Lapcharoensuk, Ravipat

Preferred name

Alternative Name

Lapcharoensuk, R.

Main Affiliation

School of Engineering

ravipat.la@kmitl.ac.th

Now showing 1 - 10 of 37

Some of the metrics are blocked by your
consent settings
Discrimination model of geographical area from coconut milk by near-infrared spectroscopy: Exploration in tandem with classical chemometrics, machine learning, and deep learning
(2024-11-01)
Sitorus, Agustami
;
Lapcharoensuk, Ravipat
This work proposes exploring the discrimination model by near-infrared (NIR) spectroscopy (FT-NIR and Micro-NIR) for geographical source areas of coconut milk in tandem with the classical to modern chemometrics classifier. The discrimination model was developed using qualitative chemometrics techniques from classic (Principal Component Analysis-PCA, Partial Least Squares Discriminant Analysis-PLS-DA, Linear Discriminant Analysis-LDA) to modern, including classifiers from machine learning (Support Vector Machine-SVM, k-Nearest Neighbor-KNN, Artificial Neural Network-ANN) and deep learning (Simple Convolutional Neural Networks-S-CNN, S-AlexNET, Residual Networks-ResNET). Three sources as geographical areas of coconut milk originally from Thailand were used, including the south region (Chumphon Province), middle region (Samut Songkhram Province), and east region (Chonburi Province). Our findings showed that a classifier from SVM and ResNET could yield the optimal performance for discriminating the geographical source area of coconut milk using FT-NIR. Furthermore, when using Micro-NIR, the classifier from LDA, SVM, KNN and ResNET delivered the highest accuracy. The performance discrimination models above were excellent when classified based on the kappa coefficient. This study concluded that both FT-NIR and Micro-NIR supported by classical to modern chemometric classifiers could be used to evaluate the geographical area source from coconut milk. Also, the method in this study includes a strategy for discovering feature-important NIR spectra for interpretability purposes, thereby facilitating the qualitative interpretation of results for all types of classifiers.
Some of the metrics are blocked by your
consent settings
Evaluation of the physicochemical and textural properties of pomelo fruit following storage
(2012-12-01)
Sirisomboon, Panmanas
;
Lapcharoensuk, Ravipat
Introduction. Because of the long transportation times and storage durations that are often experienced, it is important to understand how pomelo properties change over time; that will be indicative of how long samples can be stored before they drop below acceptable quality limits. As no information is available regarding storage of pomelo fruit in the literature, the goal of our work was to study the change in pomelo physicochemical and textural properties following storage over a period of approximately 4 months. Materials and methods. The changes in physical, chemical and textural properties of commercial pomelo fruit were extensively evaluated over the course of a 4-month storage period. The correlation among physical, color, chemical and textural properties were also assessed. Results. Color properties (L*, a*, b*) changed significantly with storage; however, they did not change much during the initial 45 days of storage. The change in soluble solids content (SSC), acidity (A) and the [(SSC) / (A)] ratio suggested that pomelo fruit should not be stored for more than 75 days. Crucially, our study demonstrates that the a* parameter (greenness, R = -0.556) correlates best with the chemical property the [(SSC) / (A)] ratio, which is a recognized measurement of the consumer acceptability of citrus fruit. This means that measuring a* is a non-destructive way of monitoring the taste characteristics of pomelos in storage. This property also correlated well with the average firmness of the fruit and with the flesh texture. Conclusion. This fundamental information on the pomelo fruit could prove useful in the physical handling and processing of the fruit by breeders and postharvest technologists as well as distributors, market agents, importers and exporters. © 2012 Cirad/EDP Sciences.
Some of the metrics are blocked by your
consent settings
Evaluation of acetic acid and ethanol concentration in a rice vinegar internal venturi injector bioreactor using Fourier transform near infrared spectroscopy
(2019-12-01)
Phanomsophon, Thitima
;
Sirisomboon, Panmanas
;
Lapcharoensuk, Ravipat
;
Shrestha, Bim
;
Krusong, Warawut
In the process of fermenting rice vinegar, the concentration of acetic acid and ethanol concentration must be measured for monitoring of the total concentration. Near infrared spectroscopy has been used to rapidly monitor the concentration of acetic acid and ethanol concentration daily during 10 cycles of the fermentation process. The model was developed using partial least squares regression. For predicting concentration of acetic acid with near infrared spectroscopy, the coefficient of determination (R2), root mean square error of calibration, root mean square error of cross validation, ratio of standard error of validation to standard deviation, and bias was 0.96, 2.30 g L−1, 2.44 g L−1, 1.11 g L−1, and 5.56, respectively. For ethanol concentration, the value of R2, root mean square error of calibration, root mean square error of cross validation, bias and ratio of prediction to deviation were predicted to be 0.94, 3.15 g L−1, 2.73 g L−1, −0.40 g L−1, and 4.04, respectively. However, both models provided fair performance when tested with an external set of samples, indicating that the models could be applied for rough screening.
Some of the metrics are blocked by your
consent settings
Development of the near infrared spectroscopy model for detecting herbicide concentrations contaminated in water
(2019-09-09)
Lapcharoensuk, Ravipat
;
Wongpromrat, Patthranit
This research aims to develop the near infrared spectroscopy (NIR) models for detecting herbicide concentrations contaminated in water. Atrazine, the organochlorine herbicide, solution in the concentration range of 0-15 ppm were prepared in distilled water. Near infrared spectra were scanned by using Fourier transform spectrometer at wavenumbers of 12,500-4,000 cm-1 (800-2, 500 nm). Partial least square regression technique was used to establish the NIR models for detecting herbicide concentrations. The developed models showed high prediction potential of herbicide concentrations contaminated in water with the R2 of 0.97, RMSEE of 0.899 ppm, bias of -0.0003 ppm and RPD of 5.43. This indicated that these models can apply to analyse contamination of atrazine in the natural water sources.
Some of the metrics are blocked by your
consent settings
Eating quality of cooked rice determination using Fourier transform near infrared spectroscopy
(2014-10-20)
Lapcharoensuk, Ravipat
;
Sirisomboon, Panmanas
The goal of this research was to study the relationship between the eating quality of cooked rice and near infrared spectra measured by a Fourier Transform near infrared (FT-NIR) Spectrometer. Samples of milled: parboiled rice, white rice, new Jasmine rice (harvested in 2012) and aged Jasmine rice (harvested in 2006 or during the period 2007-2011) were used in this study. The eating quality of the cooked rice, i.e., adhesiveness, hardness, dryness, whiteness and aroma, were evaluated by trained sensory panelists. FT-NIR spectroscopy models for predicting the eating quality of cooked rice were established using the partial least squares regression. Among the eating quality, the stickiness model indicated its highest prediction ability (i.e., R <inf>val</inf>2 = 0:71; RMSEP = 0:65; Bias = 0:00; RPD = 1:87) and SEP/SD of 2. In addition, it was clear that the water content did not affect the eating quality of cooked rice, rather the main chemical component implicated was starch.
Some of the metrics are blocked by your
consent settings
A rapid method to predict type and adulteration of coconut milk by near-infrared spectroscopy combined with machine learning and chemometric tools
(2023-12-01)
Sitorus, Agustami
;
Lapcharoensuk, Ravipat
Coconut milk is a soft target for adulterators owing to its simplicity of chemical composition. Professionals and consumers want to control the originalitas of coconut milk, while sellers can profit by mixing fresh coconut milk from low-cost products into high-value fresh coconut milk. Non-destructively and rapidly identifying coconut milk classification goods may be useful in quality assurance settings. However, no studies to date have investigated this topic. In this study, near-infrared spectra (NIRs) were collected from fresh coconut milk (FCM), instant coconut milk (ICM), and adulterated fresh coconut milk (A-FCM) in order to investigate the prospect of non-invasively discriminating coconut milk type and at the same time predicting the level of A-FCM. Partial least squares (PLS), linear discriminant analysis (LDA), support vector machine (SVM), and multilayer perceptron (MLP) were employed to establish classification and regression models using NIRs. Combining 18 preprocessing types and hyperparameter optimization of individual machine learning algorithms is carried out together and evaluated using 5-folds cross-validation. All algorithms in this study (LDA, SVM, MLP) obtained the same satisfactory results with all the precision, recall, F1-score, and perfect accuracy (100%) to distinguish FCM, ICM, and A-FCM in both calibration and prediction. Regression models using the SVM obtained acceptable results, with a determination coefficient of calibration and prediction all over 0.93, root mean square error of calibration and prediction all below 8.30%, and ratio of prediction to deviation over 3.80. Last but not least, this study would help apply NIRs to detect the originality of coconut milk in real-world conditions.
Some of the metrics are blocked by your
consent settings
A COMPREHENSIVE OVERVIEW OF NEAR INFRARED AND INFRARED SPECTROSCOPY FOR DETECTING THE ADULTERATION ON FOOD AND AGRO-PRODUCTS—A CRITICAL ASSESSMENT
(2022-01-01)
Sitorus, Agustami
;
Lapcharoensuk, Ravipat
In the past decade, fast and non-destructive methods based on spectroscopy technology have been studied to detect and discriminate against food adulteration and agro-products. Numerous linear and nonlinear chemometric approaches have been developed for spectroscopy analysis. Recently, various approaches have been developed for spectroscopic calibration modelling to detect and discriminate adulteration food and agro-products. This article discusses the application of spectroscopy technology, including near infrared and infrared, in detecting and discriminating the adulteration of food and agro-products based on recent research and delivered a critical assessment on this topic to serve as lessons from current studies and future outlooks. The current state-of-the-art techniques, including detection and classification of various adulteration in food and agro-products, have been addressed in this paper. Key findings from this study, near infrared and infrared spectroscopy is a non-destructive, rapid, simple-preparation, analytical rapidity, and straightforward method for classification and determination of adulteration in the food and agro-products so it is suitable for large-scale screening and on-site detection. Although there are still some unsatisfactory research results, especially in detecting tiny adductors, these technologies can potentially detect any adulteration in the various food and agro-products at an economically viable level, at least for the initial screening process. In that respect, near infrared and infrared spectroscopy should be expanded to cover all food and agro-products sold in the market. Only then will there be an acceptable deterrent in place to stop adulteration activity in widely consumed food and agro-products ingredients
Some of the metrics are blocked by your
consent settings
Systematic evaluation of one-dimensional-to-two-dimensional near-infrared spectroscopy transformations with deep learning for quantifying coconut sap adulteration
(2026-10-01)
Lapcharoensuk, Ravipat
;
Sitorus, Agustami
Near-infrared (NIR) spectroscopy have limitations when combined with deep learning (DL) algorithms because they rely on low-dimensional datasets. Therefore, we investigated the potential of transforming one-dimensional (1D) NIR spectra into two-dimensional (2D) spectrograms using synchronous and asynchronous techniques and the continuous wavelet transform (CWT) and their effectiveness by integrating with DL for detecting adulteration in coconut sap. NIR spectra (12,500–4000 cm−1) were collected from binary mixtures (0%–100%; w /w). The performance of all DL (convolutional neural networks-CNN, AlexNet and ResNet) models was compared with that of partial least squares (PLS). The models were ranked in the mentioned order based on their performances: 2D-CWT ' 2D-asynchronous ' 2D-synchronous ' 1D/2D-PLS. The important features of the best model can be explained and visualized using gradient-weighted-class-activation-mapping. The findings highlight that the 1D-to-2D NIR data transformation combined with DL is a highly robust approach because it addresses the feature representation gap in NIR data and effectively captures the spatial–spectral correlations.
Some of the metrics are blocked by your
consent settings
Gross calorific and ash content assessment of recycled sawdust from mushroom cultivation using near infrared spectroscopy
(2018-08-14)
Posom, Jetsada
;
Phuphanutada, Jirawat
;
Lapcharoensuk, Ravipat
The aim of this study was to use the near infrared spectroscopy for predicting the gross calorific value (GCV) and ash content (AC) of recycled sawdust from mushroom cultivation. The wavenumber was in range of 12500-4000 cm-1 with the diffuse reflection mode was used. The NIR models was established using partial least square regression (PLSR) and was validated via using full cross validation. GCV model provided the coefficient of determination (R2), root mean square error of cross validation (RMSECV), ratio of prediction to deviation (RPD), and bias of 0.90, 445 J/g, 3.19 and 4 J/g, respectively. The AC model gave the R2, RMSECV, RPD and bias of 0.83, 1.7000 %wt, 2.44 and 0.0059 %wt, respectively. For prediction of unknow samples, GCV model provided the standard error of prediction (SEP) and bias of 670 J/g and -654 J/g, respectively. The AC model gave the SEP and bias of 1.84 %wt and 0.912 %wt, respectively. The result represented that the GCV and AC model probably used as the rapid method and non-destructive method.
Some of the metrics are blocked by your
consent settings
LOW COST TELEMONITORING TECHNOLOGY OF SEMISPHERICAL SOLAR DRYER FOR DRYING ARABICA COFFEE BEANS
(2022-01-01)
Pramono, Eko Kuncoro
;
Karim, Mirwan Ardiansyah
;
Fudholi, Ahmad
;
Bulan, Ramayanty
;
Lapcharoensuk, Ravipat
This study focusses on the development of a low-cost Internet of Things (IoT) system for semispherical solar dryers to dry arabica coffee beans. The temperatures and relative humidity (Rh) of a solar dryer room are measured using a DHT22 sensor module. The moisture content of hard arabica coffee beans is calculated by measuring the mass of the dried product using the load cell sensor module. All detected data are then sent using wireless networks and saved on a database cloud server. Tests are conducted to evaluate the uniformity of the DHT22 sensor module in a semispherical solar dryer, measure the temperature and Rh and reduce the mass of the dried coffee beans. The performance of the DHT22 sensor module at the uniformity testing stage shows promising results in terms of temperature and Rh, with standard deviations of 0.46 and 3.55, respectively. In addition, the performance of the semispherical solar dryer in relation to the drying kinetics of arabica coffee beans is evaluated. Arabica coffee beans are dried from 49.59% (w.b.) to 10% (w.b.) moisture content within 69 h. In addition, the drying kinetics of coffee arabica beans are investigated. Three models are compared with experimental data on arabica coffee beans dried in a semispherical solar dryer. The Page model is selected to represent the thin layer drying behaviour of arabica coffee beans.

Lapcharoensuk, Ravipat

Filters

Settings

Sort By

Results per page