• Communications for Statistical Applications and Methods
• /
• v.12 no.3
• /
• 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.

• Journal of Korean Institute of Industrial Engineers
• /
• v.27 no.4
• /
• 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)
• /
• v.5 no.2
• /
• 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.

• Korean Journal of Computational Design and Engineering
• /
• v.11 no.3
• /
• pp.223-233
• /
• 2006

Layered manufacturing(LM) is emerging as a new technology that enables the fabrication of three dimensional heterogeneous objects such as Multi-materials and Functionally Gradient Materials (FGMs). Among various types of heterogeneous objects, more attention has recently paid on the fabrication of FGMs because of their potentials in engineering applications. The necessary steps for LM fabrication of FGMs include representation and process planning of material information inside an FGM. This paper introduces a new process planning algorithm that takes into account the processing of material information. The detailed tasks are discretization (i.e., decomposition-based approximation of volume fraction), orientation (build direction selection), and adaptive slicing of heterogeneous objects. In particular, this paper focuses on the discretization process that converts all of the material information inside an FGM into material features like geometric features. It is thus possible to choose an optimal build direction among various pre-selected ones by approximately estimating build time. This is because total build time depends on the complexity of features. This discretization process also allows adaptive slicing of heterogeneous objects to minimize surface finish and material composition error. In addition, tool path planning can be simplified into fill pattern generation. Specific examples are shown to illustrate the overall procedure.

• Communications for Statistical Applications and Methods
• /
• v.18 no.1
• /
• pp.89-102
• /
• 2011

The discretization process that converts continuous attributes into discrete ones is a preprocessing step in data mining such as classification. Some classification algorithms can handle only discrete attributes. The purpose of discretization is to obtain discretized data without losing the information for the original data and to obtain a high predictive accuracy when discretized data are used in classification. Many discretization algorithms have been developed. This paper presents the results of our comparative study on recently proposed representative discretization algorithms from the view point of splitting versus merging and supervised versus unsupervised. We implemented R codes for discretization algorithms and made them available for public users.

• Journal of Korean Institute of Industrial Engineers
• /
• v.17 no.1
• /
• pp.117-126
• /
• 1991

When {X(t), t ${\geq}$ 0} is a Markov process representing time-varying system states, we develop efficient bounding methods for some time-dependent performance measures. We use the discretization technique for stochastically monotone Markov processes and a combination of discretization and uniformization for Markov processes with the stochastic convexity(concavity) property. Sufficient conditions for stochastic monotonocity and stochastic convexity of a Markov process are also mentioned. A simple example is given to demonstrate the validity of the bounding methods.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.28 no.1
• /
• pp.1-7
• /
• 2005

Data mining is widely used for turning huge amounts of data into useful information and knowledge in the information industry in recent years. When analyzing data set with continuous values in order to gain knowledge utilizing data mining, we often undergo a process called discretization, which divides the attribute's value into intervals. Such intervals from new values for the attribute allow to reduce the size of the data set. In addition, discretization based on rough set theory has the advantage of being easily applied. In this paper, we suggest a discretization algorithm based on Rough Set theory and SOM(Self-Organizing Map) as a means of extracting valuable information from large data set, which can be employed even in the case where there lacks of professional knowledge for the field.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.9
• /
• pp.920-928
• /
• 1991

This paper proposes a design procedure based on the LQG/LTR (Linear Quadratic Gaussian/ Loop Transfer Recovery) method for a launch vehicle. Continuous-discrete type LQG/LTR compensators are designed using the e-transformation to overcome numerical problems occurring in the process of discretization. The e-LQG/LTR compensator using the e-transformation is compared width the z-LQG/LTR compensator using the z-transformation. The performance of the overall system controlled by the compensator is evaluated via simulations, which show that the discretization error problem is resolved and the control performances are satisfactory in the proposed compensator.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.9
• /
• pp.2165-2172
• /
• 1995

Optimization of mesh discretization has been proposed to improve the accuracy of limit analysis solution of collapse load by using the Rigid Body Spring Model(R. B. S. M) under the plane strain condition. Moreover, the fracture behaviour of materials was investigated by employing the fracture mechanism of a spring connecting the triangular rigid body element. It has been clarified that the collapse load and the geometry of slip boundary for optimized mesh discretization were close to those of the slip line solution. Further, the wedge-shaped fracture of a cylinder under a lateral load and the central fracture of a strip in the drawing process were well simulated.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.1
• /
• pp.57-61
• /
• 2009

To increase the efficiency of mining process and derive accurate spatio-temporal patterns, continuous values of attributes should be discretized prior to mining process. In this paper, we propose a discretization method which improves the mining efficiency by reducing the data size without losing the correlations in the data. The proposed method first s original trajectories into approximations using line simplification and then groups them into similar clusters. Our experiments show that the proposed approach improves the mining efficiency as well as extracts more intuitive patterns compared to existing discretization methods.