KMITL

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

Browse

Search Results

Now showing 1 - 9 of 9

Some of the metrics are blocked by your
consent settings
Identification and quantification of quality of intact durian fruits using NIR spectroscopy
(2026-01-01)
Pitak, Lakkana
;
Ditcharoen, Sirirak
;
Maraphum, Kanvisit
;
Khamwan, Buathip
;
Warorost, Nithithada
Quality classification of durian fruits is based on the dry matter (DM) content of the pulp. According to Thai agricultural standards, durian fruit (Monthong variety) must contain at least 32% DM. This study aimed to develop a classification model for assessing durian quality based on DM content, categorizing fruits as either “rejected” (DM < 32%) or “accepted” (DM ≥ 32%). Near-infrared (NIR) spectra were collected as the durian fruits moved along a conveyor belt. The models were developed using two spectral ranges: short-wavelength near-infrared (SWNIR; 4501000 nm) and long-wavelength near-infrared (LWNIR; 8601750 nm). Owing to the imbalance in the dataset between the two classes, the data were adjusted using the synthetic minority oversampling technique to create a balanced dataset. Prediction models were built using different spectral preprocessing methods and algorithms. For the LWNIR range, the models constructed using LDA, SVM, KNN, and SDA achieved accuracies of 95%, 90%, 93%, and 93%, respectively, for the test set. The SWNIR models, developed using the same algorithms, achieved accuracies of 90%, 88%, 90%, and 90%, respectively, for the test set. PLS-regression was used to predict the DM content from both LWNIR and SWNIR data. With the 2nd derivative preprocessing method, the models achieved R² values of 0.89 and 0.79, SEP values of 5% and 6.89%, and RPD values of 2.29 and 1.66, respectively. The wavelength range significantly influenced the model performance, whereas spectral pretreatment had a minor effect on the model's predictive ability. Overall, NIR spectroscopy demonstrated the potential for nondestructive quality grading of whole durian fruits. This work is the first to establish real-time, in-line models for durian grading based on DM content, advancing beyond the previous destructive method. The findings demonstrate the feasibility of automated, nondestructive, and objective quality assessment, supporting industrial automation, precision agriculture, and export quality assurance.
Some of the metrics are blocked by your
consent settings
Nondestructive evaluation of SW-NIRS and NIR-HSI for predicting the maturity index of intact pineapples
(2023-01-01)
Tantinantrakun, Achiraya
;
Sukwanit, Supawan
;
Thompson, Anthony Keith
;
Teerachaichayut, Sontisuk
Determination of optimum maturity and ripeness of fruit is essential in the production of processed fruit, including pineapples, but this is difficult to achieve consistently by visual grading in commercial factories. Therefore, this study tested two nondestructive techniques for predicting the maturity index of intact pineapple. These were transmittance short wavelength near infrared spectroscopy (SW-NIRS) in the wavelength range of 665–955 nm and reflectance near infrared hyperspectral imaging (NIR-HSI) in the wavelength range of 935–1720 nm. The number of samples used for calibration was 120 for both SW-NIRS and NIR-HSI. The maturity index and spectral information of individual pineapple fruit were acquired from both techniques and analysed using the same procedure. Then, partial least squares regression (PLSR) was used to establish the models for predicting the maturity index of each intact fruit. The leave-one-out cross validation was used for evaluating the performance of the models. The results showed that both techniques gave reliable performance in predicting the maturity index of individual fruit, with a coefficient of determination considering cross validation (R<inf>cv</inf><sup>2</sup>) for the prediction of the maturity index of 0.70 and a root mean square error in cross validation (RMSECV) of 2.16 when using SW-NIRS and R<inf>cv</inf><sup>2</sup> of 0.72 and RMSECV of 1.68 when using NIR-HSI. It was therefore concluded that both SW-NIRS and NIR-HSI had the potential for use in nondestructive analysis of the maturity of intact pineapple fruit in fruit processing factories.
Some of the metrics are blocked by your
consent settings
Utilizing near infrared hyperspectral imaging for quantitatively predicting adulteration in tapioca starch
(2021-05-01)
Khamsopha, Duangkamolrat
;
Woranitta, Sahachairungrueng
;
Teerachaichayut, Sontisuk
Fraud creates huge problems for the food industry. One type of fraud is adulteration in order to reduce costs and increase profitability. Fraud occurs in the starch industry, which is difficult or impossible to detect by visual inspection. Therefore this study was to test a possible nondestructive method that could be used to detect the adulterants in tapioca starch by utilizing reflectance near infrared hyperspectral imaging (NIR-HSI) at wavelengths in the range of 935–1720 nm. Pure tapioca starch was adulterated with limestone powder at 0.5% intervals over the range of 0–100% (wt/wt). The samples (n = 201) were divided into a calibration set (n = 140) and a prediction set (n = 61). Chemometrics was investigated and used to establish a calibration model for predicting the concentration of adulterant using partial least squares regression (PLSR). The accuracy of prediction using the model gave excellent results with the correlation coefficient (R) of 0.996 and the root mean square error of prediction (RMSEP) of 2.47%. The model was then used to create the predictive images of pure tapioca starch, adulterated tapioca starch and pure adulterant. It showed different colors based on the concentration of the adulterant. Therefore, NIR-HSI was shown to have potential as a method for rapidly detecting the level of concentration of adulterant in tapioca starch using both the predictive model and visualization.
Some of the metrics are blocked by your
consent settings
Detection of adulteration of tapioca starch with dolomite by near infrared hyperspectral imaging
(2020-01-01)
Khamsopha, Duangkamolrat
;
Teerachaichayut, Sontisuk
Tapioca starch adulterated with dolomite is sold in markets, but this adulteration cannot be identified by normal visual inspection. Near infrared (NIR) hyperspectral imaging has been successfully used as a non-destructive method of identifying various characteristics of food, therefore it was tested to identify dolomite adulteration. Adulterated tapioca starch samples were prepared by adding dolomite in the range of 0.5-100% (wt/wt). Samples (N=400) of pure tapioca starch (0) and adulterated tapioca starch (1) were divided into calibration set (N=300) and a prediction set (N=100). All samples were scanned using NIR hyperspectral imaging (935-1720 nm) and spectra were pre-processed using Savitzky-Golay first derivative differentiation pretreatment in order to obtain the optimal conditions for establishing a classification model. Partial least squares-discriminant analysis was carried out to evaluate the accuracy of classification tapioca starch adulterated with dolomite. The results showed the total accuracy of prediction for classification was 100%. Therefore, NIR hyperspectral imaging was demonstrated to have a potential for use in detecting adulteration of tapioca starch with dolomite.
Some of the metrics are blocked by your
consent settings
Quantitative analysis of quality for marian plum (Bouea burmanica Griff.) by transmittance near infrared spectroscopy
(2018-10-05)
Phonmakham, S.
;
Suttivijitpukdee, N.
;
Teerachaichayut, S.
Marian plum (Bouea burmanica Griff.) is one of the most popular tropical fruits in Thailand. The good quality of marian plum is required by consumers. Total soluble solid (TSS) and titratable acidity (TA) are important indices for consideration of quality for marian plum. Transmittance mode of near infrared (NIR) spectroscopy in the short wavelength (665-955 nm) was considered for nondestructive evaluation of quality in marian plum. A set of 153 marian plums (105 samples for a calibration group and 48 samples for a prediction group) was carried out in this research. The partial least squares regression (PLSR) was used to develop the calibration models. Spectral pretreatments were investigated in order to obtain the best performance of the models. A calibration model for TSS using original spectra obtained best results for calibration and prediction (R=0.90, RMSEC=0.57 °Bx and R=0.88, RMSEP=0.65 °Bx, respectively). As well as the calibration model for TA using original spectra obtained best results for calibration and prediction (R=0.98, RMSEC=0.01% and R=0.88, RMSEP=0.03%, respectively). All results indicated that it is possible to use transmittance SW-NIRS for nondestructive prediction of TSS and TA in marian plums.
Some of the metrics are blocked by your
consent settings
Interactance and reflectance near infrared spectroscopy for freshness evaluation of hen eggs
(2018-10-05)
Suktanarak, S.
;
Teerachaichayut, S.
;
Jannok, P.
;
Supprung, P.
Haugh units is an important index for evaluate freshness of hen eggs. High score of Haugh units (≥60) from eggs means those are new fresh eggs. This research is aimed to use near infrared spectroscopy for nondestructive prediction of egg's freshness by quantitative evaluation based on Haugh units. Interactance mode (588-1091 nm) and reflectance mode (1000-2500 nm) of near infrared spectroscopy were investigated in this research. Hen eggs from farm in Thailand were studied by storage at 25°C for 21 days. Samples were taken for measurements at different days of storage (0, 4, 7, 10, 14, 18 and 21 days). A set of 247 samples (165 for calibration and 82 for prediction) was used for interactance mode and a set of 150 samples (102 for calibration and 48 for a prediction) was used for reflectance mode. Calibration models were established and cross-validated using partial least squares regression (PLSR). The accuracies were considered by test in prediction groups. The results showed that the interactance obtained better accuracy for prediction (correlation coefficient, R=0.91 and root mean square error prediction, RMSEP=5.64) when compared with reflectance mode (R=0.83 and RMSEP=7.11). In this study, the interactance near infrared spectroscopy is more suitable to use in application for freshness sorting of hen eggs.
Some of the metrics are blocked by your
consent settings
Quantitative prediction of nitrate level in intact pineapple using Vis-NIRS
(2015-01-01)
Srivichien, Sasathorn
;
Terdwongworakul, Anupun
;
Teerachaichayut, Sontisuk
Before pineapples are canned, the ones with high nitrate level must be sorted out first because nitrate causes black stains on the surface of the can; therefore, a nondestructive technique for sorting out pineapples is clearly needed. The use of visible and near infrared (Vis-NIR) spectroscopy for such purpose was investigated in this study. A batch of 75 pineapple fruits that would have been delivered to a canning factory was tested. Spectra were acquired using a spectrophotometer in interactance mode with wavelengths in the region of 400-2500 nm. Twelve scans of different parts of each pineapple were made. The actual amount of nitrate in the pineapple flesh was determined by HPLC. Original spectra and pretreated spectra were both used to construct calibration models with partial least squares regression (PLSR). The best model was obtained from an average spectrum pretreated with first derivative treatment at the wavelength range of 600-1200 nm. Predictions based on this model matched closely with the actual nitrate contents, with a high correlation coefficient (R) of 0.95 and a low root mean square error of prediction (RMSEP) of 1.77 ppm. These results demonstrate that Vis-NIR spectroscopy can be used for rough screening of intact pineapple.
Some of the metrics are blocked by your
consent settings
Detection of hardening pericarp disorder and determination of firmness at hardening area in mangosteen by visible-near infrared reflectance spectroscopy
(2015-01-01)
Workhwa, S.
;
Teerachaichayut, S.
Mangosteen (Garcinia mangostona L.) is an economically important fruit grown commercially in Thailand for domestic consumption and export. The fruit has a thick and hard pericarp. However, hardening pericarp disorder can easily occur as a result of compression or impact during harvest and transport. Classification and prediction of hardening pericarp disorder in mangosteen was investigated using visible-near infrared spectroscopy (Vis/NIRS). Reflectance spectra were acquired on each of 1100 mangosteen samples. The number of samples for training and test set was 733 and 367 samples, respectively. Partial least squares-discriminant analysis (PLS-DA) was used for quantitative analysis. The results of discriminant analysis of normal and hardening pericarp samples using leave-one-out cross-validation achieved an average total accuracy of 92.92%. A further goal was quantitative analysis of firmness of mangosteens with hardening pericarp using Vis/NIR measurements. The optimum calibration model was pretreated using standard normal variate transformation (SNV) pretreatment and was developed using partial least squares regression (PLSR). The model was proven useful for prediction of the degree of pericarp hardening of mangosteen. The coefficients of correlation (R) and root mean square error of cross validation (RMSECV) were 0.89 and 2.67N respectively. This technique has potential use for nondestructive and rapid classification of quality for mangosteen.
Some of the metrics are blocked by your
consent settings
Nondestructive prediction of internal browning in pineapple using transmittance short wavelength near infrared spectroscopy
(2013-01-01)
Sukwanit, S.
;
Teerachaichayut, S.
Pineapple [Ananas comosus (L.) Merr.] is one of the most important commercial fruit of Thailand. The taste and consistency of the fruit is of great importance, however "internal browning", a common physiological disorder affecting the fruit, which cannot be identified by visual inspection, makes the product unacceptable for export. In this study, Near Infrared (NIR) spectroscopy in the range of 665-955 nm was investigated as a non-destructive means to identify internal browning. Partial least squares-discriminant analysis (PLS-DA) was used in conjunction with the pre-treated NIR spectra as a first step in the development of an automated method of pineapple fruit sorting. A set of 243 samples was used for this research (131 commercially acceptable pineapples and 112 pineapples suffering from internal browning). A sample of 145 fruits was used for a training set and 98 samples for a test set. The smoothing and the first derivative pretreatment of averaged spectra were performed to obtain the best calibration model. The overall classification accuracy of the PLS-DA/NIR model on the prediction set was 90.8% (47 out of 53 for the sound pineapples and 42 out of 45 for the internally browned pineapples). This study demonstrates that NIR transmittance spectroscopy is potentially a useful nondestructive method that can be used to predict internal browning disorder in intact pineapples. © ISHS 2013.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results