• Journal of Biosystems Engineering
• /
• v.43 no.2
• /
• pp.148-159
• /
• 2018

Purpose: Unmanned air vehicle (UAV) remote sensing was applied to test various vegetation indices and make prediction models of protein content of rice for monitoring grain quality and proper management practice. Methods: Image acquisition was carried out by using NIR (Green, Red, NIR), RGB and RE (Blue, Green, Red-edge) camera mounted on UAV. Sampling was done synchronously at the geo-referenced points and GPS locations were recorded. Paddy samples were air-dried to 15% moisture content, and then dehulled and milled to 92% milling yield and measured the protein content by near-infrared spectroscopy. Results: Artificial neural network showed the better performance with $R^2$ (coefficient of determination) of 0.740, NSE (Nash-Sutcliffe model efficiency coefficient) of 0.733 and RMSE (root mean square error) of 0.187% considering all 54 samples than the models developed by PR (polynomial regression), SLR (simple linear regression), and PLSR (partial least square regression). PLSR calibration models showed almost similar result with PR as 0.663 ($R^2$) and 0.169% (RMSE) for cloud-free samples and 0.491 ($R^2$) and 0.217% (RMSE) for cloud-shadowed samples. However, the validation models performed poorly. This study revealed that there is a highly significant correlation between NDVI (normalized difference vegetation index) and protein content in rice. For the cloud-free samples, the SLR models showed $R^2=0.553$ and RMSE = 0.210%, and for cloud-shadowed samples showed 0.479 as $R^2$ and 0.225% as RMSE respectively. Conclusion: There is a significant correlation between spectral bands and grain protein content. Artificial neural networks have the strong advantages to fit the nonlinear problem when a sigmoid activation function is used in the hidden layer. Quantitatively, the neural network model obtained a higher precision result with a mean absolute relative error (MARE) of 2.18% and root mean square error (RMSE) of 0.187%.

• Journal of the Korean Chemical Society
• /
• v.53 no.1
• /
• pp.27-33
• /
• 2009

A sensitive technique for the determination of trace Cd(II) in various real samples after preconcentration onto microcrystalline p-dichlorobenzene loaded with 2-mercaptobenzothiazole was developed. Several experimental conditions such as the pH of the sample solution, the amount of chelating agent 2-mercaptobenzothiazole, the amount of adsorbent p-dichlorobenzene-2-MBT, and the flow rate of sample solution were optimized. The interfering effects of various concomitant ions were investigated. Cu(II) interfered with more seriously than any other ions. However, the interference by Cu(II) could be overcome sufficiently by adjusting tartrate ion concentration to be 0.01M or by controlling the amount of 2-mercaptobenzothiazole contained in 0.20 g p-dichlorobenzene to be 0.12 g. The dynamic range, the correlation coefficient ($R^2$) and the detection limit obtained by this proposed technique were $0.5{\sim}30$ ng $mL^{-1}$, 0.9962, and 0.39 ng $mL^{-1}$, respectively. Thus, good results were obtained by the use of p-dichlorobenze as adsorbent matrix. For validating this proposed technique, the aqueous samples(wastewater, stream water, and reservoir water) and the plastic sample were used. Recovery yields of $93{\sim}104$ % were obtained. By F test, these measured data were not different from ICP-MS data at 95 % confidence level. Based on the results from the experiment, it was found that this proposed technique could be applied to the preconcentration and determination of Cd(II) in various real samples.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.37 no.2
• /
• pp.303-310
• /
• 2017

Evapotranspiration is a significant hydrologic quantity for understanding the amount of available water resource evaluation, water balance analysis, water circulation and energy circulation. Various methods have been developed for estimating the evapotranspiration using data observed at meteorological observatories. Especially, the focus of methods has been on the complementary relationship that the actual evapotranspiration is equal to the difference between the twice of evapotranspiration in the wet condition and the potential evapotranspiration. The Granger and Gary (GG) method is an empirical formula that can be used to estimate the evapotranspiration using only empirical parameters based on the complementary relationship and using only the net radiation and temperature of the region. In this study, we compared the evapotranspiration data observed at 10 sites in Asia within the dataset of FLUXNET2015, with the evapotranspiration calculated by GG method. The evapotranspiration in inland area was estimated more accurately than that of coastal area. Simulated Annealing (SA) was used for the coastal area to modify the parameters. Using the modified GG method, we could improve the statistics such as root mean square error, the coefficient of determination ($R^2$), and the mean absolute ${\mid}BIAS{\mid}$ of the evapotranspiration estimation in coastal area.

• Journal of radiological science and technology
• /
• v.46 no.3
• /
• pp.239-246
• /
• 2023

In this study, we assessed the effect of reduction of tumor volume in the head and neck cancer by using RANDO phantom in Static Intensity-Modulated Radiation Therapy (S-IMRT) and Volumetric-Modulated Arc Therapy (VMAT) planning. RANDO phantom's body and protruding volumes were delineated by using Contour menu of Eclipse™ (Varian Medical System, Inc., Version 15.6, USA) treatment planning system. Inner margins of 2 mm to 10 mm from protruding volumes of the reference were applied to generate the parameters of reduced volume. In addition, target volume and Organ at Risk (OAR) volumes were delineated. S-IMRT plan and VMAT plan were designed in reference. These plans were assigned in the reduced volumes and dose was calculated in reduced volumes using preset Monitor unit (MU). Dose Volume Histogram (DVH) was generated to evaluate treatment planning. Conformity Index (CI) and R² in reference S-IMRT were 0.983 and 0.015, respectively. There was no significant relationship between CI and the reduced volume. Homogeneity Index (HI) and R² were 0.092 and 0.960, respectively. The HI increased when volume reduced. In reference VMAT, CI and R² were 0.992 and 0.259, respectively. There was no relationship between the volume reduction and CI. On the other hand, HI and R² were 0.078 and 0.895, respectively. The value of HI increased when the volume reduced. There was significant difference (p<0.05) between parameters (D_mean and D_max) of normal organs of S-IMRT and VMAT except brain stem. Volume reduction affected the CI, HI and OAR dose. In the future, additional studies are necessary to incorporate the reduction of the volume in the clinical setting.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.43 no.11
• /
• pp.1791-1795
• /
• 2014

The objective of this study was to compare two extraction methods for determination of vitamin K1 (phylloquinone) in vegetables. In addition, analytical method validation parameters such as accuracy, precision, limit of detection (LOD), limit of quantification (LOQ), and linearity were calculated to ensure the method's validity. Vitamin K1 was quantified by reversed-phase HPLC using post-column derivatization and fluorescence detection ($Ex{\lambda}=243nm$, $Ex{\lambda}=430nm$). Higher analytical values were observed using solvent extraction compared to those from the enzyme extraction method. The results from the method validation showed high linearity in the calibration curve with a coefficient of correlation ($R^2$) of 0.9994. The LOD and LOQ were 0.1335 and 0.2784 ng/injection volume ($50{\mu}L$), respectively. The inter-day precision and inter-day precision were 2.0% and 2.1%, respectively. Overall recovery was close to 100% (n=5). The phylloquinone contents ranged from 9.42 to $1,212.57{\mu}g/100g$. Our study provides reliable data on the phylloquinone contents in commonly consumed vegetables in Korea.

• Computers and Concrete
• /
• v.24 no.4
• /
• pp.295-302
• /
• 2019

Evolutionary algorithms based on conventional statistical methods such as regression and classification have been widely used in data mining applications. This work involves application of gene expression programming (GEP) for predicting compressive strength of fly ash geopolymer concrete, which is gaining increasing interest as an environmentally friendly alternative of Portland cement concrete. Based on 56 test results from the existing literature, a model was obtained relating the compressive strength of fly ash geopolymer concrete with the significantly influencing mix design parameters. The predictions of the model in training and validation were evaluated. The coefficient of determination ($R^2$), mean (${\mu}$) and standard deviation (${\sigma}$) were 0.89, 1.0 and 0.12 respectively, for the training set, and 0.89, 0.99 and 0.13 respectively, for the validation set. The error of prediction by the model was also evaluated and found to be very low. This indicates that the predictions of GEP model are in close agreement with the experimental results suggesting this as a promising method for compressive strength prediction of fly ash geopolymer concrete.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.247-253
• /
• 2021

The outbreak of the deadly virus COVID-19 is said to infect 17.3Cr people around the globe since 2019. This outbreak is continuously affecting a lot of new people till this day and, most of it is said to under control. However, vaccines introduced around the world can help mitigate the risk of the virus. Apart from medical professionals, prediction models are also said to combinedly help predict the risk of infection based on given datasets. This paper is based on publication of a machine learning approach using regression models to predict the output based on dataset which have indictors grouped based on active, tested, recovered and critical cases along with regions and cities covering most of it from Dubai. Hence, the active cases are tested based on the other indicators and other attributes. The coefficient of the determination (r²) is 0.96, which is considered promising. This model can be used as an frame work, among others, to predict the resources related to the dangerous outbreak.

• Asian-Australasian Journal of Animal Sciences
• /
• v.16 no.6
• /
• pp.928-939
• /
• 2003

A study was carried out to determine the effect of de-hulling on apparent and true ileal amino acids digestibility of soybean meals for growing pigs. Twenty barrows (Duroc${\times}$Large white${\times}$Longer white) were fitted with a simple T-cannula at the distal ilium. Digestibility of 20 experimental diets was determined, nine of them were de-hulled soybean meal diets, and nine of them were regular soybean meal diets and two low protein casein diets for determination of endogenous amino acid correction for true digestibility determination. A TEX>$5<{\times}5<$ Latin Squares Design was adopted in this trail. The results showed that de-hulling increased apparent ileal digestibility of isoleucine, threonine, aspartic, tyrosine and indispensable and dispensable amino acid (p<0.05) in soybean meals. Furthermore, dehulling is also increased apparent digestibility of arginine, leucine, lysine, phenylalanine, alanine, glutamic acid, serine and gross amino acids (p<0.01). However, there were no significant differences found for histidine, methionine, tryptophan, cystine and glycine (p>0.05). Similar responses were found for true ileal digestibility. In three dehulled and non-dehulled pairs soybean meals from the same respective sources, de-hulling increased apparent digestibility of lysine, methionine, threonine and cystine 1.42%, 2.06%, 2.18% and 1.40% respectively. True digestibility of lysine, methionine, threonine and cystine was increased 1.65%, 1.94%, 2.30% and 1.82% respectively. A prediction equation for true ileal amino acid digestibility (including lysine and arginine) was established by multivariate linear regression. The independent variables included relevant amino acid, organic matter, crude protein, ether extract and nitrogen free extract. The coefficient R2 values of lysine and agrinine were 0.596 and 0.531 respectively. According to the crude protein content, a prediction equation for lysine and arginine content in soybean meal was also established by single linear regression. The coefficient $R^2$ values of lysine and agrinine were 0.636 and 0.636 respectively.

• Journal of radiological science and technology
• /
• v.47 no.4
• /
• pp.263-270
• /
• 2024

The objective of this study was to evaluate the accuracy and impact of leaf open time (LOT) and pitch using various machine learning models on EBT film-based delivery quality assurance (DQA) performed on 211 patients of helical tomotherapy (HT). We randomly selected passed (n=191) and failed (n=20) DQA measurements to evaluate the accuracy of the k-nearest neighbor (KNN), support vector machine (SVM), naive Bayes (NB) and logistic regression (LR) models using scale-dependent metrics such as the coefficient of determination (R2), mean squared error (MSE), and root MSE (RMSE). We evaluated the performance of the four prediction models in terms of the accuracy, precision, sensitivity, and F1-score using a confusion matrix, finding the NB and LR models to achieve optimal results. The results of this study are expected to reduce the workload of medical physicists and dosimetrists by predicting DQA results according to LOT and pitch in advance.

• Bulletin of the Korean Chemical Society
• /
• v.34 no.6
• /
• pp.1643-1650
• /
• 2013

A non linear QSAR model was constructed on a series of 57 xanthone and curcuminoide derivatives as ${\alpha}$-glucosidase inhibitors by back-propagation neural network method. The neural network architecture was optimized to obtain a three-layer neural network, composed of five descriptors, nine hidden neurons and one output neuron. A good predictive determination coefficient was obtained (${R^2}_{Pset}$ = 86.7%), the statistical results being better than those obtained with the same data set using a multiple regression analysis (MLR). As in the MLR model, the descriptor MATS7v weighted by Van der Waals volume was found as the most important independent variable on the ${\alpha}$-glucosidase inhibitory.