Phetpan, Kittisak
Loading...
Preferred name
Phetpan, Kittisak
Main Affiliation
Email
kittisak.ph@kmitl.ac.th
13 results
Now showing 1 - 10 of 13
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Near-infrared hyperspectral imaging combined with machine learning for physicochemical-based quality evaluation of durian pulp(2023-06-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Development of the partial least-squares model to determine the soluble solids content of sugarcane billets on an elevator conveyor(2021-01-01); ; This study aimed to determine the optimum multivariate model for monitoring the soluble solids content (SSC) of sugarcane billets being transferred on a conveyor. The study covered two main issues: the exploration of an appropriate spectral range (450–900 nm versus 700–900 nm) and the assessment of the influence of different levels of cane billets on an elevator via modelling to predict the SSC values. Partial least squares regression (PLSR) was used for model development. Modelling using the range of 450–900 nm employed 4 latent variables (LVs) and showed the coefficient of determination (R<sup>2</sup>) and root mean squares error of prediction (RMSEP) of 0.83 and 0.29 °Brix, respectively. This caused the model established using the range of 700–900 nm, employed 3 LVs and provided the R<sup>2</sup> and RMSEP values of 0.81 and 0.31 °Brix, respectively, seems more appropriate. In case of assessing the different cane levels on the conveyor, the outcomes presented model performance of the full and half cane levels in predicting half and full cane datasets with R<sup>2</sup> and RMSEP of 0.52 and 0.55 °Brix and 0.53 and 0.48 °Brix, respectively. This showed that the different levels affected the SSC predictive accuracy of the model. The combined model was developed to cover variations of this difference and was used to predict two external sets. The predictions of ninety and thirty samples that were collected from the same and different growing seasons as the samples for the modelling presented the R<sup>2</sup>, RMSEP and RPD of 0.70, 0.42 °Brix and 1.83 and 0.56, 0.42 °Brix and 2.00, respectively. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Transflection Near-infrared Spectroscopy Combined with Machine Learning for Mechanical Stability Time Evaluation in Concentrated Rubber Latex(2023-01-01); ; - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Non-linear viscoelastic behavior of cooked white, brown, and germinated brown Thai jasmine rice by large deformation relaxation test(2017-07-03); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Evaluation of the moisture content of tapioca starch using near-infrared spectroscopy(2015-03-25); The purpose of this study was to develop a calibration model to evaluate the moisture content of tapioca starch using the near-infrared (NIR) spectral data in conjunction with partial least square (PLS) regression. The prediction ability was assessed using a separate prediction data set. Three groups of tapioca starch samples were used in this study: tapioca starch cake, dried tapioca starch and combined tapioca starch. The optimum model obtained from the baseline-offset spectra of dried tapioca starch samples at the outlet of the factory drying process provided a coefficient of determination (R<sup>2</sup>), standard error of prediction (SEP), bias and residual prediction deviation (RPD) of 0.974, 0.16%, -0.092% and 7.4, respectively. The NIR spectroscopy protocol developed in this study could be a rapid method for evaluation of the moisture content of the tapioca starch in factory laboratories. It indicated the possibility of real-time online monitoring and control of the tapioca starch cake feeder in the drying process. In addition, it was determined that there was a stronger infl uence of the NIR absorption of both water and starch on the prediction of moisture content of the model. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Classification of the Crosslink Density Level of Para Rubber Thick Film of Medical Glove by Using Near-Infrared Spectral Data(2024-01-01); ; Posom, JetsadaClassification of the crosslink density level of para rubber medical gloves by using near-infrared spectral data combined with machine learning is the first time reported in this paper. The spectra of medical glove samples with different crosslink densities acquired by an ultra-compact portable MicroNIR spectrometer were correlated with their crosslink density levels, which were referencely evaluated by the toluene swell index (TSI). The machine learning protocols used to classify the 3 groups of TSI were specified as less than 80% TSI, 80–88% TSI, and more than 88% TSI. The 80–88% TSI group was the group in which the compounded latex was suitable for medical glove production, which made the glove specification comply with the requirements of customers as indicated by the tensile test. The results show that when comparing the algorithms used for modeling, the linear discriminant analysis (LDA) developed by 2nd derivative spectra with 15 k-best selected wavelengths fairly accurately predicted the class but was most reliable among other algorithms, i.e., artificial neural networks (ANN), support vector machines (SVM), and k-nearest neighbors (kNN), due to higher prediction accuracy, precision, recall, and F1-score of the same value of 0.76 and no overfitting or underfitting prediction. This developed model can be implemented in the glove factory for screening purposes in the production line. However, deep learning modeling should be explored with a larger sample number required for better model performance. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Filter-based short-wave infrared imaging combined with machine learning for non-destructive quality assessment of durian pulp(2026-09-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, In-line near infrared spectroscopy for the prediction of moisture content in the tapioca starch drying process(2019-03-01); ; Moisture content is an important parameter measured in tapioca starch production as this parameter has been shown to correlate strongly with the quality of the finished product. However, there is currently no in-line sensor which can be used to directly measure the moisture content of the product in real time. The objective of the present work was to study the use of an in-line measurement which can be introduced at the end of the drying process for tapioca starch moisture content evaluation. Either in-line NIR data or at-line NIR data was used to develop the necessary calibration models for evaluating the moisture content. Furthermore, calibration models were also developed by pooling the in-line and at-line data. Its performance was then verified using additional in-line data. The NIR model developed using 100% of the at-line data and 50% of the in-line data was validated using the unused 50% of the inline data. This model was shown to provide better performance in moisture content prediction with an SEP of 0.61% and a bias of 0.001%. In addition, the results showed that the at-line spectrum can also be used for the calibration model development to predict the moisture content of the samples scanned by an in-line spectrometer. However, the in-line spectrometer installation on a pneumatic conveying circular tube where tapioca starch and air mixed was found to be complicated due to significant vibration. This caused additional variation in the data with time. Therefore, it is concluded that the most suitable place for installing a spectrometer would be at a position involving a low pressure, or where the stream flow of a product is steadier in order to avoid the dynamic mixing of the product within the drying tube affecting the uncertainty of NIR scattering during the measurement. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Machine learning-based prediction of nutritional status in oil palm leaves using proximal multispectral images(2022-07-01); ; ; This study evaluated the application of proximal multispectral images accompanied by 4 machine learning approaches for estimating the nutritional status of oil palm leaves. The image responded for five bands: blue, green, red, red edge, and near-infrared regions with a center wavelength of 475, 560, 668, 717, and 840 nm. Average and standard deviation (SD) values from the leaf pixels of each band were extracted, obtaining 5 average and 5 SD values from 5 bands. Thirty-four vegetation variables were generated based on those average and SD values. In total, forty-four variables consisted of 10 average-and SD-based features, and 34 vegetation variables were used as the input candidates for analyses against 10 target variables: nitrogen (N), phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg), iron (Fe), manganese (Mn), zinc (Zn), boron (B), and chlorophyll (SPAD). No significant input came out for modeling with P and Zn based on the stepwise selection. Therefore, 8 nutritional models were proposed in this study. A training set with 50 samples was used to be modeled for each target, and a test set with 15 samples was employed to evaluate the models' performances. Based on random forest (RF), support vector regression (SVR), partial least square regression (PLSR), and artificial neuron network (ANN) applied to be modeled, the models for chlorophyll, N, and Ca predictions were acceptable for screening, and those for K and Mg predictions were acceptable for rough screening. The chlorophyll model developed based on the RF had the predictive statistics in terms of coefficient of determination for prediction (r<sup>2</sup>), root mean square error of prediction (RMSEP), and standard error of prediction (SEP) of 0.752, 5.46 SPAD, and 5.65 SPAD, respectively. The other 2 screening models developed based on SVR and RF for N and Ca, respectively, gave the performances with the r<sup>2</sup>, RMSEP, and SEP ranging from 0.655 to 0.718, 0.12 to 0.17%, and 0.12 to 0.18%, respectively. In the case of the 2 rough screening models established using the RF algorithm, the predictive statistics ranged from 0.496 to 0.530 for the r<sup>2</sup> and 0.07–0.16% for both RMSEP and SEP. In this study, the Fe, Mn, and B models had poor results presenting the range of r<sup>2</sup>, RMSEP, and SEP of 0.308–0.491, 2.39–72.9 ppm, and 2.45–62.8 ppm, respectively. Based on the results, this study confirmed that the proximal multispectral information of oil palm leaves had enough significance to account for the status of chlorophyll and macro-nutrients: N, K, Ca, and Mg in the leaves. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Evaluation of physiological properties and texture traits of durian pulp using near-infrared spectra of the pulp and intact fruit(2021-04-01); ; This study aimed to investigate the feasibility of non-destructively predicting physiological properties (color, dry matter, and soluble solids) and texture properties (initial firmness, average firmness, rupture force, rupture distance, toughness, average penetrating force, and penetrating energy) of ‘Monthong’ durian using Fourier transform near-infrared spectroscopy of the pulp of the largest locule, the intact fruit at the largest locule, and the stylar end of the intact fruit. Based on partial least squares regression modeling, the internal quality evaluation of durian obtained by scanning the pulp could provide rough screening capability, with coefficient of determination of validation (r<sup>2</sup>), root mean square error of prediction (RMSEP), and the ratio of standard error of validation to standard deviation (RPD) values for the dry matter content, average penetrating force, and rupture force of 0.89, 3.60%, and 3.27; 0.73, 5.53 N, and 1.95; and 0.74, 6.15 N, and 1.96, respectively. Only the dry matter content of the pulp could be reasonably predicted based on scanning the intact durian fruit at the largest locule, with r<sup>2</sup>, RMSEP, and RPD values of 0.79, 5.23%, and 2.18, respectively. This finding could be applied at the first stage of trade between durian agriculturalists and exporters to prevent the exportation of immature durian and would be helpful for the industries producing frozen durian pulp and intact durian fruit for export.