• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.145-155
• /
• 2002

In content-based image retrieval (CBIR), most conventional approaches assume a linear relationship between different features and require users themselves to assign the appropriate weights to each feature. However, the linear relationship assumed between the features is too restricted to accurately represent high-level concepts and the intricacies of human perception. In this paper, a neural network-based image retrieval (NNIR) model is proposed. It has been developed based on a human-computer interaction approach to CBIR using a radial basis function network (RBFN). By using the RBFN, this approach determines the nonlinear relationship between features and it allows the user to select an initial query image and search incrementally the target images via relevance feedback so that more accurate similarity comparison between images can be supported. The experiment was performed to calculate the level of recall and precision based on a database that contains 1,015 images and consists of 145 classes. The experimental results showed that the recall and level of the proposed approach were 93.45% and 80.61% respectively, which is superior than precision the existing approaches such as the linearly combining approach, the rank-based method, and the backpropagation algorithm-based method.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.4
• /
• pp.33-42
• /
• 2010

The induction motor drive applied to field oriented control is widely used in industry applications. However, it is deceased performance and authenticity by saturation, temperature changing, disturbance and parameters changing because modeling of induction motor is nonlinear and complex. In order to control variable speed operation, conventional PI-like controllers are commonly used. These controllers provide limited good performance over a wide range of operation, even under ideal field oriented conditions. This paper proposes self tuning PI controller based on fuzzy-neural network(FNN)-PI controller that is implemented using fuzzy control, neural network, and adaptive fuzzy controller(AFC). Also, this paper proposes estimation of speed using ANN. The proposed control algorithm is applied to induction motor drive system using FNN-PI, AFC and ANN controller. Also, this paper proposes the anlysis results to verify the effectiveness of controller.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.4
• /
• pp.698-706
• /
• 2016

In order to move mobile robots to desired locations in a minimum time, optimal control problems have to be solved; however, their analytic solutions are almost impossible to obtain due to robot nonlinear equations. This paper presents a method to get optimal control gains of mobile robots using genetic algorithms. Since the optimal control gains of mobile robots depend on the initial conditions, the initial condition range is discretized to form some grid points, and genetic algorithms are applied to provide the optimal control gains for the corresponding grid points. The optimal control gains for general initial conditions may be obtained by use of neural networks. So the optimal control gains and the corresponding grid points are used to train neural networks. The trained neural networks can supply pseudo-optimal control gains. Finally simulation studies have been conducted to verify the effectiveness of the method presented in this paper.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.3
• /
• pp.718-723
• /
• 2017

When structural analysis modelling methods of practical fields are investigated, a slab is generally modeled by a finite element mesh using plate elements and a shear wall is modeled using a shell element or wall element for 3-D structural analysis. The point worthy of notice in this practice is that a shear wall is modelled using only one wall or shell element divided by floors and column lines to produce structural models. The modeling method like this can cause analysis errors according to the type of computer programs in use, and these errors reduce the reliability of the analysis results. Therefore, to secure the reliability of structural analysis, studies of the causes of errors and finding reasonable modeling methods are necessary. In this study, the causes of analysis errors according to the modelling methods of a shear wall, which are used in practical fields, were investigated and some considering matters for modelling a shear wall are presented to reduce the analysis errors on these analysis results.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.40 no.11
• /
• pp.979-987
• /
• 2012

This paper implements and integrates algorithms for terrain following of UCAVs (Unmanned Combat Aerial Vehicles): trajectory generation, guidance, and navigation. Terrain following is very important for UCAVs because they perform very dangerous missions such as Suppression of Enemy Air Defences while the terrain following can improve the survivability of UCAVs against from the air defence systems of the enemy. To deal with the GPS jamming, terrain referenced navigation based on nonlinear filter is chosen. For the trajectory generation, Voronoi diagram is adopted to generate horizontal plane path to avoid the air defense system. Cubic spline method is used to generate vertical plane path to prevent collisions with ground while flying sufficiently close to surface. Follow-the-Carrot and pure pursuit tracking methods, which are look-ahead point based guidance algorithms, are applied for the guidance. Numerical simulation is performed to verify the performance of the integrated terrain following algorithm.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.10
• /
• pp.851-857
• /
• 2014

This paper addresses the design of the auto race-track and figure-8 flight mode which can be applied to expand the loitering flight mode and increase the safety of UAV. To implement these flight modes, necessary waypoints and entry points can be calculated automatically from several information of the ground control system. The flight logic is proposed to pass the desired waypoints as well as entry points and transfer to the desired flight path by combining the light-of-sight and loitering guidance controller. The proposed algorithm and logic is verified using the 6-DOF UAV model and nonlinear simulation under the several flight conditions.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.4
• /
• pp.414-427
• /
• 2006

This paper presents an adaptive feedback linearization control scheme for induction motors with simultaneous variation of rotor and stator resistances. Two typical modeling techniques, rotor flux model and stator flux model, have been developed and successfully applied to the controller design and adaptive observer design, respectively. By using stator fluxes as states, over-parametrization in adaptive control can be prevented and control strategy can be developed without the need of nonlinear transformation. It also decrease the relative degree for the flux modulus by one, thereby, yielding, a simple control algorithm. However, when this method is used for flux observer, it cannot guarantee the convergence of flux. Similarly, the rotor flux model may be appropriate for observers, but it is not so for adaptive controllers. In addition, if these two existing methods are merged into overall adaptive control system, it brings about structural complexies. In this paper, we did not use these two modeling methods, and opted for the airgap flux model which takes on only the positive aspects of the existing rotor flux model and stator flux model and prevents structural complexity from occuring. Through theoretical analysis by using Lyapunov's direct method, simulations, and actual experiments, it is shown that stator and rotor resistances converge to their actual values, flux is well estimated, and torque and flux are controlled independently with the measurements of rotor speed, stator currents, and stator voltages. These results were achieved under the persistent excitation condition, which is shown to hold in the simulation.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.3 no.1
• /
• pp.55-66
• /
• 1999

This paper presents an analytical prediction of the hysteresis behavior of reinforced concrete long column with rectangular section under the cyclic loading state. The mechanical characteristic of cracked concrete and reinforcing bar in concrete has been modeled, considering the bond effect between reinforcing bar and concrete, the effect of aggregate interlocking at crack surface and the stiffness degradation after the crack has taken place. The strength increase of concrete due to the lateral confining reinforcement has been also taken into account to model the confined concrete. The formulation of these models for concrete and reinforcing bar has been based on the smeared crack concept that the stress-strain relationship of reinforced concrete element would be defined using the average values. In addition to the material nonlinear properties, the algorithm for large displacement problem that may give an additional deformation has been formulated using total Lagrangian formulation. The analytically predicted behavior was compared with test result and they showed good agreement in overall behavior.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.9
• /
• pp.35-42
• /
• 1998

Finding a technique to achieve high machining precision and high productivity is an important issue for CNC machining. One of the solutions to meet better performance of machining is feedrate control. In this paper we present an adaptive feedrate neuro-control method for high precision and high speed machining. The adaptive neuro-control architecture consists of a neural network identifier(NNI) and an iterative learning control algorithm with inversion of the NNI. The NNI is an identifier for the nonlinear characteristics of feedrate and contour error, which is utilized in iterative learning for adaptive feedrate control with specified contour error tolerance. The proposed neuro-control method has been successfully evaluated for machining circular, corner and involute contours by computer simulations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.154-162
• /
• 2003

In this paper, Associative Memory with Cellular Neural Networks classifies and recognizes image patterns as an operator applied to image process. CNN processes nonlinear data in real-time like neural networks, and made by cell which communicates with each other directly through its neighbor cells as the Cellular Automata does. It is applied to the optimization problem, associative memory, pattern recognition, and computer vision. Image processing with CNN is appropriate to 2-D images, because each cell which corresponds to each pixel in the image is simultaneously processed in parallel. This paper shows the method for designing the structure of associative memory based on CNN and getting output image by choosing the most appropriate weight pattern among the whole learned weight pattern memories. Each template represents weight values between cells and updates them by learning. Hebbian rule is used for learning template weights and LMS algorithm is used for classification.