• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.392-395
• /
• 2017

본 연구에서는 일 증발접시 증발량 산정을 위한 딥러닝 (deep learning) 모형의 적용성을 평가하였다. 본 연구에서 적용된 딥러닝 모형은 deep belief network (DBN) 기반 deep neural network (DNN) (DBN-DNN) 모형이다. 모형 적용성 평가를 위하여 부산 관측소에서 측정된 기상자료를 활용하였으며, 증발량과의 상관성이 높은 기상변수들 (일사량, 일조시간, 평균지상온도, 최대기온)의 조합을 고려하여 입력변수집합 (Set 1, Set 2, Set 3)별 모형을 구축하였다. DBN-DNN 모형의 성능은 통계학적 모형성능 평가지표 (coefficient of efficiency, CE; coefficient of determination, $r^2$; root mean square error, RMSE; mean absolute error, MAE)를 이용하여 평가되었으며, 기존의 두가지 형태의 ANN (artificial neural network), 즉 모형학습 시 SGD (stochastic gradient descent) 및 GD (gradient descent)를 각각 적용한 ANN-SGD 및 ANN-GD 모형과 비교하였다. 효과적인 모형학습을 위하여 각 모형의 초매개변수들은 GA (genetic algorithm)를 이용하여 최적화하였다. 그 결과, Set 1에 대하여 ANN-GD1 모형, Set 2에 대하여 DBN-DNN2 모형, Set 3에 대하여 DBN-DNN3 모형이 가장 우수한 모형 성능을 나타내는 것으로 분석되었다. 비록 비교 모형들 사이의 모형성능이 큰 차이를 보이지는 않았으나, 모든 입력집합에 대하여 DBN-DNN3, DBN-DNN2, ANN-SGD3 순으로 모형 효율성이 우수한 것으로 나타났다.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.4
• /
• pp.153-162
• /
• 2019

Recently, it is necessary to develop a technology for quantitatively evaluating railway vibration to prevent civil complaints about orbital structures caused by railway noise and normal operation of ultra-precise equipment of orbital industrial complexes. The existing analytical method requires a very complicated dynamic response model, and it is difficult to secure the reliability of the result due to the inaccuracy of the demand model. Therefore, in this paper, we propose a railway vibration evaluation algorithm and system that deduce the vibration value generated from railway operation by using Linear Regression and Gradient Descent technique based on actual measurement railway vibration database that classifies factors affecting railway vibration. The prediction results obtained by the proposed algorithm show higher efficiency and accuracy than the existing analytical methods.

• Progress in Superconductivity and Cryogenics
• /
• v.23 no.3
• /
• pp.14-19
• /
• 2021

The reduction of carbon dioxide emissions becomes a global issue, the main source of carbon dioxide emissions in the Asian region is the energy conversion sector, especially coal-fired power plants. We are working to develop technologies that will at least limit the increase in carbon dioxide emissions from the thermal power plants as one way to reduce carbon dioxide emissions. Our research aims to reduce carbon dioxide emissions by removing iron oxide scale from the feedwater system of thermal power plants using a superconducting high-gradient magnetic separation (HGMS) system, thereby reducing the loss of power generation efficiency. In this paper, the background of thermal power plants in Asia is outlined, followed by a case study of the introduction of a chemical cleaning line at an actual thermal power plant in Japan, and the possibility of introducing it into the thermal power plants in China based on the results.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.190-198
• /
• 2023

To enhance customer satisfaction for higher profits, an e-commerce sector can establish a continuous relationship and acquire new customers. Utilize machine-learning models to analyse their customer's behavioural evidence to produce their competitive advantage to the e-commerce platform by helping to improve overall satisfaction. These models will forecast customers who will churn and churn causes. Forecasts are used to build unique business strategies and services offers. This work is intended to develop a machine-learning model that can accurately forecast retainable customers of the entire e-commerce customer data. Developing predictive models classifying different imbalanced data effectively is a major challenge in collected data and machine learning algorithms. Build a machine learning model for solving class imbalance and forecast customers. The satisfaction accuracy is used for this research as evaluation metrics. This paper aims to enable to evaluate the use of different machine learning models utilized to forecast satisfaction. For this research paper are selected three analytical methods come from various classifications of learning. Classifier Selection, the efficiency of various classifiers like Random Forest, Logistic Regression, SVM, and Gradient Boosting Algorithm. Models have been used for a dataset of 8000 records of e-commerce websites and apps. Results indicate the best accuracy in determining satisfaction class with both gradient-boosting algorithm classifications. The results showed maximum accuracy compared to other algorithms, including Gradient Boosting Algorithm, Support Vector Machine Algorithm, Random Forest Algorithm, and logistic regression Algorithm. The best model developed for this paper to forecast satisfaction customers and accuracy achieve 88 %.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.16 no.2
• /
• pp.3395-3409
• /
• 1974

The purpose of this study is to test and compare the efficiency of heating-system for materials and construction of the wall, ceiling and window in soil brick house, cement house and boulder house respectively, in order to construct ideal farm houses in rural area. The results obtained were as follows: 1. In heat conservation due to construction of walls the thermal efficiency of cement brick house was equivalent to 66.3% of that of soil brick house, and boulder house 60.3% 2. In the case of ceiling, the thermal efficiency of paper ceiling was amounted to 84.2% of that of the composite ceiling (thickness 6mm veneer+thickness. l0m chaffs), and the common ceiling putting on soil above the ceiling, 76% of the composite while the efficiency of the ceiling putting on chaffs above them was 15.8% higher than that of the paper. 3. In the case of improving the window, the double type was 12% higher than. the efficiency of single type. 4. The warming velocity of conventional house was slower but the velocity of radiation was quicker than that of experimental one. It was thought to be due to unscietific constructions of the room bottom, fire inlet and chimney, 5. The temperature gradient line was not dependad upon the amount of throwing into fuel in the rural farm house. 6. It was concluded that the final thermal efficiency of the conventional farm house was 10.6% lower than that of experimental farm house.

• Bulletin of the Korean Mathematical Society
• /
• v.55 no.4
• /
• pp.1303-1315
• /
• 2018

For principal component analysis (PCA) to efficiently analyze large scale matrices, it is crucial to find a few singular vectors in cheaper computational cost and under lower memory requirement. To compute those in a fast and robust way, we propose a new stochastic method. Especially, we adopt the stochastic variance reduced gradient (SVRG) method [11] to avoid asymptotically slow convergence in stochastic gradient descent methods. For that purpose, we reformulate the PCA problem as a unconstrained optimization problem using a quadratic penalty. In general, increasing the penalty parameter to infinity is needed for the equivalence of the two problems. However, in this case, exact penalization is guaranteed by applying the analysis in [24]. We establish the convergence rate of the proposed method to a stationary point and numerical experiments illustrate the validity and efficiency of the proposed method.

• Journal of computational fluids engineering
• /
• v.6 no.4
• /
• pp.15-25
• /
• 2001

Numerical prediction of the diffusion controlled transition in a turbine gas pass is important because it can change the local heat transfer rate over a turbine blade as much as three times. In this study, the gas flow over turbine blade is simplified to the flat plate boundary layer, and an adaptive grid scheme redistributing grid points within the computation domain is proposed with a great emphasis on the construction of the grid control function. The function is sensitized to the second invariant of the mean strain tensor, its spatial gradient, and the interaction of pressure gradient and flow deformation. The transition process is assumed to be described with a κ-ε turbulence model. An elliptic solver is employed to integrate governing equations. Numerical results show that the proposed adaptive grid scheme is very effective in obtaining grid independent numerical solution with a very low grid number. It is expected that present scheme is helpful in predicting actual flow within a turbine to improve computation efficiency.

• Journal of Magnetics
• /
• v.5 no.2
• /
• pp.59-64
• /
• 2000

A drum type of high gradient magnetic separator was designed and optimized by computer simulations. The magnetic separator consists of high performance rare earth $(Nd_2Fe_14B)$ permanent magnets and magnetic yokes of extremely low carbon steel interconnecting the permanent magnets. Magnetic circuits of the separator were simulated for the aim of the least cost, highest magnetic strength and most efficient function by using specialized S/W (Vector Field Program) employing the Finite Element Method. The magnetic flux density was provided to be strong enough to collect the invisible fine metal particles from the surface of hot rolled steel plate with the efficiency of almost 95%.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.9
• /
• pp.1124-1132
• /
• 2004

The inverse problem of determining unknown inlet temperature in thermally developing, hydrodynamically developed two phase laminar flow in a parallel plate duct is considered. The inlet temperature profile is determined by measuring temperature in the flow field. No prior information is needed for the functional form of the inlet temperature profile. The inverse convection problem is solved by minimizing the objective function with regularization method. The conjugate gradient method as iterative method and the Tikhonov regularization method are employed. The effects of the functional form of inlet temperature, the number of measurement points and the measurement errors are investigated. The accuracy and efficiency of these two methods are compared and discussed.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.706-709
• /
• 1997

Extruders are the heart of the polymer processing industry. The single most important mechanical element of a screw extruder is the screw. The proper design of the geometriy of the extruder screw is of crucial importance to the proper functioning of the extruder. If material transport instabilities occur as a result of improper screw geometry, even the most sophisticated computerized control system cannot solve the problem. For this purpose, characteristics design on helix angle of the extruder screw. This paper presents strength of the screw flight, optimum helix angle versus dimensionless down channel pressure gradient, optimum helix angle versus the power law index in simultaneous optimization, volumetric efficiency versus helix angle at various number of flights and power consumption versus helix angle in the barrel of screw extruder.