• 한국음향학회지
• /
• 제34권4호
• /
• pp.321-327
• /
• 2015

본 연구에서는 음성인식기 성능향상을 위한 영상기반 음성구간 검출방법을 제안한다. 기존의 광류기반 방법은 조도변화에 대응하지 못하고 연산량이 많아서 이동형 플렛홈에 적용되는 스마트 기기에 적용하는데 어려움이 있고, 카오스 이론 기반 방법은 조도변화에 강인하지만 차량 움직임 및 입술 검출의 부정확성으로 인해 발생하는 오검출이 발생하는 문제점이 있다. 본 연구에서는 기존 영상기반 음성구간 검출 알고리즘의 문제점을 해결하기 위해 지역 분산 히스토그램(Local Variance Histogram, LVH)과 적응적 문턱값 추정 방법을 이용한 음성구간 검출 알고리즘을 제안한다. 제안된 방법은 조도 변화에 따른 픽셀 변화에 강인하고 연산속도가 빠르며 적응적 문턱값을 사용하여 조도변화 및 움직임이 큰 차량 운전자의 발화를 강인하게 검출할 수 있다. 이동중인 차량에서 촬영한 운전자의 동영상을 이용하여 성능을 측정한 결과 제안한 방법이 기존의 방법에 비하여 성능이 우수함을 확인하였다.

• 융합신호처리학회논문지
• /
• 제11권4호
• /
• pp.270-277
• /
• 2010

BAMS(Baysian Adaptive Multiresolution Smoother) 필터는 모의실험 없이 Bayes 추정에 기초한 웨이블릿 축소기법에 의해 잡음을 제거하며 따라서 실시간 처리가 가능하다. BAMS 필터에 의한 영상잡음 제거 성능은 웨이블릿 분해 각 대역의 잡음분산에 크게 의존한다. 기존의 BAMS 필터는 웨이블릿 분해의 고주파 대역에서 사분위 통계량을 이용하여 잡음분산을 추정하여 잡음을 제거하였다. 본 논문에서는 영상신호의 중간대역을 포함한 잡음제거를 위해 변형된 사분위 통계량 및 모노토닉 변환으로 중간대역 잡음편차 추정하고 이를 이용해서 중간대역 및 고주파 대역의 영상잡음을 제거한 결과 중간대역의 잡음을 제거하므로 약 2[dB]정도의 PSNR이 증가하였으며 잡음편차가 작은 영상의 잡음제거에서도 효과가 있었다.

• 방송공학회논문지
• /
• 제6권1호
• /
• pp.72-81
• /
• 2001

An adaptive channel estimation technique for OFDM-based DTV receivers is proposed using a new mobility estimator. Sample mean techniques for channel estimation have displayed good performance in slow fading channels, because averaging reduces noise In channel estimation operation. This paper suggests an algorithm which selects the optimal number of symbols within which the sample mean of consecutive pilot data can be obtained. The designed mobility estimator determines the optimal number by comparing mobility variance and estimated noise valiance. The algorithm using the mobility estimator obtains an optimal channel function under time-invariant or time-variant multipath fading channels, thereby making the best BER performance.

• 전기학회논문지
• /
• 제60권3호
• /
• pp.648-653
• /
• 2011

We propose a new frequency offset estimation technique for multiband orthogonal frequency modulation (MB-OFDM) based ultra wideband (UWB) systems. The proposed frequency offset estimation technique is related to the scheme of Schmidl for channel model 1 (4-1Om NLOS, rms. delay =14.3ns.) using more than two symbols and with alternate symbols. Variance of frequency offset estimate obtained from the proposed frequency offset estimation technique approaches very nearing to Cramer Rao Lower Bound (CRLB) in an AWGN channel. BER performance of the proposed technique is also presented.

• Journal of Electrical Engineering and Technology
• /
• 제13권1호
• /
• pp.430-437
• /
• 2018

Ultrasonic attenuation is an important parameter in Quantitative Ultrasound and many algorithms have been proposed to improve estimation accuracy and repeatability for multiple independent estimates. In this work, we propose an improved algorithm for estimating ultrasonic attenuation utilizing the optimal frequency compounding technique based on stochastic noise model. We formulate mathematical compounding equations in the AWGN channel model and solve optimization problems to maximize the signal-to-noise ratio for multiple frequency components. Individual estimates are calculated by the reference phantom method which provides very stable results in uniformly attenuating regions. We also propose the guideline to select frequency ranges of reflected RF signals. Simulation results using numerical phantoms show that the proposed optimal frequency compounding method provides improved accuracy while minimizing estimation bias. The estimation variance is reduced by only 16% for the un-compounding case, whereas it is reduced by 68% for the uniformly compounding case. The frequency range corresponding to the half-power for reflected signals also provides robust and efficient estimation performance.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 한국컴퓨터종합학술대회 논문집 Vol.32 No.1 (A)
• /
• pp.820-822
• /
• 2005

The current paper is on a study of the performance estimation fer data processing time and CPU utilization to efficiently develop the real-time system. The analytical modeling and OPNET modeling and benchmarking tests are applied to perform the estimation for data processing time and CPU utilization in real-time system. We demonstrate that the estimation results can be predicted fairly and accurately through the benchmarking test results although there is a small variance between the estimation results and the benchmarking test results.

• Journal of the Korean Statistical Society
• /
• 제15권2호
• /
• pp.87-96
• /
• 1986

Sequential estimation of parameters in a compound Poisson process whose jump sizes are one-parameter exponential class random variables is discussed. Cramer-Rao type information inequality is used as an efficiency cirterion. Unbiased estimators for certain parametric functions whose variance attain the lower bound are all characterized with the corresponding sampling plans.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2000년도 추계학술발표회 논문집
• /
• pp.65-73
• /
• 2000

Kernel estimator is very popular in nonparametric density estimation. In this paper we propose an estimator which reduces the bias to the fourth power of the bandwidth, while the variance of the estimator increases only by at most moderate constant factor. The estimator is fully nonparametric in the sense of convex combination of three kernel estimators, and has good numerical properties.

• Communications for Statistical Applications and Methods
• /
• 제8권2호
• /
• pp.327-336
• /
• 2001

This work concerns estimating a regression function, which is not linear, using aggregate data. In much of the empirical research, data are aggregated for various reasons before statistical analysis. In a traditional parametric approach, a linear estimation of the non-linear function with aggregate data can result in unstable estimators of the parameters. More serious consequence is the bias in the estimation of the non-linear function. The approach we employ is the kernel regression smoothing. We describe the conditions when the aggregate data can be used to estimate the regression function efficiently. Numerical examples will illustrate our findings.

• Journal of the Korean Data and Information Science Society
• /
• 제6권2호
• /
• pp.1-7
• /
• 1995

This paper considers the reliability estimation of a two-component shared-load system based on Freund model. Maximum likelihood estimator, order restricted maximum likelihood estimator and uniformly minimum variance unbiased estimator of the reliability function for the system are obtained. Performance of three estimators for moderate sample sizes is studied by simulation.