• 대한조선학회논문집
• /
• 제59권2호
• /
• pp.72-79
• /
• 2022

Deep-learning-based Super-Resolution (SR) methods were evaluated to reconstruct pressure fields with a high resolution from low-resolution images taken from a coarse grid simulation. In addition to a canonical SRCNN(super-resolution convolutional neural network) model, two modified models from SRCNN, adding an activation function (ReLU or Sigmoid function) to the output layer, were considered in the present study. High resolution images obtained by three models were more vivid and reliable qualitatively, compared with a conventional super-resolution method of bicubic interpolation. A quantitative comparison of statistical similarity showed that SRCNN model with Sigmoid function achieved best performance with less dependency on original resolution of input images.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2005년도 추계 종합학술대회 논문집
• /
• pp.649-653
• /
• 2005

눈 모형이 닫혀있는 등화 초기에 축소 신호점을 적용한 시그모이드 비선형성으로 오차신호를 추정하면, 기존 연판정의거 알고리즘의 문제점인 고차 신호점을 적용 시 계산 복잡도가 증가하고 수렴속도가 저하되는 단점을 개선할 수 있다. 시그모이드 함수는 평균과 분산 파라미터로 특성이 조절되므로, 분산 값을 조절함에 따라 축소 신호점의 값$(\gamma)$이+$\gamma$와-$\gamma$ 사이의 범위를 가질 수 있다. 본 논문에서는 등화가 올바르게 진행하여 각 신호점에서 군집의 크기가 줄어들 때 분산 값을 가변함으로써 정상상태 성능을 개선할 수 있는 가변 모듈러스 알고리즘(Variable Modulus Algorithm: VMA)을 제안한다.

• Steel and Composite Structures
• /
• 제30권6호
• /
• pp.603-615
• /
• 2019

In the present work, free vibration of beams made of imperfect functionally graded materials (FGMs) including porosities is investigated. Because of faults during process of manufacture, micro voids or porosities may arise in the FGMs, and this situation causes imperfection in the structure. Therefore, material properties of the beams are assumed to vary continuously through the thickness direction according to the volume fraction of constituents described with the modified rule of mixture including porosity volume fraction which covers two types of porosity distribution over the cross section, i.e., even and uneven distributions. The governing equations of power law FGM (P-FGM) and sigmoid law FGM (S-FGM) beams are derived within the frame works of classical beam theory (CBT) and first order shear deformation beam theory (FSDBT). The resulting equations are solved using separation of variables technique and assuming FG beams are simply supported at both ends. To validate the results numerous comparisons are carried out with available results of open literature. The effects of types of volume fraction function, beam theory and porosity volume fraction, as well as the variations of volume fraction index, span to depth ratio and porosity volume fraction, on the first three non-dimensional frequencies are examined in detail.

• Advances in nano research
• /
• 제12권5호
• /
• pp.441-455
• /
• 2022

This study explores the linear and nonlinear solutions of sigmoid functionally graded material (S-FGM) nanoplate with porous effects. A size-dependent numerical solution is established using the strain gradient theory and isogeometric finite element formulation. The nonlinear nonlocal strain gradient is developed based on the Reissner-Mindlin plate theory and the Von-Karman strain assumption. The sigmoid function is utilized to modify the classical functionally graded material to ensure the constituent volume distribution. Two different patterns of porosity distribution are investigated, viz. pattern A and pattern B, in which the porosities are symmetric and asymmetric varied across the plate's thickness, respectively. The nonlinear finite element governing equations are established for bending analysis of S-FGM nanoplates, and the Newton-Raphson iteration technique is derived from the nonlinear responses. The isogeometric finite element method is the most suitable numerical method because it can satisfy a higher-order derivative requirement of the nonlocal strain gradient theory. Several numerical results are presented to investigate the influences of porosity distributions, power indexes, aspect ratios, nonlocal and strain gradient parameters on the porous S-FGM nanoplate's linear and nonlinear bending responses.

• Steel and Composite Structures
• /
• 제35권5호
• /
• pp.671-685
• /
• 2020

This manuscript presents impacts of gradation of material functions and axial load functions on critical buckling loads and mode shapes of functionally graded (FG) thin and thick beams by using higher order shear deformation theory, for the first time. Volume fractions of metal and ceramic materials are assumed to be distributed through a beam thickness by both sigmoid law and symmetric power functions. Ceramic-metal-ceramic (CMC) and metal-ceramic-metal (MCM) symmetric distributions are proposed relative to mid-plane of the beam structure. The axial compressive load is depicted by constant, linear, and parabolic continuous functions through the axial direction. The equilibrium governing equations are derived by using Hamilton's principles. Numerical differential quadrature method (DQM) is developed to discretize the spatial domain and covert the governing variable coefficients differential equations and boundary conditions to system of algebraic equations. Algebraic equations are formed as a generalized matrix eigenvalue problem, that will be solved to get eigenvalues (buckling loads) and eigenvectors (mode shapes). The proposed model is verified with respectable published work. Numerical results depict influences of gradation function, gradation parameter, axial load function, slenderness ratio and boundary conditions on critical buckling loads and mode-shapes of FG beam structure. It is found that gradation types have different effects on the critical buckling. The proposed model can be effective in analysis and design of structure beam element subject to distributed axial compressive load, such as, spacecraft, nuclear structure, and naval structure.

• 한국유통학회지:유통연구
• /
• 제10권3호
• /
• pp.1-14
• /
• 2005

성공적인 공급사슬관리에 있어 성과에 따른 지속적 협업 통제는 매우 중요하다. 본 연구에서는 기계학습 알고리즘인 SVM(Support Vector Machiness)을 이용해 균형성과표에 기반한 공급사슬관리 성과에 따른 지속적 협업 통제 모델을 개발하였다. 우리는 지속적 협업 통제모델 개발에 있어 108명의 전문가를 상대로 실증조사를 수행하였다. 본 연구 수행에 있어 4가지 형태의 SVM 커늘 (1) linear, (2) polynomail, (3) Radial Basis Function(RBF), (4) sigmoid kernel을 이용해 공급사슬관리 지속적 협업 예측 정확도를 비교하였다. SVM 커늘 4가지 중 linear kernel의 예측성과가 가장 좋았다. 그리고 본 연구에서는 SVM linear kernel의 예측성과를 ANN(Artificial Neural Network)의 예측성과와 비교하였다. 분석결과 SVM linear kernel이 공급사슬관리에 있어 지속적 협업 예측에 우수한 예측성과를 보여주는 것을 발견하였다. 이러한 곁과는 SVM linear kernel이 공급사슬관리의 지속적 협업 예측 통제에 있어 우수한 대안을 제공해 줄 것이다. 그러므로 공급사슬관리를 추구하는 기업들은 분 모델을 통해 지속적 협업 통제에 유용한 정보를 얻을 수 있을것이다.

• 한국전자통신학회논문지
• /
• 제16권2호
• /
• pp.287-292
• /
• 2021

본 논문에서는 유도전동기 고정자 고장 진단에 있어서 활성화 함수가 미치는 영향을 분석하여 효율적인 CNN 활용 방법을 제안하였다. 일반적으로 유도전동기 고정자 고장 진단의 주된 목적은 미세한 턴 단락을 빠르게 진단함으로 고장을 미리 방지함에 있다. 이에 활성화 함수 활용에 있어서 전반적인 고정자 고장에는 ReLu가 우수성을 보임을 알 수 있었으나, 미세한 턴 단락인 2턴 단락에 있어서는 Sigmoid 함수가 ReLu 함수보다 진단의 정확도에 있어서 23.23% 유용함을 실험을 통해 확인할 수 있었다.

• Journal of Electrical Engineering and Technology
• /
• 제4권2호
• /
• pp.185-193
• /
• 2009

This paper presents a methodology for photovoltaic (PV) system allocation in distribution systems using a discrete particle swarm optimization (DPSO). The PV allocation problem is in the category of mixed integer nonlinear programming and its formulation may include multi-valued dis-crete variables. Thus, the PSO requires a scheme to deal with multi-valued discrete variables. This paper introduces a novel multi-level quantization scheme using a sigmoid function for discrete particle swarm optimization. The technique is employed to a standard PSO architecture; the same velocity update equation as in continuous versions of PSO is used but the particle's positions are updated in an alternative manner. The set of multi-level quantization is defined as integer multiples of powers-of-two terms to efficiently approximate the sigmoid function in transforming a particle's position into discrete values. A comparison with a genetic algorithm (GA) is performed to verify the quality of the solutions obtained.

• Journal of Electrical Engineering and Technology
• /
• 제10권3호
• /
• pp.1233-1243
• /
• 2015

The contrast enhancement is great challenge in the image processing when images are suffering from poor contrast problem. Therefore, in order to overcome this problem an automatic method is proposed for contrast enhancement of natural color images. The proposed method consist of two stages: in first stage lightness component in YIQ color space is normalized by sigmoid function after the adaptive histogram equalization is applied on Y component and in second stage automatic color contrast enhancement algorithm is applied on output of the first stage. The proposed algorithm is tested on different NASA color images, hyperspectral color images and other types of natural color images. The performance of proposed algorithm is evaluated and compared with the other existing contrast enhancement algorithms in terms of colorfulness metric and color enhancement factor. The higher values of colorfulness metric and color enhancement factor imply that the visual quality of the enhanced image is good. Simulation results demonstrate that proposed algorithm provides higher values of colorfulness metric and color enhancement factor as compared to other existing contrast enhancement algorithms. The proposed algorithm also provides better visual enhancement results as compared with the other existing contrast enhancement algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2788-2808
• /
• 2023

Brain tumors are one of the most threatening malignancies for humans. Misdiagnosis of brain tumors can result in false medical intervention, which ultimately reduces a patient's chance of survival. Manual identification and segmentation of brain tumors from Magnetic Resonance Imaging (MRI) scans can be difficult and error-prone because of the great range of tumor tissues that exist in various individuals and the similarity of normal tissues. To overcome this limitation, the Amended Convolutional Neural Network (ACNN) model has been introduced, a unique combination of three techniques that have not been previously explored for brain tumor detection. The three techniques integrated into the ACNN model are image tissue preprocessing using the Kalman Bucy Smoothing Filter to remove noisy pixels from the input, image tissue segmentation using the Isotonic Regressive Image Tissue Segmentation Process, and feature extraction using the Marr Wavelet Transformation. The extracted features are compared with the testing features using a sigmoid activation function in the output layer. The experimental findings show that the suggested model outperforms existing techniques concerning accuracy, precision, sensitivity, dice score, Jaccard index, specificity, Positive Predictive Value, Hausdorff distance, recall, and F1 score. The proposed ACNN model achieved a maximum accuracy of 98.8%, which is higher than other existing models, according to the experimental results.