• Communications for Statistical Applications and Methods
• /
• 제12권3호
• /
• pp.659-672
• /
• 2005

This paper evaluates discretization of continuous variables to select relevant variables for supervised learning using mutual information. Three discretization methods, MDL, Histogram and 4-Intervals are considered. The process of discretization and variable subset selection is evaluated according to the classification accuracies with the 6 real data sets of UCI databases. Results show that 4-Interval discretization method based on quantiles, is robust and efficient for variable selection process. We also visually evaluate the appropriateness of the selected subset of variables.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.152-154
• /
• 2007

Anew discretization method for the input-driven nonlinear continuous-time system with time delay is proposed. It is based on the combination of Taylor series expansion and first-order hold assumption. The mathematical structure of the new discretization scheme is explored. The performance of the proposed discretization procedure is evaluated by case studies. The results demonstrate that the proposed discretization scheme can assure the system requirements even though under a large sampling period. A comparison between first order hold and zero-order hold is simulated also.

• 대한산업공학회지
• /
• 제27권4호
• /
• pp.394-405
• /
• 2001

Since most real-world application data involve continuous-valued attributes, properly addressing the discretization process for constructing a decision tree is an important problem. A continuous-valued attribute is typically discretized during decision tree generation by partitioning its range into two intervals recursively. In this paper, by removing the restriction to the binary discretization, we present a hybrid multi-interval discretization algorithm for discretizing the range of continuous-valued attribute into multiple intervals. On the basis of experiment using semiconductor etching machine, it has been verified that our discretization algorithm constructs a more efficient incremental decision tree compared to previously proposed discretization algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권2호
• /
• pp.374-388
• /
• 2011

Biometric discretization is a process of transforming continuous biometric features of an identity into a binary bit string. This paper mainly focuses on improving the global discretization method - a discretization method that does not base on information specific to each user in bitstring extraction, which appears to be important in applications that prioritize strong security provision and strong privacy protection. In particular, we demonstrate how the actual performance of a global discretization could further be improved by embedding a global discriminative feature selection method and a Linearly Separable Subcode-based encoding technique. In addition, we examine a number of discriminative feature selection measures that can reliably be used for such discretization. Lastly, encouraging empirical results vindicate the feasibility of our approach.

• 대한수학회보
• /
• 제48권4호
• /
• pp.873-896
• /
• 2011

The semi-discrete central scheme and central upwind scheme use Runge-Kutta (RK) time discretization. We do the Lax-Wendroff (LW) type time discretization for both schemes. We perform numerical experiments for various problems including two dimensional Riemann problems for Burgers' equation and Euler equations. The results show that the LW time discretization is more efficient in CPU time than the RK time discretization while maintaining the same order of accuracy.

• Structural Engineering and Mechanics
• /
• 제6권3호
• /
• pp.339-345
• /
• 1998

The computation size and accuracy in the boundary element method are mutually coupled and strongly influenced by the formulations in boundary discretization and integration. This aspect is studied numerically for two-dimensional elastodynamic problems in the frequency-domain. The localized nature of error is observed in the computed results. A boundary discretization criterion is examined. The number of integration points in the boundary integration is studied to find the optimum number for accuracy. Useful information is obtained concerning the optimization in boundary discretization and integration.

• 데이타베이스연구회지:데이타베이스연구
• /
• 제34권3호
• /
• pp.159-169
• /
• 2018

연속형 변수의 이산화(Discretization)는 양적 변수(Quantitative variable)를 질적 변수(Qualitative variable)로 변형시켜 데이터 마이닝(Data mining) 기법 등 다양한 알고리즘의 성능을 향상시키는데 사용 목적이 있다. 데이터에 적절한 이산화 기법을 사용한다면 분류 알고리즘에 대해 더 좋은 성능뿐 아니라 간결한 결과 해석, 속도 향상까지 기대할 수 있다. 현재까지 다양한 이산화 기법들이 연구되었으며, 현재도 이산화와 관련한 연구에 수요가 많다. 본 논문은 데이터의 클래스에 대한 연속형 변수 값의 분포를 고려하여, Wasserstein 거리를 이용해 분할점을 자동 설정하는 이산화 기법을 제안한다. 본 논문에서 제안하는 기법과 우수함이 입증된 기존의 이산화 기법에 대해 성능비교를 통해 제안 기법의 우수성을 보인다.

• Structural Engineering and Mechanics
• /
• 제3권4호
• /
• pp.391-410
• /
• 1995

The application of adaptive finite element method to dynamic problems is investigated. Both the kinetic and strain energy errors induced by space and time discretization were estimated in a consistent manner and controlled by the simultaneous use of the adaptive mesh generation and the automatic time stepping. Also an optimal ratio of spatial discretization error to temporal discretization error was discussed. In this study it was found that the best performance can be obtained when the specified spatial and temporal discretization errors have the same value. Numerical examples are carried out to verify the performance of the procedure.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.125-127
• /
• 2005

In this paper, we propose a new scheme for the discretization of nonlinear systems using Taylor series expansion and the zero-order hold assumption. This scheme is applied to the sample-data representation of a nonlinear system with constant state tine-delay. The mathematical expressions of the discretization scheme are presented and the effect of the time-discretization method on key properties of nonlinear control system with state tine-delay, such as equilibrium properties and asymptotic ability, is examined. The proposed scheme provides a finite-dimensional representation for nonlinear systems with state time-delay enabling existing controller design techniques to be applied to then. The performance of the proposed discretization procedure is evaluated using a nonlinear system. For this nonlinear system, various sampling rates and time-delay values are considered.

• Communications for Statistical Applications and Methods
• /
• 제10권3호
• /
• pp.879-894
• /
• 2003

We evaluated the efficiencies of applying attribute selection methods and prior discretization to supervised learning, modelled by C4.5 and Naive Bayes. Three databases were obtained from UCI data archive, which consisted of continuous attributes except for one decision attribute. Four methods were used for attribute selection : MDI, ReliefF, Gain Ratio and Consistency-based method. MDI and ReliefF can be used for both continuous and discrete attributes, but the other two methods can be used only for discrete attributes. Discretization was performed using the Fayyad and Irani method. To investigate the effect of noise included in the database, noises were introduced into the data sets up to the extents of 10 or 20%, and then the data, including those either containing the noises or not, were processed through the steps of attribute selection, discretization and classification. The results of this study indicate that classification of the data based on selected attributes yields higher accuracy than in the case of classifying the full data set, and prior discretization does not lower the accuracy.