• Analytical Science and Technology
• /
• v.24 no.6
• /
• pp.544-555
• /
• 2011

The acute toxicity in the rainbow trout (Oncorhynchus mykiss) was analyzed and predicted using quantitative structure-activity relationships (QSAR). The aquatic toxicity, 96h $LC_{50}$ (median lethal concentration) of 275 organic pesticides, was obtained from EU-funded project DEMETRA. Prediction models were derived from 558 2D molecular descriptors, calculated in PreADMET. The linear (multiple linear regression) and nonlinear (support vector machine and artificial neural network) learning methods were optimized by taking into account the statistical parameters between the experimental and predicted p$LC_{50}$. After preprocessing, population based forward selection were used to select the best subsets of descriptors in the learning methods including 5-fold cross-validation procedure. The support vector machine model was used as the best model ($R^2_{CV}$=0.677, RMSECV=0.887, MSECV=0.674) and also correctly classified 87% for the training set according to EU regulation criteria. The MLR model could describe the structural characteristics of toxic chemicals and interaction with lipid membrane of fish. All the developed models were validated by 5 fold cross-validation and Y-scrambling test.

• Applied Chemistry for Engineering
• /
• v.28 no.3
• /
• pp.351-354
• /
• 2017

An experimental design method was used to optimize the synthesis of gamma-alumina with a superior thermal stability using the reverse micelle method. First, twelve experimental conditions were derived by using the mixture design method to optimize conditions for the ratio of surfactant, water and oil, which are main factors in the synthesis process. When the particles synthesized by reverse micelle method were calcined at $900^{\circ}C$ under the designed condition, they all had gamma-alumina crystal structure although there were differences in particle sizes. The coefficient of determination of the second-order regression model using the derived experimental results was 93.68% and the P-value was 0.002. The synthesis conditions forgamma-alumina with various particle sizes were presented using surface and contour lines. As a result, it was calculated that the smallest particle size of about 2.8 nm was synthesized when the ratio of surfactant/water/oil was 0.3450/0.0729/0.5821.

• Korean Journal of Food Science and Technology
• /
• v.22 no.5
• /
• pp.497-502
• /
• 1990

The effect of sugar concentration, immersion time and temperature on water loss, solid gain or loss, and sugar molality of potatoes during osmotic concentration was analyzed by a response surface methodology (RSM), and those values were predicted by using a second degree polynomial regression model. Effect of osmotic concentration and blanching on vitamin C retention of air dried potatoes (6% MC: wet basis) was also evaluated. The most significant factor was sugar concentration for water loss, solid gain or loss, sugar molality, rate parameter and retention of vitamin C. Second and third factors were immersion time and temperature respectively. Water loss and solid gain were rapid in the first 10 min and then levelled off. A 44.6% of water loss was observed during osmotic concentration using a sugar solution $(60\;Brix,\;80^{\circ}C$) with 20 min of immersion time. Dried potatoes after osmotic concentration had higher vitamin C content than dried potatoes after blanching. Optimum regions for osmotic concentration process of potatoes were $60-70^{\circ}C$ of immersion temperature, 60 Brix of sugar solution and 16-20 min of immersion time based on above 30% of water loss and 50% of vitamin C retention.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.5
• /
• pp.1193-1200
• /
• 2010

This paper presents a new adaptive macroblock quantization algorithm which generates the output bits corresponding to the target bit budget. The H.264 standard uses various coding modes and optimization methods to improve the compression performance, which makes it difficult to control the amount of the generated traffic accurately. In the proposed scheme, linear regression analysis is used to analyze the relationship between the bit rate of each macroblock and the quantization parameter and to predict the MAD values. Using the predicted values, the quantization parameter of each macroblock is determined by the Lagrange multiplier method and then modified according to the difference between the bit budget and the generated bits. It is shown by experimental results that the new algorithm can generate output bits accurately corresponding to the target bit rates.

• Journal of the Korean Applied Science and Technology
• /
• v.39 no.5
• /
• pp.623-631
• /
• 2022

Using the design of experiment (DOE), factors affecting the particle size of hydrated liquid crystalline vesicles containing a high content of ceramide were analyzed and the mixture composition was optimized. Manufacturing temperature, amount of ethanol, and ultrasonic time were selected as the main variables affecting the droplet size of the vesicles, and the effect of these variables on the droplet size was examined through the signal to noise (S/N) ratios of Taguchi method and ANOVA analysis. In addition, mixture composition experiments of three lipid components constituting the vesicle membrane, hydrogenated phosphatidyl choline (HPC), cholesterol (Chol), and ceramide (Cer), were performed according to the simplex central design matrix of the mixture. Regression analysis was conducted with the experimental data to obtain a model equation, and the optimal mixing composition of the three lipid components to minimize the vesicle droplet size was determined as HPC (0.6), Chol (0.1), and Cer (0.3).

• Journal of Information Technology Services
• /
• v.21 no.4
• /
• pp.91-103
• /
• 2022

This study proposes a model for predicting contracted power using electric power data collected in real time from convenience stores nationwide. By optimizing the prediction model using machine learning, it will be possible to predict the contracted power required to renew the contract of the existing convenience store. Contracted power is predicted through the XGBoost regression model. For the learning of XGBoost model, the electric power data collected for 16 months through a real-time monitoring system for convenience stores nationwide were used. The hyperparameters of the XGBoost model were tuned using the GridesearchCV, and the main features of the prediction model were identified using the xgb.importance function. In addition, it was also confirmed whether the preprocessing method of missing values and outliers affects the prediction of reduced power. As a result of hyperparameter tuning, an optimal model with improved predictive performance was obtained. It was found that the features of power.2020.09, power.2021.02, area, and operating time had an effect on the prediction of contracted power. As a result of the analysis, it was found that the preprocessing policy of missing values and outliers did not affect the prediction result. The proposed XGBoost regression model showed high predictive performance for contract power. Even if the preprocessing method for missing values and outliers was changed, there was no significant difference in the prediction results through hyperparameters tuning.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.41 no.12
• /
• pp.1813-1822
• /
• 2012

The purpose of this study was to determine the optimal mixing conditions of two different amounts of purple barley flour ($X_1$), and olive oil ($X_2$) in baking white pan bread. The experiment was designed according to the central composite design of response surface methodology, which showed 10 experimental points including 2 replicates. The more purple barley flour added, the more weight, yellowness (b-value), hardness, gumminess, and chewiness increased; but the more volume, specific loaf volume, lightness (L-value), and springiness decreased. The greater the amount of olive oil added, the more hardness, cohesiveness, gumminess, and chewiness increased; but the more yellowness (b-value) and springiness decreased. The physical and mechanical properties were affected more by the amount of purple barley flour than by the amount of olive oil. Sensory properties except flavor were more affected by the amount of purple barley flour than by the amount of olive oil.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.18-31
• /
• 2002

In this study, we introduce a concept of advanced neurofuzzy polynomial networks(ANFPN), a hybrid modeling architecture combining neurofuzzy networks(NFN) and polynomial neural networks(PNN). These networks are highly nonlinear rule-based models. The development of the ANFPN dwells on the technologies of Computational Intelligence(Cl), namely fuzzy sets, neural networks and genetic algorithms. NFN contributes to the formation of the premise part of the rule-based structure of the ANFPN. The consequence part of the ANFPN is designed using PNN. At the premise part of the ANFPN, NFN uses both the simplified fuzzy inference and error back-propagation learning rule. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. As the consequence structure of ANFPN, PNN is a flexible network architecture whose structure(topology) is developed through learning. In particular, the number of layers and nodes of the PNN are not fixed in advance but is generated in a dynamic way. In this study, we introduce two kinds of ANFPN architectures, namely the basic and the modified one. Here the basic and the modified architecture depend on the number of input variables and the order of polynomial in each layer of PNN structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the ANFPN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed ANFPN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.1
• /
• pp.8-14
• /
• 2002

In this paper, we realized a real-time text-independent speaker recognition system using gaussian mixture model, and applied frame level likelihood normalization method which shows its effects in verification system. The system has three parts as front-end, training, recognition. In front-end part, cepstral mean normalization and silence removal method were applied to consider speaker's speaking variations. In training, gaussian mixture model was used for speaker's acoustic feature modeling, and maximum likelihood estimation was used for GMM parameter optimization. In recognition, likelihood score was calculated with speaker models and test data at frame level. As test sentences, we used text-independent sentences. ETRI 445 and KLE 452 database were used for training and test, and cepstrum coefficient and regressive coefficient were used as feature parameters. The experiment results show that the frame-level likelihood method's recognition result is higher than conventional method's, independently the number of registered speakers.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.59-76
• /
• 2023

Since the COVID-19 era, the rise in apartment prices has been unconventional. In this uncertain real estate market, price prediction research is very important. In this paper, a model is created to predict the actual transaction price of future apartments after building a vast data set of 870,000 from 2015 to 2020 through data collection and crawling on various real estate sites and collecting as many variables as possible. This study first solved the multicollinearity problem by removing and combining variables. After that, a total of five variable selection algorithms were used to extract meaningful independent variables, such as Forward Selection, Backward Elimination, Stepwise Selection, L1 Regulation, and Principal Component Analysis(PCA). In addition, a total of four machine learning and deep learning algorithms were used for deep neural network(DNN), XGBoost, CatBoost, and Linear Regression to learn the model after hyperparameter optimization and compare predictive power between models. In the additional experiment, the experiment was conducted while changing the number of nodes and layers of the DNN to find the most appropriate number of nodes and layers. In conclusion, as a model with the best performance, the actual transaction price of apartments in 2021 was predicted and compared with the actual data in 2021. Through this, I am confident that machine learning and deep learning will help investors make the right decisions when purchasing homes in various economic situations.