• Journal of The Korean Society of Grassland and Forage Science
• /
• v.35 no.2
• /
• pp.125-130
• /
• 2015

The objective of this study was to investigate the feasibility of using near infrared spectroscopy (NIRS) to discriminate between grass spices. A combination of NIRS and chemometrics was used to discriminate between Italian ryegrass, perennial ryegrass, and tall fescue seeds. A total of 240 samples were used to develop the best discriminant equation, whereby three spectra range (visible, NIR, and full range) were applied within a 680 nm to 2500 nm wavelength. The calibration equation for the discriminant analysis was developed using partial least square (PLS) regression and discrimination equation (DE) analysis. A PLS discriminant analysis model for the three spectra range that was developed with the mathematic pretreatment "1,8,8,1" successfully discriminated between Italian ryegrass, perennial ryegrass, and tall fescue. An external validation indicated that all of the samples were discriminated correctly. The discriminant accuracy was shown as 68%, 78%, and 73% for Italian ryegrass, perennial ryegrass, and tall fescue, respectively, with the NIR full-range spectra. The results demonstrate the usefulness of the NIRS-chemometrics combination as a rapid method for the discrimination of grass species by seed.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.26 no.1
• /
• pp.53-62
• /
• 2006

Near infrared reflectance spectroscopy (NIRS) has been increasingly used as a rapid, accurate method of evaluating some chemical compositions in forages. Analysis of forage quality by NIRS usually involves dry ground samples. Costs might be reduced if samples could be analyzed without drying or grinding. The objective of this study was to investigate effect of sample preparations and spectral math treatments on prediction ability of chemical composition for corn silage by NIRS. A population of 112 corn silage representing a wide range in chemical parameters were used in this investigation. Samples of com silage were scanned at 2nm intervals over the wavelength range 400-2500nm and the optical data recorded as log l/Reflectance(log l/R) and scanned in overt-dried grinding(ODG), liquid nitrogen grinding(LNG) or intact fresh(IF) condition. Samples were analysed for neutral detergent fiber(NDF), acid detergent fiber(ADF), acid detergent lignin(ADL), crude protein(CP) and crude ash content were expressed on a dry-matter(DM) basis. The spectral data were regressed against a range of chemical parameters using modified partial least squares(MPLS) multivariate analysis in conjunction with four spectral math treatments to reduce the effect of extraneous noise. The optimum calibrations were selected on the basis of minimizing the standard error of cross validation(SECV). The results of this study show that NIRS predicted the chemical parameters with very high degree of accuracy(the correlation coefficient of cross validation$(R^2cv)$ range from $0.70{\sim}0.95$) in ODG. The optimum equations were selected on the basis of minimizing the standard error of prediction(SEP). The Optimum sample preparation methods and spectral math treatment were for ADF, the ODG method using 2,10,5 math treatment(SEP = 0.99, $R^2v=0.93$), and for CP, the ODG method using 1,4,4 math treatment(SEP = 0.29. $R^2v=0.91$).

• Journal of the Korean Chemical Society
• /
• v.53 no.6
• /
• pp.717-726
• /
• 2009

Multivariate models were developed for the simultaneous spectrophotometric determination of copper (II), nickel (II) and zinc (II) in water with 1-(2-thiazolylazo)-2-naphthol as chromogenic reagent in the presence of Triton X-100. To overcome the drawback of spectral interferences, principal component regression (PCR) and partial least square (PLS) multivariate calibration approaches were applied. Performances were validated with several test sets, and their results were then compared. In general, no significant difference in analytical performance between PLS and PCR models. The root mean square error of prediction (RMSEP) using three components for $Cu^{2+}$, $Ni^{2+}$ and $Zn^{2+}$ were 0.018, 0.010, 0.011 ppm, respectively. Figures of merit such as sensitivity, analytical sensitivity, limit of detection (LOD) were also estimated. High reliability was achieved when the proposed procedure was applied to simultaneous determination of $Cu^{2+}$, $Ni^{2+}$ and $Zn^{2+}$ in synthetic mixture and tap water.

• 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.

• Journal of the Korea Concrete Institute
• /
• v.14 no.4
• /
• pp.457-466
• /
• 2002

An artificial neural network was applied to predict compressive strength, slump value and mix proportion of a concrete. Standard mixed tables were trained and estimated, and the results were compared with those of the experiments. To consider variabilities of material properties, the standard mixed fables from two companies of Ready Mixed Concrete were used. And they were trained with the neural network. In this paper, standard back propagation network was used. The mix proportion factors such as water cement ratio, sand aggregate ratio, unit water, unit cement, unit weight of sand, unit weight of crushed sand, unit coarse aggregate and air entraining admixture were used. For the arrangement on the approval of prediction of mix proportion factor, the standard compressive strength of $180kgf/cm^2{\sim}300kgf/cm^2$, and target slump value of 8 cm, 15 cm were used. For the arrangement on the approval of prediction of compressive strength and slump value, the standard compressive strength of $210kgf/cm^2{\sim}240kgf/cm^2$, and target slump value of 12 cm and 15 cm wore used because these ranges are most frequently used. In results, in the prediction of mix proportion factor, for all of the water cement ratio, sand aggregate ratio, unit water, unit cement, unit weight of sand, unit weight of crushed sand, unit coarse aggregate, air entraining admixture, the predicted values and the values of standard mixed tables were almost the same within the target error of 0.10 and 0.05, regardless of two companies. And in the prediction of compressive strength and slump value, the predicted values were converged well to the values of standard mixed fables within the target error of 0.10, 0.05, 0.001. Finally artificial neural network is successfully applied to the prediction of concrete mixture and compressive strength.