光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
SPECTROSCOPY AND SPECTRAL ANALYSIS
2015年
5期
1233-1238
,共6页
孔庆明%苏中滨%沈维政%张丙芳%王建波%纪楠%葛慧芳
孔慶明%囌中濱%瀋維政%張丙芳%王建波%紀楠%葛慧芳
공경명%소중빈%침유정%장병방%왕건파%기남%갈혜방
近红外光谱%间隔偏最小二乘%连续投影算法%遗传算法
近紅外光譜%間隔偏最小二乘%連續投影算法%遺傳算法
근홍외광보%간격편최소이승%련속투영산법%유전산법
Near infrared spectroscopy%Interval partial least squares%Successive projections algorithm%Genetic algorithm
在近红外光谱分析模型中全谱信息通常含有大量冗余信息,会导致模型解析时间延长、加大模型解析难度,因此如何快速有效地选取特征波长至关重要。采用基于间隔偏最小二乘(interval partial least squares ,IPLS)结合连续投影算法(successive projections algorithm ,SPA)对小麦秸秆发酵过程微生物生物量进行特征波长选择,共制备85个样本,采用氨基葡萄糖法测定微生物生物量,选择68个样本作为校正集,17个样本作为验证集。首先对全谱区520个波长点根据间隔点大小10,20,30,40进行分段建模,选取出4450~4925和9194~9993 cm-1两个波段范围作为特征波段,将选取出的特征波段再进行连续投影算法及遗传算法(genetic algorithm ,GA)特征波长点选取,并进行综合分析对比。实验结果表明采用IPLS-SPA算法选择4450~4925和9194~9993 cm-1的组合波段具有最佳建模效果,相比于全谱建模其参与建模的波长点由520个减少到10个,模型验证集决定系数(R-Square ,R2)从0.8849提升至0.94528,验证集均方误差根(root mean square error prediction ,RMSEP)从11.1049降至8.2033,GA遗传算法虽取得了更优的模型精度,但其实验结果并不稳定且随机性较强,而IPLS结合SPA方法能够稳定而准确的(地)选择特征波长信息,提高模型运算速度并降低模型拟合难度,可以作为一种新的波段选择参考方法。结果表明采用近红外光谱分析方法对秸秆发酵生物量进行快速检测是可行的。
在近紅外光譜分析模型中全譜信息通常含有大量冗餘信息,會導緻模型解析時間延長、加大模型解析難度,因此如何快速有效地選取特徵波長至關重要。採用基于間隔偏最小二乘(interval partial least squares ,IPLS)結閤連續投影算法(successive projections algorithm ,SPA)對小麥秸稈髮酵過程微生物生物量進行特徵波長選擇,共製備85箇樣本,採用氨基葡萄糖法測定微生物生物量,選擇68箇樣本作為校正集,17箇樣本作為驗證集。首先對全譜區520箇波長點根據間隔點大小10,20,30,40進行分段建模,選取齣4450~4925和9194~9993 cm-1兩箇波段範圍作為特徵波段,將選取齣的特徵波段再進行連續投影算法及遺傳算法(genetic algorithm ,GA)特徵波長點選取,併進行綜閤分析對比。實驗結果錶明採用IPLS-SPA算法選擇4450~4925和9194~9993 cm-1的組閤波段具有最佳建模效果,相比于全譜建模其參與建模的波長點由520箇減少到10箇,模型驗證集決定繫數(R-Square ,R2)從0.8849提升至0.94528,驗證集均方誤差根(root mean square error prediction ,RMSEP)從11.1049降至8.2033,GA遺傳算法雖取得瞭更優的模型精度,但其實驗結果併不穩定且隨機性較彊,而IPLS結閤SPA方法能夠穩定而準確的(地)選擇特徵波長信息,提高模型運算速度併降低模型擬閤難度,可以作為一種新的波段選擇參攷方法。結果錶明採用近紅外光譜分析方法對秸稈髮酵生物量進行快速檢測是可行的。
재근홍외광보분석모형중전보신식통상함유대량용여신식,회도치모형해석시간연장、가대모형해석난도,인차여하쾌속유효지선취특정파장지관중요。채용기우간격편최소이승(interval partial least squares ,IPLS)결합련속투영산법(successive projections algorithm ,SPA)대소맥갈간발효과정미생물생물량진행특정파장선택,공제비85개양본,채용안기포도당법측정미생물생물량,선택68개양본작위교정집,17개양본작위험증집。수선대전보구520개파장점근거간격점대소10,20,30,40진행분단건모,선취출4450~4925화9194~9993 cm-1량개파단범위작위특정파단,장선취출적특정파단재진행련속투영산법급유전산법(genetic algorithm ,GA)특정파장점선취,병진행종합분석대비。실험결과표명채용IPLS-SPA산법선택4450~4925화9194~9993 cm-1적조합파단구유최가건모효과,상비우전보건모기삼여건모적파장점유520개감소도10개,모형험증집결정계수(R-Square ,R2)종0.8849제승지0.94528,험증집균방오차근(root mean square error prediction ,RMSEP)종11.1049강지8.2033,GA유전산법수취득료경우적모형정도,단기실험결과병불은정차수궤성교강,이IPLS결합SPA방법능구은정이준학적(지)선택특정파장신식,제고모형운산속도병강저모형의합난도,가이작위일충신적파단선택삼고방법。결과표명채용근홍외광보분석방법대갈간발효생물량진행쾌속검측시가행적。
The whole spectrum usually contains a lot of redundant information in the near-infrared spectroscopy model ,the pres-ence of redundant information will increase the model resolution time and increase the difficulty of parsing model ,Therefore , how to select the characteristic wavelength quickly and effectly is very crucial .In this paper ,we combined the algorithm based on SPA (successive projections algorithm ) with IPLS (interval partial least squares ) to selec the characteristic wavelength in the fermentation of wheat straw microbial biomass ,A total of 85 samples prepared by measuring microbial biomass using glu-cosamine method ,68 samples are chosen as calibration set and 17 samples are chosen as verification set .First ,the w hole spec-tral region 520 points are segmented modeling according to the interval wavelength point size 10 ,20 ,30 ,40 and 4 450~4 925 cm -1 ,9 194~9 993 cm -1 two-band range are selected as the characteristic wavelength band ,then pick out the new feature wavelength points by Successive Projections Algorithm band and Genetic Algorithm (GA) ,comprehensive analysis and compari-son the result of model .The experimental results show that the using of IPLS-SPA algorithm to select the combination band 4 450~4 925 cm -1 & 9 194~9 993 cm-1 has the best modeling effect ,compared with the modeling of whole spectrum ,the wavelength points decrease from 520 to 10 ,the correction coefficient of determination R2 rised from 0.884 9 to 0.945 28 ,root mean square error (RMSE) dropped from 11.104 9 to 8.203 3 ,although the genetic algorithm model achieved the better accura-cy ,but the results are instable and have a strong randomness ,while IPLS combined SPA method can select characteristic wave-length information stability and accurately ,which can improve the model calculation speed and reduce the fitting difficulty of the model ,it can be used as a new reference method for band selection .The results show that using near infrared spectroscopy method for straw biomass rapid detection is feasible .