• Journal of Information Processing Systems
• /
• 제11권1호
• /
• pp.22-38
• /
• 2015

While Modern Standard Arabic is the formal spoken and written language of the Arab world; dialects are the major communication mode for everyday life. Therefore, identifying a speaker's dialect is critical in the Arabic-speaking world for speech processing tasks, such as automatic speech recognition or identification. In this paper, we examine two approaches that reduce the Universal Background Model (UBM) in the automatic dialect identification system across the five following Arabic Maghreb dialects: Moroccan, Tunisian, and 3 dialects of the western (Oranian), central (Algiersian), and eastern (Constantinian) regions of Algeria. We applied our approaches to the Maghreb dialect detection domain that contains a collection of 10-second utterances and we compared the performance precision gained against the dialect samples from a baseline GMM-UBM system and the ones from our own improved GMM-UBM system that uses a Reduced UBM algorithm. Our experiments show that our approaches significantly improve identification performance over purely acoustic features with an identification rate of 80.49%.

• 품질경영학회지
• /
• 제36권1호
• /
• pp.72-79
• /
• 2008

The policy for credit card approval/disapproval is based on the applier's personal and financial information. In this paper, we will analyze 2 credit card approval data with several classification methods. We identify which variables are important factors to decide the approval of credit card. Our main tool is an open-source statistical programming environment R which is freely available from http://www.r-project.org. It is getting popular recently because of its flexibility and a lot of packages (libraries) made by R-users in the world. We will use most widely used methods, LDNQDA, Logistic Regression, CART (Classification and Regression Trees), neural network, and SVM (Support Vector Machines) for comparisons.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2002년도 가을 학술발표논문집 Vol.29 No.2 (2)
• /
• pp.559-561
• /
• 2002

서포트 벡터 머신은 얼굴인식이나 문자인식과 같은 다양한 패턴인식 문제에서 좋은 성능을 보여준다. 그러나 이러한 문제는 Quadratic Programming(QP) 문제에 관하여 몇 가지 단점을 가지고 있다. 일반적으로 대용량의 QP 문제를 해결하기 위해 많은 계산비용이 요구되며, QP 기반 시스템을 효과적으로 구현하는 것이 쉽지 않은 문제이다. 또한 대규모 데이터의 처리 시에는 입출력을 맞추기 또한 쉽지 않은 단점이 있다. 본 논문에서는 위의 단점을 극복하기 위하여 단일부류 문제를 최소제곱 서포트 벡터 머신을 기반으로 하여 해결하였다. 제안한 방법은 QP 문제를 해결하는 과정이 없이 단일부류 문제를 표현하여 최소제곱 방법을 이용하는 알고리즘이다. 제안된 방법으로 쉽고, 계산 비용을 줄이는 결과를 얻었다. 또한 서포트 벡터 영역 표식자에 확장 적용하여 선형방정식으로 구현하여, 문제를 해결하였다. 제안된 방법의 효율성을 입증하기 위하여 패턴인식 분야 중에 얼굴 인증 방법과 바이오인포매틱스 분야 중에 전립선 암 분류 문제에 적용하였다. 우리의 실험결과는 적합한 성능과 좋은 Equal Error Rate(EER)를 보여준다. 제안된 방법은 알 수 없는 물체의 분류 방법의 효율성을 증대시켰고, 실시간 응용분야에 직접적으로 적용될 수 있을 것으로 기대 된다.

• 한국측량학회지
• /
• 제12권1호
• /
• pp.25-34
• /
• 1994

현대 도시의 상수도 업무를 효율화, 고도화하기 위해서는 적절한 상수도정보체계의 운용이 필요하다. 이는 궁극적으로 도시종합정보체계의 부분이 되야 한다. 이를 수행하기 위해, 서울시 강남지역을 사례로 한국의 상수도 업무를 분석하고, 이를 바탕으로, 벡테 GIS의 macro-programming language를 이용하여, 한국토지행정업무의 기본인 지번을 기초로 도시상수도정보체계를 구축하여, 사례지역에 적용 후, 한국에서의 도시상수도정보체계가 효율적으로 운용되기 위한 활용방안, 제도적, 기술적 문제점 등을 논의하였다.

• KIEE International Transactions on Power Engineering
• /
• 제2A권3호
• /
• pp.109-113
• /
• 2002

This paper addresses the issue of parameter error identification and estimation in electric power systems. Parameter error identification and estimation is carried out as a part of the state estimation. A two stage estimation procedure is used to detect and identify parameter errors. Suspected parameters are identified by the WLAV state estimator in the first stage. A new WLAV state estimator adding suspected system parameters in the state vector is used to estimate the exact values of parameters. Supporting examples are given by using the IEEE 14 bus system.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1998년도 가을 학술발표회 논문집
• /
• pp.69-76
• /
• 1998

Due to the drastic improvement of computer hardware and operating system, it is easy to break through the main defects of limited computer memory and processing time, etc. To keep up with this situation, this paper is focused on developing the preprocessor program with the input method based on vector graphic editor and the preprocessing technique including automatic node generation algorithm for the $\rho$-version finite element program. To develop this preprocessor program, the special data structure and the OOP(Object Oriented Programming) have been used by the Visual Basic 4.0. The Special data structure is proposed to describe the geometric data of node numberings and coordinates suitable for the $\rho$-version finite element program, which are quite different from the comvential h-version finite element program.

• 한국CDE학회논문집
• /
• 제6권4호
• /
• pp.271-276
• /
• 2001

A geometric kernel is the library of core mathematical functions that defines and stores 3D shapes in response to users'commands. We developed a light geometric kernel suitable to develop CAD/CAM application systems. The kernel contains geometric objects, such as points, curves and surfaces and a minimal set of functions for each type but does not contain lots of modeling and handling functions that are useful to create and maintain complex shapes from an idea sketch. The kernel was developed on MS-Windows NT using C++ with STL(Standard Template Library) but it is compatible with UNIX environments. This paper describes the structure of the kernel including several components: base, math, point sequence curve, geometry, translators. The base kernel gives portability to applications and the math kernel contains basic arithmetic and their classes, such as vector and matrix. The geometry kernel contains points, parametric curves, and parametric surfaces. A neutral fie format and programming and document styles are also presented in this paper.

• 한국지능시스템학회논문지
• /
• 제19권2호
• /
• pp.273-278
• /
• 2009

The determination of the associated weights in the theory of ordered weighted averaging (OWA) operators is one of the important issue. Recently, Wang and Parkan [Information Sciences 175 (2005) 20-29] proposed a minimax disparity approach for obtaining OWA operator weights and the approach is based on the solution of a linear program (LP) model for a given degree of orness. Recently, Liu [International Journal of Approximate Reasoning, accepted] showed that the minimum variance OWA problem of Fuller and Majlender [Fuzzy Sets and Systems 136 (2003) 203-215] and the minimax disparity OWA problem of Wang and Parkan always produce the same weight vector using the dual theory of linear programming. In this paper, we give an improved proof of the minimax disparity problem of Wang and Parkan while Liu's method is rather complicated. Our method gives the exact optimum solution of OWA operator weights for all levels of orness, $0\leq\alpha\leq1$, whose values are piecewise linear and continuous functions of $\alpha$.

• 대한산업공학회지
• /
• 제19권4호
• /
• pp.3-11
• /
• 1993

We propose a new dual simplex method using a primal interior point. The dropping variable is chosen by utilizing the primal feasible interior point. For a given dual feasible basis, its corresponding primal infeasible basic vector and the interior point are used for obtaining a decreasing primal feasible point The computation time of moving on interior point in our method takes much less than that od Karmarker-type interior methods. Since any polynomial time interior methods can be applied to our method we conjectured that a slight modification of our method can give a polynomial time complexity.

• 한국통신학회논문지
• /
• 제37C권10호
• /
• pp.940-948
• /
• 2012

안드로이드 프로그램은 JAVA SDK로 제작되어 가상머신(virtual machine) 기반으로 동작한다. 따라서 기존의 C 언어에 비해 프로그램 작성은 편리해 졌지만 동작 속도는 떨어지는 단점이 있다. 이러한 단점을 보완하기 위해 안드로이드 상에서 C언어, 어셈블리 언어의 사용이 가능한 안드로이드 NDK가 제안되어 보다 효율적인 프로그램 작성이 가능하게 되었다. 이와 더불어 ARM에서 제공하는 NEON기능을 사용하면 벡터연산을 통해 성능을 향상 시킬 수 있다. 본 논문에서는 NDK의 효용성에 대해 알아보며 NEON기능을 이용한 향상된 곱셈구조를 제안한다.