• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.4
• /
• pp.343-350
• /
• 2000

In this paper, we propose the Multi-FPNN(Fuzzy Polynomial Neural Networks) model based on FNN and PNN(Polyomial Neural Networks) for optimal system identifacation. Here FNN structure is designed using fuzzy input space divided by each separated input variable, and urilized both in order to get better output performace. Each node of PNN structure based on GMDH(Group Method of Data handing) method uses two types of high-order polynomials such as linearane and quadratic, and the input of that node uses three kinds of multi-variable inputs such as linear and quadratic, and the input of that node and Genetic Algorithms(GAs) to identify both the structure and the prepocessing of parameters of a Multi-FPNN model. Here, HCM clustering method, which is carried out for data preproessing of process system, is utilized to determine the structure method, which is carried out for data preprocessing of process system, is utilized to determance index with a weighting factor is used to according to the divisions of input-output space. A aggregate performance inddex with a wegihting factor is used to achieve a sound balance between approximation and generalization abilities of the model. According to the selection and adjustment of a weighting factor of this aggregate abjective function which it is acailable and effective to design to design and optimal Multi-FPNN model. The study is illustrated with the aid of two representative numerical examples and the aggregate performance index related to the approximation and generalization abilities of the model is evaluated and discussed.

• Journal of Korea Water Resources Association
• /
• v.55 no.3
• /
• pp.245-255
• /
• 2022

Evaluating the qualitative the qualitative process of water resources by using various indicators, as one of the most prevalent methods for optimal managing of water bodies, is necessary for having one regular plan for protection of water quality. In this study, zoning maps were developed on a yearly basis by collecting and reviewing the process, validating, and performing statistical tests on qualitative parameters҆ data of the Iranian aquifers from 1995 to 2020 using Geographic Information System (GIS), and based on Inverse Distance Weighting (IDW), Radial Basic Function (RBF), and Global Polynomial Interpolation (GPI) methods and Kriging and Co-Kriging techniques in three types including simple, ordinary, and universal. Then, minimum uncertainty and zoning error in addition to proximity for ASE and RMSE amount, was selected as the optimum model. Afterwards, the selected model was zoned by using Scholar and Wilcox. General evaluation of groundwater situation of Iran, revealed that 59.70 and 39.86% of the resources are classified into the class of unsuitable for agricultural and drinking purposes, respectively indicating the crisis of groundwater quality in Iran. Finally, for validating the extracted results, spatial changes in water quality were evaluated using the Groundwater Quality Index (GWQI), indicating high sensitivity of aquifers to small quantitative changes in water level in addition to severe shortage of groundwater reserves in Iran.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• Korean Journal of Poultry Science
• /
• v.11 no.2
• /
• pp.86-92
• /
• 1984

Present study was carried out to estimate phenotypic and genetic parameters influencing body weight (BW) at 4 weeks of age egg breadth (EB), egg length(EL), egg shape index (SI) and egg weight (EW) at 32 weeks of age and egg numbers (EN) up to 38 weeks of age in broiler male and female lines. The data were collected from closed White Plymouth Rock (female line; G) and Cornish (male line; C) flocks involving 1193 pullets from 211 dams and 48 sires in 1982. The results obtained are summarized as follow: 1. General performance for various trails of lines C and G. The means and standard deviations of BW, EB, EL, SI, EW and EN were 668.34${\pm}$47.18, 4.23${\pm}$0,11, 5.49 ${\pm}$0.19, 77.06${\pm}$2.98, 55.73${\pm}$3.54 and 59.72${\pm}$13.39 in line C, respectively and 487.89${\pm}$ 41.43, 4.22${\pm}$0.11, 5.51${\pm}$0.19, 76.72${\pm}$3.20, 55.43${\pm}$3.26 and 76.93${\pm}$12.17 in line G, respectively. 2. Heritability Heritabilities were estimated from sire, dam and combined components. Estimates for BW, EB, EL, SI, EW and EN from combined components were 0.30, 0.29, 0,40, 0.22, 0.45 and 0.60 in line C, respectively and 0.33, 0.23, 0.28, 0.13, 0.49 and. 0.33 in line G, respectively. 3. Correlation Genetic and phenotypic correlations showed similar trend in line C and G. Genetic correlations, estimated EW with EB and EL, were high and positive (line C; 0.99, 0.75, respectively and line G; 0.94, 0.82, respectively), also correlation of EB with EL was 0.58 (both lines; 0.58). High and negative genetic correlations were shown between SI and EL in line C and G (-0.70, -0.65, respectively). Genetic correlations between SI and EW were relatively low and negative in line C and G (-0.11, -0.19, respectively) and between SI and EN were relatively low and positive in line C and G (0.25, 0.17, respectively). Between other traits, low genetic correlations were shown in both lines, High and positive correlation was estimated between hatchability and egg shape index and polynomial regression of egg shape index on hatchability was estimated; Y=-216.77＋7.6216X-0.0146939X$^2$.

• Journal of Biomedical Engineering Research
• /
• v.30 no.5
• /
• pp.401-411
• /
• 2009

In this paper, we correct pulse wave velocity(PWV) with heart-rate and derive regression equations to estimate intima-media thickness(IMT). Widely used methods for diagnosis of arteriosclerosis are IMT and PWV. Arterial wall stiffness determines the degree of energy absorbed by the elastic aorta and its recoil in diastole but there is not correlation between sclerosis and IMT in an existing study. In this study, we will correct PWV with heart-rate and get regression equation to estimate IMT using heart-rate correction index(HCI). We executed experiments for this study. Made up question of physical condition and measured electrocardiogram(ECG), photoplethysmogram (PPG) of finger-tip and toe-tip and ultrasound image of carotid artery. Calculated PWV and IMT using ECG, PPG and ultrasound image. We found that every p-value between PWV and IMT is not significant(<0.05). But p-value between IMT and HCI which is a corrected PWV using heart-rate is significant(>0.01). We use HCI and various measured parameter for estimating regression equation and apply backward estimation to select parameters for regression analysis. Result of backward estimation, found that only HCI is possible to derive proper regression equation of IMT. Relationship between PWV and IMT is the second order. Result of regression equation of E-H PWV is $R^2$=0.735, adj $R^2$=0.711. This is the best correlation value. We calculate error of its analysis for verification of earlobe PWV regression equation. Its result is RMSEP=0.0328, MAPE(%) = 4.7622. Like this regression analysis, we know that HCI is useful parameter and relationship between PWV, HCI and IMT. In addition, we are able to suggest possibility which is that we can get different parameter of prediction throughout just one measurement.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.47-59
• /
• 2014

Volcanic ash (VA) can be estimated by remote sensing sensors through their spectral signatures determined by the inherent optical property (IOP) including complex refractive index and the scattering properties. Until now, a very limited range of VA refractive indices has been reported and the VA from each volcanic eruption has a different composition. To improve the robustness of VA remote sensing, there is a need to understanding of VA - radiation interactions. In this study, we calculated extinction coefficient, scattering phase function, asymmetry factor, and single scattering albedo which show different values between andesite and pumice. Then, IOPs were used to analyze the relationship between theoretical remote sensed radiation calculated by radiative transfer model under various aerosol optical thickness (${\tau}$) and sun-sensor geometries and characteristics of VA. It was found that the mean rate of change of radiance at top of atmosphere versus ${\tau}$ is six times larger than in radiance values at 0.55 ${\mu}m$. At the surface, positive correlation dominates when ${\tau}$ <1, but negative correlation dominates when ${\tau}$ >1. However, radiance differences between andesite and pumice at 11 ${\mu}m$ are very small. These differences between two VA types are expressed as the polynomial regression functions and that increase as VA optical thickness increases. Finally, these results would allow VA to be better characterized by remote sensing sensors.

• 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 Korea Academia-Industrial cooperation Society
• /
• v.21 no.9
• /
• pp.405-413
• /
• 2020

The normal stress of cement paste measured under squeeze flow is divided into an elastic solid region at strains between 0.0003 and 0.003 and a strain-hardening region at strains of 0.003 and 0.8. A modeling equation at the strain-hardening region was proposed. First, from the viewpoint of fluid behavior, the power-law non-Newtonian fluid model, with a power-law consistency (m) of 700 and a power index (n) of 0.2, was applied. The results showed good agreement with the experimental results except for an elastic solid region. Second, from the viewpoint of ductile yielding solid behavior, the force balance model was applied, and the friction coefficient between the sensor part measuring the load and the surface of the cement paste was derived as a polynomial of the normal strain by applying the half-interval search method to the experimental data. The results showed good agreement with the experimental results only in the middle normal strain region at strains between 0.003 and 0.3. The rheological behavior of the cement paste under squeeze flow was more consistent with the experimental results from the viewpoint of power-law non-Newtonian fluid behavior than from the viewpoint of ductile yielding solid behavior in the strain-hardening region.

• Science of Emotion and Sensibility
• /
• v.26 no.4
• /
• pp.15-28
• /
• 2023

Considering the necessity for individuals to check and manage their wellness to promote happiness, this study conducted preliminary research on the effect of wellness enhancement of the self-life coaching app. Thirty-six participants were randomly assigned to experimental groups 1 and 2 and a control group, respectively. In particular, the experimental groups were asked to perform self-life coaching for 4 weeks using a research app. Weekly feedback was provided to experimental group 1, but not to experimental group 2. The wellness index for workers (WIW) and the Korean wellness scale (KWS) were used as dependent variables. The analysis results of interaction effects between pre-, post-, and follow-up time points and groups reveal no statistically significant effects in both dependent variables, but the tendency of the effects was confirmed. Moreover, no difference was determined in terms of the presence or absence of weekly feedback in the experimental treatment effect. As a result of repeated measures variance analysis on KWS measured at five times, the wellness enhancement effect over time was statistically significant. Meanwhile, the polynomial trend analysis result confirmed the linear effect of the experimental treatment on wellness. The participation opinion survey also revealed that 84.2% of the participants perceived the activity to be helpful, and 78.9% responded that they would use it once every 1 or 2 weeks if the app is commercially available. This study is meaningful in that it suggests a methodology for utilizing the self-life coaching app so that anyone can use it to promote their wellness and partially confirms the effectiveness of this method.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.119-133
• /
• 2020

Fama asserted that in an efficient market, we can't make a trading rule that consistently outperforms the average stock market returns. This study aims to suggest a machine learning algorithm to improve the trading performance of an intraday short volatility strategy applying asymmetric volatility spillover effect, and analyze its trading performance improvement. Generally stock market volatility has a negative relation with stock market return and the Korean stock market volatility is influenced by the US stock market volatility. This volatility spillover effect is asymmetric. The asymmetric volatility spillover effect refers to the phenomenon that the US stock market volatility up and down differently influence the next day's volatility of the Korean stock market. We collected the S&P 500 index, VIX, KOSPI 200 index, and V-KOSPI 200 from 2008 to 2018. We found the negative relation between the S&P 500 and VIX, and the KOSPI 200 and V-KOSPI 200. We also documented the strong volatility spillover effect from the VIX to the V-KOSPI 200. Interestingly, the asymmetric volatility spillover was also found. Whereas the VIX up is fully reflected in the opening volatility of the V-KOSPI 200, the VIX down influences partially in the opening volatility and its influence lasts to the Korean market close. If the stock market is efficient, there is no reason why there exists the asymmetric volatility spillover effect. It is a counter example of the efficient market hypothesis. To utilize this type of anomalous volatility spillover pattern, we analyzed the intraday volatility selling strategy. This strategy sells short the Korean volatility market in the morning after the US stock market volatility closes down and takes no position in the volatility market after the VIX closes up. It produced profit every year between 2008 and 2018 and the percent profitable is 68%. The trading performance showed the higher average annual return of 129% relative to the benchmark average annual return of 33%. The maximum draw down, MDD, is -41%, which is lower than that of benchmark -101%. The Sharpe ratio 0.32 of SVS strategy is much greater than the Sharpe ratio 0.08 of the Benchmark strategy. The Sharpe ratio simultaneously considers return and risk and is calculated as return divided by risk. Therefore, high Sharpe ratio means high performance when comparing different strategies with different risk and return structure. Real world trading gives rise to the trading costs including brokerage cost and slippage cost. When the trading cost is considered, the performance difference between 76% and -10% average annual returns becomes clear. To improve the performance of the suggested volatility trading strategy, we used the well-known SVM algorithm. Input variables include the VIX close to close return at day t-1, the VIX open to close return at day t-1, the VK open return at day t, and output is the up and down classification of the VK open to close return at day t. The training period is from 2008 to 2014 and the testing period is from 2015 to 2018. The kernel functions are linear function, radial basis function, and polynomial function. We suggested the modified-short volatility strategy that sells the VK in the morning when the SVM output is Down and takes no position when the SVM output is Up. The trading performance was remarkably improved. The 5-year testing period trading results of the m-SVS strategy showed very high profit and low risk relative to the benchmark SVS strategy. The annual return of the m-SVS strategy is 123% and it is higher than that of SVS strategy. The risk factor, MDD, was also significantly improved from -41% to -29%.