KMITL

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

Browse

Settings

Author: search.filters.author.Pitak, LakkanaSubject: search.filters.subject.Durian

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    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.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Deep neural networks (DNNs) chemical compositions estimation of fresh durian in-line via near infrared spectroscopy
    (2025-06-01)
    Posom, Jetsada
    ;
    Saenphon, Chirawan
    ;
    Ditcharoen, Sirirak
    ;
    Pitak, Lakkana
    ;
    Sirisomboon, Panmanas
    Near infrared (NIR) spectroscopy and deep neural network (DNN) models were adopted for evaluating the nutritional compositions in durian pulp. The quality inspection of durians through online channels remains challenging because consumers cannot directly touch or smell the fruit. This leads to issues with substandard durians, such as unripe ones or those infested with pests. One hundred and sixty durian samples of Mon Thong varieties were used in this experiment. Then, the collected NIR spectra were augmented to improve the generalization ability of regression models. Deep neural network (DNNs) regressions were developed. The results showed that deep neural network (DNN) regression model possessed the best prediction performance, which were provided performance index. Almost all the best performance models were developed from the second derivative, except for the fat content model, which was developed from raw spectra. The best total soluble solids (TSS) model provided the coefficient of determination of calibration (R<sup>2</sup>c) and root mean square error of calibration (RMSEc) were 0.84 and 2.25 % and coefficient of determination of calibration (R<sup>2</sup>p), root mean square error of prediction (RMSEp) and ratio of performance to deviation (RPD) were 0.72 2.92 % and 1.92, respectively, and those of dry matter content (DMC) were provided R<sup>2</sup>c and RMSEc were 0.997, 0.58 %, and for prediction set provided R<sup>2</sup>p, RMSEp and RPD were 0.94, 3.13 %, and 4.21, respectively. For fat content (FC), they have also provided R<sup>2</sup>c and RMSEc were 0.84, 0.36 (g/100 g), while it provided R<sup>2</sup>p, RMSEp and RPD were 0.86, 0.50 (g/100 g), and 2.72, respectively. Moreover, for total sugar content (TSC) value, it also gave high accuracy, which provided R<sup>2</sup>c and RMSEc were 0.93, 0.49 (g/100 g) and R<sup>2</sup>p, RMSEp, and RPD were 0.91, 0.81 (g/100 g), 3.44, and for starch content (SC) also provided R<sup>2</sup>c and RMSEc were 0.93, 0.49(g/100 g) and R<sup>2</sup>p, RMSEp, and RPD were 0.76, 2.79 (g/100 g), 2.09, respectively. Therefore, the proposed method offers an ultrasensitive and effective strategy for estimation of nutritional compositions.