• Journal of Biosystems Engineering
• /
• v.34 no.2
• /
• pp.114-119
• /
• 2009

Field test was conducted to investigate primary factors reducing rapeseed harvesting using a reciprocating cutter-bar of combine. The results showed that the correlation between crop moisture content and yield loss had a U-type, which indicated that the yield reduction increased at too high and too low crop moisture contents. The proper ranges of crop moisture contents were 27${\sim}$35%, 21${\sim}$56%, and 62${\sim}$73% in case of grain, pod and stem, respectively. Crop moisture content was negatively correlated with header loss, but positively correlated with threshing loss. In contrary, stem moisture content showed positive correlations with total loss, threshing loss and separation loss. Working speed was positively correlated with header loss. Total flow rate, pod flow rate and stem flow rate were highly correlated with threshing loss and separation loss. However, grain flow rate did not show any correlation with total loss. According to the principal component analysis, two principal components were derived as components with eigenvalues greater than 1.0. The contribution rates of the first and the second components were 52.7% and 38.9%, which accounted for 91.6% of total variance. As a contributive factor influencing total loss of rapeseed mechanical harvesting, a crop moisture content factor was greater than a crop flow rate factor. The stepwise multiple regression analysis for total loss was conducted using crop moisture content factor, crop flow rate factor and coefficient. However, the model did not show any correlation among independent and dependent factors ($R^2$=0.060).

• Journal of Environmental Science International
• /
• v.24 no.6
• /
• pp.743-753
• /
• 2015

In this study, it is an object to develop a regression model for the estimation of TOC (total organic carbon) concentration using investigated data for three years from 2010 to 2012 in the Gam Stream unit watershed, and applied in 2009 to verify the applicability of the regression model. TOC and $COD_{Mn}$ (chemical oxygen demand) were appeared to be derived the highest correlation. TOC was significantly correlated with 5 variables including BOD (biological oxygen demand), discharge, SS (suspended solids), Chl-a (chlorophyll a) and TP (total phosphorus) of p<0.01. As a result of PCA (principal component analysis) and FA (factor analysis), COD, TOC, SS, discharge, BOD and TP have been classified as a first factor. TOCe concentration was estimated using the model developed as an independent variable $BOD_5$ and $COD_{Mn}$. R squared value between TOC and measurement TOC is 0.745 and 0.822, respectively. The independent variable were added step by step while removing lower importance variable. Based on the developed optimal model, R squared value between measurement value and estimation value for TOC was 0.852. It was found that multiple independent variables might be a better the estimation of TOC concentration using the regression model equation(in a given sites).

• Korean Journal of Acupuncture
• /
• v.36 no.4
• /
• pp.210-220
• /
• 2019

Objectives : Warm needling is a combined treatment technique of acupuncture and moxibustion. In this study, we aimed to find out the components related with the thermal stimulation of the warm needling and to provide basic data for the guideline of the warm needling technique in the clinic. Methods : In this study, we measured thermal change of 3% agarose phantom embedding K-type thermocouples in depths of 0, 1, 2, 4, 8 and 16 mm. The warm needling was performed with acupuncture needles of various specifications (0.50×30, 0.50×40, 0.30×30, 0.30×40, 0.20×30 and 0.20×40 mm). A linear regression analysis was performed to find out the major component and quantify the effectiveness of the thermal stimulation during warm needling. Results : As a result of the measurement of temperature change, we could observe the thermal change pattern from the surface of the phantom to the 16mm deep part of the phantom. The thermal pattern was similar among the needles of different specifications. The regression analysis pointed the distance between the moxa cautery and the skin surface as the main component for the thermal stimulation of the warm needling. Conclusions : The authors suggest considering the distance between moxa cautery and the skin rather than the diameter of the acupuncture needle in accordance to the result of the study.

• Korean Chemical Engineering Research
• /
• v.45 no.6
• /
• pp.596-603
• /
• 2007

Rapid or on-line coal analysis is of great interest in coal industry as it would allow efficient plant operation. Multivariate analysis has been applied to near-infrared(NIR) spectra coal for investigating the relationship between coal properties(%) (moisture, ash, volatile matter, fixed carbon, carbon, hydrogen, nitrogen, oxygen, sulfur), heating value(kcal/kg) and corresponding near-infrared spectral data. The quantitative analysis was carried out by applying PLS(partial least squares regression) to determine a methodology able to establish a relationship between coal properties and NIR spectral data being applied mathematical pre-treatments for minimizing the physical features of the samples. As a results of the analysis, this technique is able to classify the species of coals and to predict the all coal properties except ash, nitrogen and sulfur. The efficient operation of coal fired power plant is expected owing to real time on-line coal analysis of moisture and heating value.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1333-1342
• /
• 2018

Until now, Electroencephalography(: EEG) has been the most important and convenient method for the diagnosis and treatment of epilepsy. However, it is difficult to identify the wave characteristics of an epileptic EEG signals because it is very weak, non-stationary and has strong background noise. In this paper, we analyse the effect of dimensionality reduction methods on Epileptic EEG feature selection and classification. Three dimensionality reduction methods: Pincipal Component Analysis(: PCA), Kernel Principal Component Analysis(: KPCA) and Linear Discriminant Analysis(: LDA） were investigated. The performance of each method was evaluated by using Support Vector Machine SVM, Logistic Regression(: LR), K-Nearestneighbor(: K-NN), Decision Tree(: DR) and Random Forest(: RF). From the experimental result, PCA recorded 75% of highest accuracy in SVM, LR and K-NN. KPCA recorded 85% of best performance in SVM and K-KNN while LDA achieved 100% accuracy in K-NN. Thus, LDA dimensionality reduction is found to provide the best classification result for epileptic EEG signal.

• Journal of the Korean Society of Food Culture
• /
• v.37 no.3
• /
• pp.239-247
• /
• 2022

This study evaluated the sensory characteristics of sauerkraut prepared by adding 0.5, 1.0, 1.5, 2.0, and 2.5% (w/w) sea salt to cabbage. The quantitative descriptive analysis (QDA) and acceptance test of sauerkraut were determined for each salt concentration, and the principal component analysis (PCA) and partial least square regression (PLSR) analysis were performed to confirm the correlation between each factor. Results of the QDA determined 14 descriptive terms; furthermore, brightness and yellowness of appearance and the sour, salty, and bitter flavors differed significantly according to the salt concentration. Results from the PCA explained 22.56% PC1 and 65.34% PC2 of the total variation obtained. Sauerkraut prepared using 0.5, 1.0, and 1.5% sea salt had high brightness, moistness, sour odor, green odor, sour flavor, carbonation, hardness, chewiness, and crispness, whereas sauerkraut prepared with 2.0 and 2.5% sea salt had high yellowness, glossiness, salty flavor, sweet flavor, and bitter flavor. Hierarchical cluster analysis classified the products into two clusters: sauerkraut of 0.5, 1.0, and 1.5%, and sauerkraut of 2.0 and 2.5%. Results of PLSR determined that sauerkraut of 1.0 and 1.5% were the closest to texture, taste, and overall acceptance. We, therefore, conclude that sauerkrauts prepared using 1.0 and 1.5% sea salt have excellent characteristics in appearance, taste, and texture.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1245-1245
• /
• 2001

Food adulteration is a serious consumer fraud and a matter of concern to food processors and regulatory agencies. A range of analytical methods have been investigated to facilitate the detection of adulterated or mis-labelled foods & food ingredients but most of these require sophisticated equipment, highly-qualified staff and are time-consuming. Regulatory authorities and the food industry require a screening technique which will facilitate fast and relatively inexpensive monitoring of food products with a high level of accuracy. Near infrared spectroscopy has been investigated for its potential in a number of authenticity issues including meat speciation (McElhinney, Downey & Fearn (1999) JNIRS, 7(3), 145-154; Downey, McElhinney & Fearn (2000). Appl. Spectrosc. 54(6), 894-899). This report describes further analysis of these spectral sets using a hierarchical approach and binary decisions solved using logistic regression. The sample set comprised 230 homogenized meat samples i. e. chicken (55), turkey (54), pork (55), beef (32) and lamb (34) purchased locally as whole cuts of meat over a 10-12 week period. NIR reflectance spectra were recorded over the wavelength range 400-2498nm at 2nm intervals on a NIR Systems 6500 scanning monochromator. The problem was defined as a series of binary decisions i. e. is the meat red or white\ulcorner is the red meat beef or lamb\ulcorner, is the white meat pork or poultry\ulcorner etc. Each of these decisions was made using an individual binary logistic model based on scores derived from principal component or partial least squares (PLS1 and PLS2) analysis. The results obtained were equal to or better than previous reports using factorial discriminant analysis, K-nearest neighbours and PLS2 regression. This new approach using a combination of exploratory and logistic analyses also appears to have advantages of transparency and the use of inherent structure in the spectral data. Additionally, it allows for the use of different data transforms and multivariate regression techniques at each decision step.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1152-1152
• /
• 2001

Food adulteration is a serious consumer fraud and a matter of concern to food processors and regulatory agencies. A range of analytical methods have been investigated to facilitate the detection of adulterated or mis-labelled foods & food ingredients but most of these require sophisticated equipment, highly-qualified staff and are time-consuming. Regulatory authorities and the food industry require a screening technique which will facilitate fast and relatively inexpensive monitoring of food products with a high level of accuracy. Near infrared spectroscopy has been investigated for its potential in a number of authenticity issues including meat speciation (McElhinney, Downey & Fearn (1999) JNIRS, 7(3), 145 154; Downey, McElhinney & Fearn (2000). Appl. Spectrosc. 54(6), 894-899). This report describes further analysis of these spectral sets using a hierarchical approach and binary decisions solved using logistic regression. The sample set comprised 230 homogenized meat samples i. e. chicken (55), turkey (54), pork (55), beef (32) and lamb (34) purchased locally as whole cuts of meat over a 10-12 week period. NIR reflectance spectra were recorded over the wavelength range 400-2498nm at 2nm intervals on a NIR Systems 6500 scanning monochromator. The problem was defined as a series of binary decisions i. e. is the meat red or white\ulcorner is the red meat beef or lamb\ulcorner, is the white meat pork or poultry\ulcorner etc. Each of these decisions was made using an individual binary logistic model based on scores derived from principal component or partial least squares (PLS1 and PLS2) analysis. The results obtained were equal to or better than previous reports using factorial discriminant analysis, K-nearest neighbours and PLS2 regression. This new approach using a combination of exploratory and logistic analyses also appears to have advantages of transparency and the use of inherent structure in the spectral data. Additionally, it allows for the use of different data transforms and multivariate regression techniques at each decision step.

• Journal of Wetlands Research
• /
• v.22 no.2
• /
• pp.106-112
• /
• 2020

Wetlands play an important function and role in hydrological, environmental, and ecological, aspects of the watershed. Water level in wetlands is essential for various analysis such as for the determination of wetland function and its effects on the environment. Since several wetlands are ungauged, research on wetland water level prediction are uncommon. Therefore, this study developed a water level prediction model using multiple regression analysis, principal component regression analysis, artificial neural network, and DNN to predict wetland water level. Geumjeong-Mountain Wetland located in Yangsan-city, Gyeongsangnam-do province was selected as the target area, and the water level measurement data from April 2017 to July 2018 was used as the dependent variable. On the other hand, hydrological and meteorological data were used as independent variables in the study. As a result of evaluating the predictive power, the water level prediction model using DNN was selected as the final model as it showed an RMSE value of 6.359 and an NRMSE value of 18.91%. This research study is believed to be useful especially as a basic data for the development of wetland maintenance and management techniques using the water level of the existing unmeasured points.

• Journal of the Korean Geotechnical Society
• /
• v.36 no.6
• /
• pp.5-15
• /
• 2020

This study deals with the use of porewater pressure transducers to evaluate the stability of a fill dam through the correlation between the porewater pressure and water level. As a result of performing principal component analysis on a total of eight porewater pressure transducers installed in the fill dam, they were distributed into three groups. It was found to be distributed as internal, external, and top based on seepage line in the dam body. The correlation coefficient between porewater pressures and water level in group A located inside the seepage line indicated 0.94 to 1.00 and they are showing a strong positive linear relationships. It indicates that maintenance of the dam is required by the porewater pressure transducers of the group A. In addition, a linear regression analysis was performed with the determination coefficients of the group A of 0.89 to 0.99. It was found that the pore water pressure can be predicted and the stability of the dam can be evaluated by comparing it with the currently measured values when the water level is fixed as an explanatory variable.