• 응용통계연구
• /
• 제18권1호
• /
• pp.83-98
• /
• 2005

다변량 자료를 분석하는 데 있어서 관측 개체들의 분포적 양태를 파악하는 것은 자료 특성의 이해에 도움이 될 뿐만 아니라 이후 모형화 과정에도 큰 도움을 준다. 이를 위하여 다변량자료의 저차원 시각화에 대한 많은 연구가 진행되어 왔다. 그 중 하나가 코호넨(T. Kohonen)의 자기조직화지도(Self-Organizing Map; SOM)이다. SOM은 저차원 그리드 공간에 고차원 다변량 자료를 축약하여 시각적으로 나타내는 비지도 학습법의 일종으로 최근 들어 통계 분석자들이 많은 관심을 가지고 있는 분야이다. 그러나 SOM은 개체공간의 연속형으로 표현되는 개체를 저차원 그리드 공간에 승자노드에 의해 비연속적으로 표현한다는 단점을 지니고 있다. 본 논문에서는 SOM을 통계적 목적으로 사용하기 위해 요구되는 그리드 공간에 개체를 연속적으로 표현하는 방법들을 제안하고 환용 예를 제시 하고자 한다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.

• Journal of Korean Neurosurgical Society
• /
• 제46권2호
• /
• pp.123-129
• /
• 2009

Objective: This study was aimed to identify the incidence and risk factors of vancomycin-resistant enterococcus (VRE) colonization in neurosurgical practice of field, with particular attention to intensive care unit (ICU). Methods: This retrospective study was carried out on the Neurosurgical ICU (NICU), during the period from January. 2005 to December. 2007, in 414 consecutive patients who had been admitted to the NICU. Demographics and known risk factors were retrieved and assessed by statistical methods. Results: A total of 52 patients had VRE colonization among 414 patients enrolled, with an overall prevalence rate of 6.1%. E. faecium was the most frequently isolated pathogen, and 92.3% of all VRE were isolated from urine specimen. Active infection was noticed only in 2 patients with bacteremia and meningitis. Relative antibiotic agents were third-generation cephalosporin in 40%, and vancomycin in 23%, and multiple antibiotic usages were also identified in 13% of all cases. Multivariate analyses showed Glasgow coma scale (GCS) score less than 8, placement of Foley catheter longer than 2 weeks, ICU stay over 2 weeks and presence of nearby VRE-positive patients had a significantly independent association with VRE infection. Conclusion: When managing the high-risk patients being prone to be infected VRE in the NICU, extreme caution should be paid upon. Because prevention and outbreak control is of ultimate importance, clinicians should be alert the possibility of impending colonization and infection by all means available. The most crucial interventions are careful hand washing, strict glove handling, meticulous and active screening, and complete segregation.

• Asian-Australasian Journal of Animal Sciences
• /
• 제31권11호
• /
• pp.1700-1713
• /
• 2018

Objective: The aim of this study was to verify the usefulness of artificial neural networks (ANN), multivariate adaptive regression splines (MARS), naïve Bayes classifier (NBC), general discriminant analysis (GDA), and logistic regression (LR) for dystocia detection in Polish Holstein-Friesian Black-and-White heifers and cows and to indicate the most influential predictors of calving difficulty. Methods: A total of 1,342 and 1,699 calving records including six categorical and four continuous predictors were used. Calving category (difficult vs easy or difficult, moderate and easy) was the dependent variable. Results: The maximum sensitivity, specificity and accuracy achieved for heifers on the independent test set were 0.855 (for ANN), 0.969 (for NBC), and 0.813 (for GDA), respectively, whereas the values for cows were 0.600 (for ANN), 1.000 and 0.965 (for NBC, GDA, and LR), respectively. With the three categories of calving difficulty, the maximum overall accuracy for heifers and cows was 0.589 (for MARS) and 0.649 (for ANN), respectively. The most influential predictors for heifers were an average calving difficulty score for the dam's sire, calving age and the mean yield of the farm, where the heifer was kept, whereas for cows, these additionally included: calf sex, the difficulty of the preceding calving, and the mean daily milk yield for the preceding lactation. Conclusion: The potential application of the investigated models in dairy cattle farming requires, however, their further improvement in order to reduce the rate of dystocia misdiagnosis and to increase detection reliability.

• 응용통계연구
• /
• 제30권6호
• /
• pp.943-955
• /
• 2017

전화를 이용한 19대 대선 선거예측조사에서 ARS 조사비율과 무선전화 조사비율을 달리함에 따라 조사결과가 어떻게 달라지는가를 보았다. 조사방법이 조사결과에 미치는 효과를 추정하는 인과연구를 시도하였으며, 이를 위해 변수들 사이의 인과관계를 가정하는 인과 그래프를 그린 다음 모형에 포함시켜야 할 변수와 포함시키면 안 되는 변수를 판단하였다. 조사를 실시한 조사기관은 중첩변수로서 모형에 포함시켜야 하는 변수이며 응답률은 모형에 포함시키면 안 되는 변수임을 설명하였다. ARS 조사비율의 효과는 자료 한계 때문에 추정할 수 없었으며, 무선전화 조사비율이 약 90%를 넘지 않으면 효과에 별 차이가 없으나 전체 조사를 무선전화로만 실시하면 문재인후보지지율이 높아진다.

• Journal of Biosystems Engineering
• /
• 제40권2호
• /
• pp.124-136
• /
• 2015

Purpose: Grain quality is a general concept that covers many characteristics, ranging from physical to biochemical and physiochemical properties. Rice aging during storage is currently a challenge in the rice industry, and is a complicated process involving changes in all of the above properties. Spectroscopic techniques can be used to obtain information on the quality of rice samples in a non-destructive manner. Methods: The objective of this review was to highlight the factors that contribute to rice quality and aging, and to describe various spectroscopic modalities, particularly vibrational and hyperspectral imaging, for the assessment of rice quality. Results: Starch and protein are the main components of the rice endosperm, and are therefore key factors contributing to eating and cooking quality. While the overall starch, protein, and lipid content in the rice grain remains essentially unchanged during storage, structural changes do occur. These changes affect pasting and gel properties, and ultimately the flavor of cooked rice. In addition, grain quality is significantly affected by growing and environmental conditions, such as water availability, temperature, fertilizer application, and salinity stress. These properties can be evaluated using spectroscopic techniques, and rice samples can be discriminated by using multivariate statistical analysis methods. Conclusion: Hyperspectral imaging and vibrational spectroscopy techniques have good potential for determining rice quality properties in a non-invasive manner, i.e., not requiring the introduction of instruments into the rice grain.

• Gut and Liver
• /
• 제12권6호
• /
• pp.704-713
• /
• 2018

Background/Aims: Gastric varices (GVs) are a major cause of upper gastrointestinal bleeding in patients with liver cirrhosis. The current treatments of choice are balloon-occluded retrograde transvenous obliteration (BRTO) and the placement of a transjugular intrahepatic portosystemic shunt (TIPS). We aimed to compare the efficacy and outcomes of these two methods for the management of GV bleeding. Methods: This retrospective study included consecutive patients who received BRTO (n=157) or TIPS (n=19) to control GV bleeding from January 2005 to December 2014 at a single tertiary hospital in Korea. The overall survival (OS), immediate bleeding control rate, rebleeding rate and complication rate were compared between patients in the BRTO and TIPS groups. Results: Patients in the BRTO group showed higher immediate bleeding control rates (p=0.059, odds ratio [OR]=4.72) and lower cumulative rebleeding rates (logrank p=0.060) than those in the TIPS group, although the difference failed to reach statistical significance. There were no significant differences in the rates of complications, including pleural effusion, aggravation of esophageal varices, portal hypertensive gastropathy, and portosystemic encephalopathy, although the rate of the progression of ascites was significantly higher in the BRTO group (p=0.02, OR=7.93). After adjusting for several confounding factors using a multivariate Cox analysis, the BRTO group had a significantly longer OS (adjusted hazard ratio [aHR]=0.44, p=0.01) and a longer rebleeding-free survival (aHR=0.34, p=0.001) than the TIPS group. Conclusions: BRTO provides better bleeding control, rebleeding-free survival, and OS than TIPS for patients with GV bleeding.

• 응용통계연구
• /
• 제37권3호
• /
• pp.283-295
• /
• 2024

무응답을 적절히 처리하기 위한 많은 방법이 연구되었다. 최근 다수의 무응답 대체법이 개발되고 실질적으로 사용되고 있다. 기존에 발표된 다수의 방법은 MCAR (missing completely at random) 또는 MAR (missing at random) 가정을 사용하고 있다. 그러나 관심변수에 영향을 받는 MNAR (missing not at random) 또는 무시할 수 없는 무응답(non-ignorable non-response; NN)은 편향을 발생시켜 대체 결과의 정확성을 크게 떨어뜨리지만 이에 관한 연구는 상대적으로 미미하다. Lee와 Shin (2022)은 등분산 가정하에서 무시할 수 없는 무응답을 적절히 처리할 수 있는 편향수정 무응답 대체법을 제안하였다. 본 연구에서는 Lee와 Shin (2022)이 제안한 방법을 확장한 무응답 대체법으로 초모집단 모형의 오차가 이분산인 경우에서 편향을 제거함으로써 추정의 정확성을 향상하는 방법을 제안하였다. 모의실험을 이용하여 제안된 방법의 타당성을 확인하였다.

• Journal of Trauma and Injury
• /
• 제25권2호
• /
• pp.49-56
• /
• 2012

Purpose: For determining the prognosis of critically injured patients, transporting patients to medical facilities capable of providing proper assessment and management, running rapid assessment and making rapid decisions, and providing aggressive resuscitation is vital. Considering the high mortality and morbidity rates in critically injured patients, various studies have been conducted in efforts to reduce those rates. However, studies related to diagnostic factors for predicting severity in critically injured patients are still lacking. Furthermore, patients showing stable vital signs and alert mental status, who are injured via a severe trauma mechanism, may be at a risk of not receiving rapid assessment and management. Thus, this study investigates diagnostic factors, including physical examination and laboratory results, that may help predict severity in trauma patients injured via a severe trauma mechanism, but showing stable vital signs. Methods: From March 2010 to December 2011, all trauma patients who fit into a diagnostic category that activated a major trauma team in CHA Bundang Medical Center were analyzed retrospectively. The retrospective analysis was based on prospective medical records completed at the time of arrival in the emergency department and on sequential laboratory test results. PASW statistics 18(SPSS Inc., Chicago, IL, USA) was used for the statistical analysis. Patients with relatively stable vital signs and alert mental status were selected based on a revised trauma score of more than 7 points. The final diagnosis of major trauma was made based on an injury severity score of greater than 16 points. Diagnostic variables include systolic blood pressure and respiratory rate, glasgow coma scale, initial result from focused abdominal sonography for trauma, and laboratory results from blood tests and urine analyses. To confirm the true significance of the measured values, we applied the Kolmogorov-Smirnov one sample test and the Shapiro-Wilk test. When significance was confirmed, the Student's t-test was used for comparison; when significance was not confirmed, the Mann-Whitney u-test was used. The results of focused abdominal sonography for trauma (FAST) and factors of urine analysis were analyzed using the Chi-square test or Fisher's exact test. Variables with statistical significance were selected as prognostics factors, and they were analyzed using a multivariate logistics regression model. Results: A total of 269 patients activated the major trauma team. Excluding 91 patients who scored a revised trauma score of less than 7 points, 178 patients were subdivided by injury severity score to determine the final major trauma patients. Twenty-one(21) patients from 106 major trauma patients and 9 patients from 72 minor trauma patients were also excluded due to missing medical records or untested blood and urine analysis. The investigated variables with p-values less than 0.05 include the glasgow coma scale, respiratory rate, white blood cell count (WBC), serum AST and ALT, serum creatinine, blood in spot urine, and protein in spot urine. These variables could, thus, be prognostic factors in major trauma patients. A multivariate logistics regression analysis on those 8 variables showed the respiratory rate (p=0.034), WBC (p=0.005) and blood in spot urine (p=0.041) to be independent prognostic factors for predicting the clinical course of major trauma patients. Conclusion: In trauma patients injured via a severe trauma mechanism, but showing stable vital signs and alert mental status, the respiratory rate, WBC count and blood in the urine can be used as predictable factors for severity. Using those laboratory results, rapid assessment of major trauma patients may shorten the time to diagnosis and the time for management.

• Korean Chemical Engineering Research
• /
• 제48권5호
• /
• pp.589-597
• /
• 2010

하수처리 시스템에서의 생물학적 영양염류 기준이 강화됨에 따라, 표준활성슬러지공법으로 운전 중인 하수처리장의 고도처리 공법으로의 개보수 필요성이 증가하고 있다. 그러나 실제 하수처리 시스템에서의 다양한 유입조건 및 운전조건의 복잡한 반응 구성으로 인해 실험을 통하여 개보수된 고도처리공법의 최적조건을 찾는 것은 쉽지 않은 일이며, 이는 많은 시간과 비용을 소모하여 비효율적이다. 따라서 본 연구에서는 활성슬러지공정모델(ASMs)을 기반으로 한 하수처리장의 모델링 및 시뮬레이션 기법을 통하여 하수처리장의 고도처리공법으로의 upgrading 설계를 수행하며, 이를 통계적이며 체계적으로 접근하기 위해 반응표면분석법(Response surface method)을 통한 고도처리공법의 설계 최적화를 수행하였다. 또한 실규모 하수처리장에서의 운전 최적화를 위해서는 하수처리의 동력학적 매개변수에 대한 정확한 분석이 수행되어야 한다. 본 연구에서는 다변량 통계분석 기법인 부분최소승자법(PLS)을 통하여 하수처리 시스템의 동력학적 매개변수 간의 상관관계를 파악하며, 고도처리공법 하수처리장의 운전 결과에 가장 큰 영향을 미치는 매개변수를 도출하였다. 본 연구를 통해 하수처리장의 고도처리공법 upgrading 설계 및 운전 최적화를 위한 방법론을 제시하였으며, 이를 통하여 설계시간 및 경비 절감 등 고도처리공법으로의 고효율적인 개보수가 가능할 것으로 예상된다.