• Structural Engineering and Mechanics
• /
• 제75권2호
• /
• pp.175-191
• /
• 2020

In this study, multi-story structures are actively controlled using metaheuristic algorithms. The soil conditions such as dense, normal and soft soil are considered under near-fault ground motions consisting of two types of impulsive motions called directivity effect (fault normal component) and the flint step (fault parallel component). In the active tendon-controlled structure, Proportional-Integral-Derivative (PID) type controller optimized by the proposed algorithms was used to achieve a control signal and to produce a corresponding control force. As the novelty of the study, the parameters of PID controller were determined by different metaheuristic algorithms to find the best one for seismic structures. These algorithms are flower pollination algorithm (FPA), teaching learning based optimization (TLBO) and Jaya Algorithm (JA). Furthermore, since the influence of time delay on the structural responses is an important issue for active control systems, it should be considered in the optimization process and time domain analyses. The proposed method was applied for a 15-story structural model and the feasible results were found by limiting the maximum control force for the near-fault records defined in FEMA P-695. Finally, it was determined that the active control using metaheuristic algorithms optimally reduced the structural responses and can be applied for the buildings with the soil-structure interaction (SSI).

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 1999년도 추계학술대회-지능형 정보기술과 미래조직 Information Technology and Future Organization
• /
• pp.323-335
• /
• 1999

In this paper, we propose a new hybrid model of artificial neural networks(ANNs) and genetic algorithm (GA) to optimal feature transformation and feature weighting. Previous research proposed several variants of hybrid ANNs and GA models including feature weighting, feature subset selection and network structure optimization. Among the vast majority of these studies, however, ANNs did not learn the patterns of data well, because they employed GA for simple use. In this study, we incorporate GA in a simultaneous manner to improve the learning and generalization ability of ANNs. In this study, GA plays role to optimize feature weighting and feature transformation simultaneously. Globally optimized feature weighting overcome the well-known limitations of gradient descent algorithm and globally optimized feature transformation also reduce the dimensionality of the feature space and eliminate irrelevant factors in modeling ANNs. By this procedure, we can improve the performance and enhance the generalisability of ANNs.

• 대한원격탐사학회지
• /
• 제38권6_2호
• /
• pp.1589-1605
• /
• 2022

위상 언래핑은 위성레이더 간섭기법의 필수적인 자료처리 절차다. 이에 따라 비 딥러닝 기반 언래핑 기법이 다수 개발되었으며 최근에는 딥러닝 기반 언래핑 기법이 제안되고 있다. 본 논문에서는 딥러닝 기반 위성레이더 언래핑 기법을 1) 언래핑된 위상의 예측 방법, 2) 위상 언래핑을 위한 딥러닝 모델의 구조 그리고 3) 학습데이터 제작 방법의 측면에서 최근 연구 동향을 소개하였다. 언래핑된 위상을 예측하는 방법은 모호 정수 분류방법, 위상 단절 구간 탐지 방법, 위상 예측 방법, 딥러닝과 전통적인 언래핑 기법의 연계 방법에 따라 다시 세분화하여 연구 동향을 나타냈다. 일반적으로 활용되는 딥러닝 모델 구조의 특징과 전체 위상 정보를 파악하기 위한 모델 최적화 방법에 대한 연구 사례를 소개하였다. 또한 학습데이터 제작 방법은 주로 위상 변이 제작과 노이즈 시뮬레이션 방법으로 구분하여 연구 동향을 정리하였으며 추후 발전 방향을 제시하였다. 본 논문이 추후 국내의 딥러닝 기반 위상 언래핑 연구의 발전 방향을 모색하는 데에 필요한 기반 자료로 활용되기를 기대한다.

• Steel and Composite Structures
• /
• 제29권6호
• /
• pp.749-758
• /
• 2018

This article derived a hybrid coupling technique using the higher-order displacement polynomial and three soft computing techniques (teaching learning-based optimization, particle swarm optimization, and artificial bee colony) to predict the optimal stacking sequence of the layered structure and the corresponding frequency values. The higher-order displacement kinematics is adopted for the mathematical model derivation considering the necessary stress and stain continuity and the elimination of shear correction factor. A nine noded isoparametric Lagrangian element (eighty-one degrees of freedom at each node) is engaged for the discretisation and the desired model equation derived via the classical Hamilton's principle. Subsequently, three soft computing techniques are employed to predict the maximum natural frequency values corresponding to their optimum layer sequences via a suitable home-made computer code. The finite element convergence rate including the optimal solution stability is established through the iterative solutions. Further, the predicted optimal stacking sequence including the accuracy of the frequency values are verified with adequate comparison studies. Lastly, the derived hybrid models are explored further to by solving different numerical examples for the combined structural parameters (length to width ratio, length to thickness ratio and orthotropicity on frequency and layer-sequence) and the implicit behavior discuss in details.

• 전기학회논문지
• /
• 제60권2호
• /
• pp.398-406
• /
• 2011

In this paper, we introduce a new architecture of PSO-based Polynomial Neural Networks (PNN) and discuss its comprehensive design methodology. The conventional PNN is based on a extended Group Method of Data Handling (GMDH) method, and utilized the polynomial order (viz. linear, quadratic, and modified quadratic) as well as the number of node inputs fixed (selected in advance by designer) at Polynomial Neurons located in each layer through a growth process of the network. Moreover it does not guarantee that the conventional PNN generated through learning results in the optimal network architecture. The PSO-based PNN results in a structurally optimized structure and comes with a higher level of flexibility that the one encountered in the conventional PNN. The PSO-based design procedure being applied at each layer of PNN leads to the selection of preferred PNs with specific local characteristics (such as the number of input variables, input variables, and the order of the polynomial) available within the PNN. In the sequel, two general optimization mechanisms of the PSO-based PNN are explored: the structural optimization is realized via PSO whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the PSO-based PNN, the model is experimented with using Gas furnace process data, and pH neutralization process data. For the characteristic analysis of the given entire data with non-linearity and the construction of efficient model, the given entire system data is partitioned into two type such as Division I(Training dataset and Testing dataset) and Division II(Training dataset, Validation dataset, and Testing dataset). A comparative analysis shows that the proposed PSO-based PNN is model with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• 한국산업융합학회 논문집
• /
• 제26권1호
• /
• pp.113-119
• /
• 2023

In this paper, we propose an optimization of a pose estimation deep learning model for recognition of abnormal behavior in unmanned stores using radio frequencies. The radio frequency use millimeter wave in the 30 GHz to 300 GHz band. Due to the short wavelength and strong straightness, it is a frequency with less grayness and less interference due to radio absorption on the object. A millimeter wave radar is used to solve the problem of personal information infringement that may occur in conventional CCTV image-based pose estimation. Deep learning-based pose estimation models generally use convolution neural networks. The convolution neural network is a combination of convolution layers and pooling layers of different types, and there are many cases of convolution filter size, number, and convolution operations, and more cases of combining components. Therefore, it is difficult to find the structure and components of the optimal posture estimation model for input data. Compared with conventional millimeter wave-based posture estimation studies, it is possible to explore the structure and components of the optimal posture estimation model for input data using genetic algorithms, and the performance of optimizing the proposed posture estimation model is excellent. Data are collected for actual unmanned stores, and point cloud data and three-dimensional keypoint information of Kinect Azure are collected using millimeter wave radar for collapse and property damage occurring in unmanned stores. As a result of the experiment, it was confirmed that the error was moored compared to the conventional posture estimation model.

• Structural Engineering and Mechanics
• /
• 제87권6호
• /
• pp.555-574
• /
• 2023

An efficient optimization algorithm and damage-sensitive objective function are two main components in optimization-based Finite Element Model Updating (FEMU). A suitable combination of these components can considerably affect damage detection accuracy. In this study, a new hybrid damage-sensitive objective function is proposed based on combining two different objection functions to detect the location and extent of damage in structures. The first one is based on Generalized Pseudo Modal Strain Energy (GPMSE), and the second is based on the element's Generalized Flexibility Matrix (GFM). Four well-known population-based metaheuristic algorithms are used to solve the problem and report the optimal solution as damage detection results. These algorithms consist of Cuckoo Search (CS), Teaching-Learning-Based Optimization (TLBO), Moth Flame Optimization (MFO), and Jaya. Three numerical examples and one experimental study are studied to illustrate the capability of the proposed method. The performance of the considered metaheuristics is also compared with each other to choose the most suitable optimizer in structural damage detection. The numerical examinations on truss and frame structures with considering the effects of measurement noise and availability of only the first few vibrating modes reveal the good performance of the proposed technique in identifying damage locations and their severities. Experimental examinations on a six-story shear building structure tested on a shake table also indicate that this method can be considered as a suitable technique for damage assessment of shear building structures.

• 디지털융복합연구
• /
• 제19권10호
• /
• pp.253-263
• /
• 2021

기계학습은 학습에 이용되는 학습 데이터와 데이터를 예측할 인공신경망을 이용하여 비용함수를 만들고, 비용함수를 최소화시키는 파라미터들을 찾는 과정이다. 파라미터들은 비용함수의 그래디언트 기반 방법들을 이용하여 변화하게 된다. 디지털 신호가 복잡할수록, 학습하고자 하는 문제가 복잡할수록, 인공신경망의 구조는 더욱 복잡해지고 깊어진다. 복잡하고, 깊어지는 인공신경망 구조는 과적합(Over-fitting) 문제를 발생시킨다. 과적합 문제를 해결하기 위하여 파라미터의 가중치 감소 정규화 방법이 사용되고 있다. 우리는 이러한 방법에서 추가로 비용함수의 값을 이용한다. 이러한 방법으로 기계학습의 정확도가 향상되는 결과를 얻었으며 이는 수치 실험을 통하여 우수성이 확인된다. 이러한 결과는 기계학습을 통한 인공지능의 폭넓은 데이터에 대한 정확한 값을 도출한다.

• International Journal of Control, Automation, and Systems
• /
• 제1권2호
• /
• pp.194-202
• /
• 2003

In this paper, we introduce a category of Multi-FNN (Fuzzy-Neural Networks) models, analyze the underlying architectures and propose a comprehensive identification framework. The proposed Multi-FNNs dwell on a concept of fuzzy rule-based FNNs based on HCM clustering and evolutionary fuzzy granulation, and exploit linear inference being treated as a generic inference mechanism. By this nature, this FNN model is geared toward capturing relationships between information granules known as fuzzy sets. The form of the information granules themselves (in particular their distribution and a type of membership function) becomes an important design feature of the FNN model contributing to its structural as well as parametric optimization. The identification environment uses clustering techniques (Hard C - Means, HCM) and exploits genetic optimization as a vehicle of global optimization. The global optimization is augmented by more refined gradient-based learning mechanisms such as standard back-propagation. The HCM algorithm, whose role is to carry out preprocessing of the process data for system modeling, is utilized to determine the structure of Multi-FNNs. The detailed parameters of the Multi-FNN (such as apexes of membership functions, learning rates and momentum coefficients) are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. To evaluate the performance of the proposed model, two numeric data sets are experimented with. One is the numerical data coming from a description of a certain nonlinear function and the other is NOx emission process data from a gas turbine power plant.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권4호
• /
• pp.1110-1127
• /
• 2022

To improve the training efficiency and generalization performance of a support vector machine (SVM) in a large-scale set, an optimal SVM learning method based on adaptive sparse sampling and the granularity shift factor is presented. The proposed method combines sampling optimization with learner optimization. First, an adaptive sparse sampling method based on the potential function density clustering is designed to adaptively obtain sparse sampling samples, which can achieve a reduction in the training sample set and effectively approximate the spatial structure distribution of the original sample set. A granularity shift factor method is then constructed to optimize the SVM decision hyperplane, which fully considers the neighborhood information of each granularity region in the sparse sampling set. Experiments on an artificial dataset and three benchmark datasets show that the proposed method can achieve a relatively higher training efficiency, as well as ensure a good generalization performance of the learner. Finally, the effectiveness of the proposed method is verified.