• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.374-382
• /
• 2020

The purpose of this study is to improve the learning speed of an ammunition stockpile reliability classification artificial neural network model by proposing a normalization method that reduces the number of input variables based on the characteristic of Ammunition Stockpile Reliability Program (ASRP) data without loss of classification performance. Ammunition's performance requirements are specified in the Korea Defense Specification (KDS) and Ammunition Stockpile reliability Test Procedure (ASTP). Based on the characteristic of the ASRP data, input variables can be normalized to estimate the lot percent nonconforming or failure rate. To maintain the unitary hypercube condition of the input variables, min-max normalization method is also used. Area Under the ROC Curve (AUC) of general min-max normalization and proposed 2-step normalization is over 0.95 and speed-up for marching learning based on ASRP field data is improved 1.74 ~ 1.99 times depending on the numbers of training data and of hidden layer's node.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.5
• /
• pp.2507-2511
• /
• 2016

Purpose: To study the diagnostic accuracies of serum human epididymis protein 4 (HE-4) levels, virtual organ computer-aided analysis (VOCAL) parameters and endometrial volume in endometrial cancer cases. Materials and Methods: One hundred and seven patients (37 with endometrial cancer and 70 with benign endometrial pathology) were included in this study. VOCAL parameters and serum HE-4 levels were compared between the groups. Results: Area under the curve (AUC) values were 0.702, 0.658, 0.706 for vascularization index (VI), the flow index (FI) and the vascularization flow index (VFI), respectively. A cut off value of 0.568 for VI demonstrated 70% sensitivity, 72% specificity, 56% positive predictive value (PPV) and a81% negative predictive value (NPV). A cut off value of 25.8 for showed a senitivith of 70% and a specificity of 58% with aPPV of 46% and NPV of 78%, and with a cut off value of 0.12 for VFI 70%, 69%, 54% and 81%, respectively. The area under the curve for HE-4 was 0.814. A cut off value of 458 pmol/L was predictive of malignancy with 86% sensitivity and 63% specificity. Conclusions: VOCAL parameters and serum HE-4 levels were statistically significantly higher in the endometrial cancer patients. Serum HE-4 levels provided a greater sensitivity compared to power doppler angiography for predicting malignancy or benign endometrial pathology.

• Physical Therapy Rehabilitation Science
• /
• v.6 no.4
• /
• pp.176-181
• /
• 2017

Objective: The timed up and go (TUG) test is method used to determine the functional mobility of persons with stroke. Its reliability, validity, reaction rate, fall prediction, and psychological characteristics concerning ambulation ability have been validated. However, the relationship between TUG performance and community ambulation ability is unclear. The purpose of this study was to investigate whether the TUG performance time could indicate community ambulation levels (CAL) differentially in persons with chronic stroke. Design: Cross-sectional study. Methods: Eighty-seven stroke patients had participated in this study. Based on the self-reporting survey results on the difficulties experienced when walking outdoors, the subjects were divided into the independent community ambulation (ICA) group (n=35) and the dependent community ambulation group (n=52). Based on the area under the curve (AUC), the discrimination validity of the TUG performance time was calculated for classifying CAL. The Binomial Logistic Regression Model was utilized to produce the likelihood ratio of selected TUG cut-off values for the distinguishing of community ambulation ability. Results: The selected TUG cut-off values and the area under the curve were <14.87 seconds (AUC=0.871, 95% confidence interval=0.797-0.945), representing a mid-level accuracy. Concerning the likelihood ratio of the selected TUG cut-off value, it was found that the group with TUG performance times shorter than 14.87 seconds showed a 2.889 times higher probability of ICA than those with a TUG score of 14.87 seconds or longer (p<0.05). Conclusions: The TUG can be viewed as an assessment tool that is capable of classifying CAL.

• Research in Community and Public Health Nursing
• /
• v.22 no.3
• /
• pp.302-314
• /
• 2011

Purpose: This study aimed to validate instruments to classify the frailty of Korean elderly people in community. Methods: For this study, 632 elders were selected from community-based elderly houses and home visiting registries, and data on frailty were collected using three instruments during November, 2008. The Korean Frail Scale (KFS) was composed of 10 domains with the maximum score of 20. The Edmonton Frail Scale (EFS) had 10 domains with the maximum score of 17. The 25_Japan Frail Scale (25_JFS) was composed of 6 domains with the maximum score of 25. Internal consistency was measured with Cronbach's ${\alpha}$. Sensitivity, specificity and area under the curve (AUC) of ROC were measured to see validity with long.term care insurance grade as a gold standard. Results: The Cronbach's ${\alpha}$ was .72 for KFS, .55 for EFS, and .80 for 25_JFS. Sensitivity, specificity, and AUC were 70.0%, 83.2%, and .83, respectively, at cutting point 10.5 for the KFS, 50.0%, 80.9%, and .66, respectively, at 8.5 for EFS, and 80.0%, 85.9%, and .86, respectively, at 12.5 for 25_JFS. Conclusion: KFS and three JFS showed favorable internal consistency and predictive validity. Further longitudinal studies are recommended to confirm predictive validity.

• The Korean Journal of Applied Statistics
• /
• v.28 no.3
• /
• pp.495-509
• /
• 2015

We study a classification problem of significant differences in the proportion of two groups known as the unbalanced classification problem. It is usually more difficult to classify classes accurately in unbalanced data than balanced data. Most observations are likely to be classified to the bigger group if we apply classification methods to the unbalanced data because it can minimize the misclassification loss. However, this smaller group is misclassified as the larger group problem that can cause a bigger loss in most real applications. We compare several classification methods for the unbalanced data using sampling techniques (up and down sampling). We also check the total loss of different classification methods when the asymmetric loss is applied to simulated and real data. We use the misclassification rate, G-mean, ROC and AUC (area under the curve) for the performance comparison.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.1
• /
• pp.22-29
• /
• 2016

Many studies in detection and classification of the targets in the underwater environments have been conducted for military purposes, as well as for non-military purpose. Due to the complicated characteristics of underwater acoustic signal reflecting multipath environments and spatio-temporal varying characteristics, active sonar target detection technique has been considered as a difficult technique. In this paper, we describe the basic concept of Fractional Fourier transform and optimal transform order. Then we analyze the relationship between time-frequency characteristics of an LFM signal and its spectrum using Fractional Fourier transform. Based on the analysis results, we present active sonar target detection method. To verify the performance of proposed methods, we compared the results with conventional FFT-based matched filter. The experimental results demonstrate the superiority of the proposed method compared to the conventional method in the aspect of AUC(Area Under the ROC Curve).

• Clinical and Experimental Pediatrics
• /
• v.59 no.3
• /
• pp.139-144
• /
• 2016

Purpose: Acute pyelonephritis (APN) is a serious bacterial infection that can cause renal scarring in children. Early identification of APN is critical to improve treatment outcomes. The neutrophil-lymphocyte ratio (NLR) is a prognostic marker of many diseases, but it has not yet been established in urinary tract infection (UTI). The aim of this study was to determine whether NLR is a useful marker to predict APN or vesicoureteral reflux (VUR). Methods: We retrospectively evaluated 298 pediatric patients ($age{\leq}36months$) with febrile UTI from January 2010 to December 2014. Conventional infection markers (white blood cell [WBC] count, erythrocyte sedimentation rate [ESR], C-reactive protein [CRP]), and NLR were measured. Results: WBC, CRP, ESR, and NLR were higher in APN than in lower UTI (P<0.001). Multiple logistic regression analyses showed that NLR was a predictive factor for positive dimercaptosuccinic acid (DMSA) defects (P<0.001). The area under the receiver operating characteristic (ROC) curve was high for NLR (P<0.001) as well as CRP (P<0.001) for prediction of DMSA defects. NLR showed the highest area under the ROC curve for diagnosis of VUR (P<0.001). Conclusion: NLR can be used as a diagnostic marker of APN with DMSA defect, showing better results than those of conventional markers for VUR prediction.

• The Journal of Internal Korean Medicine
• /
• v.35 no.1
• /
• pp.50-58
• /
• 2014

Objectives : The aim of this study was to analyze relationship between post-stroke depression (PSD) and cold, heat, deficiency and excess patterns. Methods : Twenty-eight PSD patients were recruited from STROKE center and measured with questionnaires for cold, heat, deficiency and excess patternvalues and saliva for cortisol awakening response (CAR). Saliva samples were collected immediately, 15, 30 and 45 min after awakening. In addition, Beck Depression Inventory (BDI) and Hamilton Depression Rating Scale (HDRS) were conducted for PSD severity. We conducted correlation analysis to find the relationship between cold, heat, deficiency and excess patterns and CAR or BDI and HDRS. Results : Deficiency and excess patterns werepositively correlated with area under the curve with respect to the increase (AUCi), but not with area under the curve with respect to the global (AUCg), in CAR. Furthermore, it was negatively correlated with BDI and HDRS, while cold and heat patterns were not correlated with CAR, BDI and HDRS. Conclusions : In terms of deficiency and excess patterns, the higher the PSD severity, the higher the deficiency and the lower the PSD severity, the higher the excess. However, there was not a significant relationship between PSD and cold and heat patterns.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.11
• /
• pp.6327-6330
• /
• 2013

Haematuria is a common presentation of bladder cancer and requires a full urologic evaluation. This study aimed to develop a scoring system capable of stratifying patients with haematuria into high or low risk groups for having bladder cancer to help clinicians decide which patients need more urgent assessment. This cross-sectional study included all adult patients referred for haematuria and subsequently undergoing full urological evaluation in the years 2001 to 2011. Risk factors with strong association with bladder cancer in the study population were used to design the scoring system. Accuracy was determined by the area under the receiver operating characteristic (ROC) curve. A total of 325 patients with haematuria were included, out of which 70 (21.5%) were diagnosed to have bladder cancer. Significant risk factors associated with bladder cancer were male gender, a history of cigarette smoking and the presence of gross haematuria. A scoring system using 4 clinical parameters as variables was created. The scores ranged between 6 to 14, and a score of 10 and above indicated high risk for having bladder cancer. It was found to have good accuracy with an area under the ROC curve of 80.4%, while the sensitivity and specificity were 90.0% and 55.7%, respectively. The scoring system designed in this study has the potential to help clinicians stratify patients who present with haematuria into high or low r isk for having bladder cancer. This will enable high-risk patients to undergo urologic assessment earlier.

• Nutrition Research and Practice
• /
• v.8 no.4
• /
• pp.469-475
• /
• 2014

BACKGROUND/OBJECTIVE: The goal of the present study was to investigate the effects of moderate caloric restriction on ${\beta}$-cell function and insulin sensitivity in middle-aged obese Korean women. SUBJECTS/METHODS: Fifty-seven obese pre-menopausal Korean women participated in a 12-week calorie restriction program. Data on total cholesterol (TC), high density lipoprotein cholesterol (HDL-C), low density lipoprotein cholesterol (LDL-C), triglycerides (TG), and fasting serum levels of glucose, insulin, C-peptide, blood pressure, leptin and anthropometrics were collected. A dietary intake assessment was based on three days of food recording. Additionally, ${\beta}$-cell function [homeostasis model assessment of ${\beta}$-cell (HOMA-${\beta}$), insulinogenic index (ISI), C-peptide:glucose ratio, and area under curve insulin/glucose ($AUC_{ins/glu}$)] and insulin sensitivity [homeostasis model assessment for insulin resistance (HOMA-IR), Quantitative insulin-sensitivity check index (QUICKI) and Matsuda index (MI)] were recorded. RESULTS: When calories were reduced by an average of 422 kcal/day for 12 weeks, BMI (-2.7%), body fat mass (-10.2%), and waist circumference (-5%) all decreased significantly (P < 0.05). After calorie restriction, weight, body fat percentage, hip circumference, BP, TC, HDL-C, LDL-C, plasma glucose at fasting, insulin at fasting and 120 min, $AUC_{glu}$ and the insulin area under the curve all decreased significantly (all P < 0.05), while insulin sensitivity (HOMA-IR, QUICKI and Matsuda index) measured by OGTT improved significantly (P < 0.01). CONCLUSIONS: Moderate weight loss due to caloric restriction with reduction in insulin resistance improves glucose tolerance and insulin sensitivity in middle-aged obese women and thereby may help prevent the development of type 2 diabetes mellitus.