• ETRI Journal
• /
• v.14 no.3
• /
• pp.67-74
• /
• 1992

Discrete variable을 갖는 Mean Field Theory(MFT) neural network은 이미 많은 combinatorial optimization 문제에 적용되어져 왔다. 본 논문에서는 이를 확장하여 continuous variable을 갖는 mean field annealing을 제안하고, 이러한 network에서 integral로 표현되는 spin average를 mean field에 기초하여 어렵지 않게 구할 수 있는 one-variable stochastic simulated annealing을 제안하였다. 이런 방법으로 multi-body problem을 single-body problem으로 바꿀 수 있었다. 또한 이 방법을 이용한 응용으로서 통계학에서 잘 알려진 문제중의 하나인 quantification analysis 문제에 적용하여 타당성을 보였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1346-1349
• /
• 1993

In this paper, we describe the use of certain optimization techniques, principally dynamic programming and high level computational methods, to enhance the capabilities of a fuzzy adaptive neural network controller which we had developed for on-line control and adaption on complex nonlinear processes. Potential applications to an array of processes from diverse fields are discussed.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.5
• /
• pp.526-538
• /
• 2007

This paper presents a neural network based decentralized excitation controller design for large-scale power systems. The proposed controller design considers not only the dynamics of generators but also the algebraic constraints of the power flow equations. The control signals are calculated using only local signals. The transient stability and the coordination of the subsystem control activities are guaranteed through rigorous stability analysis. Neural networks in the controller design are used to approximate the unknown/imprecise dynamics of the local power system and the interconnections. All signals in the closed loop system are guaranteed to be uniformly ultimately bounded. To evaluate its performance, the proposed controller design is compared with conventional controllers optimized using particle swarm optimization. Simulations with a three-machine power system under different disturbances demonstrate the effectiveness of the proposed controller design.

• Smart Structures and Systems
• /
• v.26 no.3
• /
• pp.263-275
• /
• 2020

This research is dedicated to slope stability analysis using novel intelligent models. By coupling a neural network with spotted hyena optimizer (SHO), salp swarm algorithm (SSA), shuffled frog leaping algorithm (SFLA), and league champion optimization algorithm (LCA) metaheuristic algorithms, four predictive ensembles are built for predicting the factor of safety (FOS) of a single-layer cohesive soil slope. The data used to develop the ensembles are provided from a vast finite element analysis. After creating the proposed models, it was observed that the best population size for the SHO, SSA, SFLA, and LCA is 300, 400, 400, and 200, respectively. Evaluation of the results showed that the combination of metaheuristic and neural approaches offers capable tools for estimating the FOS. However, the SSA (error = 0.3532 and correlation = 0.9937), emerged as the most reliable optimizer, followed by LCA (error = 0.5430 and correlation = 0.9843), SFLA (error = 0.8176 and correlation = 0.9645), and SHO (error = 2.0887 and correlation = 0.8614). Due to the high accuracy of the SSA in properly adjusting the computational parameters of the neural network, the corresponding FOS predictive formula is presented to be used as a fast yet accurate substitution for traditional methods.

• Journal of Korea Multimedia Society
• /
• v.24 no.11
• /
• pp.1552-1559
• /
• 2021

Convolution neural networks (CNNs) show notable performance in image processing and are used as representative core models. CNNs extract and learn features from large amounts of train dataset. In general, it has a structure in which a convolution layer and a fully connected layer are stacked. The core of CNN is the convolution layer. The size of the kernel used for feature extraction and the number that affect the depth of the feature map determine the amount of weight parameters of the CNN that can be learned. These parameters are the main causes of increasing the computational complexity and memory usage of the entire neural network. The most computationally expensive components in CNNs are fully connected and spatial convolution computations. In this paper, we propose a Fourier Convolution Neural Network that performs the operation of the convolution layer in the Fourier domain. We work on modifying and improving the amount of computation by applying the fast fourier transform method. Using the MNIST dataset, the performance was similar to that of the general CNN in terms of accuracy. In terms of operation speed, 7.2% faster operation speed was achieved. An average of 19% faster speed was achieved in experiments using 1024x1024 images and various sizes of kernels.

• Steel and Composite Structures
• /
• v.27 no.4
• /
• pp.427-438
• /
• 2018

In this paper, the single and multi-objective optimization of thin-walled conical tubes with different types of indentations under axial impact has been investigated using surrogate models called metamodels. The geometry of tapered thin-walled tubes has been studied in order to achieve maximum specific energy absorption (SEA) and minimum peak crushing force (PCF). The height, radius, thickness, tapered angle of the tube, and the radius of indentation have been considered as design variables. Based on the design of experiments (DOE) method, the generated sample points are computed using the explicit finite element code. Different surrogate models including Kriging, Feed Forward Neural Network (FNN), Radial Basis Neural Network (RNN), and Response Surface Modelling (RSM) comprised to evaluate the appropriation of such models. The comparison study between surrogate models and the exploration of indentation shapes have been provided. The obtained results show that the RNN method has the minimum mean squared error (MSE) in training points compared to the other methods. Meanwhile, optimization based on surrogate models with lower values of MSE does not provide optimum results. The RNN method demonstrates a lower crashworthiness performance (with a lower value of 125.7% for SEA and a higher value of 56.8% for PCF) in comparison to RSM with an error order of $10^{-3}$. The SEA values can be increased by 17.6% and PCF values can be decreased by 24.63% by different types of indentation. In a specific geometry, higher SEA and lower PCF require triangular and circular shapes of indentation, respectively.

• Convergence Security Journal
• /
• v.24 no.3
• /
• pp.95-104
• /
• 2024

The performance capability of the future battlefield depends on whether the next-generation technology of the Fourth Industrial Revolution, called ABCMS (AI, Bigdata, Cloud, Mobile, Security), can be applied to secure innovative defense capabilities It is no exaggeration to say. In addition, the future military operation environment is rapidly changing into a net work-oriented war (NCW) in which all weapon systems mutually share battlefield information and operate in real-time within a single integrated information and communication network based on the network and is expanding to the scope of operation of the manned and unmanned complex combat system. In particular, communication networks responsible for high-speed and hyperconnectivity require high viability and efficiency in power operation based on multi-tier (defense mobile, satellite, M/W, wired) networks for the connection of multiple combat elements and smooth distribution of information. From this point of view, this study is different from conventional single-media, single-path transmission with fixed specifications, It is an artificial intelligence-based transmission technology using RNN (Recurrent Neural Networks) algorithm and load distribution during traffic congestion using available communication wired and wireless infrastructure multimedia simultaneously and It is the development of MMMP-Multi-Media Multi-Path adaptive network technology.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.1
• /
• pp.158-164
• /
• 2002

This paper proposes the optimization of ultrasonic signal recognition in ferrite carbon steel weld zone using neural networks. For these purposes, the ultrasonic signals for defects as porosity, incomplete penetration and slag inclusion in the weld zone are acquired in the type of time series data. And then their applications evaluated feature extraction based on the time-frequency-attractor domain(peak to peak, rise time, rise slope, fall time, fall slope, pulse duration, power spectrum, and bandwidth) and attractor characteristics (fractal dimension and attractor quadrant) etc. The proposed neural networks system in this study can enhances performance of ultrasonic signal recognition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.755-778
• /
• 2024

In recent years, the number of devices being connected to the internet has grown enormously, as has the intrusive behavior in the network. Thus, it is important for intrusion detection systems to report all intrusive behavior. Using deep learning and machine learning algorithms, intrusion detection systems are able to perform well in identifying attacks. However, the concern with these deep learning algorithms is their inability to identify a suitable network based on traffic volume, which requires manual changing of hyperparameters, which consumes a lot of time and effort. So, to address this, this paper offers a solution using the extended compact genetic algorithm for the automatic tuning of the hyperparameters. The novelty in this work comes in the form of modeling the problem of identifying attacks as a multi-objective optimization problem and the usage of linkage learning for solving the optimization problem. The solution is obtained using the feature map-based Convolutional Neural Network that gets encoded into genes, and using the extended compact genetic algorithm the model is optimized for the detection accuracy and latency. The CIC-IDS-2017 and 2018 datasets are used to verify the hypothesis, and the most recent analysis yielded a substantial F1 score of 99.23%. Response time, CPU, and memory consumption evaluations are done to demonstrate the suitability of this model in a fog environment.

• Transactions on Control, Automation and Systems Engineering
• /
• v.2 no.4
• /
• pp.268-273
• /
• 2000

Plasma models are crucial to equipment design and process optimization. A radial basis function network(RBFN) in con-junction with statistical experimental design has been used to model a process plasma. A 2$^4$ full factorial experiment was employed to characterized a hemispherical inductively coupled plasma(HICP) in characterizing HICP, the factors that were varied in the design include source power, pressure, position of shuck holder, and Cl$_2$ flow rate. Using a Langmuir probe, plasma attributes were collected, which include typical electron density, electron temperature. and plasma potential as well as their spatial uniformity. Root mean-squared prediction errors of RBEN are 0.409(10(sup)12/㎤), 0.277(eV), and 0.699(V), for electron density, electron temperature, and Plasma potential, respectively. For spatial uniformity data, they are 2.623(10(sup)12/㎤), 5.704(eV) and 3.481(V), for electron density, electron temperature, and plasma potential, respectively. Comparisons with generalized regression neural network(GRNN) revealed an improved prediction accuracy of RBFN as well as a comparable performance between GRNN and statistical response surface model. Both RBEN and GRNN, however, experienced difficulties in generalizing training data with smaller standard deviation.