• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.9
• /
• pp.540-546
• /
• 2003

A fast pattern classification algorithm with Cellular Nonlinear Network-based dynamic programming is proposed. The Cellular Nonlinear Networks is an analog parallel processing architecture and the dynamic programing is an efficient computation algorithm for optimization problem. Combining merits of these two technologies, fast pattern classification with optimization is formed. On such CNN-based dynamic programming, if exemplars and test patterns are presented as the goals and the start positions, respectively, the optimal paths from test patterns to their closest exemplars are found. Such paths are utilized as aggregating keys for the classification. The algorithm is similar to the conventional neural network-based method in the use of the exemplar patterns but quite different in the use of the most likely path finding of the dynamic programming. The pattern classification is performed well regardless of degree of the nonlinearity in class borders.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.1
• /
• pp.149-156
• /
• 2014

NGE(Nested Generalized Exemplar Method) can increase the performance of the noisy data at the same time, can reduce the size of the model. It is the optimal distance-based classification method using a matching rule. NGE cross or overlap hyperrectangles generated in the learning has been noted to inhibit the factors. In this paper, We propose the DHGen(Dominant Hyperrectangle Generation) algorithm which avoids the overlapping and the crossing between hyperrectangles, uses interval weights for mixed hyperrectangles to be splited based on the mutual information. The DHGen improves the classification performance and reduces the number of hyperrectangles by processing the training set in an incremental manner. The proposed DHGen has been successfully shown to exhibit comparable classification performance to k-NN and better result than EACH system which implements the NGE theory using benchmark data sets from UCI Machine Learning Repository.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3642-3667
• /
• 2021

Texture synthesis technology has the advantages of repairing texture and structure at the same time. However, during the filling process, the size of the patch is fixed, and the content of the filling is not fully considered. In order to be able to adaptively change the patch size, we used the exemplar-based inpainting technique as the test algorithm, considering the image structure and texture, calculated the image structure patch size and texture patch size, and comprehensively determined the image patch size. This can adaptively change the patch size according to the filling content. In addition, we use multi-layer images to calculate the priority, so that the order of image repair was more stable. The proposed repair algorithm is compared with other image repair algorithms. The experimental results showed that the proposed adaptive image repair algorithm can better repair the texture and structure of the image, which proved the effectiveness of the proposed algorithm.

• Korean Journal of Cognitive Science
• /
• v.28 no.4
• /
• pp.329-347
• /
• 2017

Early research into category-based feature inference reported various phenomena in human thinking including typicality, diversity, similarity effects, etc. Later research discovered that participants' prior knowledge has an extensive influence on these sorts of reasoning. The current research tested the effects of causal knowledge on feature inference and conducted modeling on the results. Participants performed feature inference for categories consisted of four features where the features were connected either in common cause or common effect structure. The results showed typicality effects along with violations of causal Markov condition in common cause structure and causal discounting in common effect structure. To model the results, it was assumed that participants perform feature inference based on the difference between the probabilities of an exemplar with the target feature and an exemplar without the target feature (that is, $p(E_{F(X)}{\mid}Cat)-p(E_{F({\sim}X)}{\mid}Cat)$). Exemplar probabilities were computed based on causal model theory (Rehder, 2003) and applied to inference for target features. The results showed that the model predicts not only typicality effects but also violations of causal Markov condition and causal discounting observed in participants' data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.11a
• /
• pp.477-480
• /
• 2005

메모리 기반 추론 기법에서 기억공간의 효율적 사용과 분류 시간을 줄이기 위한 다양한 방법들이 연구되고 있으며, NGE(Nested Generalized Exemplar) 이론을 예로 들 수 있다. 본 논문에서는 학습 패턴 집합으로부터 대표패턴을 생성하는 RPA(Recursive Partition Averaging) 기법과 점진적으로 대표패턴을 추출하는 IRPA(Incremental RPA) 기법을 제안한다.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.365-366
• /
• 2007

In this paper, a novel correction method of red-eye effect is proposed. Conventional methods simply reduce red components in red-eye regions, not considering the expanded size of a pupil, thus the correction results can be unnatural. In the proposed method, an exemplar-based inpainting method is used for reducing the pupil region and filling the iris texture instead. Experimental results show that the proposed method is effective and its correction results look more natural than those of conventional methods.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.127-132
• /
• 2006

K-NN (k-Nearest Neighbors), which is a well-known instance-based learning algorithm, simply stores entire training patterns in memory, and uses a distance function to classify a test pattern. K-NN is proven to show satisfactory performance, but it is notorious formemory usage and lengthy computation. Various studies have been found in the literature in order to minimize memory usage and computation time, and NGE (Nested Generalized Exemplar) theory is one of them. In this paper, we propose RPA (Recursive Partition Averaging) and IRPA (Incremental RPA) which is an incremental version of RPA. RPA partitions the entire pattern space recursively, and generates representatives from each partition. Also, due to the fact that RPA is prone to produce excessive number of partitions as the number of features in a pattern increases, we present IRPA which reduces the number of representative patterns by processing the training set in an incremental manner. Our proposed methods have been successfully shown to exhibit comparable performance to k-NN with a lot less number of patterns and better result than EACH system which implements the NGE theory.

• Architectural research
• /
• v.9 no.2
• /
• pp.11-18
• /
• 2007

A cabin for Mr. and Mrs. Popenoe of 1922 was designed by the eminent Los Angeles architect, Rudolph M. Schindler. It stands out as an early exemplar of Schindler's most notable work in its unique employment of compositional strategy. Unfortunately, the cabin was demolished before an in-depth research was executed. In addition, there remains no documentary record with regard to the construction process, structural details and the use of materials of the built cabin. However, a set of drawings of the house are housed in the Schindler Archive. Reworking drawings and fabricating a scale model based on the materials obtained from the Archive, this article first depicts the evolution of the design, and then, attempts to investigate underlying principles governing the spatial composition of the cabin.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.22 no.2
• /
• pp.91-100
• /
• 2018

In this paper, we propose a new method for template matching, patch ratio, to inpaint unknown pixels. Before this paper, many inpainting methods used sum of squared differences(SSD) or sum of absolute differences(SAD) to calculate distance between patches and it was very useful for closest patches for the template that we want to fill in. However, those methods don't consider about geometric similarity and that causes unnatural inpainting results for human visuality. Patch ratio can cover the geometric problem and moreover computational cost is less than using SSD or SAD. It is guaranteed about finding the most similar patches by Cauchy-Schwarz inequality. For ignoring unnecessary process, we compare only selected candidates by priority calculations. Exeperimental results show that the proposed algorithm is more efficent than Criminisi's one.

• KDI Journal of Economic Policy
• /
• v.37 no.2
• /
• pp.1-21
• /
• 2015

The creation of S&T knowledge and development of S&T- based innovation has spread worldwide from traditionally advanced countries to traditionally developing countries, often under the direction of governments. Korea is an exemplar in this new locus. Korea's burst in Science and Technology during the last three decades has made Korea a substantive player in the global production of S&T knowledge and its application to business. Although Korea still trails the US and other top countries in the quality of research, it has leaped from its 1980s standing as bit player in the knowledge economy to being among the leaders in the early 21st Century. This paper shows that Korea's advance benefited from its active participation in the global market in higher education, in international research collaborations, and its close ties to the U.S. Korea's experience offers lessons for other countries who seek to advance by becoming knowledge economies. Korea proves that a developing country can gain comparative advantage in knowledge production and use; that government policy can stimulate such a development; and that openness to the world of higher education and research is the best way to move forward and overcome the middle income trap.