• The Journal of the Acoustical Society of Korea
• /
• v.12 no.2E
• /
• pp.19-26
• /
• 1993

이 논문에서는 가산성 잡음과 신호 의존성 잡음이 바라는 신호와 섞일 때, 약한 복합신호를 검파하는 국소 최적 검파기의 검정 통계량을 얻었다. 순가산성 잡음 분만 아니라 비가산성 잡음도 고려하기 위하여 일반화된 관측 모델을 사용하였다. 알려진 신호, 확률 신호, 그리고 신호 의존성 잡음 성분의 상대적인 크기의 모든 경우에 대하여 국소 최적 검정통계량을 얻었다. 또한, 국소 최적 검파기의 얼개를 그림으로 나타냈다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.13 no.4
• /
• pp.332-339
• /
• 1988

Using a generalized observation model, in which one can express the effects of non-additive noise such as signal-dependent noise and multiplicative noise in addition to purely-additive noise, the problem of weak random-signal detection is investigated. It is shown that the test statistics of locally optimum detectors for detection of weak random signals in signal-dependent noise model are interesting extensions of those in purely-additive noise model. This result is a complement to the result for weak random-signal detction in multiplicative noise model.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.11
• /
• pp.955-961
• /
• 1990

Test statistics are obtained for detection of weak signals in signal-dependent noise using rank statistics. A generalized model is used in this paper in order to consider non-additivenoise as well as purely-additive noise. Locally optimum rank detectors for the model are shown to have similarity to locally optimum detectors and to be generalizations of these for the purely-additive noise model. A similar result is obtained for multi-input cases.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.4C
• /
• pp.374-378
• /
• 2003

The asymptotic performance of the two-sample locally optimum rank detector for random signals buried in signal-dependent noise and additive noise is consigered in this paper. It is shown that the locally optimum rank detector, a nonparametric detector, has reasonable asymptotic performance for a class of correlated random signals, compared with the locally optimum detector. It is noteworthy that the the two-sample locally optimum rank detector perform almost the same with the one-sample locally optimum rank detector.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.1
• /
• pp.155-160
• /
• 1996

In this paper, we consider the discrete-time known signal detection problem under the presence of additive noise exhibiting weak dependence. We derive the locally optimum, memoryless, and one-memory detector test statistics under a seakly dependent noise model. The performance characteristics of the one-memory detector can achieve almost optimum performance at the expense of only one memory unit under the weakly dependent noise model.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.4
• /
• pp.319-325
• /
• 1991

A nonparametric detection scheme which uses rank statistics for detection of known signals is considered in a special case of a generalized observation model. Specifically locally optimum rank detectors for detection of known deterministic singals in a singnal-dependent noise model are derived, and compared to those derived for the purely-additive noise model. Examples of the score functions are given, which constitutes the test statistics of the locally optimum rank detectors.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.1
• /
• pp.76-82
• /
• 2000

In this paper, we consider nonparametric signal detection problems under the presence of additive noise exhibiting weak dependence We derive the test statistics of the locally optimum rank detectors under a weakly dependent noise model for known and random signal cases The performance characteristic of the locally optimum rank detectors are analyzed in terms of asymptotic relative efficiency.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.1
• /
• pp.69-75
• /
• 2000

In this paper, we consider the problem of discrete-time random signal detection problem under the presence of additive noise exhibiting weak dependence The test statistic of the locally optimum detector for correlated random signals under a weakly dependent noise model is derived The performance characteristic of the locally optimum detector is analyzed and compared with that of the square-law detector in terms of the asymptotic relative efficiency.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.4
• /
• pp.3-15
• /
• 2000

In this paper we present a new image denoising filter that can suppress additive noise components while preserving signal components in the wavelet domain. The proposed filter, which we call an adaptive wavelet shrinkage(AWS) filter, is composed of two operators: the wavelet killing operator and the adaptive shrinkage operator. Each operator is selected based on the threshold value which is estimated adaptively by using the local statistics of the wavelet coefficients. In the wavelet killing operation, the small wavelet coefficients below the threshold value are replaced by zero to suppress noise components in the wavelet domain. The adaptive shrinkage operator attenuates noise components from the wavelet components above the threshold value adaptively. The experimental results show that the proposed filter is more effective than the other methods in preserving signal components while suppressing noise.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.8C
• /
• pp.709-712
• /
• 2010

In this paper, the two sample locally optimum rank detector is obtained in the weakly dependent noise with non-zero temporal correlation between noise observations. The test statistic of the locally optimum rank detector is derived from the Neyman-Pearson lemma suitable for the two sample observation models, where it is assumed that reference observations are available in addition to regular observations. Two-sample locally optimum rank detecter shows the same performance with the one-sample locally optimum rank detector asymptotically. The structure of the two-sample rank detector is simpler than that of the one-sample rank detector because the sign statistic is not processed separately.