KMITL

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

Browse

Settings

Author: search.filters.author.Siahaan, Herbert HasudunganSubject: search.filters.subject.Chemometrics

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A novel strategy of NIR spectra multivariate calibration in the presence both of small dataset and non-linearity: A comparative study
    (2023-12-01)
    Devianti
    ;
    Ismy, Adi Saputra
    ;
    Siahaan, Herbert Hasudungan
    ;
    Sitorus, Agustami
    The presence of non-linearity and, at the same time, the small number of datasets are often the constraints that appear together in the case of NIR spectra (381–1065nm). This makes some chemometricians think again about presenting a reasonable and robust calibration model using the linear calibration method. On the other hand, even though obtaining a high and robust calibration model, the NIR spectra-based approach is still an alternative method that must still consider low cost and ease of getting it. This study introduces a novel strategy for developing robust calibration models from small and non-linearity NIR spectra datasets. The prediction performance of two groups of chemometric methods, linear (partial least squares regression, PLSR) and non-linear calibration techniques (k-nearest neighbor, k-NN; Ada boosting, AB; Bayesian ridge regression, BRR), were also compared and investigated in depth. A total of forty raw NIR spectral data was used to develop a calibration model to predict the content of B-pinene, D-limonene, and safrole from the nutmeg fruit. The first strategy, non-linearity due to the effect of light scattering on the NIR spectral data, will be handled directly by the non-linear calibration technique algorithm from machine learning to generate the non-linearity model without preprocessing techniques. The second strategy, the robustness of the model, is tested by performing random splitting of data several times without supervision and ending with a rigorous statistical procedure adopted to ensure reliable comparison. The results suggest that the non-linear calibration method is the most promising among the investigated methods. Furthermore, although none of the techniques is always the best to predict on all references, k-NN (for prediction of B-pinene and safrole) and BRR (for prediction of B-pinene and D-limonene), some of them are found to be the most promising in terms of low prediction error (the maximum R<inf>p</inf><sup>2</sup> is 81.6%, and RMSE is less than 1.139%). There are non-linear calibration techniques explored with limited success being achieved.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A Vis-NIRs Calibration Model for the Prediction of Myristicin and Alpha-Pinene on Nutmeg: A Comparison Study of PLSR Algorithm and Machine Learning Algorithm
    (2022-01-01)
    Devianti, Devianti
    ;
    Sufardi, Sufardi
    ;
    Yusmanizar, Yusmanizar
    ;
    Siahaan, Herbert Hasudungan
    ;
    Sitorus, Agustami
    Determination of the myristicin and alpha-pinene content of nutmeg is still constrained by the extended testing time in the laboratory, which is expensive and is carried out destructively. In addition, non-destructive testing using spectroscopy often faces problems in building models that only rely on algorithms that perform linearly, such as PCR and PLSR. Therefore, the present study studied Vis-NIR (381-1065 nm) as a fast, inexpensive, and non-destructive mechanism to determine the myristicin and alphapinene of nutmeg fruits from Aceh, Indonesia. Two algorithms commonly used in spectral data processing, partial least squares regression (PLSR) and machine learning represented by a support vector machine (SVM), were employed and compared to predict myristicin and alpha-pinene in nutmeg fruits. The chemical reference parameters (myristicin and alpha-pinene) were measured using gas chromatography mass spectrometry (GC-MS). Standard normal variate (SNV) and multiplicative scatter correction (MSC) preprocessing were involved as spectra enhancement before the prediction models outcome. The results show that the kernel of the radial basis function (RBF) kernel v-SVM algorithm is better than PLSR for myristicin prediction with gamma (γ), c, and nu (v) of 0.1, 1.0, and 0.99, respectively. Also, the ε-SVM algorithm by RBF kernel is better than PLSR for the prediction of alpha-pinene in nutmeg fruits with gamma (γ), c, and epsilon (ε) compositions of 0.01, 10, 0.1, respectively. The coefficient correlation of calibration (rc) and coefficient determination of prediction (R<inf>p</inf> <sup>2</sup>), the root means square error of calibration (RMSEC) and prediction (RMSEP), and the ratio (RPD) for the prediction of myristicin were 0.992, 0.986, 0.941%, 1.325% and 8.348, respectively. The coefficient correlation of calibration (rc) and coefficient determination of prediction (R<inf>p</inf> <sup>2</sup>), the root mean square error of calibration (RMSEC) and prediction (RMSEP), and the ratio of prediction to deviation ratio (RPD) for the prediction of alpha-pinene were 0.976, 0.979, 0.305%, 0.317% and 6.826, respectively. In general, the results satisfactorily indicate that Vis-NIRS, with the appropriate algorithm, has promising results in determining myristicin and alpha-pinene on nutmeg from Aceh, Indonesia, as nondestructive measurement.