• Composites Research
• /
• v.36 no.2
• /
• pp.92-100
• /
• 2023

In this paper, a machine learning and deep learning model for the design of circuit analog (CA) radar absorbing structure with a cross-dipole pattern on a glass fiber fabric reinforced plastic is presented. The proposed model can directly calculate reflection loss in the Ku-band (12-18 GHz) without three-dimensional electromagnetic numerical analysis based on the geometry of the Cross-Dipole pattern. For this purpose, the optimal learning model was derived by applying various machine learning and deep learning techniques, and the results calculated by the learning model were compared with the electromagnetic wave absorption characteristics obtained by 3D electromagnetic wave numerical analysis to evaluate the comparative advantages of each model. Most of the implemented models showed similar calculated results to the numerical results, but it was found that the Fully-Connected model could provide the most similar calculated results.

• Structural Engineering and Mechanics
• /
• v.57 no.4
• /
• pp.657-680
• /
• 2016

Reinforced concrete (RC) deep beams are structural members that predominantly fail in shear. Therefore, determining the shear strength of these types of beams is very important. The strut-and-tie method is commonly used to design deep beams, and this method has been adopted in many building codes (ACI318-14, Eurocode 2-2004, CSA A23.3-2004). In this study, the efficiency of artificial neural networks (ANNs) in predicting the shear strength of RC deep beams is investigated as a different approach to the strut-and-tie method. An ANN model was developed using experimental data for 214 normal and high-strength concrete deep beams from an existing literature database. Seven different input parameters affecting the shear strength of the RC deep beams were selected to create the ANN structure. Each parameter was arranged as an input vector and a corresponding output vector that includes the shear strength of the RC deep beam. The ANN model was trained and tested using a multi-layered back-propagation method. The most convenient ANN algorithm was determined as trainGDX. Additionally, the results in the existing literature and the accuracy of the strut-and-tie model in ACI318-14 in predicting the shear strength of the RC deep beams were investigated using the same test data. The study shows that the ANN model provides acceptable predictions of the ultimate shear strength of RC deep beams (maximum $R^2{\approx}0.97$). Additionally, the ANN model is shown to provide more accurate predictions of the shear capacity than all the other computed methods in this study. The ACI318-14-STM method was very conservative, as expected. Moreover, the study shows that the proposed ANN model predicts the shear strengths of RC deep beams better than does the strut-and-tie model approaches.

• 한국사회복지학회:학술대회논문집
• /
• 2006.04a
• /
• pp.265-267
• /
• 2006

• 한국지구물리탐사학회:학술대회논문집
• /
• 2006.06a
• /
• pp.153-153
• /
• 2006

• Economic and Environmental Geology
• /
• v.31 no.6
• /
• pp.557-567
• /
• 1998

In order to utilize the data obtained during the deep-sea resources exploration program, the analysis of data structure and database were conducted to develop an appropriate data operating system called Deep-sea Database System. The Relation Data Base Management System, RDBMS, was chosen as a data managing system and the MS Access$^{TM}$ as a DB engine, and the MapInfo$^{TM}$ software as GIS tools. Problems in networking and security were detected and solved during the operation test. Accordingly, development of standardized operative procedure was proposed in obtaining raw data. This proposal will also be reflected in the subsequent phase of the deep-sea program. The Deep-sea Database System could be applied to the selection of potential mining sites and the estimation of economical efficiency over th KODOS (Korea Deep Ocean Study) region. It is also expected that this system might improve the efficiency of detail survey and help in the relinquishment process as a fulfillment of the obligation as a pioneer investor.

• Geomechanics and Engineering
• /
• v.14 no.5
• /
• pp.439-451
• /
• 2018

The stress path characteristics of surrounding rock in the formation of gob were analysed and the unloading was solved. Taking Chengchao Iron Mine as the engineering background, the model for analysing the instability of deep gob was established based on the mechanism of stress relief in deep mining. The energy evolution law was investigated by introducing the local energy release rate index (LERR), and the energy criterion of instability of surrounding rock was established based on the cusp catastrophe theory. The results showed that the evolution equation of the local energy release energy of the surrounding rock was quartic function with one unknown and the release rate increased gradually during the mining. The calculation results showed that the gob was stable. The LERR per unit volume of the bottom structure was relatively smaller, which mean the stability was better. The LERR distribution showed that there was main energy release in the horizontal direction and energy concentration in the vertical direction which meet the characteristics of deep mining. In summary, this model could effectively calculate the stability of surrounding rock in the formation of gob. The LERR could reflect the dynamic process of energy release, transfer and dissipation which provided an important reference for the study of the stability of deep mined out area.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.111-117
• /
• 2022

Many studies have been conducted on software fault prediction models for decades, and the models using machine learning techniques showed the best performance. Deep learning techniques have become the most popular in the field of machine learning, but few studies have used them as classifiers for fault prediction models. Some studies have used deep learning to obtain semantic information from the model input source code or syntactic data. In this paper, we produced several models by changing the model structure and hyperparameters using MLP with three or more hidden layers. As a result of the model evaluation experiment, the MLP-based deep learning models showed similar performance to the existing models in terms of Accuracy, but significantly better in AUC. It also outperformed another deep learning model, the CNN model.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.58 no.3
• /
• pp.272-280
• /
• 2022

The first step is to determine the principal dimensions of the design ship, such as length between perpendiculars, beam, draft and depth when accomplishing the design of a new vessel. To make this process easier, a database with a large amount of existing ship data and a regression analysis technique are needed. Recently, deep learning, a branch of artificial intelligence (AI) has been used in regression analysis. In this paper, deep learning neural networks are used for regression analysis to find the regression function between the input and output data. To find the neural network structure with the highest accuracy, the errors of neural network structures with varying the number of the layers and the nodes are compared. In this paper, Python TensorFlow Keras API and MATLAB Deep Learning Toolbox are used to build deep learning neural networks. Constructed DNN (deep neural networks) makes helpful in determining the principal dimension of the ship and saves much time in the ship design process.

• Journal of Ocean Engineering and Technology
• /
• v.37 no.2
• /
• pp.49-57
• /
• 2023

Since Chappelear developed a Fourier approximation method, considerable research efforts have been made. On the other hand, Fourier approximations are unsuitable for deep water waves. The purpose of this study is to provide a Fourier approximation suitable even for deep water waves and a numerical method to determine the Fourier coefficients and the wave properties. In addition, the convergence of the solution was tested in terms of its order. This paper presents a velocity potential satisfying the Laplace equation and the bottom boundary condition (BBC) with a truncated Fourier series. Two wave profiles were derived by applying the potential to the kinematic free surface boundary condition (KFSBC) and the dynamic free surface boundary condition (DFSBC). A set of nonlinear equations was represented to determine the Fourier coefficients, which were derived so that the two profiles are identical at specified phases. The set of equations was solved using Newton's method. This study proved that there is a limit to the series order, i.e., the maximum series order is N=12, and that there is a height limitation of this method which is slightly lower than the Michell theory. The reason why the other Fourier approximations are not suitable for deep water waves is discussed.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2008.10a
• /
• pp.921-924
• /
• 2008

We investigated new deep blue emitting materials including a novel side group such as CB-203. CB-203 shows relatively 40% increased PL quantum efficiency and higher Tg of $30^{\circ}C$ compared to MADN. It exhibits high External Quantum Efficiency (EQE) of 7.18% that is two times bigger than MADN's, which is the best efficiency in case of non-doped blue fluorescence OLED device to our knowledge. And deep blue emitting materials with a new core structure (CB-301) have been synthesized. CB-301 exhibit excellent blue fluorescence properties. Undoped OLED devices using CB-301 as blue emitters was found to deep blue CIE value (0.154, 0.078) and exhibit high luminance efficiencies of 2.01cd/A at $10\;mA/cm^2$.