ass日本风韵熟妇pics男人扒开女人屁屁桶到爽|扒开胸露出奶头亲吻视频|邻居少妇的诱惑|人人妻在线播放|日日摸夜夜摸狠狠摸婷婷|制服 丝袜 人妻|激情熟妇中文字幕|看黄色欧美特一级|日本av人妻系列|高潮对白av,丰满岳妇乱熟妇之荡,日本丰满熟妇乱又伦,日韩欧美一区二区三区在线

稻谷千粒質(zhì)量近紅外光譜預(yù)測(cè)模型的波長(zhǎng)選擇方法
CSTR:
作者:
作者單位:

作者簡(jiǎn)介:

通訊作者:

中圖分類(lèi)號(hào):

基金項(xiàng)目:

江蘇省高校優(yōu)勢(shì)學(xué)科建設(shè)項(xiàng)目和中央高校基本科研業(yè)務(wù)費(fèi)專(zhuān)項(xiàng)資金資助項(xiàng)目(KWZ201224)


Wavelength Selecting Methods of NIRS Predicting Model of Paddy 1000grain Weight
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 圖/表
  • |
  • 訪問(wèn)統(tǒng)計(jì)
  • |
  • 參考文獻(xiàn)
  • |
  • 相似文獻(xiàn)
  • |
  • 引證文獻(xiàn)
  • |
  • 資源附件
  • |
  • 文章評(píng)論
    摘要:

    為研究波長(zhǎng)選擇方法對(duì)稻谷千粒質(zhì)量近紅外光譜分析(NIRS)模型預(yù)測(cè)能力的影響,用偏最小二乘法(PLS),,在600~1100nm的波長(zhǎng)區(qū)間,,建立稻谷千粒質(zhì)量的全光譜近紅外光譜預(yù)測(cè)模型,得到模型的內(nèi)部交叉驗(yàn)證系數(shù)為0.714,外部驗(yàn)證決定系數(shù)為0.659,內(nèi)部交叉驗(yàn)證誤差和預(yù)測(cè)誤差分別為1.809和1.756。采用相關(guān)系數(shù)法,、互信息法、逐步回歸法,、無(wú)信息變量消除方法,、遺傳算法和間隔偏最小二乘法對(duì)建模波長(zhǎng)區(qū)間進(jìn)行選擇和優(yōu)化,再以同樣的方法建立稻谷千粒質(zhì)量NIRS預(yù)測(cè)模型,。結(jié)果顯示,,通過(guò)波長(zhǎng)選擇和優(yōu)化后,不僅參與建模的波長(zhǎng)顯著減少,,而且所建模型的內(nèi)部交叉驗(yàn)證和外部驗(yàn)證決定系數(shù)均有所增大,,交叉驗(yàn)證誤差和預(yù)測(cè)誤差均有所減小。其中,,采用遺傳算法進(jìn)行波長(zhǎng)選擇后,,所建模型的內(nèi)部交叉驗(yàn)證和外部驗(yàn)證決定系數(shù)最大,分別為0.729和0.710,交叉驗(yàn)證誤差和預(yù)測(cè)誤差則分別降低了9.50%和5.72%,,是6種方法中最優(yōu)的,。表明經(jīng)過(guò)波長(zhǎng)選擇后,可以提高稻谷千粒質(zhì)量近紅外光譜預(yù)測(cè)模型的預(yù)測(cè)能力,。

    Abstract:

    Effect of wavelength selecting method on the predictive ability of NIR spectroscopy models was studied. Predictive models for 1000grain weight of paddy based on near infrared (NIR) spectra were developed using partial least square (PLS) regression in the wavelength region between 600nm and 1100nm. The resultant standard error of crossvalidation and standard error of prediction were 1.809 and 1.756, respectively, with corresponding coefficients of determination of 0.714 for crossvalidation and 0.659 for prediction. The wavelength regions in which the calibrations for 1000grain weight would be developed were optiminized using six methods: the regression coefficient, mutual information, regression, uninformative variables elimination, genetic algorithm and interval partial least square before establishing the calibrations. Then the NIRprediction models for 1000grain weight were developed based on the selected wavelength regions in the same way as the above. Experimental results showed that, after wavelength optimization, the wavelength regions used in model developing significantly decreased, and SEP reduced while Rv2 and Rp2 increased. Of them, after the wavelength selection was carried out by using the genetic algorithm, the developed model was of the highest Rv2 and Rp2. Moreover, the SEP were decreased by 9.50% and 5.72%, respectively. This suggested that predictive ability of the NIR models for 1000grain weight prediction can be improved after wavelength optimization.

    參考文獻(xiàn)
    相似文獻(xiàn)
    引證文獻(xiàn)
引用本文

於海明,李 石,吳 威,葉長(zhǎng)文,康 睿,陳彩蓉.稻谷千粒質(zhì)量近紅外光譜預(yù)測(cè)模型的波長(zhǎng)選擇方法[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2015,46(11):275-279. Yu Haiming, Li Shi, Wu Wei, Ye Changwen, Kang Rui, Chen Cairong. Wavelength Selecting Methods of NIRS Predicting Model of Paddy 1000grain Weight[J]. Transactions of the Chinese Society for Agricultural Machinery,2015,46(11):275-279.

復(fù)制
分享
文章指標(biāo)
  • 點(diǎn)擊次數(shù):
  • 下載次數(shù):
  • HTML閱讀次數(shù):
  • 引用次數(shù):
歷史
  • 收稿日期:2015-06-08
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2015-11-10
  • 出版日期: 2015-11-10
文章二維碼