• Database Research
• /
• v.34 no.3
• /
• pp.159-169
• /
• 2018

Discretization of continuous variables intended to improve the performance of various algorithms such as data mining by transforming quantitative variables into qualitative variables. If we use appropriate discretization techniques for data, we can expect not only better performance of classification algorithms, but also accurate and concise interpretation of results and speed improvements. Various discretization techniques have been studied up to now, and however there is still demand of research on discretization studies. In this paper, we propose a new discretization technique to set the cut-point using Wasserstein distance with considering the distribution of continuous variable values with classes of data. We show the superiority of the proposed method through the performance comparison between the proposed method and the existing proven methods.

• 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.792-797
• /
• 2011

This paper discusses the application of a hybrid discretiziation method for the discretization procedure that needs to be included in discrete particle swarm optimization (DPSO) for the problem of allocating PV (photovoltaic) systems onto distribution power systems. For this purpose, this paper proposes a rule-based expert system considering the objective function value and its optimizing speed as the input parameters and applied it to the PV allocation problem including discrete decision variables. For multi-level discretization, this paper adopts a hybrid method combined with a simple rounding and sigmoid funtion based 3-step and 5-step quantization methods, and the application of the rule based expert system proposing the adequate discretization method at each PSO iteration so that the DPSO with the hybrid discretization can provide better performance than the previous DPSO.

• Journal of Korean Association for Spatial Structures
• /
• v.10 no.2
• /
• pp.77-86
• /
• 2010

This paper provides background theories and numerical results of automatic finite element (FE) mesh generation for freeform discrete structures. The present method adopts the computer aided geometric design (CAGD) technique to overcome the limitation of case-sensitive traditional automatic FE mesh generator. The present technique involves two steps. The first one is to represent the shape of the structure using the geometric model based on the CAGD and the second one is to generate the discrete FE mesh of spatial structures over the geometric model. From numerical results, it is found to be that the present technique is very easy to produce the FE mesh for free-form spatial structures and it can also reuse some features of traditional automatic mesh generator in the process. Furthermore, it shows the possibility to be used for the shape optimization of large spatial structures.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.7
• /
• pp.967-974
• /
• 2001

This paper aims at deriving an equivalent finite dimensional discrete-time system for $H{\infty}$ type problem for sampled-data control systems. A widely used approach is based on the lifting technique, but it needs somewhat complicate computation. Instead, this paper derives an equivalent finite-dimensional discrete-time system directly from a description of the sampled-data system which is achieved via a closed-loop expression of the worst-case intersample disturbance.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1995.04a
• /
• pp.246-251
• /
• 1995

유연구조물의 진동제어를 위해 압전필름 작동기를 사용하였고 이와 연계하 여 샘플링 과정을 고려한 DSMC를 구성하였다. 변수변화 및 외란의 경계치 를 알고 있다는 가정하에 시스템을 이산화시킨 후 제어기를 설계하였다. 일 반적으로 연속시간 시스템의 이산화 과정에서 정합조건의 가정이 보장되지 않기 때문에 제어기 설계시 이를 배제하였다. 이산시간 리아푸노프 이론을 근거로 DSMC의 존재성을 도출하였고, 이것에 기초하여 슬라이딩 모드가 발생되도록 불연속제어기를 설계하였다. 이때, 불연속게인을 상수로 하지 않고 RP의 위치에 따라 계속 새롭게 수정함으로써 슬라이딩 영역을 최소화 하였다. 그리고 기존의 DSMC 기법상에서 발생되는 슬라이딩 영역의 문제를 .betha. 등가제어기를 이용하는 이원화 방법으로 극복하였으며, 컴퓨터 시뮬 레이션을 통하여 제안된 기법의 설계 효율성 및 제어기의 강건성을 입증하였다. 향후, 제안된 기법에 대한 실험적 고찰 및 중요 제어인자에 대한 연구가 계속적으로 수행될 예정이다.

• Environmental and Resource Economics Review
• /
• v.6 no.1
• /
• pp.111-128
• /
• 1996

본 연구는 대기오염물질인 이산화질소와 인체의 호흡기질환과의 반응도를 실증분석하고, 이 반응도를 이용해 이산화질소의 대기오염으로 인한 사회적 비용을 계산하는 것이다. 사람들이 대기오염에 노출되었을 때 발생하는 질환의 피해를 측정하기 위하여 손실함수(damage function)를 설정하고, 이를 회귀분석기법(regression technique)을 이용해 추정한 결과 이산화질소는 호흡기질환에 상당히 유의적인 영향을 미쳤고, 1994년 한해 동안 배출된 이산화질소량이 발생시킨 사회적 비용은 약 8조 2천 억원이었다.

• The Journal of the Korea Contents Association
• /
• v.10 no.9
• /
• pp.97-106
• /
• 2010

Various time series representation methods have been suggested in order to process time series data efficiently and effectively. SAX is the representative time series representation method combining segmentation and discretization techniques, which has been successfully applied to the time series classification task. But SAX requires a large number of segments in order to represent the meaningful dynamic patterns of time series accurately, since it loss the dynamic property of time series in the course of smoothing the movement of time series. Therefore, this paper suggests a new time series representation method that combines PIPs detection and Persist discretization techniques. The suggested method represents the dynamic movement of high-diemensional time series in a lower dimensional space by detecting PIPs indicating the important inflection points of time series. And it determines the optimal discretizaton ranges by applying self-transition and marginal probabilities distributions to KL divergence measure. It minimizes the information loss in process of the dimensionality reduction. The suggested method enhances the performance of time series classification task by minimizing the information loss in the course of dimensionality reduction.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2003.06a
• /
• pp.185-190
• /
• 2003

이산사건 시스템을 기술하는데는 다양한 방법론들이 있으며 event의 관점에서 본다면, event loss 방법론과 event lossless방법론이 있다. event loss방법론의 경우 때때로 원치 않는 event loss가 발생하여 시스템을 deadlock의 상태로 이끌 수가 있으며, 이러한 것을 피하기 위해 본 논문은 event loss방식의 동기식방법론인 DEVS형식론으로 기술된 모델을 본 논문에서 제안하는 TSRG란 방법을 이용하여 event loss의 유무를 해석할 수 있는 기법을 소개하고자 한다. 소개된 해석 기법은 linear programming을 이용하여 해를 구할 수 있으며, DEVS형식론으로 기술된 이산사건 모델들간의 event loss의 유무를 해석함으로써 서로간의 통신 동기화의 가능성 분석을 가능하도록 한다.

• Water for future
• /
• v.26 no.2
• /
• pp.89-97
• /
• 1993

For the system benefit optimization by considering risk or reliability from a multiple reservoir system using the Monte Carlo technique, many stochastically generated inflow series have to be used for the system analysis. In this study, the stochastically generated inflow series for the multiple reservoir system operation are preprocessed according to the considered system objectives and operating time periods. Through this procedure, several representative inflow series which have discrete probability levels and operation horizons are selected among the thousands of generated inflows. Then a deterministic optimization technique is applied to the power energy estimation from the Han River Reservoirs System which considers five reservoirs in the study. It took much lower computational requirements then using the original Monte Carlo Technique, even though estimated result was almost similar.