• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.200-206
• /
• 2021

Fraud in e-commerce transaction increased in the last decade especially with the increasing number of online stores and the lockdown that forced more people to pay for services and groceries online using their credit card. Several machine learning methods were proposed to detect fraudulent transaction. Neural networks showed promising results, but it has some few drawbacks that can be overcome using optimization methods. There are two categories of learning optimization methods, first-order methods which utilizes gradient information to construct the next training iteration whereas, and second-order methods which derivatives use Hessian to calculate the iteration based on the optimization trajectory. There also some training refinements procedures that aims to potentially enhance the original accuracy while possibly reduce the model size. This paper investigate the performance of several NN models in detecting fraud in e-commerce transaction. The backpropagation model which is classified as first learning algorithm achieved the best accuracy 96% among all the models.

• 정보교육학회논문지
• /
• 제25권5호
• /
• pp.791-801
• /
• 2021

본 논문은 예비교사와 현직교사를 위한 인공지능 소양 교육으로 적용할 수 있는 교육 사례를 연구하였다. 이를 위해, 이미지를 인식하는 인공신경망의 동작 원리를 교육하는 사례를 제안하였다. 본 교육 사례는 인공신경망 동작 및 구현의 기초 원리 교육에 초점을 맞추어, 인공신경망 구현에 필요한 매개변수 최적화 해들을 스프레드시트로 찾는 방법을 적용하였다. 본 논문에서는 지도학습 방식의 인공신경망에 초점을 맞추었다. 첫 번째로, 인공신경망 원리 교육 사례로서 2종 이미지를 인식하는 인공신경망 교육 사례를 제안하였다. 두번째로 인공신경망 확장 교육 사례로서 3종 이미지를 인식하는 인공신경망 교육 사례를 제안하였다. 마지막으로 인공신경망 교육 사례를 분석한 결과와 교육 만족도 분석 결과를 제시하였다. 제안한 교육 사례를 통해, 인공신경망 동작 원리, 학습 데이터 작성 방법, 학습 데이터양에 따라 실행되는 매개변수 계산 회수 그리고 매개변수 최적화에 대해 학습할 수 있다. 예비교사와 현직교사에 대한 교육 만족도 조사 결과는 각 조사 항목에 대해 모두 70%이상 긍정적인 응답 결과를 나타내어, 높은 수업 적용 적합성을 나타내었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권7호
• /
• pp.2356-2376
• /
• 2021

In this paper, we proposed a novel modulation recognition method based on quantum elephant herding algorithm (QEHA) evolving neural network under impulse noise environment. We use the adaptive weight myriad filter to preprocess the received digital modulation signals which passing through the impulsive noise channel, and then the instantaneous characteristics and high order cumulant features of digital modulation signals are extracted as classification feature set, finally, the BP neural network (BPNN) model as a classifier for automatic digital modulation recognition. Besides, based on the elephant herding optimization (EHO) algorithm and quantum computing mechanism, we design a quantum elephant herding algorithm (QEHA) to optimize the initial thresholds and weights of the BPNN, which solves the problem that traditional BPNN is easy into local minimum values and poor robustness. The experimental results prove that the adaptive weight myriad filter we used can remove the impulsive noise effectively, and the proposed QEHA-BPNN classifier has better recognition performance than other conventional pattern recognition classifiers. Compared with other global optimization algorithms, the QEHA designed in this paper has a faster convergence speed and higher convergence accuracy. Furthermore, the effect of symbol shape has been considered, which can satisfy the need for engineering.

• Current Optics and Photonics
• /
• 제6권5호
• /
• pp.479-488
• /
• 2022

To account for the internal thermal effects of solid-state lasers, a method using a back propagation (BP) neural network integrated with a particle swarm optimization (PSO) algorithm is developed, which is a new wavefront distortion correction technique. In particular, by using a slab laser model, a series of fiber pumped sources are employed to form a controlled array to pump the gain medium, allowing the internal temperature field of the gain medium to be designed by altering the power of each pump source. Furthermore, the BP artificial neural network is employed to construct a nonlinear mapping relationship between the power matrix of the pump array and the thermally induced wavefront aberration. Lastly, the suppression of thermally induced wavefront distortion can be achieved by changing the power matrix of the pump array and obtaining the optimal pump light intensity distribution combined using the PSO algorithm. The minimal beam quality β can be obtained by optimally distributing the pumping light. Compared with the method of designing uniform pumping light into the gain medium, the theoretically computed single pass beam quality β value is optimized from 5.34 to 1.28. In this numerical analysis, experiments are conducted to validate the relationship between the thermally generated wavefront and certain pumping light distributions.

• International Journal of Korean Welding Society
• /
• 제1권2호
• /
• pp.12-17
• /
• 2001

With the advance of the robotic welding process, procedure optimization that selects the welding procedure and predicts bead width that will be deposited is increased. A major concern involving procedure optimization should define a welding procedure that can be shown to be the best with respect to some standard and chosen combination of process parameters, which give an acceptable balance between production rate and the scope of defects for a given situation. This paper presents a new algorithm to establish a mathematical model f3r predicting bead width through a neural network and multiple regression methods, to understand relationships between process parameters and bead width, and to predict process parameters on bead width for GMA welding process. Using a series of robotic arc welding, additional multi-pass butt welds were carried out in order to verify the performance of the neural network estimator and multiple regression methods as well as to select the most suitable model. The results show that not only the proposed models can predict the bead width with reasonable accuracy and guarantee the uniform weld quality, but also a neural network model could be better than the empirical models.

• 한국정보통신학회논문지
• /
• 제10권1호
• /
• pp.206-211
• /
• 2006

수량화 문제는 n개의 성질을 갖는 m개의 개체들을 각 개체들의 유사도(similarity)를 가장 잘 반영하도록 p차원의 공간 상에 대응시키는 문제이다. 본 논문에서는 물리학에서의 열평형 상태(thermal equilibrium state)에서 분자시스템의 해석적 근사 움직임에 대한 이론인 평균장 이론(mean field theory)에 의한 분자의 평균 변화량 계산과 어닐링(annealing) 방법에 의한 평균장 신경회로망(mean field neural network)을 수량화 문제(quantification analysis problem)의 해결에 적용하였다. 그 결과, 제안한 최적화 응용기법 이 기존의 고유치 분석방법(eigen value analysis)에 비해 비용측면에서 좀 더 최적에 가까운 해답을 찾아낼 수 있음을 확인하였다.

• Nuclear Engineering and Technology
• /
• 제55권9호
• /
• pp.3150-3163
• /
• 2023

To improve the performance of blanket: maximizing the tritium breeding rate (TBR) for tritium self-sufficiency, and minimizing the Dose of backplate for radiation protection, most previous studies are based on manual corrections to adjust the blanket structure to achieve optimization design, but it is difficult to find an optimal structure and tends to be trapped by local optimizations as it involves multiphysics field design, which is also inefficient and time-consuming process. The artificial intelligence (AI) maybe is a potential method for the optimization design of the blanket. So, this paper aims to develop an intelligent optimization method based on an improved multi-objective NSGA-III algorithm and an adaptive BP neural network to solve these problems mentioned above. This method has been applied on optimizing the radial arrangement of a conceptual design of CFETR HCSB blanket. Finally, a series of optimal radial arrangements are obtained under the constraints that the temperature of each component of the blanket does not exceed the limit and the radial length remains unchanged, the efficiency of the blanket optimization design is significantly improved. This study will provide a clue and inspiration for the application of artificial intelligence technology in the optimization design of blanket.

• Structural Engineering and Mechanics
• /
• 제52권4호
• /
• pp.815-827
• /
• 2014

Buckling optimization of laminated composite plates is significant as they fail because of buckling under in-plane compressive loading. The plate is usually modeled without cutout so that the buckling strength is found analytically using classical laminate plate theory (CLPT). However in real world applications, the composite plates are modeled with cutouts for getting them assembled and to offer the provisions like windows, doors and control system. Finite element analysis (FEA) is used to analyze the buckling strength of the plate with cutouts and it leads to high computational cost when the plate is optimized. In this article, a genetic algorithm based optimization technique is used to optimize the composite plate with cutout. The computational time is highly reduced by replacing FEA with artificial neural network (ANN). The effectiveness of the proposed method is explored with two numerical examples.

• 한국유체기계학회 논문집
• /
• 제11권2호
• /
• pp.46-54
• /
• 2008

This study presents a numerical optimization to optimize an axial flow fan blade to increase the efficiency. The radial basis neural network is used as an optimization method with the numerical analysis by Reynolds-averaged Navier-Stokes equations using SST model as turbulence closure. Four design variables related to airfoil maximum camber, maximum camber location, leading edge radius and trailing edge radius, respectively, are selected, and efficiency is considered as objective function which is to be maximized. Thirty designs are evaluated to get the objective function values of each design used to train the neural network. Optimum shape shows the efficiency increased by 1.0%.

• 전기학회논문지
• /
• 제67권6호
• /
• pp.767-772
• /
• 2018

Recently, some meta-heuristic algorithms, such as GA(Genetic Algorithm) and GP(Genetic Programming), have been used to optimize CNN(Convolutional Neural Network). The CNN, which is one of the deep learning models, has seen much success in a variety of computer vision tasks. However, designing CNN architectures still requires expert knowledge and a lot of trial and error. In this paper, the recent attempts to automatically construct CNN architectures are investigated and analyzed. First, two GA based methods are summarized. One is the optimization of CNN structures with the number and size of filters, connection between consecutive layers, and activation functions of each layer. The other is an new encoding method to represent complex convolutional layers in a fixed-length binary string, Second, CGP(Cartesian Genetic Programming) based method is surveyed for CNN structure optimization with highly functional modules, such as convolutional blocks and tensor concatenation, as the node functions in CGP. The comparison for three approaches is analysed and the outlook for the potential next steps is suggested.