• Journal of Welding and Joining
• /
• 제34권2호
• /
• pp.67-72
• /
• 2016

Aluminum alloy is one of light weight material and it is used to make LNG tank and ship. However, in order to weld aluminum alloy high density heat source is needed. In this paper, I-butt welding of Al 5083 with 6mm thickness using Plasma-MIG welding was carried out. The experiment was performed to investigate the influence of plasma-MIG welding parameters such as plasma current, wire feeding rate, MIG-welding voltage and welding speed on the tensile strength of weld. In addition we suggested 3 strength estimation models which are second order polynomial regression model, multiple nonlinear regression model and neural network model. The estimation performance of 3 models was evaluated in terms of average error rate (AER) and their values were 0.125, 0.238, and 0.021 respectively. Neural network model which has training concept and reflects non -linearity was best estimation performance.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.483-486
• /
• 2020

Age estimation and gender classification for human is a classic problem in computer vision. Almost research focus just only one task and the models are too heavy to run on low-cost system. In our research, we aim to apply multitasking learning to perform both task on a lightweight model which can achieve good precision on embedded system in the real time.

• 한국산업정보학회논문지
• /
• 제23권1호
• /
• pp.1-12
• /
• 2018

본 논문은 듀얼 에너지 X-ray 검색기의 영상을 이용한 물질의 추정 방법 알고리즘을 제안한다. 물질 추정 알고리즘으로 많이 사용되는 기존 4가지 분별 곡선 이외에 로그 함수를 사용한 새로운 분별곡선을 이용하여 물질을 분류한다. 여기에 기존의 선형 보간을 이용한 원자번호 추정 방법이 아닌 확률분포를 이용한 원자번호 추정 방법을 제시한다. 확률분포를 이용한 가중치 계산에는 근접한 두 기준물질을 사용하는 방법과 모든 기준물질을 사용하는 방식, 2가지 방식을 실험하였다. 확률분포를 가중치로 사용하여 물질의 원자번호를 추정 할 경우 기존의 방법보다 더 정확한 원자번호 추정 결과를 나타내었다. 추정된 원자번호를 육안으로 확인하기 위하여 HSI 모델을 이용하여 결과영상에 채색하였다.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.1223-1230
• /
• 2009

In the construction industry, Case-Based Reasoning (CBR) is considered to be the most suitable approach and determining the attribute weights is an important CBR problem. In this paper, a method is proposed for determining attribute weights that are calculated with attribute relation. The basic items of consideration were qualitative and quantitative influence factors. These quantitative factors were related to the qualitative factors to develop a Cost Drivers-structural equation model which can be used to estimate construction cost by considering attribute weight. The process of determining the attribute weight-structural equation model consists o 4 phases: selecting the predominant Cost Drivers for the SEM, applying the Cost Driers in the SEM, determining and verifying the attribute weights and deriving the Cost Estimation Equation. This study develops a cost estimating technique that complements the CBR method with a Cost Drivers-structural equation model which can be actively used during the schematic estimating phases of construction.

• Asian-Australasian Journal of Animal Sciences
• /
• 제33권10호
• /
• pp.1633-1641
• /
• 2020

Objective: The objective of this study was to develop a model for estimating the carcass weight of Hanwoo cattle as a function of body measurements using three different modeling approaches: i) multiple regression analysis, ii) partial least square regression analysis, and iii) a neural network. Methods: Data from a total of 134 Hanwoo cattle were obtained from the National Institute of Animal Science in South Korea. Among the 372 variables in the raw data, 20 variables related to carcass weight and body measurements were extracted to use in multiple regression, partial least square regression, and an artificial neural network to estimate the cold carcass weight of Hanwoo cattle by any of seven body measurements significantly related to carcass weight or by all 19 body measurement variables. For developing and training the model, 100 data points were used, whereas the 34 remaining data points were used to test the model estimation. Results: The R² values from testing the developed models by multiple regression, partial least square regression, and an artificial neural network with seven significant variables were 0.91, 0.91, and 0.92, respectively, whereas all the methods exhibited similar R² values of approximately 0.93 with all 19 body measurement variables. In addition, relative errors were within 4%, suggesting that the developed model was reliable in estimating Hanwoo cattle carcass weight. The neural network exhibited the highest accuracy. Conclusion: The developed model was applicable for estimating Hanwoo cattle carcass weight using body measurements. Because the procedure and required variables could differ according to the type of model, it was necessary to select the best model suitable for the system with which to calculate the model.

• Archives of Plastic Surgery
• /
• 제40권3호
• /
• pp.203-208
• /
• 2013

Background Preoperative volume assessment is useful in breast reconstruction. Magnetic resonance imaging (MRI) and mammography are commonly available to reconstructive surgeons in the care of a patient with breast cancer. This study aimed to verify the accuracy of breast volume measured by MRI, and to identify any factor affecting the relationship between measured breast volume and actual breast weight to derive a new model for accurate breast volume estimation. Methods From January 2012 to January 2013, a retrospective review was performed on a total of 101 breasts from 99 patients who had undergone total mastectomy. The mastectomy specimen weight was obtained for each breast. Mammographic and MRI data were used to estimate the volume and density. A standard statistical analysis was performed. Results The mean mastectomy specimen weight was 340.8 g (range, 95 to 795 g). The mean MRI-estimated volume was $322.2mL^3$. When divided into three groups by the "difference percentage value", the underestimated group showed a significantly higher fibroglandular volume, higher percent density, and included significantly more Breast Imaging, Reporting and Data System mammographic density grade 4 breasts than the other groups. We derived a new model considering both fibroglandular tissue volume and fat tissue volume for accurate breast volume estimation. Conclusions MRI-based breast volume assessment showed a significant correlation with actual breast weight; however, in the case of dense breasts, the reconstructive surgeon should note that the mastectomy specimen weight tends to overestimate the volume. We suggested a new model for accurate breast volume assessment considering fibroglandular and fat tissue volume.

• 운동영양학회지
• /
• 제25권1호
• /
• pp.23-29
• /
• 2021

[Purpose] This preliminary study aimed to develop a regression model to estimate the non-exercise activity thermogenesis (NEAT) of Korean adults using various easy-to-measure dependent variables. [Methods] NEAT was measured in 71 healthy adults (male n = 29; female n = 42). Statistical analysis was performed to develop a NEAT estimation regression model using the stepwise regression method. [Results] We confirmed that age^A, weight^B, heart rate (HR)_average^C, weight × HR_average^D, weight × HR_sum^E, systolic blood pressure (SBP) × HR_rest^F, fat mass ÷ height^2G, gender × HR_average^H, and gender × weight × HR_sum^I were important variables in various NEAT activity regression models. There was no significant difference between the measured NEAT values obtained using a metabolic gas analyzer and the predicted NEAT. [Conclusion] This preliminary study developed a regression model to estimate the NEAT in healthy Korean adults. The regression model was as follows: sitting = 1.431 - 0.013 × (A) + 0.00014 × (D) - 0.00005 × (F) + 0.006 × (H); leg jiggling = 1.102 - 0.011 × (A) + 0.013 × (B) + 0.005 × (H); standing = 1.713 - 0.013 × (A) + 0.0000017 × (I); 4.5 km/h walking = 0.864 + 0.035 × (B) + 0.0000041 × (E); 6.0 km/h walking = 4.029 - 0.024 × (C) + 0.00071 × (D); climbing up 1 stair = 1.308 - 0.016 × (A) + 0.00035 × (D) - 0.000085 × (F) - 0.098 × (G); and climbing up 2 stairs = 1.442 - 0.023 × (A) - 0.000093 × (F) - 0.121 × (G) + 0.0000624 × (E).

• 한국해양학회지:바다
• /
• 제5권3호
• /
• pp.177-185
• /
• 2000

자료동화기법의 하나인 adjoint 방법은 제약조건으로서 모델의 기본방정식을 만족시키는 동시에 모델 결과와 관측자료 차이의 함수인 비용함수의 크기를 최소화시키는 모델변수를 찾아냄으로서 모델 결과를 향상시키는 기법이다. 본 연구에서는 수평방향 2차원 선형 조석모델과 adjoint 모델로 구성된 adjoint 꾸러미를 수립하고, 이를 임의로 설정한 직사각형 모델영역에 적용하였다. 조석모델로부터의 조위 모델 결과를 관측자료로 삼아 개방경계조건인 조위의 진폭을 역 추정하는 수치실험을 실시하여 자료 가중치에 대한 반응, 모델변수 초기 추정치의 중요성 및 지형 변화에 대한 반응 등을 살펴보았다 특히, adjoint꾸러미 적용시 대부분 경험적으로 설정되어왔던 가중치의 선정방법을 제시하였다.

• 한국건설관리학회논문집
• /
• 제11권4호
• /
• pp.22-31
• /
• 2010

프로젝트 초기단계에서 산정된 공사비는 발주자의 중요한 의사결정에 영향을 미치므로 그 중요성이 강조되고 있지만, 정보의 부족으로 인하여 주로 견적전문가의 경험과 지식에 의존하여 진행된다. 이것은 현재 문제와 가장 유사한 과거 사례를 선택하여 사용하는 사례기반추론으로 발전되었다. 사례기반추론 모델의 예측 성능은 속성 가중치의 산정 결과에 많은 영향을 받으므로, 정확한 속성 가중치의 산정이 요구된다. 기존의 연구는 수학적 방법 또는 전문가의 주관적 판단을 이용하는 방법을 사용한다. 본 연구는 기존 연구의 문제점을 보완하기 위해 유전자 알고리즘을 이용한 사례기반추론 공사비 예측 모델을 제안한다. 공사비 예측 모델은 최근이웃 조회 방법의 과정에 의해 추출한 사례의 공사비 정보를 이용하여 예측 대상의 공사비를 산정한다. 검증 결과 AACE에서 정의한 견적시기별 예측 정확도와 표준화 회귀계수 동일가중치를 사용한 방법보다 높은 오차율을 나타내었다. 따라서 본 연구는 유전자 알고리즘을 도입하여 예측 성능을 향상시키고, 사례기반추론 방법을 사용하여 사용자가 이해하기 용이한 해결책 도출과정을 제시하였다는데 그 의미가 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.440-445
• /
• 1992

The major purpose here is to estimate the drying time required in the fish-drying process employed. The basic element of the prediction of the drying time is the model or the equation, which governs the change in weight. By an intuitive consideration on the mechanism of dehydration, a mathematical model of the fish-drying process is built, which is described by a system of linear differential equations. Further, a modified system of linear differential equations for a model of drying is also proposed for more accurate estimation. The parameter estimation of this system of equations provides the prediction of necessary drying time.