• Genomics & Informatics
• /
• 제14권4호
• /
• pp.138-148
• /
• 2016

The success of genome-wide association studies (GWASs) has enabled us to improve risk assessment and provide novel genetic variants for diagnosis, prevention, and treatment. However, most variants discovered by GWASs have been reported to have very small effect sizes on complex human diseases, which has been a big hurdle in building risk prediction models. Recently, many statistical approaches based on penalized regression have been developed to solve the "large p and small n" problem. In this report, we evaluated the performance of several statistical methods for predicting a binary trait: stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN). We first built a prediction model by combining variable selection and prediction methods for type 2 diabetes using Affymetrix Genome-Wide Human SNP Array 5.0 from the Korean Association Resource project. We assessed the risk prediction performance using area under the receiver operating characteristic curve (AUC) for the internal and external validation datasets. In the internal validation, SLR-LASSO and SLR-EN tended to yield more accurate predictions than other combinations. During the external validation, the SLR-SLR and SLR-EN combinations achieved the highest AUC of 0.726. We propose these combinations as a potentially powerful risk prediction model for type 2 diabetes.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제6권6호
• /
• pp.303-308
• /
• 2017

생활 수준의 향상 및 소비자들의 건강에 대한 관심의 증가로 인해 자신의 건강에 대해서 스스로 결정하고자 하는 요구가 점차 증가하고 있다. 이로 인해 개인 맞춤형 의료에 대한 요구가 높아지고 있으며 각종 의료 정보를 기반으로 하는 질병 진단에 대한 연구가 많이 진행되고 있다. 하지만 기존의 연구들은 특정 질환과 관련된 데이터를 이용한 특정 질환 예측을 위한 것으로 진료과목을 예측한 연구는 없었다. 본 논문에서는 국민건강정보데이터를 이용하여 진료과목 예측에 관한 연구를 진행하였다. 실험 결과에서 보여주다시피 일반 건강검진 데이터를 이용하여 진료과목을 예측한 결과 평균 80% 이상의 정확도를 보여 주고 있으며 SVM은 다른 예측 알고리즘들보다 뛰어난 성능을 보여 주었다.

• 한국정밀공학회지
• /
• 제10권3호
• /
• pp.69-80
• /
• 1993

It is important to prevent roll failure in hot rolling process for reducing maintenance coat and production loss. Roll material and rolling conditions such as the roll force and torque have been intensively investigated to overcome the roll failures. In this study, a computer roll life prediction system under working condition is developed and evaluated on IBM-PC level. The system is composed and fatigue estimation models which are stress analysis, crack propagation, wear and fatigue estimation. Roll damage can be predicted by calculating the stress anplification, crack depth propagation and fatigue level in the roll using this computer model. The developed system is applied to a work roll in actual hot rolling process for reliability evaluation. Roll failures can be diagnosed and the propriety of current working condition can be determined through roll life prediction simulation.

• 한국멀티미디어학회논문지
• /
• 제20권11호
• /
• pp.1811-1819
• /
• 2017

As the induction motor is the core production equipment of the industry, it is necessary to construct a fault prediction and diagnosis system through continuous monitoring. Many researches have been conducted on motor fault diagnosis algorithm based on signal processing techniques using Fourier transform, neural networks, and fuzzy inference techniques. In this paper, we propose a fault diagnosis method of induction motor using LPC and DNN. To evaluate the performance of the proposed method, the fault diagnosis was carried out using the vibration data of the induction motor in steady state and simulated various fault conditions. Experimental results show that the learning time of our proposed method and the conventional spectrum+DNN method is 139 seconds and 974 seconds each executed on the experimental PC, and our method reduces execution time by 1/8 compared with conventional method. And the success rate of the proposed method is 98.08%, which is similar to 99.54% of the conventional method.

• 대한의용생체공학회:의공학회지
• /
• 제33권1호
• /
• pp.1-7
• /
• 2012

Hemorrhagic shock is a common cause of death in emergency rooms. Early diagnosis of hemorrhagic shock makes it possible for physicians to treat patients successfully. Therefore, the purpose of this study was to select an optimal survival prediction model using physiological parameters for the two analyzed periods: two and five minutes before and after the bleeding end. We obtained heart rates, mean arterial pressures, respiration rates and temperatures from 45 rats. These physiological parameters were used for the training and testing data sets of survival prediction models using an artificial neural network (ANN) and support vector machine (SVM). We applied a 5-fold cross validation method to avoid over-fitting and to select the optimal survival prediction model. In conclusion, SVM model showed slightly better accuracy than ANN model for survival prediction during the entire analysis period.

• 한국태양에너지학회 논문집
• /
• 제39권6호
• /
• pp.55-65
• /
• 2019

With the rapid development of the national industry, the importance of electrical safety was recognized because of a lot of new electrical equipment are installing and the electrical accidents have been occurring annually. Today, the electrical equipments is inspect by using the portable Infrared thermal imaging camera. but the most negative element of using the camera is inspected for only state of heating, the reliable diagnosis is depended with inspector's knowledge, and real-time monitoring is impossible. This paper present the infrared thermal imaging safety diagnosis system. This system is able to monitor in real time, predict the state of fault, and diagnose the state with analysis of thermal and power data. The system consists of a main processor, an infrared camera module, the power data acquisition board, and a server. The diagnostic algorithm is based on a mathematical model designed by analyzing the Pearson's Correlation Coefficient between temperature and power data. To test the prediction algorithm, the simulations were performed by damaging the terminals or cables on the switchboard to generate a large amount of heat. Utilizing these simulations, the developed prediction algorithm was verified.

• 대한의용생체공학회:의공학회지
• /
• 제32권2호
• /
• pp.134-143
• /
• 2011

The selection of meaningful clinical tests and its reference values from a high-dimensional clinical data with imbalanced class distribution, one class is represented by a large number of examples while the other is represented by only a few, is an important issue for differential diagnosis between similar diseases, but difficult. For this purpose, this study introduces methods based on the concepts of both discernibility matrix and function in rough set theory (RST) with two discretization approaches, equal width and frequency discretization. Here these discretization approaches are used to define the reference values for clinical tests, and the discernibility matrix and function are used to extract a subset of significant clinical tests from the translated nominal attribute values. To show its applicability in the differential diagnosis problem, we have applied it to extract the significant clinical tests and its reference values between normal (N = 351) and abnormal group (N = 101) with either cholecystitis or cholelithiasis disease. In addition, we investigated not only the selected significant clinical tests and the variations of its reference values, but also the average predictive accuracies on four evaluation criteria, i.e., accuracy, sensitivity, specificity, and geometric mean, during l0-fold cross validation. From the experimental results, we confirmed that two discretization approaches based rough set approximation methods with relative frequency give better results than those with absolute frequency, in the evaluation criteria (i.e., average geometric mean). Thus it shows that the prediction model using relative frequency can be used effectively in classification and prediction problems of the clinical data with imbalanced class distribution.

• KNOM Review
• /
• 제24권1호
• /
• pp.13-19
• /
• 2021

최근 산업 분야에서는 공장 자동화 뿐만 아니라 장애 진단/예측을 통해 고장/사고를 사전에 방지하여 생산량을 극대화하기 위한 연구가 진행되고 있으며, 이를 구성하기 위해 많은 양의 데이터 축적을 위한 클라우드 기술, 데이터 처리를 위한 빅 데이터 기술, 그리고 데이터 분석을 쉽게 진행하기 위한 AI(Artificial Intelligence)기술이 도입되고 있다. 또한 최근에는 장애 진단/예측의 발전으로 인해 설비 유지보수(PM: Productive Maintenance) 방식도 정기적으로 설비를 유지보수 하는 방식인 TBM(Time Based Maintenance)에서 설비 상태에 따라 유지보수 하는 방식인 CBM(Condition Based Maintenance)을 조합하는 방식으로 발전하고 있다. CBM 기반 유지보수를 수행하기 위하여 설비의 상태(condition)의 정의와 분석이 필요하다. 따라서 본 논문에서는 머신 러닝(Machine Learning) 기반의 장애 진단을 위한 시스템 및 데이터 모델(Data Model)을 제안하며, 이를 기반으로 장애를 사전 예측한 사례를 제시하고자 한다.

• 한국멀티미디어학회논문지
• /
• 제13권5호
• /
• pp.722-729
• /
• 2010

예측 문제를 해결하기 위한 데이타마이닝 기법은 다양한 분야에서 주목받고 있다. 이것에 대한 한 예로 컴퓨터-기반의 질병의 예측 혹은 진단은 CDSS(Clinical Decision support System)에서 가장 중요한 요소이기도 하다. 이러한 예측 문제를 해결하기 위해서 RBF커널 같은 비선형 커널을 사용한 SVM이 가장 널리 사용되고 있는데, 이는 비선형 SVM이 어떠한 다른 분류기법보다 정확한 성능을 보이기 때문이다. 하지만 비선형 SVM을 사용한 경우에는 모델내부를 시각화하는 일이 어려워서 예측결과에 대한 직관적인 이해가 힘들고, 의학 전문가들은 이러한 비선형 SVM의 사용을 기피하고 있는 실정이다. Nomogram은 SVM을 시각화하기 위해 제안된 기법이다. 하지만 이는 선형 SVM의 경우에만 사용이 가능하고. 이 문제를 해결하기 위해서 LRBF 커널이 제안된 바 있다. LRBF 커널은 기존의 RBF 커널을 사용한 SVM과 대등한 결과를 보이면서도 예측결과의 선형적 분석도 가능하게 한다. 본 논문에서는 노모그램(Nomogram)과 LRBF 커널을 사용한 SVM이 통합되어 있는 예측 툴 VRIFA를 제안한다. 이 툴은 사용자와 상호작용하며 비선형 SVM 모델의 내부구조를 데이타의 각 속성별로 보여주는 방법으로 사용자가 예측결과를 직관적으로 이해하도록 도와준다. VRIFA는 Nomogram기반의 피쳐선택(feature selection) 기능도 포함하고 있는데, 이 기능은 예측결과에 부정적인 영향을 끼치거나 중복된 연관성을 보이는 속성을 제거함으로써 모델의 정확도를 높이는 데 기여한다. 그리고 데이터에 포함된 클래스의 비율이 한 쪽으로 치우쳐져 있는 경우에는 ROC 곡선 넓이(AUC)를 예측결과를 평가하기 위한 측도로 사용할 수 있다. 이 툴은 컴퓨터-기반의 질병 예측 혹은 질병의 위험 요소 분석에 대해 연구하는 연구자들에게 유용하게 사용될 것으로 전망하는 바이다.

• 한국가축번식학회지
• /
• 제11권2호
• /
• pp.132-138
• /
• 1987

This study was carried out to evaluate the ability of clinical application of pregnancy diagnosis based upon the determinatin of progesterone in milk, utilizing a chymosin inhibitor labelled with progesterone and monoclonal antibody to progesterone, and its compared with progesterone concentrations in the milk were assayed by radioimmunoassay. 1. The progesterone concentration of the pregnant cows (2.07$\pm$0.54ng/ml) were significantly higher than those of non-pregnant cows (1.04$\pm$0.19 ng/ml), and thereafter began to increase and maintained high levels. 2. During 20 to 22 days after artificial insemination, the accuracy of pregnancy diagnosis from monoclonal antigen of progesterone were 92.9% for non-pregnant cows, and 88.5% for pregnant cows. 3. During 20 to 22 days after artificial inseminatin, the accuracy of pregnancy diagnosis from milk progesterone concentrations were 92.9% for non-pregnant cows(<3.4ng/ml), and 92.3% for pregnant cows( 4.0ng/ml). The average overall accuracy of pregnancy prediction for pregnant and non-pregnant cows were 92.6%. 4. Accordingly, the pregnancy diagnosis from monoclonal antigen of progesterone is thought to be recommendable because this early diagnostic means are simple with accurate result.