• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.315-322
• /
• 1999

설비에 고장이 발생하여 고객이 수리를 요청하기 전에 미리 고객을 방문하여 예방점검을 실시하는 것은 고객의 만족도를 높이고 수리기술자의 효과적인 활용을 위해서 매우 중요한 활동이다. 본 연구에서는 설비에 고장이 발생하여 수리가 이루어진 후에 그 설비의 다음 고장은 언제 발생할 것인가를 예측하기 위하여 사례기반 추론을 적용하였다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.224-226
• /
• 2022

다양한 소스로부터 수집되고 연동되는 데이터를 모델링하는 기술로 그래프 데이터베이스를 활용한 분석 기법이 각광받고 있다. 이 연구에서는 항로표지에서 관측되는 상태 및 주변 정보를 모델링하고, 고장진단 및 예측에 적용할 수 있는 기계학습 기법을 소개한다.

• Korean Journal of Psychosomatic Medicine
• /
• v.26 no.1
• /
• pp.9-18
• /
• 2018

Objectives : The aims of this study were to investigate the psychopathology in adolescents with internalizing disorder using the self-report version of Strengths and Difficulties Questionnaire (SDQ-SR) and the Minnesota Multiphasic Personality Inventory for adolescents (MMPI-A), and to explore the complementarity between these two inventories for diagnostic assessment. Methods : Ninety-one patients aged 13-17 were divided into two groups by clinical diagnosis, 44 with internalizing disorder and 47 comparison group with other disorders. The data of SDQ-SR and MMPI-A completed by them were analyzed for the ability to predict internalizing disorder. Results : The logistic regression analysis revealed that diagnostic predictability increased by 2.27 times with every 1 point of SDQ-SR emotional symptom score increment. Comparison of ROC curves for internalizing disorders showed that the SE and SP of SDQ-SR emotional symptom with score over 4 was 88.94 and 78.72, respectively. For A-anx of MMPI-A with score over 56, SE and SP was 77.27 and 74.47, respectively. However, combination of these scales could not enhance the predictability of diagnostic classification more than that of SDQ-SR emotional symptom alone. Conclusions : Emotional symptom scale of SDQ-SR and A-anx, A-aln, A and INTR of MMPI-A should be important subscales for diagnosing the internalizing disorder of adolescents, however, which needs to be examined further with a larger sample size including normal control group.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2016.02a
• /
• pp.91.2-91.2
• /
• 2016

반도체 및 디스플레이 등과 같은 전자산업분야에 플라즈마를 이용한 생산공정이 폭넓게 활용됨에 따라서 공정 결과를 예측하고 조절할 수 있는 플라즈마 변수 측정 및 진단기술의 중요성은 더욱 증가되고 있다. 플라즈마 진단을 위해 가장 많이 사용되고 있는 량뮤어 탐침(Langmuir Probe)은 수십 볼트(V)의 전압을 탐침에 인가하여 들어오는 전류(I)를 측정한 I-V curve의 해석을 바탕으로 플라즈마 변수들(전자밀도, 전자온도, 플라즈마 전위, ${\cdots}$)을 측정하는 방법으로 탐침에 인가한 전압으로 인하여 플라즈마가 영향을 받고 이로인하여 공정 결과에 변화를 줄 수 있다. 또한, 증착공정과 같이 공정과정 중에 탐침의 증착으로 인해 탐침으로 들어와야하는 전자 및 이온의 양이 감소하여 측정에 오차가 발생할 수 있어 공정 플라즈마 진단에 적합하지 않다. 따라서 공정 플라즈마의 정확한 측정을 위해서는 플라즈마에 대한 영향을 최소화하고 증착으로 인하여 탐침이 오염 되는 환경에서도 플라즈마 변수를 정확히 측정할 수 있는 진단 장치가 요구된다. 마이크로웨이브를 이용한 진단장치들은 1 mW 이하의 매우 작은 파워를 사용하기 때문에 플라즈마에 영향을 최소화하여 보다 정확한 플라즈마 진단이 가능하다. 또, 유전체 투과특성이 있는 마이크로웨이브를 이용하기 때문에 탐침이 유전체로 증착되었다 하더라도 측정에는 문제가 없어 공정 플라즈마 진단에 용이하다. 이런 장점들로 인하여 헤어핀 탐침(Hairpin probe), 컷오프 탐침(cutoff probe), 임피던스 탐침(Impedance probe) 등과 같이 마이크로웨이브를 이용하여 다양한 형태의 진단 장치들이 개발되었다. 본 발표에서는 마이크로웨이브를 이용한 다양한 형태의 진단 장치들을 소개하고 각각이 가지는 장단점을 정리하여 각 진단장치들이 측정이 적합한 영역을 소개할 예정이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.546-548
• /
• 2023

인공지능 기술을 도입한 의료분야에서 진단 및 예측을 위한 관련 연구가 활발하게 진행되고 있다. 특히, 인공지능 기술 적용에 가장 많이 활용되고 있는 의료영상을 기반으로 하는 질환에 관한 진단 연구는 매우 복잡한 과정이 필요한 질환의 진단에 큰 영향을 미치고 있다. 복부 장기들의 분할은 환자의 질환 진단 지원 및 복강경등의 수술 지원에 매우 중요한 부분을 차지한다. 본 논문에서는 의료영상을 통해 13가지 복부 장기들을 분할하는 모델을 만들고 그 결과를 보인다. 본 논문에서 제안한 모델을 통해 13가지 복부 장기에 대한 분할로 영상분석을 통해 진단 지원이 가능할 것으로 기대한다.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.771-780
• /
• 2009

Cataract is the main cause of blindness and visual impairment, especially, age-related cataract accounts for about half of the 32 million cases of blindness worldwide. As the life expectancy and the expansion of the elderly population are increasing, the cases of cataract increase as well, which causes a serious economic and social problem throughout the country. However, the incidence of cataract can be reduced dramatically through early diagnosis and prevention. In this study, we developed a prediction model of cataracts for early diagnosis using hospital data of 3,237 subjects who received the screening test first and then later visited medical center for cataract check-ups cataract between 1994 and 2005. To develop the prediction model, we used random forests and compared the predictive performance of this model with other common discriminant models such as logistic regression, discriminant model, decision tree, naive Bayes, and two popular ensemble model, bagging and arcing. The accuracy of random forests was 67.16%, sensitivity was 72.28%, and main factors included in this model were age, diabetes, WBC, platelet, triglyceride, BMI and so on. The results showed that it could predict about 70% of cataract existence by screening test without any information from direct eye examination by ophthalmologist. We expect that our model may contribute to diagnose cataract and help preventing cataract in early stages.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.825-832
• /
• 2022

In this paper, we discuss the design and implementation of predictive and diagnostic models for realizing intelligent predictive models by collecting and storing the power output of agricultural photovoltaic power generation systems. Our model predicts the amount of photovoltaic power generation using RNN, LSTM, and GRU models, which are recurrent neural network techniques specialized for time series data, and compares and analyzes each model with different hyperparameters, and evaluates the performance. As a result, the MSE and RMSE indicators of all three models were very close to 0, and the R2 indicator showed performance close to 1. Through this, it can be seen that the proposed prediction model is a suitable model for predicting the amount of photovoltaic power generation, and using this prediction, it was shown that it can be utilized as an intelligent and efficient O&M function in an agricultural photovoltaic system.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.6
• /
• pp.111-119
• /
• 2023

Recently, a variety of new cement-based materials have been developed, and attempts to predict the properties of these new materials are increasing. In this study, we aimed to predict the rheological properties of binary blended pastes. The cementitious materials used in the study included Portland cement (PC), fly ash (FA), blast furnace slag (BS), and silica fume (SF). The three binder components, fly ash, blast furnace slag, and silica fume, were blended with cement as the foundational composition. We predicted the yield stress and plastic viscosity of the pastes using the YODEL (Yield stress mODEL) and Krieger-Dougherty's equation. The predictive model's performance was validated by comparing it with experimental results obtained using a rheometer. When the rheological properties of the binary blended paste were predicted by reconstructing the properties and parameters used to predict the individual materials, it was evident that the predictions made using the proposed method closely matched the experimental results.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.11 no.5
• /
• pp.81-88
• /
• 2007

Among deteriorations of concrete due to environmental exposure, carbonation problems of concrete structures have increased in urban and underground structures. But conventional carbonation-prediction equations that were proposed by foreign references, can not be applied directly to the prediction of carbonation for domestic concrete structures. The purpose of this study is to propose a prediction equation of carbonation depth by considering domestic exposure conditions of concrete structures. For the derivation of the equation, conventional carbonation-prediction equations are analyzed. Through considering the relationship between results of prediction equation and those of various domestic field survey data, the so-called correction factors for different domestic exposure condition of concrete structures are derived. Finally, a carbonation-prediction equation of concrete structures under domestic exposure conditions is proposed with consideration for concrete strength in core and correction factors.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2009.06a
• /
• pp.266-266
• /
• 2009

This paper describes important parameters used to evaluate the insulation performance of power supply components in metro substations. For online fault diagnosis of power supply components, we have developed a new remote condition monitoring system using wireless technology. Our developed system can continuously monitor electric power equipment such as transformers, circuit brakers, and rectifiers and have powerful wireless networking functions.