• Food Science of Animal Resources
• /
• v.39 no.2
• /
• pp.286-295
• /
• 2019

Red pepper seed (RPS) is commonly removed during the production of red pepper powder, which is contains large amounts of dietary fibers and is abundant in nutrients, readily available. In this study, we determined the effects of adding RPS powder on the physicochemical properties of emulsified meat products. Meat emulsion samples were prepared with pork hind leg meat (60%) and back fat (20%), iced water (20%), various additives, and RPS powder at different concentrations [0% (control), 1%, 2%, 3%, and 4%]. For the physicochemical properties, moisture and fat content, pH value, color, emulsion stability, cooking yield, appearance viscosity, and textural properties were examined. Addition of RPS induced significantly higher values in moisture content, pH, cooking yield, and a* values of the meat emulsion samples, regardless of the amount added. However, lower values were obtained for emulsion stability, cooking yield, and viscosity in samples with RPS powder at 3% or 4% among all groups. In general, addition of RPS powder at 1% and 2% led to the greatest values in viscosity of the meat emulsion samples. Higher values (p<0.05) in hardness and springiness were observed in samples with RPS powder at 4% and 3%, respectively. For gumminess, chewiness, and cohesiveness, the addition of RPS powder at 1%, 2%, and 3% induced the highest values (p<0.05) in the meat emulsion samples. These results showed that addition of RPS powder at optimum levels (2%) could be utilized to improve quality properties of emulsified meat products as a non-meat ingredient.

• 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%.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2003.05a
• /
• pp.93-105
• /
• 2003

Although, recently, studies on Internet banking users' behavior have been frequently found in some academic journals, most of them have ignored security anxiety which may be considered as important factors influencing usages of Internet banking. We propose an research model for Internet banking users which is an extended version of the Technology Acceptance Model(TAM) by adding new variable, security anxiety. For empirical support of our model, we survey for 298 samples and analyze it by structured equation model(SEM). In result, our proposed model is proved as a valid one in which all hypotheses except one are accepted and the values of model fitness are relatively high.

• Journal of Technologic Dentistry
• /
• v.13 no.1
• /
• pp.15-19
• /
• 1991

This study was made to effect on the porosity when model making for control of vibrator. Samples of total 600 were made by plaster and stone divided low, medium and high which is 100 each. The following results were obtained to observation porosity of surface by eyes. 1. Second stage was fewer than third stage, first stage was fewer than third stage in porosity number of plaster model. 2. Second stage was fewer than first stage in porosity number of stone model. 3. Stone model was fewer than plaster model in porosity number of third stage.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.40 no.2
• /
• pp.148-158
• /
• 1998

The aims of this study are to evaluate the application on the stress-strain behavior of granite Soil using Lade's double work hardening constitutive model based on the theories of elasticity and plasticity. From two different sites of construction work, two disturbed and compacted weathered granite samples which are different in partical size and degree of weathering respectively were obtained. The specimen employed were sampled at Iksan and Pochon in order to predict the constitutive model. Using the computer program based on the regression analysis, 11 soil parameters for the model were determined from the simple tests such as an isotropic compression-expansion test and a series of drained conventional triaxial tests. In conclusion, it is shown that Lade's double work hardening model gives the good applicability for processing of stress-strain, work-hardening, work-softening and soil dilatancy. Therefore, this model in its present form is applicable to the compacted decomposed granite soil.

• Journal of Information Technology Services
• /
• v.15 no.1
• /
• pp.153-166
• /
• 2016

Ensemble classification is an approach that combines individually trained classifiers in order to improve prediction accuracy over individual classifiers. Ensemble techniques have been shown to be very effective in improving the generalization ability of the classifier. But base classifiers need to be as accurate and diverse as possible in order to enhance the generalization abilities of an ensemble model. Bagging is one of the most popular ensemble methods. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. In this study we proposed a new bagging variant ensemble model, Randomized Bagging (RBagging) for improving the standard bagging ensemble model. The proposed model was applied to the bankruptcy prediction problem using a real data set and the results were compared with those of the other models. The experimental results showed that the proposed model outperformed the standard bagging model.

• Korean Journal of Veterinary Research
• /
• v.46 no.2
• /
• pp.159-164
• /
• 2006

A stochastic simulation model incorporated with Reed-Frost approach was derived for evaluating diagnostic performance of a test used for a screening program of an infectious disease. The Reed-Frost model was used to characterize the within-herd spread of the disease using a hypothetical example. Specifically, simulation model was aimed to estimate the number infected animals in an infected herd, in which imperfect serologic tests are performed on samples taken from herds and to illustrate better interpreting survey results at herd-level when uncertainty inevitably exists. From a risk analysis point of view, model output could be appropriate in developing economic impact assessment models requiring probabilistic estimates of herd-level performance in susceptible populations. The authors emphasize the importance of knowing the herd-level diagnostic performance, especially in performing emergency surveys in which immediate control measures should be taken following the survey. In this context this model could be used in evaluating efficacy of a survey program and monitoring infection status in the area concerned.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.4
• /
• pp.331-334
• /
• 2006

Original Support Vsctor Machines (SVMs) by Vapnik were used for binary classification problems. Some researchers have tried to extend original SVM to multiclass classification. However, their studies have only focused on classifying samples into nominal categories. This study proposes a novel multiclass SVM model in order to handle ordinal multiple classes. Our suggested model may use less classifiers but predict more accurately because it utilizes additional hidden information, the order of the classes. To validate our model, we apply it to the real-world bond rating case. In this study, we compare the results of the model to those of statistical and typical machine learning techniques, and another multi class SVM algorithm. The result shows that proposed model may improve classification performance in comparison to other typical multiclass classification algorithms.

• Journal of the Korean Mathematical Society
• /
• v.43 no.3
• /
• pp.623-634
• /
• 2006

Various methods have been studied to construct a fuzzy regression model in order to present a fuzzy relation between a dependent variable and an independent variable. However, in the fuzzy regression analysis the value of the center point of estimated fuzzy output may be either greater than the value of the right endpoint or smaller than the value of the left endpoint. In the case, we cannot predict the fuzzy output properly. This paper presents sufficient conditions to construct the fuzzy regression model using several methods investigated by some authors and then introduces the censored fuzzy regression model using the censored samples to manipulate the problem of crossing of the center and the end points of the estimated fuzzy number. Examples show that the censored fuzzy regression model is an extension of the fuzzy regression model and also it improves the problem of crossing.

• Earthquakes and Structures
• /
• v.25 no.1
• /
• pp.15-26
• /
• 2023

It is of great importance to assess the residual displacement demand in the performance-based seismic design. In this paper, a hybrid deep learning model for predicting the residual displacement spectra under near-fault (NF) ground motions is proposed by combining the long short-term memory network (LSTM) and back-propagation (BP) network. The model is featured by its capacity of predicting the residual displacement spectrum under a given NF ground motion while considering the effects of structural parameters. To construct this model, 315 natural and artificial NF ground motions were employed to compute the residual displacement spectra through elastoplastic time history analysis considering different structural parameters. Based on the resulted dataset with a total of 9,450 samples, the proposed model was finally trained and tested. The results show that the proposed model has a satisfactory accuracy as well as a high efficiency in predicting residual displacement spectra under given NF ground motions while considering the impacts of structural parameters.