• Journal of the Korean Data and Information Science Society
• /
• 제19권3호
• /
• pp.789-800
• /
• 2008

Current credit evaluation models based on financial data make use of smoothing estimated default ratios which are transformed from each financial variable. In this work, some problems of the credit evaluation models developed by financial experts are discussed and we propose improved credit evaluation models based on the stepwise variable selection method and Box-Cox transformed data whose distribution is much skewed to the right. After comparing goodness-of-fit tests of these models, the validation of the credit evaluation models using statistical methods such as the stepwise variable selection method and Box-Cox transformation function is explained.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.283-285
• /
• 2005

To account for the importance of variable in multi-sensor data fusion, random forests are applied to supervised land-cover classification. The random forests approach is a non-parametric ensemble classifier based on CART-like trees. Its distinguished feature is that the importance of variable can be estimated by randomly permuting the variable of interest in all the out-of-bag samples for each classifier. Supervised classification with a multi-sensor remote sensing data set including optical and polarimetric SAR data was carried out to illustrate the applicability of random forests. From the experimental result, the random forests approach could extract important variables or bands for land-cover discrimination and showed good performance, as compared with other non-parametric data fusion algorithms.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권5호
• /
• pp.615-623
• /
• 2016

The paper describes a hysteretic buck converter including a differentiator and an adaptive hysteresis window controller. Differentiating the feedback signal achieves ultra-fast switching of the buck converter. The adaptive hysteresis window control allows a monotonous operation with predictable noise spectrum, and gives way to efficient design for variable supply and output voltages. The measurement results in a $0.13-{\mu}m$ CMOS process indicated that the switching frequency became double times higher, and the voltage ripple was reduced by up to 69%. They also indicated that the normalized switching frequency variation was reduced by 74% with variable $V_{DD}$ and by 63% with variable $V_{OUT}$. The power efficiency was improved by 3.5% depending on loading condition.

• 한국통신학회논문지
• /
• 제21권11호
• /
• pp.2768-2775
• /
• 1996

가변블럭정합(Variable Block Matching: VBM) 알고리즘은 영상블럭의 복잡도에 따라 다른 블럭크기를 사용함으로써 복잡한 영역이나 경계부근에서의 이동벡터 추정시 효과적이지만 많은 계산량이 요구되므로 이러한 계산량의 문제점을 해결하기 위해서 최적임계치에 의한 차영상신소를 이용하여 4진 크리구조를 구성하고 각각의 블럭에 대해 여러가지 고속블럭정합 알고리즘을 응용하여 움직임을 추정하는 방법을 제안하였다.

• 전자공학회논문지B
• /
• 제32B권5호
• /
• pp.693-701
• /
• 1995

In most application programs, loops usually comprise most of the computation in a program and are the most important source of parallelism. When loops are executed on multiprocessors, the cross iteration data dependences need to be enforced by synchronization between processors. Existing synchronization schemes have been studied mainly on the loop with constant dependence distance. When these schemes are applied to the loop with variable dependence distance, there exists lots of overhead by the use of unnecessary synchronization variables and execution of unuseful synchronization instructions. Even though there exist various variable synchronization schemes, they have a lot of run-time overhead to compute synchronization information. In this paper, we present a new synchronization scheme, Synch-Free/Synch-Hold for managing synchronization efficiently on the loop with constant and variable dependence distance.

• 전기학회논문지
• /
• 제62권12호
• /
• pp.1750-1754
• /
• 2013

A variable bit rate speech coder is presented. The coder is based on the observation that a speech signal can be viewed as a combination of piecewise linear signals in a short time period. The encoder detects the sample points where the slope of the signal changes, which are called the inflection points in this paper. The coder transmits the location and value for the detected inflection sample, but only the location information for the noninflection samples. In the decoder, the noninflection samples are estimated with interpolation of the received information. Several factors affecting the performance of the coder have been tested through simulation. Simulation results show that the linear interpolation produces 1 ~ 5 dB improvement over the cubic spline interpolation. And the -law companding does not provide any benefit when it is applied before the inflection detection. With low threshold values in the inflection point detection, the coder shows better MOS and more than 16 dB improvement in SNR compared to the continuously variable slope delta modulation (CVSDM).

• 응용통계연구
• /
• 제16권1호
• /
• pp.33-44
• /
• 2003

조사과정에서 필연적으로 발생하는 무응답을 보정하기 위해 보조정보를 사용해야 한다. 이 때, 이용 가능한 보조정보의 차원이 크면, 계산과정에서 많은 시간이 소요되며 데이터를 다루기가 매우 어렵다. 또한 추정량의 분산이 보조전보의 차원에 의존하기 때문에 과소추정의 문제가 발생한다. 이러한 문제를 해결하기 위해 무응답 보정에서 적절한 보조정보의 선택 방법을 제안하였고, 이에 대한 효율성을 모의실험을 통해 살펴보았다.

• Journal of the Korean Data and Information Science Society
• /
• 제24권1호
• /
• pp.201-209
• /
• 2013

For censored regression, it is often the case that some input variables are not important, while some input variables are more important than others. We propose a novel algorithm for selecting such important input variables for censored kernel regression, which is based on the penalized regression with the weighted quadratic loss function for the censored data, where the weight is computed from the empirical survival function of the censoring variable. We employ the weighted version of ANOVA decomposition kernels to choose optimal subset of important input variables. Experimental results are then presented which indicate the performance of the proposed variable selection method.

• 한국통신학회논문지
• /
• 제35권11C호
• /
• pp.907-910
• /
• 2010

This paper presents the design of block lengths for irregular low-density parity-check (LDPC) codes based on the maximum variable degree $d_{{\upsilon},max}$. To design a block length, the performance degradation of belief-propagation (BP) decoding performance from upper bounds on the maximum likelihood (ML) decoding performance is used as an important factor. Since for large block lengths, the performance of irregular LDPC codes is very close to the Shannon limit, we focus on moderate block lengths ($5{\times}10^2\;{\leq}\;N\;{\leq}\;4{\times}10^3$). Given degree distributions, the purpose of our paper is to find proper block lengths based on the maximum variable degree $d_{{\upsilon},max}$. We also present some simulation results which show how a block length can be optimized.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2000년도 제13회 춘계학술대회 및 임시총회 학술발표 논문집
• /
• pp.815-820
• /
• 2000

Variable Reference Graph 는 C 언어로 작성된 프로그램으로부터 상호 절차적인 자료 흐름 분석 정보를 수평적 방향 그래프(directed graph)로 자동 생성해주는 역공학(reverse engineering) 도구들 중 하나이다. 본 논문에서는 판독성 있는 구조적 정보를 제공하기위한 그래픽 표현의 전략을 바탕으로 JAVA 로 구현된 그래픽 사용자 인터페이스(graphic user interface) 및 그래프 레이아웃 알고리즘(graph layout algorithm)을 기술한다. 이 알고리즘은 4 단계로 구성되어 있다: 정보 모형, 레벨 알고리즘, 순서 알고리즘, 위치 알고리즘. 각 단계별에서 수행되는 주요 알고리즘을 살펴 본다. 특히, 이 알고리즘들은 사이클(cycle) 및 비사이클(acyclic) 방향 그래프, 그리고 트리(tree)를 수평적 계층 구조를 생성하는데 사용될 수 있다. 본 논문에서 구현된 Variable Reference Graph 는 소프트웨어 재공학 도구를 개발하는 RESORT(RESearch on object-oriented SOftware Reengineering Technology) 과제에서 개발되었다.