continuous series algorithm based on the projection algorithm (SPA) to select the MWWS-ECARS and ICO algorithm in wavelength Simplified, results show that the prediction ability of SPA algorithm can model that does not appear significant decline at the same time, to further simplify the above two algorithms selected wavelengths, but the sample system is more complex, the simplified strength is small. (4) through the effects of the choice of the wavelength distribution and modeling the effect of ICO the algorithm of different pretreatment methods. The results show that different spectral pretreatment methods for the ICO algorithm to select the distribution and the effect of modeling wavelength has a stronger effect.

【學(xué)位授予單位】：中國農(nóng)業(yè)大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2017
【分類號】：O657.33

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 孫世鵬;彭俊;李瑞;朱兆龍;Vázquez-Arellano MANUEL;傅隆生;;基于近紅外高光譜圖像的冬棗損傷早期檢測[J];食品科學(xué);2017年02期

2 劉澤蒙;張瑞;張廣明;陳可泉;;基于離散螢火蟲算法的近紅外波長優(yōu)選方法研究[J];光譜學(xué)與光譜分析;2016年12期

3 孫通;莫欣欣;李曉珍;吳宜青;劉木華;;近紅外光譜技術(shù)結(jié)合變量選擇方法定性檢測食用植物油中的腐霉利[J];光譜學(xué)與光譜分析;2016年12期

4 吳雙;涂斌;陳志;彭博;鄭曉;何東平;;近紅外光譜結(jié)合蒙特卡洛交互驗證奇異樣本篩選的橄欖油摻偽定性定量分析[J];食品科技;2016年10期

5 張紅濤;母建茹;阮朋舉;李德偉;;基于ACO-SVR法的麥粒硬度預(yù)測研究[J];糧食與油脂;2016年10期

6 劉國海;韓蔚強(qiáng);江輝;;基于近紅外光譜的橄欖油品質(zhì)鑒別方法研究[J];光譜學(xué)與光譜分析;2016年09期

7 王巧華;李小明;段宇飛;;基于CUVE-PLS-DA的雞蛋新鮮度在線檢測分級[J];食品科學(xué);2016年22期

8 王立琦;劉亞楠;張青;崔月;葛慧芳;于殿宇;;食用油脂酸值近紅外光譜特征波長優(yōu)選[J];食品科學(xué);2016年16期

9 羅霞;洪添勝;羅闊;代芬;吳偉斌;梅慧蘭;林凜;;小波變換和連續(xù)投影算法在火龍果總酸無損檢測中的應(yīng)用[J];光譜學(xué)與光譜分析;2016年05期

10 王元忠;趙艷麗;張霽;金航;;近紅外光譜信息篩選在瑪咖產(chǎn)地鑒別中的應(yīng)用[J];光譜學(xué)與光譜分析;2016年02期

，

本文編號：1679482