• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.293-301
• /
• 2001

This paper reviews three methods to compute a pointwise confidence interval of neuro-fuzzy models and compares their estimation perfonnanee through simulations. The eOITl.putation methods under consideration include stacked generalization using cross-validation, predictive error bar in regressive models, and local reliability measure for the networks employing a local representation scheme. These methods implemented on the neuro-fuzzy models are applied to the problems of simple function approximation and chaotic time series prediction. The results of reliability estimation are compared both quantitatively and qualitatively.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.1
• /
• pp.82-86
• /
• 2008

The article presents ARTMAP and Fuzzy BK-Product approach underwater obstacle avoidance for the Autonomous underwater Vehicles (AUV). The AUV moves an unstructured area of underwater and could be met with obstacles in its way. The AUVs are equipped with complex sensorial systems like camera, aquatic sonar system, and transducers. A Neural integrated Fuzzy BK-Product controller, which integrates Fuzzy logic representation of the human thinking procedure with the learning capabilities of neural-networks (ARTMAP), is developed for obstacle avoidance in the case of unstructured areas. In this paper, ARTMAP-Fuzzy BK-Product controller architecture comprises of two distinct elements, are 1) Fuzzy Logic Membership Function and 2) Feed-Forward ART component. Feed-Forward ART component is used to understanding the unstructured underwater environment and Fuzzy BK-Product interpolates the Fuzzy rule set and after the defuzzyfication, the output is used to take the decision for safety direction to go for avoiding the obstacle collision with the AUV. An on-line reinforcement learning method is introduced which adapts the performance of the fuzzy units continuously to any changes in the environment and make decision for the optimal path from source to destination.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.22 no.4
• /
• pp.341-348
• /
• 2006

Accurate fit of the implant prosthesis is important in ensuring long term success of osseointegrated implant. Inaccurate fit of the implant prosthesis may give rise to complications and mechanical failure. To evaluate fite of the implant prosthesis, the development of the methods of analyzing the degree of misfit is important in clinical practice. To analyze the degree of the misfit of implant prosthesis, modal testing was used. A 2-dimensional finite element modal testing was accomplished. Four 2-dimensional finite element models with various levels of misfit of implant prostheses were constructed. Thickness gauges were simulated to make misfit in the implant prostheses. With eigenvalue analysis, the natural frequencies of the models were found in the frequency domain representation of vibration. According to the difference of degree of misfit, natural frequencies of the models were changed.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2012.11a
• /
• pp.227-228
• /
• 2012

In contemporary architectural practice, flat sections and plan drawings are no longer a primary means of representation and communication with participants. A typical building design has an ornamental exterior wall system and a roof system that should have water-proof quality and drainage function. By comparison, distinction between exterior wall and roof are unclear in freeform buildings, and they are integrated into a concept of a building envelope. This study is to propose 3D coordinate control technology for freeform structure by CNC curved tube method in order to develop a BIM-based envelope design and construction method for freeform building. Because a much wider freeform building construction can be achieved with correct 3D data and easy-to-implement in construction field, the proposed 3D coordinate control technology is highly recommended for practical use instead of the conventional CAD system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.4
• /
• pp.105-111
• /
• 2006

Recently, many electronic system with various character input systems for information representation and delivery. Character input systems for the Korean language are keyboards and mobile phone that have 12 or more input buttons and so on. But these input systems give difficulties for the disabled because the input system have 12 and more small input buttons. In this paper, we developed Korean language input software in order to develop a Korean language input system for the handicapped. The developed system have 5 input buttons and 2 function buttons for Korean language typing using Korean language shape input scheme. This system is not only easy to use by the handicapped, but also simple for children and foreigner to learn Korean language.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.3 s.180
• /
• pp.22-31
• /
• 2006

This paper introduces an approach to an ontology-based knowledge framework for product life cycle management (PLM). Participants in a product life cycle want to share comprehensive product knowledge without any ambiguity and heterogeneity. However, previous knowledge management approaches are limited in providing those aspects. Therefore, we suggest an ontology-based knowledge framework including knowledge maps, axioms and specific knowledge far domain. The bottom level, the axiom, specifies the semantics of concepts and relations of knowledge so that ambiguity of the semantics can be alleviated. The middle level is a product development knowledge map; it defines the concepts and the relations of the product domain common knowledge and guides engineers to process their engineering decisions. The middle level is then classified further into more detailed levels, such as generic product level, specific product level, product version level, and product item level for PLM. The top level is specialized knowledge fer a specific domain that gives the solution of a specific task or problem. It is classified into three knowledge types: expert knowledge, engineering function knowledge, and data-analysis-based knowledge. This proposed framework is based on ontology to accommodate a comprehensive range of unambiguous knowledge for PLM and is represented with first-order logic to maintain a uniform representation.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.05b
• /
• pp.409-413
• /
• 2005

Even though the relative importance of length scale of flow system allow us to simplify three dimensional flow problem to one or two dimensional representation, many systems still require three dimensional analysis. The objective of this study is to develop an efficient and accurate finite element model for analyzing and predicting three dimensional flow features in natural rivers and to offend to model spreading of pollutants and transport of sediments in the future. Firstly, three dimensional Reynolds averaged Navier-Stokes equations with the hydrostatic pressure assumption in generalized curvilinear coordinates were combined with the kinematic free-surface condition. Secondly. to simulate realistic high Reynolds number flow, the model employed the Streamline Upwind/Petrov-Galerkin(SU/PG) scheme as a weighting function for the finite element method in conjunction with an appropriate turbulence model(Smagorinsky scheme for the horizontal plain and Mellor-Yamada scheme for the vertical direction). Several tests is performed for the purpose of validation and verification of the developed model. A simple rectangular channel, 5-shaped and U-shaped channel are used for tests and comparisons are made with RMA-10 model. Runs for each case is converged stably without a oscillation and calculated water-surface deformation, longitudinal and transversal velocities, and velocity vector fields are in good agreement with the results of RMA-10 model.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.2
• /
• pp.13-21
• /
• 1996

The necessity and usefulness of higher-order neural networks have been well-known since early days of neurocomputing. However the explosive number of terms has hampered the design and training of such networks. In this paper we present an evolutionary learning method for efficiently constructing problem-specific higher-order neural models. The crux of the method is the neural tree representation employing both sigma and pi units, in combination with the use of an MDL-based fitness function for learning minimal models. We provide experimental results in classification and prediction problems which demonstrate the effectiveness of the method. I. Introduction topology employs one hidden layer with full connectivity between neighboring layers. This structure has One of the most popular neural network models been very successful for many applications. However, used for supervised learning applications has been the they have some weaknesses. For instance, the fully mutilayer feedforward network. A commonly adopted connected structure is not necessarily a good topology unless the task contains a good predictor for the full *d*dWs %BH%W* input space.

• Korean Institute of Interior Design Journal
• /
• v.15 no.5 s.58
• /
• pp.12-19
• /
• 2006

The artistic features of German Expressionism in the early twentieth century are often recognized for its abstract and emotional representation in art and architecture. Expressionism departed from the paintings, notably the works of Der Blaue Reiter and the Bruck, but the architectural works with curve and organic features were also taken as expressive. German architects Hans Scharoun (1893-1972) and Hugo Haring (1882-1958), in this regard, have long been regarded as Expressionist architects, but recent studies suggest that their architectural designs include a profound idea of modem functional building. Scharoun and Haring held a socialist utopian vision as other modernists have also had, but their inherent view upon modern architecture was function which was mistakenly viewed as Expressionism in earlier documents. This paper intends to exemplify how Expressionism is inappropriate to represent the expressive presentations of Scharoun and Haring. Despite the fact that their designs possess certain expressionist elements, their works can also be constructed as an advanced functionalism. Many young architects in Germany were not given chances to build due to economic hardship after the First World War, and they were naturally led to imagery sketch designs for future architecture. Abstract Idea was freely exposed in its preliminary visual form, and it is also uneasy to draw a borderline between expressive presentation and the Expressionism itself.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.173-188
• /
• 2013

In Facial Expression Recognition Systems (FERS), only particular regions of the face are utilized for discrimination. The areas of the eyes, eyebrows, nose, and mouth are the most important features in any FERS. Applying facial features descriptors such as the local binary pattern (LBP) on such areas results in an effective and efficient FERS. In this paper, we propose an automatic facial expression recognition system. Unlike other systems, it detects and extracts the informative and discriminant regions of the face (i.e., eyes, nose, and mouth areas) using Haar-feature based cascade classifiers and these region-based features are stored into separate image files as a preprocessing step. Then, LBP is applied to these image files for facial texture representation and a feature-vector per subject is obtained by concatenating the resulting LBP histograms of the decomposed region-based features. The one-vs.-rest SVM, which is a popular multi-classification method, is employed with the Radial Basis Function (RBF) for facial expression classification. Experimental results show that this approach yields good performance for both frontal and near-frontal facial images in terms of accuracy and time complexity. Cohn-Kanade and JAFFE, which are benchmark facial expression datasets, are used to evaluate this approach.