• Structural Engineering and Mechanics
• /
• 제38권5호
• /
• pp.651-674
• /
• 2011

This paper presents a novel method for predicting the failure probability of structural or mechanical systems subjected to random loads and material properties involving multiple design points. The method involves Multicut High Dimensional Model Representation (Multicut-HDMR) technique in conjunction with moving least squares to approximate the original implicit limit state/performance function with an explicit function. Depending on the order chosen sometimes truncated Cut-HDMR expansion is unable to approximate the original implicit limit state/performance function when multiple design points exist on the limit state/performance function or when the problem domain is large. Multicut-HDMR addresses this problem by using multiple reference points to improve accuracy of the approximate limit state/performance function. Numerical examples show the accuracy and efficiency of the proposed approach in estimating the failure probability.

• 전기학회논문지
• /
• 제64권7호
• /
• pp.1104-1113
• /
• 2015

In this paper, we propose Two-Dimensional Robust Face Recognition System Realized with the Aid of Facial Symmetry with Illumination Variation. Preprocessing process is carried out to obtain mirror image which means new image rearranged by using difference between light and shade of right and left face based on a vertical axis of original face image. After image preprocessing, high dimensional image data is transformed to low-dimensional feature data through 2-directional and 2-dimensional Principal Component Analysis (2D)2PCA, which is one of dimensional reduction techniques. Polynomial-based Radial Basis Function Neural Network pattern classifier is used for face recognition. While FCM clustering is applied in the hidden layer, connection weights are defined as a linear polynomial function. In addition, the coefficients of linear function are learned through Weighted Least Square Estimation(WLSE). The Structural as well as parametric factors of the proposed classifier are optimized by using Particle Swarm Optimization(PSO). In the experiment, Yale B data is employed in order to confirm the advantage of the proposed methodology designed in the diverse illumination variation

• Smart Structures and Systems
• /
• 제18권3호
• /
• pp.425-448
• /
• 2016

In this paper, a new Pigeon Colony Algorithm (PCA) based on the features of a pigeon colony flying is proposed for solving global numerical optimization problems. The algorithm mainly consists of the take-off process, flying process and homing process, in which the take-off process is employed to homogenize the initial values and look for the direction of the optimal solution; the flying process is designed to search for the local and global optimum and improve the global worst solution; and the homing process aims to avoid having the algorithm fall into a local optimum. The impact of parameters on the PCA solution quality is investigated in detail. There are low-dimensional functions, high-dimensional functions and systems of nonlinear equations that are used to test the global optimization ability of the PCA. Finally, comparative experiments between the PCA, standard genetic algorithm and particle swarm optimization were performed. The results showed that PCA has the best global convergence, smallest cycle indexes, and strongest stability when solving high-dimensional, multi-peak and complicated problems.

• 한국생산제조학회지
• /
• 제9권2호
• /
• pp.52-58
• /
• 2000

the quality of a TV is closely connected with the high quality surface of Braun tube. To get high quality surface an improved grinding system is needed. It has three main parts : the housing part of supporting frame the outershaft part rotat-ed by motor and the innershaft part having eccentricity from the rotation axis of the outershaft. the housing part and the outershaft part are connected by outerbearings, The outershaft part and the innershaft part are connected by innerbearings. Although the outershaft part is rotated at high-speed the innershaft part is not rotated by offset coupling. The high quality grinding surface can be obtained by this mechanism of panel surface grinder, Because the innershaft is unbalanced by eccentricity from rotation axis of outershaft the unbalancing vibration is resulted In this rotor system with high-speed rota-tion the unbalancing vibration makes the opertion unstable. In this research the transfer function is obtained bythe frequency response analysis of finite element model. The simu-lation result is proved by comparing with the experimental result measured by signal analyzer Then the results are corre-lated. in order to improve the design an optimization method is used instead of two-planes balancing method The parts of the 3-dimensional panel surface grinder satisfy the each constraint, The result shows that the design of the panel surface grinder can be optimized.

• Communications for Statistical Applications and Methods
• /
• 제11권3호
• /
• pp.539-551
• /
• 2004

Multiple responses are often observed in many application fields, such as customer's time-of-day pattern for using internet. Some decision trees for multiple responses have been constructed by many researchers. However, if the response is a high-dimensional vector that can be thought of as a discretized function, then fitting a multivariate decision tree may be unsuccessful. Yu and Lambert (1999) suggested spline tree and principal component tree to analyze high dimensional response vector by using dimension reduction techniques. In this paper, we shall propose factor tree which would be more interpretable and competitive. Furthermore, using Korean internet company data, we will analyze time-of-day patterns for internet user.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제2권2호
• /
• pp.102-110
• /
• 2002

In this paper, we present the fabrication of tunable capacitors and 3-dimensional inductors. This work was related to fabricated 3-dimensional device for need of micro device in developing new intelligence age. This device was fabricated by electroplating used electroplating PR and high-vacuum evaporation of metal. Fabricated micro-inductor is consisted of air-bridge on electroplating rod and electroplated core. Micro-capacitor is consisted of thin metal membrane and electroplated core. Electroplating material is used Cu metal solvent. Air-gap between metal-layers function as almost perfect isolation layer. The most advantage of our micro-inductor and micro-capacitor compared to present device is a possibility that can fabricate on RF MEMS(microelectro-mechanical systems) application with high performance and various function. In this paper, we present the fabrication of tunable capacitors and 3-dimensional inductors. This work was related to fabricated 3-dimensional device for need of micro-device in developing new intelligence age. This device was fabricated by electroplating used electroplating PR and high-vacuum evaporation of metal. Fabricated micro-inductor is consisted of air-bridge on electroplating rod and electroplated core. Micro-capacitor is consisted of thin metal membrane and electroplated core. Electroplating material is used Cu metal solvent. Air-gap between metal-layers function as almost perfect isolation layer. The most advantage of our micro-inductor and micro-capacitor compared to present device is a possibility that can fabricate on RF MEMS application with high performance and various functions.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권4호
• /
• pp.270-275
• /
• 2016

We present an approach for acceleration actor-critic algorithm for reinforcement learning with continuous action space. Actor-critic algorithm has already proved its robustness to the infinitely large action spaces in various high dimensional environments. Despite that success, the main problem of the actor-critic algorithm remains the same-speed of convergence to the optimal policy. In high dimensional state and action space, a searching for the correct action in each state takes enormously long time. Therefore, in this paper we suggest a search accelerating function that allows to leverage speed of algorithm convergence and reach optimal policy faster. In our method, we assume that actions may have their own distribution of preference, that independent on the state. Since in the beginning of learning agent act randomly in the environment, it would be more efficient if actions were taken according to the some heuristic function. We demonstrate that heuristically-accelerated actor-critic algorithm learns optimal policy faster, using Educational Process Mining dataset with records of students' course learning process and their grades.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권2호
• /
• pp.193-198
• /
• 2004

This paper describes an automatic finite element (FE) mesh generation for three-dimensional structures consisting of tree-form surfaces. This mesh generation process consists of three subprocesses: (a) definition of geometric model, (b) generation of nodes, and (c) generation of elements. One of commercial solid modelers is employed for three-dimensional solid structures. Node is generated if its distance from existing node points is similar to the node spacing function at the point. The node spacing function is well controlled by the fuzzy knowledge processing. The Voronoi diagram method is introduced as a basic tool for element generation. Automatic generation of FE meshes for three-dimensional solid structures holds great benefits for analyses. Practical performances of the present system are demonstrated through several mesh generations for three-dimensional complex geometry.

• 한국철도학회논문집
• /
• 제3권4호
• /
• pp.229-236
• /
• 2000

In this study, the unsteady flow field induced by a high-speed train passing through a tunnel is numerically simulated by using an axi-symmetric Euler Equation. The modified patched grid scheme applied to a structured grid system was used to handle the relative motion of a train. The hybrid-dimensional approach which mixed 1D and axi-symmetric dimension was used to reduce the computation time and memory storage. By employing the hybrid-dimensional approach, a long tunnel as much as 5 km was able to be simulated efficiently. The results show that the maximum pressure rise in the tunnel by the entrance of the train is a function of both train speed and train-tunnel cross-sectional area ratio. The unsteady pressure fluctuation in the tunnel and around the train was also investigated in the real condition; Korean high-speed train on the Seoul-Pusan line.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.877-878
• /
• 2008

We suggest a feature reduction method to classify mouse function data sets, which integrate several biological data sets represented as high dimensional vectors. To increase classification accuracy and decrease computational overhead, it is important to reduce the dimension of features. To do this, we employed Hybrid Huberized Support Vector Machine with kernels used for a kernel logistic regression method. When compared to support vector machine, this a pproach shows the better accuracy with useful features for each mouse function.