-
- 全部產(chǎn)品分類
- 標(biāo)準(zhǔn)物質(zhì)
中國(guó)標(biāo)準(zhǔn)物質(zhì) 美國(guó)NIST 歐洲IRMM/ERM 歐洲BCR 英國(guó)MBH 德國(guó)SUS 美國(guó)BS LGC標(biāo)準(zhǔn)物質(zhì) 美國(guó)USGS標(biāo)準(zhǔn)物質(zhì) 國(guó)立環(huán)境標(biāo)準(zhǔn)物質(zhì) IAEA標(biāo)準(zhǔn)物質(zhì) 加拿大礦產(chǎn)科學(xué)室(CCRMP) 日本JSAC標(biāo)準(zhǔn)物質(zhì) 日本GSJ地質(zhì)標(biāo)準(zhǔn)物質(zhì) 美國(guó)ERA標(biāo)準(zhǔn)物質(zhì)
- 藥典及其雜質(zhì)對(duì)照品
- 標(biāo)準(zhǔn)品
- 培養(yǎng)基
- 化學(xué)試劑
- 菌種及細(xì)胞
- 血清
- 試劑盒
- 氣相色譜
- 液相色譜
- 樣品前處理
- 實(shí)驗(yàn)室耗材
- 色譜進(jìn)樣瓶
- 實(shí)驗(yàn)室安全防護(hù)產(chǎn)品
- 電化學(xué)
- 實(shí)驗(yàn)室儀器設(shè)備
-
- 您現(xiàn)在的位置:首頁(yè) >> 技術(shù)支持 >> 電化學(xué)電化學(xué)
-
基于介電頻譜靈武長(zhǎng)棗維生素C含量預(yù)測(cè)方法的研究
發(fā)布時(shí)間:2019/11/4 15:45:22 瀏覽次數(shù):772
基于介電頻譜靈武長(zhǎng)棗維生素C含量預(yù)測(cè)方法的研究
DOI:
中文關(guān)鍵詞: 靈武長(zhǎng)棗 維生素C 介電頻譜 特征頻率 預(yù)測(cè)模型
英文關(guān)鍵詞: Lingwu long jujube vitamin C dielectric spectrum characteristic frequency predictive model
為探究基于介電頻譜預(yù)測(cè)靈武長(zhǎng)棗維生素C含量的可行性,尋找最佳預(yù)測(cè)模型,利用LCR測(cè)試儀測(cè)試1 kHz~1 MHz條件下采后10 d內(nèi)長(zhǎng)棗介電譜變化規(guī)律;以CARS法、GA法、SPA法、UVE法篩選特征頻率點(diǎn)并建立PLS、LSSVM長(zhǎng)棗VC含量預(yù)測(cè)模型。結(jié)果表明,UVE算法為最佳頻譜篩選方法,篩選特征頻率點(diǎn)38個(gè);UVE-PLS為最佳預(yù)測(cè)模型,其Rc、RMSEC、Rp、RMSEP值分別為0.9871、3.9322、0.9460、4.0400,驗(yàn)證模型預(yù)測(cè)值與實(shí)測(cè)值無顯著差異(P>0.05),說明基于介電頻譜預(yù)測(cè)靈武長(zhǎng)棗VC含量的方法是可行的。
In order to explore the feasibility of predicting vitamin C content of Lingwu long jujube based on dielectric spectrum and find the best predictive model. Dielectric spectrum of Changzao were tested and analysed under of 1kHz~1MHz using the LCR tester. The characteristic frequency points were screened out by Competitive Adaptive Reweighed Sampling, Genetic Algorithm, Successive Projection Aalgorithm, and Uninformative Variable Elimination and the predictive model of Vitamin C content Least square support vector machine and Partial Least Squares were established combining the characteristic frequencies and VC value. The results show that the UVE algorithm is the best method to screen spectrum and 38 characteristic frequency points were screened. UVE-PLS is the best predictive model, the Rc, RMSEC, Rp, RMSEP values were 0.9871, 3.9322, 0.9460, 4.0400 and no significant difference (P>0.05) between measured and predicted values of validation model. It is feasible to predict the content of VC in long jujube based on dielectric spectrum.