【摘要】：在光譜建模過程中,采用不同的變量篩選算法進(jìn)行光譜特征波段的提取已成為提高模型效果的重要方法。以真空包裝的冷卻羊肉細(xì)菌菌落總數(shù)作為研究指標(biāo),比較了兩種變量篩選算法對其高光譜偏最小二乘(partial least squares,PLS)模型效果的影響。研究提取了樣品肌肉感興趣區(qū)域(ROIs)的羊肉光譜并進(jìn)行預(yù)處理,進(jìn)而采用遺傳算法(genetic algorithm,GA)和競爭性自適應(yīng)重加權(quán)法(competitive adaptive reweighted sampling,CARS)分別對預(yù)處理后的473~1 000 nm范圍光譜進(jìn)行特征波段的提取,對比分析了不同波段下羊肉細(xì)菌菌落總數(shù)的GA-PLS,CARS-PLS和全波段PLS(W-PLS)模型效果。結(jié)果表明,GA-PLS和CARS-PLS的模型效果均優(yōu)于W-PLS,且CARS-PLS模型效果最好,其校正集的決定系數(shù)(R_c~2)和均方根誤差(root mean square error,RMSEC)分別為0.96和0.29,交互驗證的決定系數(shù)(R_(cv)~2)和均方根誤差(root mean square errorof cross validation,RMSECV)分別為0.92和0.46,預(yù)測集的決定系數(shù)(R_p~2)和均方根誤差(root mean square error of prediction,RMSEP)分別為0.92和0.47,預(yù)測相對分析誤差(relative prediction deviation,RPD)為3.58。因此利用高光譜圖像技術(shù)結(jié)合CARS-PLS可以實現(xiàn)羊肉細(xì)菌菌落總數(shù)快速無損準(zhǔn)確檢測。
[Abstract]:In the process of spectral modeling, it has become an important method to improve the effectiveness of the model by using different variable selection algorithms to extract spectral feature bands. The effects of two variable selection algorithms on the hyperspectral partial least squares (partial least squares) model were compared with the total bacterial colony count of chilled mutton in vacuum packaging. The mutton spectra of the muscle region of interest (ROIs) were extracted and pretreated, and the characteristic bands were extracted by genetic algorithm (GA) and competitive adaptive reweighting method (competitive adaptive reweighted sampling car), respectively. The effects of GA-PLS CARS-PLS model and full-band PLS (W-PLS) model of mutton bacterial colony in different bands were compared and analyzed. The results show that the model effect of GA-PLS and CARS-PLS is better than that of W-PLS, and the effect of CARS-PLS model is the best. The determination coefficient (R_c~2) and root mean square error (root mean square error) of the corrected set are 0.96 and 0.29, respectively. The determination coefficients (R _ (cv) _ 2) and the root mean square error (root mean square errorof cross) of the calibration set are 0.92 and 0.46, respectively. The determination coefficient (R_p~2) and the root mean square error (root) of the predicted set are 0.92 and 0.46, respectively. Mean square error of prediction RMSEP was 0. 92 and 0. 47, respectively. The relative analysis error (relative prediction deviation RPD) was 3. 58. Therefore, the use of hyperspectral image technology combined with CARS-PLS can achieve rapid and accurate detection of mutton bacterial colonies.
【作者單位】： 石河子大學(xué)機(jī)械電氣工程學(xué)院;石河子大學(xué)食品學(xué)院;
【基金】：國家自然科學(xué)基金項目(31460418) 高等學(xué)校博士學(xué)科點專項科研基金項目(2013651820004)資助
【分類號】：TS251.7;O657.3

【相似文獻(xiàn)】

相關(guān)期刊論文 前7條

1 殳靜;陸兵;鐘麗華;周軍;諶斌;;乘用車內(nèi)空氣微生物的污染狀況調(diào)查[J];環(huán)境與健康雜志;2012年05期

2 金立堅,孫莉;公共場所衛(wèi)生監(jiān)測結(jié)果數(shù)據(jù)換算簡表的應(yīng)用探討[J];預(yù)防醫(yī)學(xué)情報雜志;2004年05期

3 李麗莉;王碧波;;紙制品的質(zhì)量安全及其監(jiān)管[J];中國質(zhì)量技術(shù)監(jiān)督;2014年07期

4 范曉東;微生物檢驗中的幾個問題[J];肉類工業(yè);1999年02期

5 楊冬華;武佳麗;唐輝;周帆;魏琴;孫海榮;;寧夏西吉縣城鄉(xiāng)接合部地區(qū)學(xué)生人居環(huán)境衛(wèi)生學(xué)現(xiàn)況[J];職業(yè)與健康;2013年02期

6 張建軍;;托盤包裝上漿雞肉片冷藏中品質(zhì)的變化研究[J];食品科技;2011年10期

7 ;[J];;年期

相關(guān)重要報紙文章 前3條

1 中國消費者報 萬曉東;貝雅牌紙面巾細(xì)菌菌落總數(shù)超標(biāo)[N];中國消費者報;2005年

2 國家紙張質(zhì)量監(jiān)督檢驗中心物理檢驗室主任、高級工程師 馬忻;紙巾紙[N];中國質(zhì)量報;2004年

3 ;標(biāo)準(zhǔn)解讀[N];中國質(zhì)量報;2003年

，

本文編號：2176628