• Korean Journal of Agricultural Science
• /
• v.47 no.3
• /
• pp.633-644
• /
• 2020

Rice paper is an element of Vietnamese cuisine that can be used to wrap vegetables and meat. Rice and starch are the main ingredients of rice paper and their mixing ratio is important for quality control. In a commercial factory, assessment of food safety and quantitative supply is a challenging issue. A rapid and non-destructive monitoring system is therefore necessary in commercial production systems to ensure the food safety of rice and starch flour for the rice paper wrap. In this study, fluorescence hyperspectral imaging technology was applied to classify grain flours. Using the 3D hyper cube of fluorescence hyperspectral imaging (fHSI, 420 - 730 nm), spectral and spatial data and chemometric methods were applied to detect and classify flours. Eight flours (rice: 4, starch: 4) were prepared and hyperspectral images were acquired in a 5 (L) × 5 (W) × 1.5 (H) cm container. Linear discriminant analysis (LDA), partial least square discriminant analysis (PLSDA), support vector machine (SVM), classification and regression tree (CART), and random forest (RF) with a few preprocessing methods (multivariate scatter correction [MSC], 1^st and 2^nd derivative and moving average) were applied to classify grain flours and the accuracy was compared using a confusion matrix (accuracy and kappa coefficient). LDA with moving average showed the highest accuracy at A = 0.9362 (K = 0.9270). 1D convolutional neural network (CNN) demonstrated a classification result of A = 0.94 and showed improved classification results between mimyeon flour (MF)1 and MF2 of 0.72 and 0.87, respectively. In this study, the potential of non-destructive detection and classification of grain flours using fHSI technology and machine learning methods was demonstrated.

• Journal of Preventive Medicine and Public Health
• /
• v.52 no.3
• /
• pp.147-153
• /
• 2019

Objectives: The purpose of this study was to evaluate the association between body mass index (BMI) and severe lower urinary tract symptoms (LUTS) in Korean males. Methods: This study was conducted on males aged ${\geq}50years$ who participated in the 2011 Korean Community Health Survey. LUTS severity was assessed using the Korean version of the International Prostate Symptom Score (IPSS) questionnaire, and was dichotomized as severe (IPSS >19) and non-severe ($IPSS{\leq}19$). BMI was divided into 6 categories: <18.5, 18.5-22.9, 23.0-24.9, 25.0-27.4, 27.5-29.9, and ${\geq}30.0kg/m^2$. To evaluate the relationship between BMI and LUTS, a survey-weighted multivariate Poisson regression analysis was performed to estimate prevalence rate ratios (PRRs). Age, smoking status, alcohol intake, physical activity, educational level, household income, and comorbidities were adjusted for in the multivariate model. Results: A U-shaped relationship was detected between BMI and severe LUTS. Compared with a BMI of $23.0-24.9kg/m^2$, the PRR for a BMI < $18.5kg/m^2$ was 1.65 (95% confidence interval [CI], 1.35 to 2.02), that for a BMI of $18.5-22.9kg/m^2$ was 1.25 (95% CI, 1.09 to 1.44), that for a BMI of $25.0-27.4kg/m^2$ was 1.20 (95% CI, 1.00 to 1.45), that for a BMI of $27.5-29.9kg/m^2$ was 1.11 (95% CI, 0.83 to 1.47), and that for a BMI ${\geq}30.0kg/m^2$ was 1.85 (95% CI, 1.18 to 2.88). Conclusions: This study showed that both high and low BMI were associated with severe LUTS.

• Structural Engineering and Mechanics
• /
• v.60 no.3
• /
• pp.471-488
• /
• 2016

This study predicts the strength of rotary brace damper by analyzing a new set of probabilistic models using the usual method of multiple linear regressions (MLR) and advanced machine-learning methods of multivariate adaptive regression splines (MARS), Rotary brace damper can be easily assembled with high energy-dissipation capability. To investigate the behavior of this damper in structures, a steel frame is modeled with this device subjected to monotonic and cyclic loading. Several response parameters are considered, and the performance of damper in reducing each response is evaluated. MLR and MARS methods were used to predict the strength of this damper. Displacement was determined to be the most effective parameter of damper strength, whereas the thickness did not exhibit any effect. Adding thickness parameter as inputs to MARS and MLR models did not increase the accuracies of the models in predicting the strength of this damper. The MARS model with a root mean square error (RMSE) of 0.127 and mean absolute error (MAE) of 0.090 performed better than the MLR model with an RMSE of 0.221 and MAE of 0.181.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.577-582
• /
• 2002

Neural network can be trained to approximate an arbitrary nonlinear function of multivariate data like the mini-mill crown values in Automatic Shape Control. The trained weights of neural network can evaluate or generalize the process data outside the training vectors. Sometimes, the blind modeling of the process data is necessary to compare with the scattered analytical model of mini-mill process in isolated electro-mechanical forms. To come up with a viable model, we propose the blind neural-based range-division domain-clustering piecewise-linear modeling scheme. The basic ideas are: 1) dividing the range of target data, 2) clustering the corresponding input space vectors, 3)training the neural network with clustered prototypes to smooth out the convergence and 4) solving the resulting matrix equations with a pseudo-inverse to alleviate the ill-conditioning problem. The simulation results support the effectiveness of the proposed scheme and it opens a new way to the data analysis technique. By the comparison with the statistical regression, it is evident that the proposed scheme obtains better modeling error uniformity and reduces the magnitudes of errors considerably. Approximatly 10-fold better performance results.

• Journal of Korean Society for Quality Management
• /
• v.23 no.4
• /
• pp.28-41
• /
• 1995

We consider the problem of identifying multiple outliers in linear model. The available regression diagnostic methods often do not succeed in detecting multiple outliers because of the masking and swamping effect. Recently, among the various robust estimator of reducing the effect of outliers, LMS(Least Meadian Square) estimator has been to be a suitable method proposed to expose outliers and leverage points. However, as you know it, the data analysis method with LMS estimator is to be taken the median of the squared residuals in the sample which is extracted the sample space. Then this model causes the trouble, for the number of the chosen sample is nCp, i.e. as the size of sample space n is increasing, the number is increasing fastly. And the covariance matrix may be the singular matrix, so that matrix is approching collinearity. Thus we propose a procedure ELMS for the resampling in LMS method and study the size of the effective elementary set in this algorithm.

• Journal of Chest Surgery
• /
• v.27 no.10
• /
• pp.833-837
• /
• 1994

Lung contusion due to blunt chest trauma is the most common lung injury and correlated with the clinical course and prognosis. Its diagnosis by CT[Computerized Tomogram] gives a more clear and understandable three dimensional view, by which we are able to measure the volume of the contused and entire lung. Other variables are arterial blood gas, number of rib fracture, presence of hemopneumothorax, sternal fracture and clavicle fracture, number of associated non-thoracic injuries, ventilator time and presence of pulmonary complication. Percentage[%] of lung contusion are expressed as mean $\pm$ standard deviation and data analysis was performed by means of multivariate repeated measures analysis of variance to detect significant differences in variables between positive thoracic injury group and negative group. The paired t-test was used. Differences of percentage of lung contusion between groups were assessed by one-way analysis of variance. Simple linear regression was used to perform correlation analysis in the number of rib fracture and ventilator time. A p value less than 0.05 was considered statistically significant. Pneumothorax and the number of associated other injuries affect the amount of lung contusion and pulmonary complication group has more contused lung volume. Arterial blood gas study shows no correlation with the amount of lung contusion statistically. The number of rib fracture correlated with the amount of lung contusion, which also correlated with ventilator time[r=0.56, p<0.05]. In conclusion, quantitative anlysis of lung contusion by CT predicts the clinical course and treatment such as ventilator care.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.2
• /
• pp.673-676
• /
• 2016

Background: In the maxillofacial region, giant cell granulomas occur in 2 clinical forms, central and peripheral. Despite histopathological similarity between these 2 forms totally different clinical behaviors have been reported. The present study was undertaken to compare mast cell and vascular concentrations in these pathologic lesions. Materials and Methods: In this cross-sectional descriptive study, 20 pathological samples of central giant cell granuloma (CGCG) and 20 samples of peripheral giant cell granuloma (PGCG) were selected and examined through toluidine blue staining for mast cell assessment and immunohistochemical staining by VEGEF antibody for comparing the number of mast cells. T-test, chi-squared test and backward multivariate linear regression were used for statistical analysis using SPSS 20. Statistical significance was set at P<0.05. Results: This study showed significantly greater VEGF expression and mast cell concentrations in CGCG compared to PGCG cases. Also there was a significant correlation between VEGF expression and the concentration of mast cells. No relation was found between age, sex and site of the lesion and concentration of mast cells or VEGF expression. Conclusions: It is feasible that higher concentrations of mast cells in CGCG versus PGCG samples might lead to more aggressive clinical behavior via vascular proliferation and angiogenesis. However, other biologic mechanisms should be considered in this situation.

• Nutrition Research and Practice
• /
• v.7 no.5
• /
• pp.380-384
• /
• 2013

Zinc may participate in blood pressure regulation and in the pathogenesis of hypertension. The study examined the relationship between zinc status and blood pressure in obese Korean women. Forty obese women (body mass index (BMI) ${\geq}25kg/m^2$) aged 19-28 years participated in this study. Zinc intake was estimated from one 24 hour recall and 2-day diet records. Serum and urinary zinc concentrations were determined by atomic absorbance spectrophotometry. Systolic blood pressure (SBP) and diastolic blood pressure (DBP) were measured using an automatic sphygmometer. Metabolic variables, such as waist circumference, triglyceride, high density lipoprotein (HDL) cholesterol, fasting glucose, and fasting insulin, were also measured. Dietary zinc intake of obese women was averagely 7.5 mg/day. Serum zinc and urinary zinc concentrations were $13.4{\mu}mol/L$ and $378.7{\mu}g/day$, respectively. Averages of SBP and DBP were 119 mmHg and 78 mmHg. Dietary zinc intake was negatively correlated with SBP after adjusting for energy intake (P < 0.05), but serum and urinary zinc concentrations were not found to be correlated with SBP or DBP. Multivariate linear regression analysis showed that dietary zinc intake was inversely associated with SBP in obese women after adjusting for body weight, energy intake and sodium intake (P = 0.0145). The results show that dietary zinc intake may be an independent risk factor of elevated SBP in obese Korean women.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.16 no.2
• /
• pp.144-152
• /
• 2009

Purpose: The purpose of this study was to predict the risk factors for vascular complications among patients with type 2 diabetes. Method: The data were collected from August to September, 2007 using clinical examination and questionnaires. Patients (N=101) were recruited from the endocrinology department of P University hospital in D city. Descriptive statistics, Pearson correlation coefficients and multiple linear regression were used to analyze the data. Results: The cardiovascular risk of patients with diabetes was significantly related to self care behavior, family history, and smoking status. The risk of peripheral vascular complications was not related to predictors included in the study. With multivariate analyses, significant predictors of cardiovascular risk for these patients were self care behavior, family history, and smoking status ($R^2=.40$, p<.0001). Conclusion: The findings of this study indicate that smoking cessation and improving self-care behavior are essential to reduce the risk of cardiovascular complications among patients with diabetes. To enhance self-care practices for the patients with diabetes, nursing interventions, such as telephone counseling, problem focused nursing counseling, and peer group activities should be considered.

• Journal of Preventive Medicine and Public Health
• /
• v.47 no.2
• /
• pp.94-103
• /
• 2014

Objectives: The present study examined relationships between socioeconomic status (SES) and obesity and body mass index (BMI) as well as the effects of health-related behavioral and psychological factors on the relationships. Methods: A cross-sectional population-based study was conducted on Korean adults aged 20 to 79 years using data from the 2001, 2005, and 2007 to 2009 Korea National Health and Nutrition Examination Survey. Multivariate logistic and linear regression models were used to estimate odds ratios of obesity and mean differences in BMI, respectively, across SES levels after controlling for health-related behavioral and psychological factors. Results: We observed significant gender-specific relationships of SES with obesity and BMI after adjusting for all covariates. In men, income, but not education, showed a slightly positive association with BMI (p<0.05 in 2001 and 2005). In women, education, but not income, was inversely associated with both obesity and BMI (p<0.0001 in all datasets). These relationships were attenuated with adjusting for health-related behavioral factors, not for psychological factors. Conclusions: Results confirmed gender-specific disparities in the associations of SES with obesity and BMI among adult Korean population. Focusing on intervention for health-related behaviors may be effective to reduce social inequalities in obesity.