• 한국의상디자인학회지
• /
• 제10권2호
• /
• pp.125-138
• /
• 2008

For physical and hand property evaluation of fabrics, the knitted fabrics from 11 types of machines knitting fancy yarns, boucle (M1), knot (M2), snarl (M3), and slub (M4), tamtam (M5), tubular (M6), fur 1 (M7), bead (M8), fur 2 (M9), fur 3 (M10), and ladder (M11) yarns, were prepared with 7-10 G plain stitch. Washing test and pilling test had also been carried out. For hand properties by objective sensibility evaluation, 17 items of sir mechanical properties using KES-FB (Kawabata Evaluation System) had been measured. Then hand values of knitted fabrics were calculated with a calculation formula, namely KN-402-KT. Finally the total hand values were obtained through KN-301-WINTER. As a result of physical properties and objective evaluation for machines knitting fancy fabrics, most of them shrank in the direction of wale and course after the washing test, in which their shrinkage rate had a maximum of 3.5%. Therefore, the washing test indicated that the shrinkage ratio of knitted fabrics had a minor change. The results of the pilling test are mostly 4-5th grade, and all of the machines knitting fancy fabrics showed good results in the pilling resistance. In hand properties and objective sensibility evaluation, twisted fancy yarns, such as boucle (M1), knot (M2), snarl (M3), and slub (M4), were superior to bonding rigidity (B) and shear rigidity (G). The surface property between course and wale differs in all samples and course direction is tougher than wale direction. FUKURAMI (fullness and softness) of all samples have high values, besides NUMERI (smoothness) of tamtam (M5) and boucle (M1), which were rather good. Most samples except fur 1 (M7) had low KOSHI (stiffness) value. The total hand value (THV) of twisted yarns was low. This study proves that manufacturers, who plan knitting yarn products and knit fashion, can apply these data to develop machines knitting yarns and knits that fit the consumers' demands.

• 교육시설 논문지
• /
• 제23권4호
• /
• pp.11-20
• /
• 2016

Post Occupancy Evaluation(POE) has a good role to improve or adapt the design items through the survey or interview of the resident. Among buildings, the university dormitory provides the living function to support the study in the university. Therefore, it needs to find the design elements and improve the living and study condition for residents. In this paper. it aimed at conducting the POE in university women dormitory for women and providing the building and design items for the next improvement. In addition, it aimed at analyzing the relation between the building satisfaction and the affecting factors, dividing the building into 8 spatial area such as room, entrance area, toilet and etc.. For these, data are surveyed the women dormitory located in the north area of Kyungsangbuk-Do and collected the 683 samples. This study shows some results ; First, the resident evaluates living condition of the dormitory room is a little good. Second, the freshman has a good score more than any other grade, which probably affect the period of the experience and exposure in university. In addition, residents get affect from the finishings, furniture and inconvenience. Third, the resident evaluates living condition of the dormitory room is a little good. Fourth, the satisfaction degree is affected by each size more than any other components in 8 spatial areas. Especially, the number of laundry machine is important factor for satisfaction. Second, the overall satisfaction is affected by room size higher than any other factors.

• 한국산업정보학회논문지
• /
• 제28권1호
• /
• pp.47-56
• /
• 2023

메자닌 상품은 채권과 주식의 성격을 모두 가진 금융 투자 상품인데 주로 등급이 낮은 회사가 유동성을 확보하기 위해 금융시장에서 발행한다. 따라서 메자닌 상품에 투자하는 사채권자들은 해당 회사가 발행하는 메자닌 상품에 투자하면 주식으로 전환하는 여부와 함께 주식으로 전환하고자 하는 시점에 대해서 의사결정을 해야 한다. 예컨대 메자닌 상품의 투자자와 발행회사는 투자자의 전환권 행사 여부와 시점에 대한 의사결정 문제가 가장 중요한데 이를 위한 투자 판단 지표가 매우 부족하므로 직관적이거나 정성적인 판단에 의존할 수밖에 없다. 따라서 본 논문에서는 주요 업종별 주식 전환 행사가 완료된 총 2,000개의 학습 데이터와 200개의 예측 실험 데이터로 구분하고 인공신경망 모델을 통해서 메자닌 행사 알고리즘을 설계하고 성능을 분석한다. 본 주제는 금융 분야에서 관심이 높은 메자닌 상품 행사의 난제를 인공신경망 기술을 적용하여 과학적으로 해결하는 방법론을 제안했다는 점에서 그 의의를 갖는다.

• Smart Structures and Systems
• /
• 제31권1호
• /
• pp.1-11
• /
• 2023

Assessment of the compressive strength of concrete plays a major role during formwork removal and in the prestressing process. In concrete, temperature changes occur due to hydration which is an influencing factor that decides the compressive strength of concrete. Many methods are available to find the compressive strength of concrete, but the maturity method has the advantage of prognosticating strength without destruction. The temperature-time factor is found using a LM35 temperature sensor through the IoT technique. An experimental investigation was carried out with 56 concrete cubes, where 35 cubes were for obtaining the compressive strength of concrete using a universal testing machine while 21 concrete cubes monitored concrete's temperature by embedding a temperature sensor in each grade of M25, M30, M35, and M40 concrete. The mathematical prediction model equation was developed based on the temperature-time factor during the early age compressive strength on the 1^st, 2^nd, 3^rd and 7^th days in the M25, M30, M35, and M40 grades of concrete with their temperature. The 14^th, 21^st and 28^th day's compressive strength was predicted with the mathematical predicted equation and compared with conventional results which fall within a 2% difference. The compressive strength of concrete at any desired age (day) before reaching 28 days results in the discovery of the prediction coefficient. Comparative analysis of the results found by the predicted mathematical model show that, it was very close to the results of the conventional method.

• 대한안전경영과학회지
• /
• 제26권2호
• /
• pp.23-31
• /
• 2024

In the military, ammunition and explosives stored and managed can cause serious damage if mishandled, thus securing safety through the utilization of ammunition reliability data is necessary. In this study, exploratory data analysis of ammunition inspection records data is conducted to extract reliability information of stored ammunition and to predict the ammunition condition code, which represents the lifespan information of the ammunition. This study consists of three stages: ammunition inspection record data collection and preprocessing, exploratory data analysis, and classification of ammunition condition codes. For the classification of ammunition condition codes, five models based on boosting algorithms are employed (AdaBoost, GBM, XGBoost, LightGBM, CatBoost). The most superior model is selected based on the performance metrics of the model, including Accuracy, Precision, Recall, and F1-score. The ammunition in this study was primarily produced from the 1980s to the 1990s, with a trend of increased inspection volume in the early stages of production and around 30 years after production. Pre-issue inspections (PII) were predominantly conducted, and there was a tendency for the grade of ammunition condition codes to decrease as the storage period increased. The classification of ammunition condition codes showed that the CatBoost model exhibited the most superior performance, with an Accuracy of 93% and an F1-score of 93%. This study emphasizes the safety and reliability of ammunition and proposes a model for classifying ammunition condition codes by analyzing ammunition inspection record data. This model can serve as a tool to assist ammunition inspectors and is expected to enhance not only the safety of ammunition but also the efficiency of ammunition storage management.

• 한국간담췌외과학회지
• /
• 제26권1호
• /
• pp.17-30
• /
• 2022

Oncological scoring systems in surgery are used as evidence-based decision aids to best support management through assessing prognosis, effectiveness and recurrence. Currently, the use of scoring systems in the hepato-pancreato-biliary (HPB) field is limited as concerns over precision and applicability prevent their widespread clinical implementation. The aim of this review was to discuss clinically useful oncological scoring systems for surgical management of HPB patients. A narrative review was conducted to appraise oncological HPB scoring systems. Original research articles of established and novel scoring systems were searched using Google Scholar, PubMed, Cochrane, and Ovid Medline. Selected models were determined by authors. This review discusses nine scoring systems in cancers of the liver (CLIP, BCLC, ALBI Grade, RETREAT, Fong's score), pancreas (Genç's score, mGPS), and biliary tract (TMHSS, MEGNA). Eight models used exclusively objective measurements to compute their scores while one used a mixture of both subjective and objective inputs. Seven models evaluated their scoring performance in external populations, with reported discriminatory c-statistic ranging from 0.58 to 0.82. Selection of model variables was most frequently determined using a combination of univariate and multivariate analysis. Calibration, another determinant of model accuracy, was poorly reported amongst nine scoring systems. A diverse range of HPB surgical scoring systems may facilitate evidence-based decisions on patient management and treatment. Future scoring systems need to be developed using heterogenous patient cohorts with improved stratification, with future trends integrating machine learning and genetics to improve outcome prediction.

• 지능정보연구
• /
• 제17권3호
• /
• pp.25-41
• /
• 2011

최근 몇 년간 SVM(support vector machines)기법은 패턴인식 또는 분류의사결정문제를 위한 분석기법으로서 기존의 데이터마이닝 기법과 비교할 때, 매우 높은 성과를 갖는 것으로 인식되어 왔다. 더 나아나 많은 연구자들은 SVM기법이 1980년대 이후 대표적인 예측 및 분류모형으로 인정받은 인공신경망기법(ANNs : Artificial Neural Networks)에 비해 더 성과가 좋다는 사실을 실증적으로 입증해 왔다(Amendolia et al., 2003; Huang et al., 2004, Huang et al., 2005; Tay and Cao, 2001; Min and Lee, 2005; Shin et al., 2005; Kim, 2003). 일반적으로 이와 같이 다양한 데이터마이닝 기법에 의해 분석되는 이진분류 또는 다분류 의사결정문제들은 특히 금융분야 등에 있어서 오분류비용에 민감하며, 이로 인한 오분류의 경제적 손실도 상대적으로 매우 크다고 할 수 있다. 따라서 기업부도예측모형과 같은 이진분류모형의 결과값을, 부도확률에 기초하여 정교하게 계산된 사후확률의 개념으로서 다분류의 신용등급평가의 문제로 변환할 필요가 있다. 그러나, SVM 모형의 결과값은 기본적으로 그와 같은 부도확률분포를 보여주지 않는다. 따라서, 그러한 확률분포를 정교하게 보여줄 방법을 제시할 필요가 있다(Platt, 1999; Drish, 2001). 본 연구는 AdaBoost 알고리즘기반의 SVM 모형을 이용하여, 이진분류모형으로서 IT 기업의 부실예측모형에 적용한 후, 이 SVM 모형의 예측결과를 SVM의 손실함수에 적용하여 계산된 값을 사후부도확률의 정규분포 특성에 따라 이를 구간화하여 IT기업에 대한 다분류 신용등급 평가의 문제로 전환시키는 방법을 제시하였다. 그리고 본 연구에서 제안하는 방법은 이러한 AdaBoost 알고리즘기반 SVM 모형이 각 기업이 고유한 신용위험(부도확률)을 갖고 있다는 조건하에서, 신용등급부여를 위한 부도확률분포 구간을 정교하게 조정함으로써 오분류 문제를 좀 더 줄일 수 있음을 제시하였다.

• 한국수자원학회논문집
• /
• 제51권10호
• /
• pp.863-874
• /
• 2018

본 연구에서는 SWAT 모형과 random forest를 이용하여 미래 기후변화에 따른 한강유역($34,148km^2$)의 수생태계 건강성을 평가하였다. 국립환경과학원에서 8년간(2008~2015년) 봄철(4~6월)에 모니터링한 부착돌말류 지수(TDI), 저서형 대형무척추동물지수(BMI), 어류평가지수(FAI)는 0~100점, A~E등급으로 평가되며, 이를 본 연구에서 사용하였다. 수생태 건강성에 영향을 미치는 변수로는 수질(T-N, $NH_4$, $NO_3$, T-P, $PO_4$)과 수온을 선정하였으며, 수질 오염도가 낮은 경우에는 수생태계 건강성 점수가 광범위하게 분포되지만 수질 오염도가 높은 경우 수생태계 건강성 점수가 낮아지는 역상관관계를 확인하였다. 기계학습의 분류 분석 기법 중 하나인 random forest 모델을 이용한 세 개의 수생태 건강성 지수 등급분류 결과 정밀도, 재현율, f1-score 모두 0.81 이상의 예측 정확도를 나타내었다. 기상청의 HadGEM3-RA RCP 4.5와 8.5 시나리오를 적용한 미래 SWAT 수문, 수질 결과 기저유출의 증가로 인해 질소 계열 수질 농도는 기준년도 대비 최대 43.2% 증가하였고, 지표유출 감소로 인해 인 계열수질 오염도는 최대 18.9% 감소하는 것으로 분석되었다. 미래 FAI, BMI의 등급은 개선되는 경향을 보이지만 TDI는 등급이 악화되는 것으로 나타났다. 이를 통해 TDI는 질소 계열 수질에 민감하고 FAI, BMI는 인 계열 수질에 더 민감하다고 판단하였다.

• 한국재료학회지
• /
• 제20권11호
• /
• pp.617-622
• /
• 2010

We have studied methods to save Si source during the fabrication process of crystalline Si solar cells. One way is to use a thin silicon wafer substrate. As the thickness of the wafers is reduced, mechanical fractures of the substrate increase with the mechanical handling of the thin wafers. It is expected that the mechanical fractures lead to a dropping of yield in the solar cell process. In this study, the mechanical properties of 220-micrometer-solar grade Cz p-type monocrystalline Si wafers were investigated by varying saw-damage etching conditions in order to improve the flexural strength of ultra-thin monocrystalline Si solar cells. Potassium hydroxide (KOH) solution and tetramethyl ammonium hydroxide (TMAH) solution were used as etching solutions. Etching processes were operated with a varying of the ratio of KOH and TMAH solutions in different temperature conditions. After saw-damage etching, wafers were cleaned with a modified RCA cleaning method for ten minutes. Each sample was divided into 42 pieces using an automatic dicing saw machine. The surface morphologies were investigated by scanning electron microscopy and 3D optical microscopy. The thickness distribution was measured by micrometer. The strength distribution was measured with a 4-point-bending tester. As a result, TMAH solution at $90^{\circ}C$ showed the best performance for flexural strength.

• 전자공학회논문지
• /
• 제52권8호
• /
• pp.67-73
• /
• 2015

디지털 영상의 배포에서, 위 변조자에 의해 영상이 변조되는 심각한 문제가 있다. 이러한 문제를 해결하기 위하여, 본 논문에서는 영상의 Fourier 변환 변이계수를 이용한 미디언 필터링 (Median Filtering: MF) 영상의 포렌식 판정 알고리즘을 제안한다. 제안된 알고리즘에서, 영상의 각 수평, 수직라인의 Fourier 변환 (Fourier Transform: FT)을 하고, 이웃 라인과의 변이계수를 기반으로 하여 MF 검출 (Median Filtering Detection: MFD)을 위한 10 Dim. 특징벡터를 정의한다. 이는 MF 검출기의 SVM (Support Vector Machine) 학습에 사용된다. 제안된 미디언 필터링 검출 스킴은 동일 10 Dim. 특징벡터의 MFR (Median Filter Residual)과 Rhee의 MF 검출 스킴과 비교하여 원영상, JPEG (QF=90), Down 스케일링 (0.9) 그리고 Up 스케일링 (1.1) 영상에서는 성능이 우수하며, Gaussian 필터링($3{\times}3$) 영상에서는 성능이 일부 높았다. 제안된 알고리즘은 성능평가 전체항목에서 민감도 (Sensitivity; TP: True Positive rate)와 1-특이도 (1-Specificity; FP: False Positive rate)에 의한 AUC (Area Under ROC (Receiver Operating Characteristic) Curve)가 모두 1에 수렴하여 'Excellent (A)' 등급임을 확인하였다.