• 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.13 no.1
• /
• pp.199-203
• /
• 2012

Purpose: To evaluate the prognostic value of serum CYFRA21-1, CEA and hemoglobin levels regarding long-term survival of patients with esophageal squamous cell carcinoma (ESCC) treated with concurrent chemoradiotherapy (CRT). Methods: Age, gender, Karnofsky Performance Status (KPS), tumor location, tumor length, T stage, N stage and serum hemoglobin, and CYFRA21-1 and CEA levels before concurrent CRT were retrospectively investigated and related to outcome in 113 patients receiving 5-fluorouracil and cisplatin combined with radiotherapy for ESCC. The Kaplan-Meier method was used to analyze prognosis, the log-rank to compare groups, the Cox proportional hazards model for multivariate analysis, and ROC curve analysis for assessment of predictive performance of biologic markers. Results: The median survival time was 20.1 months and the 1-, 2-, 3-, 5- year overall survival rates were 66.4%, 43.4%, 31.9% and 15.0%, respectively. Univariate analysis showed that factors associated with prognosis were KPS, tumor length, T-stage, N-stage, hemoglobin, CYFRA21-1 and CEA level. Multivariate analysis showed T-stage, N-stage, hemoglobin, CYFRA21-1 and CEA level were independent predictors of prognosis. By ROC curve, CYFRA21-1 and hemoglobin showed better predictive performance for OS than CEA (AUC= 0.791, 0.704, 0.545; P=0.000, 0.000, 0.409). Conclusions: Of all clinicopathological and molecular factors, T stage, N stage, hemoglobin, CYFRA21-1 and CEA level were independent predictors of prognosis for patients with ESCC treated with concurrent CRT. Among biomarkers, CYFRA21-1 and hemoglobin may have a better predictive potential than CEA for long-term outcomes.

• Journal of Convergence for Information Technology
• /
• v.7 no.1
• /
• pp.55-60
• /
• 2017

In order to provide intelligent services without human intervention in the Internet of Things environment, it is necessary to analyze the big data generated by the IoT device and learn the normal pattern, and to predict the abnormal symptoms such as faulty or malfunction based on the learned normal pattern. The purpose of this study is to implement a machine learning model that can predict product failure by analyzing big data generated in various devices of product process. The machine learning model uses the big data analysis tool R because it needs to analyze based on existing data with a large volume. The data collected in the product process include the information about product faulty, so supervised learning model is used. As a result of the study, I classify the variables and variable conditions affecting the product failure, and proposed a prediction model for the product failure based on the decision tree. In addition, the predictive power of the model was significantly higher in the conformity and performance evaluation analysis of the model using the ROC curve.

• Physical Therapy Rehabilitation Science
• /
• v.7 no.3
• /
• pp.102-108
• /
• 2018

Objective: To investigate whether the Minimal Clinically Important Difference (MCID) clinically defines improvement of Berg Balance Scale (BBS) scores in people with acute stroke in response to rehabilitation. Design: Retrospective study. Methods: Seventy-three participants with acute stroke participated in the study. Balance evaluation was performed using the BBS. All patients received rehabilitation with physical therapy for 4 weeks, 5 times a week, for 2 hours and 20 minutes a day. An anchor-based approach using the clinical global impression was used to determine the MCID of the BBS. The MCID was used to define the minimum change in the BBS total score (postintervention-preintervention) that was needed to perceive at least a 3-point improvement on the global rating of change. Receiver operating characteristic (ROC) curves was used to define the cut-off values of the optimal MCID of the BBS in order to discriminate between improvement and no improvement groups. Results: The optimal MCID cut-off point for the BBS change scores was 12.5 points for males with a sensitivity (Sn) of 0.62 and a specificity (Sp) of 0.89, and 12.5 points for females with a Sn of 0.69 and Sp of 0.85. The area under the curve of the ROC curve for all participants were 0.84 (95% confidence interval [CI], 0.72; 0.95, p<0.001), and 0.89 (95% CI, 0.77; 1.00, p<0.001), respectively. Conclusions: The MCID for improvement in balance as measured by the BBS was 13.5 points, indicating that the MCID does clinically detect changes in balance abilities in persons with stroke.

• Journal of Korea Association of Health Promotion
• /
• v.4 no.1
• /
• pp.1-11
• /
• 2006

"본 논문은 대한외과학회지 2006년 제70권제1호에 실렸던 논문으로 대한외과학회 편집위원회 승인을 득하고 본 협회지에 게재함. Purpose: Malnutrition has been frequently reported for patients on their admission to the hospital and it has been associated with an increase in morbidity, mortality and the length of the hospital stay. Although a number of screening tools have been developed to identify those patients at risk for malnutrition, there is no' gold standard' for defining malnutrition and the malnourished patients remain largely unrecognized. The aim of this study is to evaluate the efficacy of a nutritional screening tool for use in Dankook University Hospital. Methods Nutritional evaluation was performed for 53 patients who were admitted to the department of surgery and internal medicine between October and December 2004. The screening tool was completed by the ward nurse and the nutritional support team nurse on the same patients within24 hours of admission. The nutritional support team nurse performed the full assessment. The screening sheet included 4 questions regarding body mass index, recent unintentional weight loss, food intake and disease severity. Each answer was scored and a total of 5 was tested as the criterion fey malnutrition. The full assessment included current body weight, recent weight loss, triceps skinfold thickness, mid-arm muscle circumference, serum albumin)in and total lymphocyte count. Malnutrition was defined by 3 or more values below the reference values. The reliability of the screening tool was assessed using kappa statistic. Sensitivity, specificity and accuracy were calculated to evaluate the validity of the screening tool. The receiver operating characteristic(ROC) curve was drawn to choose a cutoff valve that maximizes sensitivity and specificity. Results' The level of agreement between the ward nurse and the NST nurse was good for BMI and food intake and moderate for weight loss and disease severity. The full assessment identified7 patients(13.2%) as malnourished. The screening sheet had a sensitivity of 86% and a specificity of 80%. According to the ROC curve, a score of 5 points provided the best validity. Conclusion The nutritional screening tool is reliable when completed by different observers and it is valid for nutritional assessment.

• Korean Journal of Biological Psychiatry
• /
• v.12 no.2
• /
• pp.165-172
• /
• 2005

Objectives:The purpose of this study is to 1) conduct a discrimination analysis of schizophrenia and bipolar affective disorder using MMPI profile through artificial neural network analysis and logistic regression analysis, 2) to make a comparison between advantages and disadvantages of the two methods, and 3) to demonstrate the usefulness of artificial neural network analysis of psychiatric data. Procedure:The MMPI profiles for 181 schizophrenia and bipolar affective disorder patients were selected. Of these profiles, 50 were randomly placed in the learning group and the remaining 131 were placed in the validation group. The artificial neural network was trained using the profiles of the learning group and the 131 profiles of the validation group were analyzed. A logistic regression analysis was then conducted in a similar manner. The results of the two analyses were compared and contrasted using sensitivity, specificity, ROC curves, and kappa index. Results:Logistic regression analysis and artificial neural network analysis both exhibited satisfactory discriminating ability at Kappa index of greater than 0.4. The comparison of the two methods revealed artificial neural network analysis is superior to logistic regression analysis in its discriminating capacity, displaying higher values of Kappa index, specificity, and AUC(Area Under the Curve) of ROC curve than those of logistic regression analysis. Conclusion:Artificial neural network analysis is a new tool whose frequency of use has been increasing for its superiority in nonlinear applications. However, it does possess insufficiencies such as difficulties in understanding the relationship between dependent and independent variables. Nevertheless, when used in conjunction with other analysis tools which supplement it, such as the logistic regression analysis, it may serve as a powerful tool for psychiatric data analysis.

• Journal of The Korean Society of Clinical Toxicology
• /
• v.1 no.1
• /
• pp.27-33
• /
• 2003

Purpose: According as the accessibility about drugs becomes various, the occurrence of drug intoxication is increasing. Since report that doxylamine causes rhabdomyolysis often, drug-induced rhabdomyolysis is one of the most important complications in patients with drug intoxication. Acute renal failure (ARF)'s availability is important to the management in rhabdomyolysis, but report about rhabdomyolysis or ARF occurrence for whole intoxicated drugs is lacking up to now. Methods: This research did to 61 patient who had rhabdomyolysis of drug intoxication. First, object patients were divided into two gruops: doxylamine-ingested (Group I) vs non-doxylamine ingested (Group II). And then we analyzed on the early patient's clinical events and laboratory data. We used ROC curve to recognize'the early clinical factors that could forecast ARF appearance among these patients in addition. Results: Almost rhabdomyolysis was happened by doxylamine in drug intoxication ($55.7\%$). However, as compared to group II, group I showed better clinical course, lesser ARF occurrence and hemodialysis requirement. In group II, time was longer in hospital reaching from intoxication, the ARF occurrence rate was higher ($52.6\%$). Analyzing the ROC curve to useful initial factors, they were creatinine, uric acid and interval time from ingestion to hospital. These cut-off values were 1.44 mg/dL, 6.8 mg/dL and 5 hrs. Sensitivity for ARF estimate was $100\%$, specificity $69-98\%$. Conclusion: Compared to group II, Doxylamine-ingested group showed good clinical course. Creatinine, uric acid, interval time from ingestion to hospital aided in ARF estimate in drug-induced rhabdomyolysis.

• 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.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.21 no.2
• /
• pp.118-126
• /
• 2018

Purpose: Classical criteria for diagnosis of autoimmune hepatitis (AIH) are intended as research tool and are difficult to apply at patient's bedside. We aimed to study the accuracy of simplified criteria and the concordance with the expert diagnosis based on the original criteria. Methods: A cohort of children under study for liver disorder was selected through consecutive sampling to obtain the prevalence of AIH within the group of differential diagnoses. AIH was defined, based on classical criteria, through committee review of medical reports. Validity indicators of the simplified criteria were obtained in an intention to diagnose approach. Optimal cut-off and the area under the receiver operating characteristic (ROC) curve were calculated. Results: Out of 212 cases reviewed, 47.2% were AIH. For the optimal cut-off (6 points), the simplified criteria showed a sensitivity of 72.0% and a specificity of 96.4%, with a 94.7% positive and a 79.4% negative predictive value. The area under the ROC curve was 94.3%. There was a good agreement in the pre-treatment concordance between the classical and the simplified criteria (kappa index, 0.775). Conclusion: Simplified criteria provide a moderate sensitivity for the diagnosis of AIH, but may help in indicating treatment in cases under suspicion with 6 or more points.