KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Wongpichet, SereeSubject: search.filters.subject.Partial least squares regression

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Rapid elemental composition measurement of commercial pellets using line-scan hyperspectral imaging analysis
    (2021-04-01)
    Pitak, Lakkana
    ;
    Sirisomboon, Panmanas
    ;
    Saengprachatanarug, Khwantri
    ;
    Wongpichet, Seree
    ;
    Posom, Jetsada
    The use of biomass pellets as a renewable energy source is increasing, leading to the need for rapid assessment of biofuel pellet quality for production monitoring. The purpose of this work was to use line-scan near-infrared (NIR) hyperspectral image technology coupled with chemometric tools to assess the elemental components of biomass pellets. The parameters influencing model performance were investigated, i.e. wavelength and spectral pretreatment technique. Either full wavelength or partial wavelength selected using interval successive projections algorithm (iSPA) and interval genetic algorithm (iGA) were investigated. Either raw spectra or pretreated spectra were used for model development. The models were developed using partial least squares regression (PLSR). The most effective model for the prediction of carbon (C), hydrogen (H), and nitrogen (N) content was developed using iGA wavelength selection and standard normal variate (SNV) spectral pretreatment and provided the highest accuracy with a coefficient of determination of prediction set (r<sup>2</sup><inf>p</inf>) and standard error of prediction (SEP) of 0.83 and 1.33%; 0.84 and 0.17%; and 0.90 and 0.098%, respectively. The model could be used for quality assurance. The S content model was poor and not recommended. The relationship between pellet chemical parameters and reflectance characteristics could be used for predicting C, H, and N of biomass pellets.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Two different portables visible-near infrared and shortwave infrared region for on-tree measurement of soluble solid content of marian plum fruit
    (2020-01-01)
    Posom, Jetsada
    ;
    Soonnamtiang, Navavit
    ;
    Kotethum, Patcharapong
    ;
    Konjun, Pakhpoom
    ;
    Sirisomboon, Panmanas
    The goal of this study was to predict the soluble solid content (SSC) of on-tree Marian plum fruit using two different wavelength range and algorithm. One of these was the commercial dispersion NIR spectrometer (MicroNIR 1700), providing shortwave infrared (SWIR), while the other was a making diode array spectrometer giving visible-near infrared (Vis-NIR). To search optimal model, the analytical ability of the two wavelength ranges spectrometers coupled with two algorithms: i.e. partial least squares regression (PLSR) and support vector machine regression (SVR), were investigated. Different spectral pre-processing methods were tested. The model providing the lowest root mean square errors of prediction (RMSEP) was selected. Overall, the proposed outcome was that the performance of SWIR was more accurate than Vis-NIR spectrometer, and that both SWIR and Vis-NIR coupled with PLSR algorithm had a higher accuracy than SVR algorithm. The best model for on-tree evaluation SSC was the SWIR constructed using the PLSR algorithm with the spectral pre-processing of the 2<sup>nd</sup> derivative, providing a coefficient of determination of calibration set (R<sup>2</sup>) of 0.81, a coefficient of determination of validation set (r<sup>2</sup>) of 0.76, RMSEP of 0.69 °Brix, and a relative standard error of prediction (RSEP) of 4.43%. The outcome showed that a portable SWIR spectrometer developed with PLSR could be used for monitoring the SSC of individual Marian plum fruit on-tree for quality assurance.