Search Results

You are looking at 1 - 10 of 80 items for :

  • partial least-squares regression x
  • Refine by Access: All x
Clear All
Free access

Yohei Kurata, Tomoe Tsuchida, and Satoru Tsuchikawa

, principle component regression, and partial least squares regression (PLSR) analysis. It was possible to predict both the sugar and acid contents in apple with high precision using TOF-NIRS. In our previous paper ( Kurata and Tsuchikawa, 2009 ), a Q

Full access

Yung-Kun Chuang, I-Chang Yang, Chao-Yin Tsai, Jiunn-Yan Hou, Yung-Huei Chang, and Suming Chen

the input for spectral analysis. Two standard multivariate analysis methods, modified partial least-squares regression (MPLSR) and stepwise multiple linear regression (SMLR), were used to explore the relationships between the reflectance spectra and

Open access

Sai Xu, Huazhong Lu, Xu Wang, Christopher M. Ference, Xin Liang, and Guangjun Qiu

redundancy. CNN was applied to conduct deep learning feature extraction of the spectral curve. PCA was applied for the dimension reduction of VIS/NIR Spectrum data for the CNN input. Partial least squares regression. PLSR ( Shetty and Gislum, 2011 ) is

Free access

Xiao-li Li and Yong He

Satsuma mandarin using Vis/NIR-spectroscopy technique J. Food Eng. 77 313 319 Helland, I.S. 2001 Some theoretical aspects of partial least squares regression Chem. Intell. 58 97 107 Hu, Y. Li

Free access

Gustavo H. de A. Teixeira, Valquiria G. Lopes, Luís C. Cunha Júnior, and José D.C. Pessoa

(cyanidin-3-glucoside g·kg −1 w/w) from partial least squares (PLSs) juçara model using first derivative of Savitzky–Golay preprocessed spectra in the near infrared region (NIR) for the juçara fruit. PLSs regression: açaí model. By using only the açaí

Free access

Jian-rong Feng, Wan-peng Xi, Wen-hui Li, Hai-nan Liu, Xiao-fang Liu, and Xiao-yan Lu

the quality of these fruit to facilitate breeding of new cultivars meeting the consumer’s expectations. Fig. 2. Loading weight plot of principal components, PC1 vs. PC2 from a partial least squares regression (PLSR) model of volatile compounds, quality

Full access

Stephen R. Delwiche, Weena Mekwatanakarn, and Chien Y. Wang

of fresh weight). Spectral analysis. The Unscrambler multivariate analysis software program (version 9.1; CAMO, Oslo, Norway) was used for partial least squares (PLS) regression calibration development and validation. Because the penetration depth of

Open access

Qiang Zhang, Minji Li, Beibei Zhou, Junke Zhang, and Qinping Wei

analysis methods used in studies. In the present study, the partial least-squares regression was used to select variables based on VIP values, thus eliminating the interference of human factors and the complex collinearity among multiple independent

Free access

K.H.S. Peiris, G.G. Dull, R.G. Leffler, and S.J. Kays

A nondestructive method for measuring the soluble solids content (SSC) of individual processing tomatoes (Lycopersicon esculentum Mill.) was developed using NIR spectrometry. A diode array fiber optic spectrometer was used to measure NIR transmittance. Each fruit was scanned at two locations on opposite sides midway along the proximal-distal axis. After scanning, each fruit was processed and pureed, and SSC was determined using a refractometer. Multiple linear regression (MLR), partial least squares (PLS) regression, and neural network (NN) calibration models were developed using the second derivatives of averaged spectra from 780 to 980 nm. The validation results showed that NN calibration was better than MLR or PLS calibrations. The NN calibration could estimate the processed SSC of individual unprocessed tomatoes with a standard error of prediction of 0.52% and could classify >72% of fruit in an independent population within ±0.5% of SSC.

Free access

Min Min, Won Suk Lee, Yong Hyeon Kim, and Ray A. Bucklin

Proper nutrient management is essential to increase yield, quality and profit. This study was conducted to estimate the N concentrations of chinese cabbage (Brassica campestris L. ssp. pekinensis `Norangbom') plug seedlings using visible and near infrared spectroscopy for nondestructive N detection. Chinese cabbage seeds were sown and raised in three 200-cell plug trays filled with growing mixture in a plant growth chamber with three different levels (40%, 80%, and 100%) of required N. Reflectance for leaves of chinese cabbage seedlings was measured with a spectrophotometer 15 days after the experiment started. Reflectance was measured in the 400 to 2500 nm wavelength range at 1.1-nm increments. The leaves were dried afterwards to measure their water content and were analyzed for their actual N contents. The experiment was repeated twice (group I and II). Correlation coefficient spectrum, standard deviation spectrum, stepwise multiple linear regression (SMLR), and partial least squares (PLS) regression were used to determine wavelengths for N prediction models. Performances of SMLR and PLS were similar. For the validation data set (group II), SMLR produced an r 2 of 0.846 and PLS yielded r 2 of 0.840. The most significant wavelength 710 nm, which was identified by all methods, was correlated to chlorophyll. Water content positively correlated with N concentration (r = 0.76). Wavelengths of 1467, 1910, and 1938 nm selected by SMLR from both groups also showed that water had a strong effect on N prediction. Wavelengths near 2136 nm indicated that protein had potential use in N prediction. Wavelengths near 550 and 840 nm could also contribute to N prediction.