• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.15-15
• /
• 2000

In the past couple of years, there has been increasing interest in the fusion of neural networks and fuzzy logic. Most of the existing fused models have been proposed to implement different types of fuzzy reasoning mechanisms and inevitably they suffer from the dimensionality problem when dealing with complex real-world problem. To overcome the problem, we propose the self-organizing networks with activation nodes based on fuzzy inference and polynomial function. The proposed model consists of two parts, one is fuzzy nodes which each node is operated as a small fuzzy system with fuzzy implication rules, and its fuzzy system operates with Gaussian or triangular MF in Premise part and constant or regression polynomials in consequence part. the other is polynomial nodes which several types of high-order polynomials such as linear, quadratic, and cubic form are used and are connected as various kinds of multi-variable inputs. To demonstrate the effectiveness of the proposed method, time series data for gas furnace process has been applied.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.6
• /
• pp.77-88
• /
• 2021

Duck industry had a rapid growth in recent years. Nevertheless, researches to improve duck house environment are still not sufficient enough. Moisture generation of duck house litter is an important factor because it may cause severe illness and low productivity. However, the measuring process is difficult because it could be disturbed with animal excrements and other factors. Therefore, it has to be calculated according to the environmental data around the duck house litter. To cut through all these procedures, we built several machine learning regression model forecasting moisture generation of litter by measured environment data (air temperature, relative humidity, wind velocity and water contents). 5 models (Multi Linear Regression, k-Nearest Neighbors, Support Vector Regression, Random Forest and Deep Neural Network). have been selected for regression. By using R-Square, RMSE and MAE as evaluation metrics, the best accurate model was estimated according to the variables for each machine learning model. In addition, to address the small amount of data acquired through lab experiments, bootstrapping method, a technique utilized in statistics, was used. As a result, the most accurate model selected was Random Forest, with parameters of n-estimator 200 by bootstrapping the original data nine times.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.18 no.3
• /
• pp.65-77
• /
• 2015

The urban park has important functions as a habitat for wildlife as well as open space of rest and community for people. This study was carried out to find what factors of structure and vegetation of urban parks could affect forest bird species diversity in Cheonan city. The study surveyed bird and vegetation species in 26 urban parks, Cheonan city. A correlation analysis and multiple linear regressions were performed to test whether habitat structure and vegetation were the major correlate with species diversity. The results showed the Dujeong park was the most high bird species diversity (H' = 2.13), and the Dujeong-8 park (H' = 2.02) and the Cheongsa park (H' = 1.73) were considerably higher than the other urban parks. The variables that were strongly correlated with bird species diversity were park area, number of subtree species, canopy of shrub, number of shrub species, shape index, canopy of subtree, canopy of tree, and impervious surface ratio. The regression of bird species diversity against the environmental variables showed that 3 variables of park area, canopy of subtree, and canopy of tree were included in the best model. Model variable selection was broadly similar for the 5 optimal models. It means park area and multi-layer vegetation were the most consistent and significant predictor of bird species diversity, because urban parks were isolated by built-up areas. Especially the subtree coverage that provides shelter and food for forest birds was an important variable. Therefore, to make parks circular-shaped and abundant multi-layer vegetation, which could be a buffer to external disturbances and improve the quality of habitats, may be used to enhance species diversity in creation and management of urban parks.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.54 no.2
• /
• pp.55-65
• /
• 2012

In the winter season, when the ventilation system is operating, the fresh cold air from the slot-type openings of broiler house which directly reached the animal zone can cause various problems such as thermal stress, decreasing of feed and water consumption, occurrence of respiratory disease, and etc. Therefore it is very important to control the trajectory of aero-flow from the slot openings to induce an efficient thermal heat change. Jet-drop distance model was proposed to predict and control the jet-trajectory. However their study was restricted due to the small scaled model and difficulties of measuring the Jet-drop distance. In this study, CFD was applied to analyze qualitatively and quantitatively the jet-drop distance in a real broiler house. The various variables were considered such as installed slot-angle, designed ventilation rate, and the outdoor ambient temperature. From the present study, two linear-regression models using the Jet-drop factor and corrected Archimedes number, and their R-squared values 0.744 and 0.736, respectively, were used. From this study, the applicability of CFD on the analysis of Jet-drop distance model was confirmed.

• Computers and Concrete
• /
• v.24 no.1
• /
• pp.37-49
• /
• 2019

In this study, the shear behaviour of reinforced concrete (RC) beams that were retrofitted using precast panels of ultra-high performance fiber reinforced concrete (UHPFRC) is presented. The precast UHPFRC panels were glued to the side surfaces of RC beams using epoxy adhesive in two different configurations: (i) retrofitting two sides, and (ii) retrofitting three sides. Experimental tests on the adhesive bond were conducted to estimate the bond capacity between the UHPFRC and normal concrete. All the specimens were tested in shear under varying levels of shear span-to-depth ratio (a/d=1.0; 1.5). For both types of configuration, the retrofitted specimens exhibited a significant improvement in terms of stiffness, load carrying capacity and failure mode. In addition, the UHPFRC retrofitting panels glued in three-sides shifted the failure from brittle shear to a more ductile flexural failure with enhancing the shear capacity up to 70%. This was more noticeable in beams that were tested with a/d=1.5. An approach for the approximation of the failure capacity of the retrofitted RC beams was evolved using a multi-level regression of the data obtained from the experimental work. The predicted values of strength have been validated by comparing them with the available test data. In addition, a 3-D finite element model (FEM) was developed to estimate the failure load and overall behaviour of the retrofitted beams. The FEM of the retrofitted beams was conducted using the non-linear finite element software ABAQUS.

• Journal of Biomedical Engineering Research
• /
• v.31 no.5
• /
• pp.375-384
• /
• 2010

The purpose of this study is to determine whether there is a correlation between the segmental bio-impedance measurement with the frequency modulations and the life-style disease of obesity. An obesity is not simply the factor for estimating the life-style disease of obesity, but also the risk factor occurring. There are many methods (BMI, WHR, Waist, CT, DEXA, BIA, etc.) for measuring a degree of obesity; the bio-impedance measurement is more economic and more effective than others. The physical examination, the blood test, the medical imaging diagnosis and the bio-impedancemeasurementswithmultiple frequencies for each body parts have been conducted for 77 people. The estimated value has been calculated through a segmental bio-impedance model based on multi-frequency that was created to reflect the highest correlation by analyzing correlation with linear regression analysis method for the measured bio-impedance and the risk factors. Then we compared with the clinical diagnosis. In case of high level cholesterol, low HDL-C and high LDL-C for life-style disease, the sensitivity is 80~100%and the specificity is 83~100%. This study has shown conclusively that bio-impedance can be a possible predictor to analyze the disease risk rate of population and individual health maintenance. And also the multi-frequency segmental bio-impedance can be used as early predictor to estimate the life-style disease of obesity.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.3
• /
• pp.135-144
• /
• 2004

In this paper, we propose competitive fuzzy polynomial neurons-based advanced Self-Organizing Neural Networks(SONN) architecture for optimal model identification and discuss a comprehensive design methodology supporting its development. The proposed SONN dwells on the ideas of fuzzy rule-based computing and neural networks. And it consists of layers with activation nodes based on fuzzy inference rules and regression polynomial. Each activation node is presented as Fuzzy Polynomial Neuron(FPN) which includes either the simplified or regression polynomial fuzzy inference rules. As the form of the conclusion part of the rules, especially the regression polynomial uses several types of high-order polynomials such as linear, quadratic, and modified quadratic. As the premise part of the rules, both triangular and Gaussian-like membership (unction are studied and the number of the premise input variables used in the rules depends on that of the inputs of its node in each layer. We introduce two kinds of SONN architectures, that is, the basic and modified one with both the generic and the advanced type. Here the basic and modified architecture depend on the number of input variables and the order of polynomial in each layer. The number of the layers and the nodes in each layer of the SONN are not predetermined, unlike in the case of the popular multi-layer perceptron structure, but these are generated in a dynamic way. The superiority and effectiveness of the Proposed SONN architecture is demonstrated through two representative numerical examples.

• Bulletin of the Korean Chemical Society
• /
• v.26 no.12
• /
• pp.2007-2016
• /
• 2005

An artificial neural network (ANN) is successfully presented for prediction acidity constant (pKa) of various benzoic acids and phenols with diverse chemical structures using a nonlinear quantitative structure-property relationship. A three-layered feed forward ANN with back-propagation of error was generated using six molecular descriptors appearing in the multi-parameter linear regression (MLR) model. The polarizability term $(\pi_1)$, most positive charge of acidic hydrogen atom $(q^+)$, molecular weight (MW), most negative charge of the acidic oxygen atom $(q^-)$, the hydrogen-bond accepting ability $(\epsilon_B)$ and partial charge weighted topological electronic (PCWTE) descriptors are inputs and its output is pKa. It was found that properly selected and trained neural network with 205 compounds could fairly represent dependence of the acidity constant on molecular descriptors. For evaluation of the predictive power of the generated ANN, an optimized network was applied for prediction pKa values of 37 compounds in the prediction set, which were not used in the optimization procedure. Squared correlation coefficient $(R^2)$ and root mean square error (RMSE) of 0.9147 and 0.9388 for prediction set by the MLR model should be compared with the values of 0.9939 and 0.2575 by the ANN model. These improvements are due to the fact that acidity constant of benzoic acids and phenols in water shows nonlinear correlations with the molecular descriptors.

• The Korean Journal of Applied Statistics
• /
• v.26 no.3
• /
• pp.441-452
• /
• 2013

This study analyzed the relationship between key film and a box office record success factors based on movies released in the first quarter of 2013 in Korea. An over-fitting problem can happen if there are too many explanatory variables inserted to regression model; in addition, there is a risk that the estimator is instable when there is multi-collinearity among the explanatory variables. For this reason, optimal variable selection based on high explanatory variables in box-office performance is of importance. Among the numerous ways to select variables, LASSO estimation applied by a generalized linear model has the smallest prediction error that can efficiently and quickly find variables with the highest explanatory power to box-office performance in order.

• Journal of Environmental Impact Assessment
• /
• v.20 no.5
• /
• pp.729-745
• /
• 2011

The purpose of this paper is to estimate the external diseconomies of an unwelcomed facility on the nearby houses. The facility and the area studied are Dangin-Ri power plant in Mapo-Gu, Seoul and the residential district surrounding it respectively. The nearby housing prices have been changed according to the time and circumstances of the public announcements about the reconstruction or removal plans of the plant. These price changes are regarded as the capitalized values of the external diseconomies due to the plant. This study is based on the hedonic price theory in order to estimate the diseconomies in monetary value. The tools for the estimation are four models of multiple regression with the transaction price as the dependant variable and various housing characteristics including the external effects of the plant as the independent variables. The sample analyzed is 833 house transactions for the past 5 years in the research area. The facts found are as follows; First, the most suitable functional form for the estimation is confirmed to be the linear model. Second, there are significant differences in influence on the housing values among the independent variables, that is, locational characteristics, physical features, and environmental changes with time. Third, the external diseconomy is estimated as \80,137,807 in case that the plant would be reconstructed in the underground of the present site, whereon a substitutional public park would be constructed and as \59,142,248 in case that the plant would move away.