• Korean Journal of Cognitive Science
• /
• v.28 no.2
• /
• pp.111-131
• /
• 2017

The connectionist model is one approach to studying language processing from a computational perspective. And building a representation in the connectionist model study is just as important as making the structure of the model in that it determines the level of learning and performance of the model. The connectionist model has been constructed in two different ways: localist representation and distributed representation. However, the localist representation used in the previous studies had limitations in that the unit of the output layer having a rare target activation value is inactivated, and the past distributed representation has the limitation of difficulty in confirming the result by the opacity of the displayed information. This has been a limitation of the overall connection model study. In this paper, we present a new method to induce distributed representation with local representation using abstraction of information, which is a feature of restricted Boltzmann machine, with respect to the limitation of such representation of the past. As a result, our proposed method effectively solves the problem of conventional representation by using the method of information compression and inverse transformation of distributed representation into local representation.

• Journal of Korea Water Resources Association
• /
• v.33 no.S1
• /
• pp.28-36
• /
• 2000

A TIN, Triagulated Irregular Network, based topographic modeling method and a distributed rainfall-runoff model using the topographic representation is presented. In the TIN based topographic representation, a watershed basin is modeled as a set of contiguous non-overlapping triagular facets : the watershed basin is subdivided according to streamlines to deal with water movement one-dimensionally ; and each partitioned catchment is approximated to a slope element having a quasi-three-dimensional shape by using cubic spline functions. On an approximated slope element, water movement is represented by combined surface-subsurface kinematic wave equations considering a change of slope gradient and slope width. By using the distributed rainfall-runoff model, the effects of spatial variability of soil properties on runoff response are examined.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2000.05a
• /
• pp.28-36
• /
• 2000

A TIN, Triangulated Irregular Network, based topographic modeling method and a distributed rainfall-runoff model using the topographic representation is presented. In the TIN based topographic representation, a watershed basin is modeled as a set of contiguous non-overlapping triangular facets: the watershed basin is subdivided according to streamlines to deal with water movement one-dimensionally; and each partitioned catchment is approximated to a slope element having a quasi-three-dimensional shape by using cubic spline functions. On an approximated slope element, water movement is represented by combined surface-subsurface kinematic wave equations considering a change of slope gradient and slope width. By using the distributed rainfall-runoff model, the effects of spatial variability of soil properties on runoff response are examined.

• Proceedings of the KIEE Conference
• /
• 1988.11a
• /
• pp.450-454
• /
• 1988

In order to represent and analyze distributed system design, the model based on an extended form of Petri nets, which enables one to represent both the structure and the behavior of a distributed system, is predented. Behavioral properties of the design representation are verified by translating the extended Petri net into an equivalent ordinary Petri net. The model emphasizes the unified representation of control flows, hierarchical structure, and distributed system state. Modeling technique isemployed for the performance and function analysis of flexible manufacturing system with a set of processors.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.2
• /
• pp.179-199
• /
• 2019

In this paper, we propose optimal methodologies for classifying patent literature by examining various feature extraction methods, machine learning and deep learning models, and provide optimal performance through experiments. We compared the traditional BoW method and a distributed representation method (word embedding vector) as a feature extraction, and compared the morphological analysis and multi gram as the method of constructing the document collection. In addition, classification performance was verified using traditional machine learning model and deep learning model. Experimental results show that the best performance is achieved when we apply the deep learning model with distributed representation and morphological analysis based feature extraction. In Section, Class and Subclass classification experiments, We improved the performance by 5.71%, 18.84% and 21.53%, respectively, compared with traditional classification methods.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.914-916
• /
• 2003

Most current 3D digital maps are 2.5 dimension models based on DEM, which can only be recognized, browsed and operated by a special software, far from meeting the needs of a modern digital city (global) with the distributed, isomerous and multiple application on the real 3D representation and open sharing models. In this paper, a new generation digital city oriented 3D digital map is studied. Firstly, a real 3D digital map representation is presented. And then, some key techniques and methods for browser-based 3D digital map’s representation, display and operation are introduced, which can realized the open sharing of 3D map in distributed, isomerous and multiple application environment. Furthermore, the scale driving technique of proposed 3D digital map is also studied. And currently, some developments based on some of the above methods are being carried to provide key and general platform for other application software’s development.

• Journal of Korean Elementary Science Education
• /
• v.23 no.3
• /
• pp.251-265
• /
• 2004

Conceptual teaming has been one of the important issue in science education, and its theory and method has been interacted with the studies of philosophy of science, cognitive science, and cognitive psychology. The last two decades have witnessed a remarkable growth of the study on brain-style computation, i.e. connectionism. This study aimed to investigate the properties of the connectionist views of the concept and its implications in the conceptual learning of science. In connectionist views, a concept was represented as a pattern of activity distributed over many connected units, and a kind of network composed of many sub-concept units. And the ＇distributed representation＇ had the features of the constructivity, the automatically generalization, and the tunability. On the base of these views, it was suggested that (ⅰ) ＇Typically-Perceived-Situation＇, a kind of mental representation rising spontaneously in an individual mind when someone is thinking about any object, should be highlighted, and (ⅱ) the roles of the sub-concept units in formation of concept and the resolution of concept into the sub-concept units should be highlighted. Finally the meanings of these implications in conceptual teaming of science are discussed.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.457-458
• /
• 2007

This paper propose a method for representing distributed data of sensor networks. The proposed method is based on a general distributed regression framework that models sensor data by fitting a global function to each of the local measurements and explores the possible extensions of distribution regression by using complex signal representations. In order to reduce the amount of processed data and the required communication, the signal model has to be as compact as possible, with the ability to restore the arbitrary measurements. To achieve this requirement, data compression step is included, where the basis function set is changed to an overcomplete set. This have better advantages in case of nonstationary signal modeling than complete base representation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.12C
• /
• pp.218-224
• /
• 2001

The objective of Distributed Parallel Computing is to solve the computationally intensive problems, which have several types of parallelism, on a suite of high performance and parallel machines in a manner that best utilizes the capabilities of each machine. In this paper, we propose a computational model including the generalized graph representation method of distributed parallel systems for speedup analysis, and analyze how the super-linear speedup is achieved when scheduling of programs with diverse embedded parallelism modes onto a distributed heterogeneous supercomputing network environment. The proposed representation method can also be applied to simple homogeneous or heterogeneous systems whose components are heterogeneous only in terms of the processor speed. In order to obtain the core speedup, the matching of the parallelism characteristics between tasks and parallel machines should be carefully handled while minimizing the communication overhead.

• Journal of Information Technology and Architecture
• /
• v.9 no.3
• /
• pp.253-263
• /
• 2012

Presented in the paper is a methodology for the distributed simulation of underwater warfare based on standard synthetic environment. In the case of underwater warfare simulation, it is very important to reflect environmental data, such as salinity and temperature. For the reusability and interoperability of environmental data, this paper adopts Synthetic Environmental Data Representation and Interchange Specification (SEDRIS(ISO standard for environmental data)). Although SEDRIS provides various merits as an international standard, applying of SEDRIS has been hindered by its broadness and heaviness. To relieve the difficulties, this paper proposes an efficient procedure to utilize SEDRIS technology for the atmosphere and underwater environment. This paper identifies SEDRIS structure for the atmosphere/underwater structured dimensional grid-based and implements the proposed procedure on the High Level Architecture (HLA) / Run-Time Infrastructure (RTI) to explain the generation of the battlefield in a distributed simulation system.