• Journal of Communications and Networks
• /
• 제13권1호
• /
• pp.6-11
• /
• 2011

In this paper, an enhanced localization algorithm based on double thresholds (LAD) is proposed for localizing narrowband signals in the frequency domain. A simplified LAD method is first studied to reduce the computational complexity of the original LAD method without performance loss. The upper and lower thresholds of the simplified LAD method are directly calculated by running the forward consecutive mean excision algorithm only once. By combining the simplified LAD method and binary morphological operators, the enhanced LAD method is then proposed and its performance is simply discussed. The simulation results verify the correctness of discussion and show that the enhanced LAD method is superior to the LAD with adjacent cluster combining method, especially at low signal-to-noise ratio.

• 응용통계연구
• /
• 제23권6호
• /
• pp.1235-1243
• /
• 2010

다차원 분할표를 구성하는 범주형 변수들의 연관관계를 식별하기 위하여 널리 이용되는 로그선형모형을 위한 절사 LAD(least absolute deviations) 추정방법을 제안하였다. 제안된 방법은 가중 LAD 추정을 반복하여 계산이 수행되므로 분할표 분석을 위해 적용할 수 있는 여러 연관성 모형(association models)에 직접 적용할 수 있다. 또한 붓스트랩을 이용한 최적절사율을 결정하는 방법이 갖는 공분산행렬을 과소추정하는 문제를 해결하기위한 절사율 결정 방법을 제안하였다. 모의실험을 통해 제안된 방법이 붓스트랩 방법에 비하여 항상 우수한 절사율을 보인다는 것을 설명하였으며, 제안된 방법들의 실제 자료분석 결과를 제시하였다.

• 한국컴퓨터정보학회논문지
• /
• 제11권1호
• /
• pp.11-18
• /
• 2006

LAD(Logical Analysis of Data)는 Boolean-logic에 기반을 둔 데이터 마이닝 방법론이다. LAD에 의한 데이터 분석 시 중요한 과정은 데이터 집합에 숨겨진 구조적 정보를 패턴의 형식으로 발견해내는 패턴 생성 단계이다. 기존의 패턴 생성 방법은 열거법에 기반을 두고 있어 높은 차수의 패턴을 생성하는 것은 실질적으로 불가능하였다. 본 논문에서는 최적화에 기반을 둔 패턴 생성 방법론을 제안하고 혼합 정수 선형 모형과 SCP(Set Covering Problem)의 두 가지 모형을 제안한다. 기계학습 분야에서 널리 쓰이는 데이터 집합에 대해 제안된 패턴 생성 방법을 이용한 분석 실험을 통하여 기존의 패턴 생성 방법으로는 생성될 수 없는 패턴을 쉽게 생성하는 효율성을 입증하였다.

• Communications for Statistical Applications and Methods
• /
• 제13권3호
• /
• pp.745-754
• /
• 2006

It has been shown that LAD estimates are more efficient than LS estimates when the error distribution is double exponential in AR(1) model. In order to explore the performance of LAD estimates one can use bootstrap approaches. In this paper we consider the efficiencies of bootstrap methods when we apply LAD estimates with highly variable data. Monte Carlo simulation results are given for comparing generalized bootstrap, stationary bootstrap and threshold bootstrap methods.

• Journal of the Korean Statistical Society
• /
• 제31권1호
• /
• pp.121-128
• /
• 2002

In this paper we provide a new proof of the asymptotic distributions of LAD estimators using the martingale limit theorem and show the efficiency of LAD estimators in a stationary AR(1) model setting.

• Journal of the Korean Statistical Society
• /
• 제26권3호
• /
• pp.383-395
• /
• 1997

This paper proves that the standard bootstrap approximation for the least absolute deviation (LAD) estimate of .beta. in AR(1) processes with infinite variance error terms is asymptotically valid in probability when the bootstrap resample size is much smaller than the original sample size. The theoretical validity results are supported by simulation studies.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2005년도 추계학술대회 및 정기총회
• /
• pp.409-413
• /
• 2005

The logical analysis of data(LAD) is an effective Boolean-logic based data mining tool. A critical step in analyzing data by LAD is the pattern generation stage where useful knowledge and hidden structural information in data is discovered in the form of patterns. A conventional method for pattern generation in LAD is based on term enumeration that renders the generation of higher degree patterns practically impossible. In this paper, we present a new optimization-based pattern generation methodology and propose two mathematical programming medels, a mixed 0-1 integer and linear programming(MILP) formulation and a well-studied set covering problem(SCP) formulation for the generation of optimal and heuristic patterns, respectively. With benchmark datasets, we demonstrate the effectiveness of our models by automatically generating with much ease patterns of high complexity that cannot be generated with the conventional approach.

• 응용통계연구
• /
• 제16권1호
• /
• pp.55-69
• /
• 2003

일반적인 다차원 분할표 분석을 위해 고려 할 수 있는 로그 선형 모형 (log-linear model)과 순위 변수(ordered variables)가 고려된 여러 연관성 모형(association models)을 위한 가중값이 부여된 LAD(least absolute deviations) 추정량을 제안하고 추정을 위한 반복 추정법을 제안하였다. 모의실험을 통하여 제안된 LAD추정량이 최우추정량에 비해 로버스트한 성질을 갖는 다는 것을 밝히고, 이상칸 식별을 위해 많은 선행 연구들에서 인용된 자료들의 경험적 분석을 통해 제안된 추정량과 추정방법이 가질 수 있는 문제점과 특징에 관하여 토론하였다

• 한국막학회:학술대회논문집
• /
• 한국막학회 1999년도 The 7th Summer Workshop of the Membrane Society of Korea
• /
• pp.15-18
• /
• 1999

A simple mathematical model for facilitated mass transport through a fixed site carrier membrane was derived by assuming an instantaneous, microscopic concentration (activity) fluctuation. The current model demonstrates that the facilitation factor depends on the extent of concentration fluctuation, the time scale ratios of diffusion to chemical reaction and the ratio of the carrier concentration to the solute solubility in matrix. The model was examined against the experimental data on oxygen transport in membranes containing metallo-porphyrin carriers, and the agreement was exceptional (within 10% error). The basic concept of this approach was applied to separate olefin from olefin/paraffin mixtures. A proprietaty carrier, developed here, resulted that the selectivity of propylene over propane was more than 120 and the propylene permeance exceed 40 gpu.

• Journal of the Korean Statistical Society
• /
• 제27권3호
• /
• pp.349-358
• /
• 1998

Consider the AR(1) model $X_{t}$=$\beta$ $X_{t-1}$+$\varepsilon$$_{t}$ where $\beta$ < 1 is an unknown parameter to be estimated and {$\varepsilon$$_{t}$} denotes the independent and identically distributed error terms with unknown common distribution function F. In this paper, a strong representation for the least absolute deviation (LAD) estimate of $\beta$ in AR(1) models is obtained under some mild conditions on F. on F.F.