KMITL

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

Browse

Search Results

Now showing 1 - 10 of 16

Some of the metrics are blocked by your
consent settings
Postharvest detection of anthracnose (Colletotrichum asianum) on mango fruit (Mangifera indica L. cv Namdokmai Sithong) using near-infrared response
(2026-12-01)
Junto, Apiwat
;
Phanomsophon, Thitima
;
Sharma, Sneha
;
Kaewsorn, Kannapot
;
Jongyingcharoen, Jiraporn Sripinyowanich
Anthracnose disease, caused by fungi of the genus Colletotrichum, poses a major threat to mango production and export industries, with Colletotrichum asianum being among the most significant pathogenic species. This work proposes the hypothesis that the simple difference in absorption between anthracnose-infected and noninfected mangoes illustrated by the average near-infrared (NIR) spectra obtained from hyperspectral images could be used for simple differentiation of the two groups. The method of depositing fungal spores by spraying the spores over the fruit surface, not a small area or specific point, allows for the number of spores per unit area to be harmonized and to detect infected or noninfected spores on every pixel of the mango surface using a hyperspectral imaging camera. Important wavelengths for differentiation included water bands of 970, 1190, and 1200 nm which resulted in the greatest difference in absorbance, and bands of chitin, the major component of the fungal cell wall; 1195 nm was the most important band. In addition, the vibration bands of 868 (protein in the fungal cell wall), 1134 (sugar and starch of the mango substrate), 1320 (NIR absorbers in the fungus-sprayed and mango substrate, not specifically defined) and 1069 nm (crystallinity and N-acetyl methyl groups in the fungal chitin and constituents of the mango), differed from each other. These wavelengths can be used for modelling, which can lead to high performance in quantifying the concentration of anthracnose and classifying the strength levels of anthracnose infection. The microbiological mechanism of anthracnose growth on infected mangoes corresponding to changes in the NIR spectrum during the 4 days after spore infection is comprehensively discussed. These results can aid in enhancing early detection and classification techniques for anthracnose-infected mangoes from noninfected mangoes using hyperspectral image sensors.
Some of the metrics are blocked by your
consent settings
Author Correction: Predicting biomass global warming potential with FT-NIR spectroscopy (Scientific Reports, (2025), 15, 1, (33725), 10.1038/s41598-025-10584-z)
(2026-12-01)
Gyawali, Prakash
;
Shrestha, Bijendra
;
Phanomsophon, Thitima
;
Posom, Jetsada
;
Pornchaloempong, Pimpen
Correction to: Scientific Reportshttps://doi.org/10.1038/s41598-025-10584-z, published online 30 September 2025 The original version of this Article contained errors. In the original version of this article, the climate-carbon effect value was not included as introduced in AR6. As a result, in the Materials and methods section, under the subheading ‘Estimation of global warming potential and emission of greenhouse gas (GHG)’, where: “Step 1: (CO<inf>2</inf>, CH<inf>4</inf>, N<inf>2</inf>O) emissions (kg) = Mass of Fuel (kg) × Carbon emission factor (kg TJ-1) × HHV (kg TJ-1) Step 2: Total GWP = (GWP of CO<inf>2</inf>×CO<inf>2</inf> emissions) +(GWP of CH<inf>4</inf>×CH<inf>4</inf> emissions) +(GWP of N<inf>2</inf>O×N<inf>2</inf>O emissions)” now reads: “Step 1: GHG (CO<inf>2</inf>, CH<inf>4</inf>, or N<inf>2</inf>O) emissions (kg) = Mass of Fuel (kg) × Specific GHG emission factor (kg TJ-1) × HHV (TJ kg-1) Step 2: Total GWP (kg CO<inf>2</inf>e) = (GWP of CO<inf>2</inf>×CO<inf>2</inf> emissions) + (GWP of CH<inf>4</inf>×CH<inf>4</inf> emissions) + (GWP of N<inf>2</inf>O×N<inf>2</inf>O emissions)” In addition, under the subheading ‘Model development and validation’, where: “The model was optimized by selecting wavenumbers through various variable selection methods, including the Correlation Method (CM), Variance Method (VM), Co-Variance Method (COVM), and Variable Importance Projection (VIP). The spectral data were pretreated using raw spectra, standard normal variate (SNV), as well as first derivative and second derivative transformations. The following spectra pretreatment methods: Standard Normal Variate (SNV) is for corrects scatter effects and baseline variations35,” now reads: “The model was optimized by selecting wavenumbers through various variable selection methods, including the Correlation Method (CM), Variance Method (VM), Co-Variance Method (COVM), and Variable Importance Projection (VIP). The following spectra pretreatment methods: Standard Normal Variate (SNV) is for correcting scatter effects and baseline variations35,” In addition, Equations 3, 4 and 6 contained typesetting errors. As a result, Equation 3: (Formula presented.) now reads, (Formula presented.) Equation 4: (Formula presented.) now reads: (Formula presented.) And Equation 6 (Formula presented.) now reads: (Formula presented.) Furthermore, under the Results section, subheading ‘Predicting performance of biomass GWP using PLSR’, where: “The model developed with CM (reduction of 1150 wavenumber of full range to 325 wavenumber) of 1st derivative spectra, gave best performance with R2<inf>P</inf> was 0.87 (Table 4).” now reads: “The model developed with COVM (reduction of 1150 wavenumber of full range to 325 wavenumber) of 1st derivative spectra, gave the best performance with R2<inf>P</inf> was 0.85 (Table 4).” Under the subheading ‘Prediction result of HHV using PLSR’, where: “This approach reduced the number of variables from 1150 to 365 wavenumbers, significantly enhancing the model’s performance (R2<inf>C</inf> of 0.98 and R2<inf>P</inf> of 0.87)” now reads: “This approach reduced the number of variables from 1150 to 365 wavenumbers, significantly enhancing the model’s performance (R2<inf>C</inf> of 0.98 and R2<inf>P</inf> of 0.86)” Under the subheading ‘Regression coefficient and x-loading of GWP model’, where: “Prominent peaks were identified and the bond vibration interpretation is shown in Table 7 and the vibration indicated by Workman and Weyer38 at the wavenumbers in bold were not found or not related to biomass.” now reads: “Prominent peaks were identified, and the bond vibration interpretation is shown in Table 7, which was indicated by Workman and Weyer38.” Equation 8: GWP for CO<inf>2</inf>, or CH<inf>4</inf>, or N<inf>2</inf>O Emissions = (1×CO<inf>2</inf> Emission) or (29.8×CH<inf>4</inf> Emission) or (273×N<inf>2</inf>O Emission) = (1×112 HHV) for CO<inf>2</inf> Emission or (29.8×30 HHV) for CH<inf>4</inf> Emission or (273×4 HHV) for N<inf>2</inf>O Emission = 112.0×HHV for CO<inf>2</inf> Emission or 894.0×HHV for CH<inf>4</inf> Emission or 1092.0×HHV for N<inf>2</inf>O Emission and GWP total = 2098.0 (HHV, TJ kg-1) = 0.000002098 kJ kg-1 = 0.000002098 Jg-1 now reads: GWP for CO<inf>2</inf>, or CH<inf>4</inf>, or N<inf>2</inf>O Emissions = (1×CO<inf>2</inf> Emission) or (27.2×CH<inf>4</inf> Emission) or (273×N<inf>2</inf>O Emission) = (1×112 HHV) for CO<inf>2</inf> Emission or (27.2×30 HHV) for CH<inf>4</inf> Emission or (273×4 HHV) for N<inf>2</inf>O Emission = 112.0×HHV for CO<inf>2</inf> Emission or 816.0×HHV for CH<inf>4</inf> Emission or 1092.0×HHV for N<inf>2</inf>O Emission and GWP total (kg CO<inf>2</inf>e) = 2020.0 (HHV, TJ kg-1) = 0.000002020 kJ kg-1 = 0.000002020 J g-1 Moreover, Tables 1 and 3 have been corrected. Incorrect Table 1: Remarks IPCC guideline Calculation of CO<inf>2</inf> emission Higher Heating Value = 17932000 J kg-1 CO<inf>2</inf> emission factor = 112 kg TJ-1, we can follow these steps: Convert HHV to TJ kg-1: Since 1 TJ = 1012 J, we need to convert the HHV from J kg-1 to TJ kg-1: HHV in TJ kg-1 = 17932000 J kg-1 / 1012 = 1.7932×10-3 TJ kg-1 CO<inf>2</inf> emission (kg) = Mass of fuel (kg) × CO<inf>2</inf> emission factor (kg TJ-1) × HHV (TJ kg-1) CO<inf>2</inf> emission (kg) = 1 kg × 112 kg TJ-1 × 0.017932 TJ kg-1 Therefore, the CO<inf>2</inf> emission from stationary fuel combustion with an HHV of 17932000 J kg-1 and using the default CO<inf>2</inf> emission factor of 112 kg TJ-1 would be approximately 2.0083×10-3 kg of CO<inf>2</inf> per kg of fuel. CO<inf>2</inf> emission factor: 112 kg dry matter TJ-1 (typical for wood combustion) Calculation of CH<inf>4</inf> emission Hight Heating Value = 17932000 J kg-1 CH<inf>4</inf> emission factor = 30 kg TJ-1 Convert HHV unit to TJ kg-1 1 TJ= 1012 J HHV from J kg-1 to TJ kg-1: HHV in TJ kg-1 = 17932000 J kg-1 / 1012 = 1,7932×10-5 TJ kg-1 CH<inf>4</inf> emission (kg) = Mass of Fuel (kg) × CH<inf>4</inf> emission factor (kg TJ-1) × HHV (TJ kg-1) CH<inf>4</inf> emission (kg) = 1 kg × 30 kg TJ-1 × 1,7932×10-5 TJ kg-1 CH<inf>4</inf> emission (kg) = 5.3796×10-4 kg of CH<inf>4</inf> per kg of fuel CH<inf>4</inf> emission factor: 30 kg dry matter TJ-1 Calculation of N<inf>2</inf>O emission Hight Heating Value = 17932000 J kg-1 N<inf>2</inf>O emission factor = 4 kg TJ-1 Convert HHV unit to TJ kg-1 1 TJ = 1012 J HHV from J kg-1 to TJ kg-1: HHV in TJ kg-1 = 17932000 J kg-1 / 1012 = 1.7932 ×10-5 TJ kg-1 N<inf>2</inf>O emission (kg) = Mass of Fuel (kg) × N<inf>2</inf>O emission factor (kg TJ-1) × HHV (TJ kg-1) N<inf>2</inf>O emission (kg) = 1 kg × 4 kg TJ-1 × 1.7932×10-5 TJ kg-1 N<inf>2</inf>O emission (kg) = 7.1728×10-5 kg of N<inf>2</inf>O per kg of fuel N<inf>2</inf>O emission factor 4 kg dry matter /TJ The concept of global warming potential (GWP) was introduced in IPCC –AR1 (Shine et al. 1990) to compare the greenhouse effects of different greenhouse gases relative to a reference gas, normally taken as carbon dioxide, under this definition, CO<inf>2</inf> would have a GWP value of 1. Total GWP = (GWP of CO<inf>2</inf>×CO<inf>2</inf> emissions)+(GWP of CH<inf>4</inf>×CH<inf>4</inf> emissions)+(GWP of N<inf>2</inf>O×N<inf>2</inf>O emissions) Total GWP =1×2.0083×10-3+29.8× 5.379 ×10-4+273×7.1728×10-5 Total GWP=0.0376 kg CO<inf>2</inf>e This calculation is by 100 years based GWP of emission gases followed AR6 7 Correct Table 1: Remarks IPCC guideline Calculation of CO<inf>2</inf> emission Higher Heating Value = 17932000 J kg-1 CO<inf>2</inf> emission factor = 112 kg TJ-1, we can follow these steps: Convert HHV to TJ kg-1: Since 1 TJ = 1012 J, we need to convert the HHV from J kg-1 to TJ kg-1: HHV in TJ kg-1 = 17932000 J kg-1 / 1012 = 1.7932×10-5 TJ kg-1 CO<inf>2</inf> emission (kg) = Mass of fuel (kg) × CO<inf>2</inf> emission factor (kg TJ-1) × HHV (TJ kg-1) CO<inf>2</inf> emission (kg) = 1 kg × 112 kg TJ-1 × 1.7932 × 10-5 TJ kg-1 Therefore, the CO<inf>2</inf> emission from stationary fuel combustion with an HHV of 17932000 J kg-1 and using the default CO<inf>2</inf> emission factor of 112 kg TJ-1 would be approximately 2.0083 × 10-3 kg of CO<inf>2</inf> per kg of fuel. CO<inf>2</inf> emission factor: 112 kg dry matter TJ-1 (typical for wood combustion) Calculation of CH<inf>4</inf> emission Higher Heating Value = 17932000 J kg-1 CH<inf>4</inf> emission factor = 30 kg TJ-1 Convert HHV unit to TJ kg-1 1 TJ= 1012 J HHV from J kg-1 to TJ kg-1: HHV in TJ kg-1 = 17932000 J kg-1 / 1012 = 1,7932×10-5 TJ kg-1 CH<inf>4</inf> emission (kg) = Mass of Fuel (kg) × CH<inf>4</inf> emission factor (kg TJ-1) × HHV (TJ kg-1) CH<inf>4</inf> emission (kg) = 1 kg × 30 kg TJ-1 × 1,7932×10-5 TJ kg-1 CH<inf>4</inf> emission (kg) = 5.3796×10-4 kg of CH<inf>4</inf> per kg of fuel CH<inf>4</inf> emission factor: 30 kg dry matter TJ-1 Calculation of N<inf>2</inf>O emission Higher Heating Value = 17932000 J kg-1 N<inf>2</inf>O emission factor = 4 kg TJ-1 Convert HHV unit to TJ kg-1 1 TJ = 1012 J HHV from J kg-1 to TJ kg-1: HHV in TJ kg-1 = 17932000 J kg-1 / 1012 = 1.7932 × 10-5 TJ kg-1 N<inf>2</inf>O emission (kg) = Mass of Fuel (kg) × N<inf>2</inf>O emission factor (kg TJ-1) × HHV (TJ kg-1) N<inf>2</inf>O emission (kg) = 1 kg × 4 kg TJ-1 × 1.7932×10-5 TJ kg-1 N<inf>2</inf>O emission (kg) = 7.1728×10-5 kg of N<inf>2</inf>O per kg of fuel N<inf>2</inf>O emission factor 4 kg dry matter /TJ-1 The concept of global warming potential (GWP) was introduced in IPCC –AR1 (Shine et al. 1990) to compare the greenhouse effects of different greenhouse gases relative to a reference gas, normally taken as carbon dioxide, under this definition, CO<inf>2</inf> would have a GWP value of 1. Total GWP = (GWP of CO<inf>2</inf>×CO<inf>2</inf> emissions) + (GWP of CH<inf>4</inf>×CH<inf>4</inf> emissions) + (GWP of N<inf>2</inf>O×N<inf>2</inf>O emissions) Total GWP = 1×2.0083×10-3+ 27.2× 5.3796 × 10-4+ 273×7.1728×10-5 Total GWP= 0.03622 kg CO<inf>2</inf>e This calculation is by 100 years based GWP of emission gases followed AR6 7 Incorrect Table 3: Calibration set Prediction set Parameter Method NT NC Max Min Mean SD NP Max Min Mean SD GWP IPCC Guidelines 197 147 0.03905 0.03080 0.03564 0.00180 50 0.038943 0.033002 0.03577 0.00165 HHV (J g-1) Bomb Calorimeter 197 147 18616 16405 16976 910 50 17950 15268 17051 787 Correct Table 3: Parameter Method NT Calibration Set Prediction Set NC Max Min Mean SD NP Max Min Mean SD GWP (kg CO<inf>2</inf>e) IPCC Guidelines 197 147 0.03905 0.03080 0.03564 0.00180 50 0.038943 0.033002 0.03577 0.00165 HHV (J g-1) Bomb Calorimeter 197 147 18616 16405 15268 910 50 17950 16976 17051 787 Finally, the legends of Tables 4 and 7 have been updated: “Table 4: Prediction of GWP of biomass of fast-growing tree and agriculture residue by PLSR. N: Number of samples in calibration set, R2<inf>c</inf>: coefficient of determination of calibration set, n: number of samples in prediction set, R2<inf>p</inf>: coefficient of determination of prediction set, RPD: ratio of prediction to deviation, CM: correlation method, VM: variance method, COVM: co-variance method, VIP: variable. Significant values are in [bold].” now reads: “Table 4. Prediction of GWP of biomass of fast-growing tree and agriculture residue by PLSR. N: Number of samples in calibration set, R2<inf>c</inf>: coefficient of determination of calibration set, n: number of samples in prediction set, R2<inf>p</inf>: coefficient of determination of prediction set, RPD: ratio of prediction to deviation, CM: correlation method, VM: variance method, COVM: co-variance method, VIP: variable important projection, FstDev: 1st derivative, SecDev: 2nd derivative. Significant values are in [bold].” “Table 7. The function groups corresponding to the wavenumber shown in regression coefficient plot and x-loading plot of models for GWP and HHV. *1ν, fundamental stretching vibration; 2ν, 1st overtone of fundamental stretching vibration; 3ν, 2nd overtone of fundamental stretching vibration; 5ν, 4th overtone of fundamental stretching vibration; 1δ, fundamental bending (deformation) vibration; 3δ, 2nd overtone of fundamental bending (deformation) vibration; 1, symmetric stretching vibration; 2, bending vibration; 3, asymmetric stretching vibration; and + is combination. now reads: “Table 7. The function groups corresponding to the wavenumber shown in regression coefficient plot and x-loading plot of models for GWP and HHV. 1ν, fundamental stretching vibration; 2ν, 1st overtone of fundamental stretching vibration; 3ν, 2nd overtone of fundamental stretching vibration; 5ν, 4th overtone of fundamental stretching vibration; 1δ, fundamental bending (deformation) vibration; 3δ, 2nd overtone of fundamental bending (deformation) vibration; and + is combination.” The original version of this Article has been corrected.
Some of the metrics are blocked by your
consent settings
Huanglongbing (HLB) disease detection using drone imagery and deep learning neural networks for early management of HLB
(2026-08-01)
Kalbande, Vishal Dashrathrao
;
Phanomsophon, Thitima
;
Hongwiangjan, Jeerayut
;
Sripinyowanich Jongyingcharoen, Jiraporn
;
Sirisomboon, Panmanas
In the modern world, machine learning and artificial intelligence have become the foundation of the digital revolution and have a significant role in daily life. It is adopted in various applications, such as object detection, recognition and classification. This research aimed to use deep learning algorithms for the detection of Huanglongbing (HLB)-infected disease, healthy and background patch in citrus orchard. HLB-infected patches need to be identified for appropriate treatments of spraying. However, farmers are unaware of infections on plant leaves and therefore adopt manual disease identification methods. This method results in loss of productivity as the infection spreads throughout the field. However, due to a lack of required facilities, instant identification needs to be improved in many aspects of the agricultural sector. To conduct this research, firstly, a dataset was created that contained drone images of citrus orchards that was categorized into three classes, specifically (i) Healthy, (ii) HLB-infected and (iii) Background. Under this research, 6000 image patches of citrus orchard were collected and categorized 2000 images in each class based on appropriate labels. The next step was to train the deep learning models to identify Healthy, HLB-infected and Background. In this research three models viz. EfficientNetV2B0, DenseNet-121 and ResNet-50 were trained to detect the HLB infection patch in the citrus orchard. The models exhibited exceptional performance, with ResNet-50 achieving the highest overall accuracy of 89%, followed by EfficientNet-V2B0 (87%) and DenseNet-121 (85%). ResNet-50 demonstrated superior balanced performance with macro-average precision of 90%, recall of 89%, and F1-score of 89%. The generated HLB detection map effectively visualized disease distribution patterns, identifying 31% of patches as HLB-infected, 7% as Healthy and 62% as Background across the orchard grid. This research establishes a reliable framework for large-scale, automated citrus disease monitoring that enables precision agriculture interventions, potentially reducing economic losses and optimizing resource allocation in citrus cultivation through early and accurate HLB disease detection.
Some of the metrics are blocked by your
consent settings
Investigation of physiological disorder classification in mangosteen fruit using visible and shortwave near-infrared spectroscopy combined with machine learning
(2025-12-01)
Ruttanadech, Nuttapong
;
Momin, Abdul
;
Phetpan, Kittisak
;
Chaichanyut, Montree
;
Thongphut, Chitwadee
Accurate classification of physiological disorders in mangosteen fruit is crucial for ensuring production quality, safety, sustainability, and economic viability. This study investigates the application of visible and shortwave near-infrared (Vis/SWNIR) reflectance spectroscopy, combined with machine learning algorithms, to classify three primary disorders: normal fruit (NF), translucent flesh disorder (TFD), and TFD with yellow gummy latex (TFD & YGL). The study specifically examines the effects of light intensity, spectral pretreatments, and machine learning models on classification performance. Spectral data were collected using two light intensities (50 % and 100 % of a 150 W light source) and processed with three pretreatments: standard normal variate (SNV), second derivative Savitzky-Golay (SGD2), and a combination of SNV and SGD2. Random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP) algorithms were used for classification. The SGD2 method improved differentiation, especially for the TFD & YGL class, in the 700–725 nm wavelength range, which is associated with xanthone content in the fruit's pericarp. Higher light intensity (100 %) significantly improved classification accuracy, achieving an overall accuracy of 0.71 and an average F1 score of 0.61 with the RF model. Despite these improvements, the model struggled to distinguish the TFD class from NF due to their similar spectral profiles. Overall, the Vis/SWNIR spectroscopy and machine learning combination shows strong potential for the non-destructive classification of mangosteen fruit disorders. Both light intensity and spectral pretreatments play critical roles in enhancing performance. Future studies should focus on improving spectral sensitivity to better capture internal fruit characteristics.
Some of the metrics are blocked by your
consent settings
Predicting biomass global warming potential with FT-NIR spectroscopy
(2025-12-01)
Gyawali, Prakash
;
Shrestha, Bijendra
;
Phanomsophon, Thitima
;
Posom, Jetsada
;
Pornchaloempong, Pimpen
This research is to predict the global warming potential (GWP) of biomass by using Fourier transform near-infrared (FT-NIR) spectroscopy. A partial least squares regression model of 197 biomass chip samples was developed for predicting GWP of fast-growing trees and agricultural residues. The reference value of GWP of biomass sample was calculated by the method provided by Intergovernmental Panel on Climate Change (IPCC). After applying different spectral pretreatments and variable selection methods, the best model for predicting GWP was found using the 1st derivative spectrum pretreatment and covariance method (COVM) based variable selection. The results indicate GWP model exhibit good predictive capabilities, where the model can be usable with caution for any purpose including research, by achieving a coefficient of determination for prediction set (R2<inf>P</inf>) of 0.86, and ratio of prediction to deviation (RPD) of 2.6. Additionally, the RMSEP of 0.00063 suggests a low prediction error. This pioneering approach presents a swift and efficient means to determine GWP, the complex functionality parameter, which reveals an optimal relationship model, showcasing its efficacy in a significant advancement in the assessment of biomass functionality related to climate change issue. Additionally, the further research is recommended to integrate FT-NIR data with thermogravimetric analyser to simulate of different thermal conversion of biomass type where different emission gases are generated and with gas chromatography–mass spectrometry for evaluation of concentration of the generated gases for further refine GWP predictions which providing more comprehensive insights and exact content of emission gases affect global warming to support the IPCC.
Some of the metrics are blocked by your
consent settings
Revealing the Power of Deep Learning in Quality Assessment of Mango and Mangosteen Purée Using NIR Spectral Data
(2025-09-01)
Pornchaloempong, Pimpen
;
Sharma, Sneha
;
Phanomsophon, Thitima
;
Sirisomboon, Panmanas
;
Lapcharoensuk, Ravipat
The quality control of fruit purée products such as mango and mangosteen is crucial for maintaining consumer satisfaction and meeting industry standards. Traditional destructive techniques for assessing key quality parameters like the soluble solid content (SSC) and titratable acidity (TA) are labor-intensive and time-consuming; prompting the need for rapid, nondestructive alternatives. This study investigated the use of deep learning (DL) models including Simple-CNN, AlexNet, EfficientNetB0, MobileNetV2, and ResNeXt for predicting SSC and TA in mango and mangosteen purée and compared their performance with the conventional chemometric method partial least squares regression (PLSR). Spectral data were preprocessed and evaluated using 10-fold cross-validation. For mango purée, the Simple-CNN model achieved the highest predictive accuracy for both SSC (coefficient of determination of cross-validation ((Formula presented.)) = 0.914, root mean square error of cross-validation (RMSE<inf>CV</inf>) = 0.688, the ratio of prediction to deviation of cross-validation (RPD<inf>CV</inf>) = 3.367) and TA ((Formula presented.) = 0.762, RMSE<inf>CV</inf> = 0.037, RPD<inf>CV</inf> = 2.864), demonstrating a statistically significant improvement over PLSR. For the mangosteen purée, AlexNet exhibited the best SSC prediction performance ((Formula presented.) = 0.702, RMSE<inf>CV</inf> = 0.471, RPD<inf>CV</inf> = 1.666), though the RPD<inf>CV</inf> values (<2.0) indicated limited applicability for precise quantification. TA prediction in mangosteen purée showed low variance in the reference values (standard deviation (SD) = 0.048), which may have restricted model performance. These results highlight the potential of DL for improving NIR-based quality evaluation of fruit purée, while also pointing to the need for further refinement to ensure interpretability, robustness, and practical deployment in industrial quality control.
Some of the metrics are blocked by your
consent settings
Analysis of the Pomelo Peel Essential Oils at Different Storage Durations Using a Visible and Near-Infrared Spectroscopic on Intact Fruit
(2024-08-01)
Sirisomboon, Panmanas
;
Duangchang, Jittra
;
Phanomsophon, Thitima
;
Lapcharoensuk, Ravipat
;
Shrestha, Bim Prasad
Pomelo fruit pulp mainly is consumed fresh and with very little processing, and its peels are discarded as biological waste, which can cause the environmental problems. The peels contain several bioactive chemical compounds, especially essential oils (EOs). The content of a specific EO is important for the extraction process in industry and in research units such as breeding research. The explanation of the biosynthesis pathway for EO generation and change was included. The chemical bond vibration affected the prediction of EO constituents was comprehensively explained by regression coefficient plots and x-loading plots. Visible and near-infrared spectroscopy (VIS/NIRS) is a prominent rapid technique used for fruit quality assessment. This research work was focused on evaluating the use of VIS/NIRS to predict the composition of EOs found in the peel of the pomelo fruit (Citrus maxima (J. Burm.) Merr. cv Kao Nam Pueng) following storage. The composition of the peel oil was analyzed by gas chromatography–mass spectrometry (GC-MS) at storage durations of 0, 15, 30, 45, 60, 75, 90, 105 and 120 days (at 10 °C and 70% relative humidity). The relationship between the NIR spectral data and the major EO components found in the peel, including nootkatone, geranial, β-phellandrene and limonene, were established using the raw spectral data in conjunction with partial least squares (PLS) regression. Preprocessing of the raw spectra was performed using multiplicative scatter correction (MSC) or second derivative preprocessing. The PLS model of nootkatone with full MSC had the highest correlation coefficient between the predicted and reference values (r = 0.82), with a standard error of prediction (SEP) of 0.11% and bias of 0.01%, while the models of geranial, β-phellandrene and limonene provided too low r values of 0.75, 0.75 and 0.67, respectively. The nootkatone model is only appropriate for use in screening and some other approximate calibrations, though this is the first report of the use of NIR spectroscopy on intact fruit measurement for its peel EO constituents during cold storage.
Some of the metrics are blocked by your
consent settings
Primary assessment of macronutrients in durian (CV Monthong) leaves using near infrared spectroscopy with wavelength selection
(2024-01-05)
Phanomsophon, Thitima
;
Jaisue, Natthapon
;
Worphet, Akarawhat
;
Tawinteung, Nukoon
;
Khurnpoon, Lampan
Farmers would be able to regulate fertilization and produce quality durian if they knew the nutrient concentration in durian leaves. A long period of time for traditional nutritional content determination is needed. Therefore, near-infrared spectroscopy is a good method for nondestructive and quick nutrient content evaluation. The leaf sample matrices (fresh leaves, dried ground leaves, and dried ground leaf pellets) were scanned by Fourier transform near-infrared (FT-NIR) with a wavelength of 12,500–3,600 cm−1. Regression models were developed using partial least squares (PLS) with full wavelength, short wavelength, and selected wavelength by successive projections algorithm (SPA). In this study, the model for N and K concentration was acceptable and the prediction was considered good but for P content not had succeeded. As a result, the PLS-SPA model using fresh leaf samples for evaluating N content in durian leaves exhibited performance of r2 = 0.852, SEP = 0.14%, RPD = 2.63 and bias = −0.020%. The PLS-SPA model using dried ground leaf samples for evaluating K content in durian leaves exhibited performance of r2 = 0.820, SEP = 0.13%, RPD = 2.36 and bias = 0.006%. This research found that it is possible to apply NIR waves to predict N and K concentrations in durian leaves. It is not necessary to predict directly from the wavelengths associated with -N or -K bonds. Instead, NIR can measure them indirectly from the bonding of proteins, which are products formed by N and K. In addition, selecting the wavelength that is related to the value to be measured can produce results that are not significantly different from using full or short wavelengths. These models can assist farmers in rapidly predicting N and K content in durian leaves for immediate fertilizer adjustment.
Some of the metrics are blocked by your
consent settings
Classification of the Crosslink Density Level of Para Rubber Thick Film of Medical Glove by Using Near-Infrared Spectral Data
(2024-01-01)
Jongyingcharoen, Jiraporn Sripinyowanich
;
Howimanporn, Suppakit
;
Sitorus, Agustami
;
Phanomsophon, Thitima
;
Posom, Jetsada
Classification 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 your
consent settings
Effect of Environment Temperature and Relative Humidity on Thermal Emissivity: Study Case of Mango Fruit
(2024-01-01)
Sirisomboon, Panmanas
;
Sripinyowanich Jongyingcharoen, Jiraporn
;
Junto, Apiwat
;
Phanomsophon, Thitima
;
Dachoupakan Sirisomboon, Cheewanun
This research was to study the effect of the environment condition during image captured including temperature and relative humidity in the packaging house of the mango exporting factory and in the orchard on the emissivity of mango fruit. The result showed that in the controlled environment of the packaging house in factory, the emissivity was increased (the mango emitted more energy) when the surface temperature was lower and the emissivity of mango is 0.71-0.84 and in the uncontrolled environment of open-air packaging yard in the mango orchard, the different transpiration rates of mango effected mainly by ambient temperature and relative humidity make the morning condition emissivity of 0.44-0.66 and the afternoon condition of 0.72-0.98. There was the effect of the different measured positions on the fruits where the physiology was different and the fluctuated environment in the latter condition made the wide range of emissivity of mangoes. This indicated the shortcoming of thermal imaging of horticultural product if the correct emissivity varied and difficult to set in the thermal camera setting, hence the inaccurate thermogram to be obtained.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results