• International Journal of Control, Automation, and Systems
• /
• v.6 no.5
• /
• pp.755-766
• /
• 2008

This study presents a recurrent compensatory fuzzy neural network (RCFNN) for dynamic system identification. The proposed RCFNN uses a compensatory fuzzy reasoning method, and has feedback connections added to the rule layer of the RCFNN. The compensatory fuzzy reasoning method can make the fuzzy logic system more effective, and the additional feedback connections can solve temporal problems as well. Moreover, an online learning algorithm is demonstrated to automatically construct the RCFNN. The RCFNN initially contains no rules. The rules are created and adapted as online learning proceeds via simultaneous structure and parameter learning. Structure learning is based on the measure of degree and parameter learning is based on the gradient descent algorithm. The simulation results from identifying dynamic systems demonstrate that the convergence speed of the proposed method exceeds that of conventional methods. Moreover, the number of adjustable parameters of the proposed method is less than the other recurrent methods.

• Proceedings of the Korean Society of Computational and Applied Mathematics Conference
• /
• 2003.09a
• /
• pp.9-9
• /
• 2003

Let $\Omega$ be a bounded, open, and polygonal domain in $R^2$ with re-entrant corners. We consider the following Partial Differential Equations: $$(I-\nabla\nabla\cdot+\nabla^{\bot}\nabla\times)u\;=\;f\;in\;\Omega$$, $$n\cdotu\;0\;0\;on\;{\Gamma}_{N}$$, $${\nabla}{\times}u\;=\;0\;on\;{\Gamma}_{N}$$, $$\tau{\cdot}u\;=\;0\;on\;{\Gamma}_{D}$$, $$\nabla{\cdot}u\;=\;0\;on\;{\Gamma}_{D}$$ where the symbol $\nabla\cdot$ and $\nabla$ stand for the divergence and gradient operators, respectively; $f{\in}L^2(\Omega)^2$ is a given vector function, $\partial\Omega=\Gamma_{D}\cup\Gamma_{N}$ is the partition of the boundary of $\Omega$; nis the outward unit vector normal to the boundary and $\tau$represents the unit vector tangent to the boundary oriented counterclockwise. For simplicity, assume that both $\Gamma_{D}$ and $\Gamma_{N}$ are nonempty. Denote the curl operator in $R^2$ by $$\nabla\times\;=\;(-{\partial}_2,{\partial}_1$$ and its formal adjoint by $${\nabla}^{\bot}\;=\;({-{\partial}_1}^{{\partial}_2}$$ Consider a weak formulation(WF): Find $u\;\in\;V$ such that $$a(u,v):=(u,v)+(\nabla{\cdot}u,\nabla{\cdot}v)+(\nabla{\times}u,\nabla{\times}V)=(f,v),\;A\;v{\in}V$$. (2) We assume there is only one singular corner. There are many methods to deal with the domain singularities. We introduce them shortly and we suggest a new Finite Element Methods by using Singular representation for the solution.

• International Journal of Contents
• /
• v.4 no.2
• /
• pp.7-12
• /
• 2008

In this paper, we present a real-time physical simulation model of water surfaces with a novel method to represent the water mass flow in full three dimensions. In a physical simulation model, the state of the water surfaces is represented by a set of physical values, including height, velocity, and the gradient. The evolution of the velocity field in previous works is handled by a velocity solver based on the Navier-Stokes equations, which occurs as a result of the unevenness of the velocity propagation. In this paper, we integrate the principle of the mass conservation in a fluid of equilateral density to upgrade the height field from the unevenness, which in mathematical terms can be represented by the divergence operator. Thus the model generates waves induced by horizontal velocity, offering a simulation that puts forces added in all direction into account when calculating the values for height and velocity for the next frame. Other effects such as reflection off the boundaries, and interactions with floating objects are involved in our method. The implementation of our method demonstrates to run with fast speed scalable to real-time rates even for large simulation domains. Therefore, our model is appropriate for a real-time and large scale water surface simulation into which the animator wishes to visualize the global fluid flow as a main emphasis.

• Proceedings of the KIEE Conference
• /
• 1998.11c
• /
• pp.910-912
• /
• 1998

In this paper, we purpose automatic diagnosis in online, as the fundamental study to diagnose the partial discharge mechanism and to predict the lifetime, by introduction a neural network. In the proposed method, Ire use acoustic emission sensing system and calculate a fixed quantity statistic operator by pulse number and amplitude. Using statically operators such as the center of gravity(G) and the gradient of the discharge distribute(C), we analyzed the early stage and the middle stage. the fixed quantity statistic operators are learned by a neural network. The diagnosis of insulation degradation and a lifetime prediction by the early stage time are achieved. On the basis of revealed excellent diagnosis ability through the neural network learning for the patterns during degradation, it was proved that the neural network is appropriate for degradation diagnosis and lifetime prediction in partial discharge.

• Journal of ILASS-Korea
• /
• v.6 no.1
• /
• pp.35-43
• /
• 2001

Previous studies on image processing techniques for panicle size measurement usually have focused on a single panicle or weakly overlapped particles. In the present work, the image processing algorithm for particle size measurement has been improved to process heavily-overlapped spherical-particle images. The algorithm consists of two steps; detection of boundaries which separate the images of the overlapped panicles from the background and the panicle identification process. For the first step, Sobel operator (using gray-level gradient) and the thinning process was adopted, and compared with the gray-level thresholding method that has been widely adopted. In the second, Hough transform was used. Hough transform is the detection algorithm of parametric curves such as straight lines or circles which can be described by several parameters. To reduce the measurement error, the process of finding the true center was added. The improved algorithm was tested by processing an image frame which contains heavily overlapped spherical panicles. The results showed that both the performances of detecting the overlapped images and separating the panicle from them were improved.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.5 s.176
• /
• pp.1254-1260
• /
• 2000

There have been many developments in super precision working technique and working method up to, now. But, it is very difficult to evaluate working surface accurately without the technicians experience and judgment. Surface roughness tester using stylus was used to measure surface condition generally But this method is not so desirable because of damage on test piece caused by contact between the workpiece and the stylus sensor. As a result, non-contact method was known as a good way to carry, out this process without damage. However, this is a difficult one among the various measuring methods. So we are tying to suggest a new method using texture analysis through image processing to get a surface information in worked test piece. Co-occurrence matrix using difference of gray levels between a pixel and its neighboring one was used to study behavior of surface roughness and to J acquire data for analysis. Standard specimen was adapted to verify this research. We suggest texture information method in order to evaluate surface state for the best measurement system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.1
• /
• pp.179-184
• /
• 2004

This paper presents an image segmentation algorithm to obtain the 3D body shape data that the grid pattern and the body contour lute in the background image are extracted using the new proposed hybrid method. The body contour line is extracted based on maximum biased anisotropic recognition(MaxBAR) algorithm which recognizes the most strong and robust edges in the image since the normal derivative at the edges is large, while the tangential derivatives can be small. The grid patterns within body contour lines are extracted by grid pattern detection (GPD). The body contour lilies and the grid patterns are combined. The consecutive run test based on heuristic method is used to link the disconnected line and reduce noise line. This proposed segmentation method is more effective than the conventional method which uses a gradient and a laplacian operator, verified with application two conventional method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.11
• /
• pp.5583-5604
• /
• 2016

In this paper, we present a novel image operator to extract textual information in natural scene images. First, a powerful refiner called the Stroke Color Extension, which extends the widely used Stroke Width Transform by incorporating color information of strokes, is proposed to achieve significantly enhanced performance on intra-character connection and non-character removal. Second, a character classifier is trained by using gradient features. The classifier not only eliminates non-character components but also remains a large number of characters. Third, an effective extractor called the Character Color Transform combines color information of characters and geometry features. It is used to extract potential characters which are not correctly extracted in previous steps. Fourth, a Convolutional Neural Network model is used to verify text candidates, improving the performance of text detection. The proposed technique is tested on two public datasets, i.e., ICDAR2011 dataset and ICDAR2013 dataset. The experimental results show that our approach achieves state-of-the-art performance.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.220-228
• /
• 2022

Image always carry useful information, detecting a text from scene images is imperative. The proposed work's purpose is to recognize scene text image, example boarding image kept on highways. Scene text detection on highways boarding's plays a vital role in road safety measures. At initial stage applying preprocessing techniques to the image is to sharpen and improve the features exist in the image. Likely, morphological operator were applied on images to remove the close gaps exists between objects. Here we proposed a two phase algorithm for extracting and recognizing text from scene images. In phase I text from scenery image is extracted by applying various image preprocessing techniques like blurring, erosion, tophat followed by applying thresholding, morphological gradient and by fixing kernel sizes, then canny edge detector is applied to detect the text contained in the scene images. In phase II text from scenery image recognized using MSER (Maximally Stable Extremal Region) and OCR; Proposed work aimed to detect the text contained in the scenery images from popular dataset repositories SVT, ICDAR 2003, MSRA-TD 500; these images were captured at various illumination and angles. Proposed algorithm produces higher accuracy in minimal execution time compared with state-of-the-art methodologies.

• Nuclear Engineering and Technology
• /
• v.56 no.8
• /
• pp.3167-3179
• /
• 2024

In abnormal states of nuclear power plants (NPPs), operators undertake mitigation actions to restore a normal state and prevent reactor trips. However, in abnormal states, the NPP condition fluctuates rapidly, which can lead to human error. If human error occurs, the condition of an NPP can deteriorate, leading to reactor trips. Sudden shutdowns, such as reactor trips, can result in the failure of numerous NPP facilities and economic losses. This study develops a remaining trip time (RTT) prediction system as part of an operator support system to reduce possible human errors and improve the safety of NPPs. The RTT prediction system consists of an algorithm that utilizes artificial intelligence (AI) and explainable AI (XAI) methods, such as autoencoders, light gradient-boosting machines, and Shapley additive explanations. AI methods provide diagnostic information about the abnormal states that occur and predict the remaining time until a reactor trip occurs. The XAI method improves the reliability of AI by providing a rationale for RTT prediction results and information on the main variables of the status of NPPs. The RTT prediction system includes an interface that can effectively provide the results of the system.