【摘要】：紅外光譜以其穩(wěn)定性高、無(wú)需對(duì)樣品做化學(xué)處理、圖譜信息含量豐富等優(yōu)點(diǎn),被廣泛應(yīng)用于化學(xué)品分析、物質(zhì)品種預(yù)測(cè)、品質(zhì)質(zhì)量鑒定等諸多領(lǐng)域。紅外光譜數(shù)據(jù)庫(kù)系統(tǒng)能幫助建立穩(wěn)定、快捷的樣品種類預(yù)測(cè)模型、質(zhì)量分析模型、特征分析模型等,使研究人員可以更加全面地掌握樣品的信息。在紅外光譜數(shù)據(jù)庫(kù)系統(tǒng)中,準(zhǔn)確、高效的光譜分類匹配算法是整個(gè)系統(tǒng)有效運(yùn)行的關(guān)鍵保證,因此,研究光譜分類匹配算法對(duì)推廣紅外光譜數(shù)據(jù)庫(kù)系統(tǒng)有促進(jìn)作用。現(xiàn)有的光譜匹配算法多從歐氏距離測(cè)度或曲線相似性方面衡量光譜之間的相似程度,而無(wú)法將兩方面因素綜合,并且隨著類別中心總數(shù)的增加,現(xiàn)有算法的準(zhǔn)確率已無(wú)法滿足光譜數(shù)據(jù)庫(kù)系統(tǒng)的要求。因此本文以馬鈴薯作為研究對(duì)象,研究了紅外光譜數(shù)據(jù)庫(kù)系統(tǒng)中的關(guān)鍵算法。首先,針對(duì)傳統(tǒng)光譜特征峰識(shí)別算法需要對(duì)光譜做多次掃描、對(duì)矮小峰及肩峰識(shí)別能力較弱的現(xiàn)象,提出了一種只需一次掃描的基于動(dòng)態(tài)峰形因子的特征峰識(shí)別算法。實(shí)驗(yàn)表明,該算法能夠準(zhǔn)確地識(shí)別出光譜曲線中的所有有效特征峰,對(duì)肩峰及矮小峰也有一定的識(shí)別能力。其次,根據(jù)漢明距離及光譜差曲線的概念提出了動(dòng)態(tài)光譜距離算法,該算法綜合考慮了光譜曲線的波形因素及絕對(duì)差異因素,實(shí)現(xiàn)了不同品種馬鈴薯的精確鑒別,實(shí)驗(yàn)結(jié)果表明,該算法的平均準(zhǔn)確率達(dá)到92.85%,高于傳統(tǒng)的歐氏距離、光譜角等算法。最后,針對(duì)類別中心總數(shù)不斷增多時(shí),光譜分類算法準(zhǔn)確率下降的問(wèn)題,提出了基于虛擬競(jìng)爭(zhēng)自組織自增長(zhǎng)特征映射神經(jīng)網(wǎng)絡(luò)VC-TGSOM的光譜分類算法。實(shí)驗(yàn)表明,VC-TGSOM網(wǎng)絡(luò)的準(zhǔn)確率不會(huì)隨著類別中心總數(shù)的增加而下降。
[Abstract]:Infrared spectroscopy has been widely used in many fields, such as chemical analysis, material variety prediction, quality identification and so on, because of its high stability, no need for chemical treatment, rich atlas information and so on. Infrared spectrum database system can help to establish stable and fast sample type prediction model, quality analysis model, feature analysis model and so on, so that researchers can master the sample information more comprehensively. In infrared spectral database system, accurate and efficient spectral classification and matching algorithm is the key to the effective operation of the whole system. Therefore, the study of spectral classification and matching algorithm can promote the promotion of infrared spectral database system. Most of the existing spectral matching algorithms measure the similarity between spectra from the aspect of Euclidean distance measure or curve similarity, but can not synthesize the two factors, and with the increase of the total number of category centers, the accuracy of the existing algorithms can no longer meet the requirements of spectral database system. Therefore, taking potato as the research object, the key algorithm of infrared spectrum database system is studied in this paper. Firstly, aiming at the fact that the traditional spectral feature peak recognition algorithm needs to scan the spectrum many times, and the recognition ability of dwarf peak and shoulder peak is weak, a feature peak recognition algorithm based on dynamic peak shape factor is proposed, which only needs one scan. The experimental results show that the algorithm can accurately identify all the effective characteristic peaks in the spectral curve, and also has a certain ability to recognize shoulder peaks and dwarf peaks. Secondly, according to the concepts of hamming distance and spectral difference curve, a dynamic spectral distance algorithm is proposed. The algorithm takes into account the waveform and absolute difference factors of spectral curve, and realizes the accurate identification of different varieties of potato. The experimental results show that the average accuracy of the algorithm is 92.85%, which is higher than the traditional Euclidean distance, spectral angle and so on. Finally, in order to solve the problem that the accuracy of spectral classification algorithm decreases when the total number of category centers increases, a spectral classification algorithm based on virtual competitive self-organizing self-growing feature mapping neural network VC-TGSOM is proposed. The experimental results show that the accuracy of VC-TGSOM network does not decrease with the increase of the total number of category centers.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：S532;TP311.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 盧肖平;;馬鈴薯主糧化戰(zhàn)略的意義、瓶頸與政策建議[J];華中農(nóng)業(yè)大學(xué)學(xué)報(bào)(社會(huì)科學(xué)版);2015年03期

2 郭志明;黃文倩;彭彥昆;王秀;湯修映;;自適應(yīng)蟻群優(yōu)化算法的近紅外光譜特征波長(zhǎng)選擇方法[J];分析化學(xué);2014年04期

3 代芬;Mads Sylvest Bergholt;Arnold Julian Vinoj Benjamin;洪添勝;Zhiwei Huang;;近紅外激發(fā)熒光光譜與拉曼光譜快速鑒別馬鈴薯品種[J];光譜學(xué)與光譜分析;2014年03期

4 王艷華;;SOM研究的若干新進(jìn)展[J];福建電腦;2013年11期

5 張其林;王先培;趙宇;屈萌;杜雙育;;基于相似系統(tǒng)理論的紅外光譜譜圖比對(duì)方法[J];光譜實(shí)驗(yàn)室;2013年06期

6 李永祥;李美齡;李貞景;張曉清;王斌;張玄和;羅成;;源于不同數(shù)據(jù)庫(kù)的食源性有機(jī)分子紅外光譜比較[J];農(nóng)業(yè)工程;2013年06期

7 薛云偉;;朗伯-比爾定律和光[J];產(chǎn)業(yè)與科技論壇;2013年13期

8 樊勁輝;陸薇;李爭(zhēng);;一種改進(jìn)的SOFM聚類算法研究[J];河北科技大學(xué)學(xué)報(bào);2012年06期

9 蔡天凈;唐瀚;;Savitzky-Golay平滑濾波器的最小二乘擬合原理綜述[J];數(shù)字通信;2011年01期

10 張軍;姜黎;陳哲;余謙;梁靜秋;王京華;;基于近紅外光譜技術(shù)成品汽油分類方法的研究[J];光譜學(xué)與光譜分析;2010年10期

相關(guān)會(huì)議論文 前1條

1 劉偉;徐水平;袁軍;董少敏;;基于差曲線信息熵的光譜相似性測(cè)度改進(jìn)方法[A];第二屆“測(cè)繪科學(xué)前沿技術(shù)論壇”論文精選[C];2010年

相關(guān)博士學(xué)位論文 前2條

1 周萬(wàn)懷;蘋果近紅外光譜數(shù)據(jù)庫(kù)系統(tǒng)關(guān)鍵算法研究及原型系統(tǒng)開(kāi)發(fā)[D];浙江大學(xué);2014年

2 雷萌;基于機(jī)器學(xué)習(xí)的煤質(zhì)近紅外光譜分析[D];中國(guó)礦業(yè)大學(xué);2013年

相關(guān)碩士學(xué)位論文 前4條

1 孫鴻燁;近紅外光譜建模中的變量選擇方法研究[D];長(zhǎng)春理工大學(xué);2014年

2 李淥潔;近紅外光譜的小波域分析及特征提取方法的研究[D];長(zhǎng)春理工大學(xué);2012年

3 王靜;紅外光譜數(shù)據(jù)庫(kù)系統(tǒng)研究[D];華東師范大學(xué);2008年

4 華國(guó)棟;常用飲片近紅外光譜數(shù)據(jù)庫(kù)建立及識(shí)別研究[D];北京中醫(yī)藥大學(xué);2007年

，

本文編號(hào)：2498431