• 한국컴퓨터산업학회논문지
• /
• 제6권5호
• /
• pp.689-696
• /
• 2005

유한고장수를 가진 비동질적인 포아송 과정에 기초한 모형들에서 잔존 결함 1개당 고장 발생률은 일반적으로 상수, 혹은 단조증가 및 단조 감소 추세를 가지고 있다. 본 논문에서는 기존의 소프트웨어 신뢰성 모형인 Goel-Okumoto 모형과 Yamada-Ohba-Osaki 모형을 재조명하고 잔존 결함 1개당 고장 발생률이 단조 감소 추세를 가진 2모수 Kappa 분포를 이용한 Kappa모형을 제안하였다. 고장 간격시간으로 구성된 자료를 이용한 모수추정 방법은 최우추정법과 일반적인 수치해석 방법인 이분법을 사용하여 모수 추정을 실시하고 효율적인 모형 선택은 편차자승합과 콜모고로프 거리를 적용하여 모형들에 대한 효율성 입증방법을 설명하였다. 소프트웨어 고장 자료 분석에서는 고장수가 비교적 큰 실측 자료(고장수가 86)인 Allen P.Nikora 와 Michael R.Lyu가 인용한 SYS2 자료을 통하여 분석하였다. 이 자료들에서 카파 모형의 비교를 위하여 산술적 및 라플라스 검정, 편의 검정등을 이용하였다.

• 대한간호학회지
• /
• 제48권3호
• /
• pp.362-374
• /
• 2018

Purpose: This study aimed to develop a triage competency scale (TCS) for emergency nurses, and to evaluate its validity and reliability. Methods: Preliminary items were derived based on the attributes and indicators elicited from a concept analysis study on triage competency. Ten experts assessed whether the preliminary items belonged to the construct factor and determined the appropriateness of each item. A revised questionnaire was administered to 250 nurses in 18 emergency departments to evaluate the reliability and validity of the scale. Data analysis comprised item analysis, confirmatory factor analysis, contrasted group validity, and criterion-related validity, including criterion-related validity of the problem solving method using video scenarios. Results: The item analysis and confirmatory factor analysis yielded 5 factors with 30 items; the fit index of the derived model was good (${\chi}^2/df=2.46$, Root Mean squared Residual=.04, Root Mean Squared Error of Approximation=.08). Additionally, contrasted group validity was assessed. Participants were classified as novice, advanced beginner, competent, and proficient, and significant differences were observed in the mean score for each group (F=6.02, p=.001). With reference to criterion-related validity, there was a positive correlation between scores on the TCS and the Clinical Decision Making in Nursing Scale (r=.48, p<.001). Further, the total score on the problem solving method using video scenarios was positively correlated with the TCS score (r=.13, p=.04). The Cronbach's ${\alpha}$ of the final model was .91. Conclusion: Our TCS is useful for the objective assessment of triage competency among emergency nurses and the evaluation of triage education programs.

• 한국환경과학회지
• /
• 제24권6호
• /
• pp.743-753
• /
• 2015

In this study, it is an object to develop a regression model for the estimation of TOC (total organic carbon) concentration using investigated data for three years from 2010 to 2012 in the Gam Stream unit watershed, and applied in 2009 to verify the applicability of the regression model. TOC and $COD_{Mn}$ (chemical oxygen demand) were appeared to be derived the highest correlation. TOC was significantly correlated with 5 variables including BOD (biological oxygen demand), discharge, SS (suspended solids), Chl-a (chlorophyll a) and TP (total phosphorus) of p<0.01. As a result of PCA (principal component analysis) and FA (factor analysis), COD, TOC, SS, discharge, BOD and TP have been classified as a first factor. TOCe concentration was estimated using the model developed as an independent variable $BOD_5$ and $COD_{Mn}$. R squared value between TOC and measurement TOC is 0.745 and 0.822, respectively. The independent variable were added step by step while removing lower importance variable. Based on the developed optimal model, R squared value between measurement value and estimation value for TOC was 0.852. It was found that multiple independent variables might be a better the estimation of TOC concentration using the regression model equation(in a given sites).

• 대한디지털의료영상학회논문지
• /
• 제13권1호
• /
• pp.39-48
• /
• 2011

Uses a Tomographic scan image and Table Object Distance(TOD) price after measuring, uses accuracy and usability of blood vessel diameter(Vessel Diameter) measurement under comparison evaluating boil TOD Calibration. The patient who enforces Prosecuting Attorney abdomen Tomographic scan in the object the superior mesentery artery uses PACS View from abdomen fault image and from blood vessel diameter and the table measures the height until of the blood vessel. Uses Angio Catheter from Angiography(5 Fr.) and enforces is measured from PACS View the height until of the table which and the blood vessel at TOD Calibration price and the size of the superior mesentery artery inputs measures an superior mesentery artery building skill. Catheter Calibration input Agnio Catheter where uses in Angiography the size of the superior mesentery artery at Catheter Calibration price and they measure. Produced an accuracy from monitoring data and comparison evaluated. The statistical program used SPSS. TOD Calibration accuracy was 96.53%, standard deviation is 0.03829. Catheter Calibration accuracy of 92.91%, standard deviation is 0.05085. Represents a statistically significant difference(p = 0). According to age and gender was not statistically significant(p > 0.05). TOD Calibration correlation coefficient R-squared of 88.8%, Catheter Calibration of the R-squared is 75.5%. High accuracy of both methods. Through this study, CT images using the measured distance between the table and the Object, TOD Calibration accuracy higher than two Catheter Calibration was measured. TOD and Catheter Calibration represents a statistically significant difference(p = 0).

• 스마트미디어저널
• /
• 제10권4호
• /
• pp.21-27
• /
• 2021

최근 COVID-19로 인한 코로나 블루로 상담의 중요성이 높아지고 있다. 또한 비대면 서비스의 증가로 상담 매체에 변화를 준 챗봇에 관한 연구들이 활발하게 진행되고 있다. 챗봇을 통한 비대면 상담에서는 내담자의 감정을 정확하게 파악하는 것이 가장 중요하다. 하지만 내담자가 작성한 문장만으로 감정을 인식하는 데는 한계가 있으므로 더 정확한 감정 인식을 위해서는 문장에 내제되어있는 차원 감정을 인식하는 것이 필요하다. 따라서 본 논문에서는 상담 챗봇의 감정 인식 개선을 위해 원본 데이터를 데이터의 특성에 맞게 보정한 후 Word2Vec 모델을 학습하여 생성된 벡터와 문장 VAD(Valence, Arousal, Dominance)를 딥러닝 알고리즘으로 학습한 다차원 감정 인식 모델을 제안한다. 제안한 모델의 유용성 검증 방법으로 3가지 딥러닝 모델을 비교 실험한 결과로 Attention 모델을 사용했을 때 R-squared가 0.8484로 가장 좋은 성능을 보인다.

• 지질공학
• /
• 제33권4호
• /
• pp.639-655
• /
• 2023

최근 지하공간에 대한 수요가 많아지면서 대심도 굴착으로 흙막이 벽체가 활용되고 있다. 흙막이 벽체는 변위에 취약한 구조물로써 국토교통부에서 제시한 관리기준으로 계측관리를 수행하고 있으나 계측관리를 통한 대비는 후처리에 가깝다고 할 수 있다. 따라서 본 연구에서는 머신러닝을 이용한 그라운드 앵커가 설치된 흙막이 벽체의 수평변위 예측뿐만 아니라 머신러닝으로 계측데이터를 학습하는 과정에서 데이터 스케일링과 분할 방법에 따른 예측모델의 영향을 분석하였다. 이 연구의 분석결과에 따르면 사용자 지정분할방법이 적합하지 않은 경우도 있었으나 일정 조건하에서 데이터 학습 및 출력에 가장 우수한 성능을 나타냈다. 데이터 스케일링은 앵커의 인장력, 수압을 표준화하였을 때 오차 1 이내, R-Squared 값이 0.77로 우수한 성능을 나타냈으며 스케일링을 적용하지 않은 모델 대비 음의 변위를 예측하는 결과를 보였다.

• 대한원격탐사학회지
• /
• 제39권6_1호
• /
• pp.1491-1495
• /
• 2023

본 연구는 북극의 해빙표면온도(ice surface temperature, IST)를 자동화된 기계 학습(automated machine learning, AutoML) 기반으로 산출하였다. AutoML 기반 IST는 상관관계(correlation coefficient, R) 0.97, 평균 제곱근 오차(root mean squared error, RMSE) 2.51K로 산출되었다. 심층신경망(deep neural network, DNN) 모델과 비교하여 AutoML IST는 Moderate Resolution Imaging Spectroradiometer (MODIS) IST 및 ice mass balance (IMB) buoy IST와의 검증 결과에서 좋은 정확도를 보인다. 이는 어려운 극지방 조건에서 IST 추정 정확도를 향상시키는 AutoML의 효과를 강조한다.

• Geomechanics and Engineering
• /
• 제36권2호
• /
• pp.111-119
• /
• 2024

In the realm of rock excavation projects, precise estimation of the drilling rate index stands as a pivotal factor in strategic planning and cost assessment. This study introduces and evaluates two pioneering computational intelligence models designed for the prognostication of the drilling rate index, a pivotal parameter with direct implications for cost estimation in rock excavation projects. These models, denoted as the Relevance Vector Regression (RVR) optimized with the Invasive Weed Optimization algorithm (IWO) (RVR-IWO model) and the RVR integrated with the Shuffled Frog Leaping algorithm (SFL) (RVR-SFL model), represent a groundbreaking approach to forecasting drilling rate index. The RVR-IWO and RVR-SFL models were meticulously devised to harness the capabilities of computational intelligence and optimization techniques for drilling rate index estimation. This research pioneers the integration of IWO and SFL with RVR, constituting an unprecedented effort in forecasting drilling rate index. The primary objective of this study was to gauge the precision and dependability of these models in forecasting the drilling rate index, revealing significant distinctions between the two. In terms of predictive precision, the RVR-IWO model emerged as the superior choice when compared to the RVR-SFL model, underscoring the remarkable efficacy of the Invasive Weed Optimization algorithm. The RVR-IWO model delivered noteworthy results, boasting a Variance Account for (VAF) of 0.8406, a Mean Squared Error (MSE) of 0.0114, and a Squared Correlation Coefficient (R²) of 0.9315. On the contrary, the RVR-SFL model exhibited slightly lower precision, yielding an MSE of 0.0160, a VAF of 0.8205, and an R2 of 0.9120. These findings serve to highlight the potential of the RVR-IWO model as a formidable instrument for drilling rate index prediction, particularly within the framework of rock excavation projects. This research not only makes a significant contribution to the realm of drilling engineering but also underscores the broader adaptability of the RVR-IWO model in tackling an array of challenges within the domain of rock engineering. Ultimately, this study advances the comprehension of drilling rate index estimation and imparts valuable insights into the practical implementation of computational intelligence methodologies within the realm of engineering projects.

• 한국입자에어로졸학회지
• /
• 제19권4호
• /
• pp.155-164
• /
• 2023

APS (Aerodynamic Particle Sizer) and OPC (Optical Particle Counter) have been widely used to real-time measurement of indoor and outdoor aerosols. The APS measures the size distribution based on an aerodynamic diameter, while the OPC uses optical diameter to measure the size distribution of aerosols. Since obtaining a size distribution based on aerodynamic diameter is important to understand aerosol characteristics, lots of researcher had been developed experimental equations which can convert optical diameter into aerodynamic diameter. However, previous studies have conducted repeated experiments on particles having a single diameter. In this study, an experimental method of converting optical diameter into aerodynamic diameter through a single experiment was presented. The collection efficiencies of an axial cyclone were measured using APS and OPC at the same time, and the correlation equation between aerodynamic diameter and optical diameter was driven through a theoretical model. Using the proposed method, the size distribution of NaCl particles measured by OPC showed a high correlation with the size distribution obtained by APS (0.93 of R-squared value). In the tests conducted on ISO A1, A2, and A4 test particles, the converted OPC size distribution tended to be similar to the APS size distribution, and for each of test particles (ISO A1, A2, and A4), the R-squared values for the APS particle size distribution were 0.75, 0.86, and 0.89, respectively.

• 기술혁신연구
• /
• 제23권1호
• /
• pp.87-105
• /
• 2015

본 연구는 한국 제조업 중소기업의 R&D 투자와 성과 간의 관계를 분석하여 비선형 형태를 확인하고, 문턱값인 투자적정수준을 도출하였다. 기존 연구들은 투자와 성과 간 시차를 고려하지 않거나, 투자와 성과 간 회귀모형에서 투자 변수의 1차, 2차 항을 이용한 산술적 계산을 통하여 간접적으로 투자수준을 결정하였는데, 본 연구에서는 이를 극복하기 위해 2년의 시차를 가정한 문턱회귀모형을 사용하였다. 분석결과에 의하면, R&D 집중도 및 연구원비율과 이익률간의 관계는 S곡선 형태를 보였고, 매출액 대비 R&D 투자액 기준으로 6.4%, 종업원수 대비 연구원수 기준으로 13%가 R&D 투자의 적정수준으로 도출되었다. 연구로부터 도출된 투자 및 성과 간 관계 형태와 문턱값은 향후 기업의 R&D 투자 전략 및 정부 지원 정책의 기초자료로 활용될 수 있을 것으로 기대된다.