• Proceedings of the KOSOMBE Conference
• /
• v.1998 no.11
• /
• pp.78-79
• /
• 1998

This paper describes a real time algorithm for blood flow estimation of LDF(laser Doppler flowmeter). Many algorithms for blood flow estimation are using power spectral density of Doppler signal by blood flow. In these research, the fast Fourier transformation is used to estimate power spectral density. This is a block processing procedure rather than real time processing. The algorithm in this paper used parametric spectral estimation. This has real time capability by estimation of AR(autoregressive) parameters sample by sample, and has smoothing power spectrum. Also, the frequency resolution is not limited by number of samples used to estimate AR parameter. Another advantage of this algorithm is that AR model enhance SNR.

• Journal of electromagnetic engineering and science
• /
• v.4 no.1
• /
• pp.23-29
• /
• 2004

In this paper we analyze convergence constraints and time constant of IT-LMS algorithm and derive a method of making it's time constant independent of signal power by using input variance estimation. The method for estimating the input variance is to use a single-pole low-pass filter(LPF) with common smoothing parameter value, θ. The estimator is with narrow bandwidth for large θ but with wide bandwidth for small θ. This small θ gives long term average estimation(low frequency) of the fluctuating input variance well as short term variations (high frequency) of the input power. In our simulations of multipath communication channel equalization environments, the method with large θ has shown not as much improved convergence speed as the speed of the original IT-LMS algorithm. The proposed method with small θ=0.01 reach its minimum MSE in 100 samples whereas the IT-LMS converges in 200 samples. This shows the proposed, tap-power normalized IT-LMS algorithm can be applied more effectively to digital wireless communication systems.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.20 no.3
• /
• pp.123-146
• /
• 1995

Several quality control schemes have been extensively compared using multivariate normal data sets simulated with various correlation structures. They include multiple univariate CUSUM charts, multivariate EWMA charts, multivariate CUSUM charts and Shewhart T$^{3}$ chart. This paper considers a new approach of the multivariate EWMA chart, in which the smoothing matrix has full elements instead of only diagonal elements. Performance of the schemes is measured by avaerage run length (ARL), coefficient of variation of run length (CVRL) and rank in order of signaling of off-target shifts in the process mean vector. The schemes are also compared by noncentrality parameter. The multiple univariate CUSUM charts are generally affected by the correlation structure. The multivariate EWMA charts provide better ARL performance. Especially, the new EWMA chart shows remarkable results in small shifts.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2005.05a
• /
• pp.97-102
• /
• 2005

This paper presents feed rate optimizaton of a PMLSM driven feed-slide for mininum vibrations by smoothing velocity curve with finite jerk. First of all, the PMLSM was designed and made to reduce detent force. Next, a PMLSM driven feed-slide system was mathematically modeled as a 4-degree-of-freedom lumped parameter model. The key idea of our vibration minimization method is to find out the most appropriate smooth velocity curve with finite jerk. The validity of our proposed method has been verified by comparing computer simulation results of the feed-slide model with experimental ones.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.3
• /
• pp.579-585
• /
• 2012

Many different semi-supervised learning algorithms have been proposed for use wit unlabeled data. However, most of them focus on classification problems. In this paper we propose a semi-supervised regression algorithm called the semi-supervised local constant estimator (SSLCE), based on the local constant estimator (LCE), and reveal the asymptotic properties of SSLCE. We also show that the SSLCE has a faster convergence rate than that of the LCE when a well chosen weighting factor is employed. Our experiment with synthetic data shows that the SSLCE can improve performance with unlabeled data, and we recommend its use with the proper size of unlabeled data.

• MALSORI
• /
• no.54
• /
• pp.63-72
• /
• 2005

The performance of speech recognition system is degraded by the mismatch between training and test environments. Many studies have been presented to compensate for noise components in the cepstral domain. Recently, higher order cepstral moment normalization method has been introduced to improve recognition accuracy. In this paper, we present real-time high order moment normalization method with post-processing smoothing filter to reduce the parameter estimation error in higher order moment computation. In experiments using Aurora2 database, we obtained error rate reduction of 44.7% with proposed algorithm in comparison with baseline system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.572-575
• /
• 2010

본 논문은 SNR 이 매우 낮은 저조도 영상의 잡음 제거를 위한 새로운 기술을 제안한다. 제안하는 기술은 입력 영상에서 파라미터를 자동/적응적 방식으로 추정하는 알고리즘을 특징으로 한다. 제안하는 기술의 효율성을 검증하기 위해 실질적인 환경에서 취득한 저조도 동영상들을 가지고 실험을 수행하였다. 실험을 통해 제안하는 기술을 활용하여 적응적으로 추정된 파라미터가 필터링(filtering) 성능을 잘 유지시킴을 검증하였다. 또한 기존 연구들과 비교할 때 저조도 동영상의 명암대비 향상과 잡음 제거에 우수한 결과를 보임을 검증하였다.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.54.1-54.1
• /
• 2019

We use iterative smoothing reconstruction method along with exploring in the parameter space of the light curves of the JLA supernova compilation (Joint Light-curve Analysis) to simultaneously reconstruct the expansion history of the universe as well as putting constrains on the light curve parameters without assuming any cosmological model. Our constraints on the light curve parameters of the JLA from our model-independent analysis seems to be closely in agreement with results assuming ΛCDM cosmology or using Chevallier-Polarski-Linder (CPL) parametrization for the equation of state of dark energy. This implies that there is no hidden significant feature in the data that could be neglected by cosmology model assumption. The reconstructed expansion history of the universe and properties of dark energy seems to be in good agreement with expectations of the standard ΛCDM model. Our results also indicate that the data allows a considerable flexibility for expansion history of the universe.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.699-704
• /
• 2001

ABSTRACT In this paper, a new hybrid modular recurrent TDNN (time-delay neural network)-HMM (hidden Markov model) architecture for speech recognition has been studied. In TDNN, the recognition rate could be increased if the signal window is extended. To obtain this effect in the neural network, a high-level memory generated through a feedback within the first hidden layer of the neural network unit has been used. To increase the ability to deal with the temporal structure of phonemic features, the input layer of the network has been divided into multiple states in time sequence and has feature detector for each states. To expand the network from small recognition task to the full speech recognition system, modular construction method has been also used. Furthermore, the neural network and HMM are integrated by feeding output vectors from the neural network to HMM, and a new parameter smoothing method which can be applied to this hybrid system has been suggested.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2009.10a
• /
• pp.147-154
• /
• 2009

Physical properties of rocks, such as velocity, are strongly dependant on detailed pore structures, and recently, pore micro-structures by X-ray tomography techniques have been used to simulate and understand the physical properties. However, the smoothing effect during the tomographic reconstruction procedure often causes an artifact - overestimating the contact areas between grains. The pore nodes near a grain contact are affected by neighboring grain nodes, and are classified into grain nodes. By this artifact, the pore structure has higher contact areas between grains and thus higher velocity estimation than the true one. To reduce this artifact, we tried two image processing techniques - sharpening filter and neural network classification. Both methods gave noticeable improvement on contact areas between grains visually; however, the estimated velocities showed only incremental improvement. We then tried to change the resolutions of tomogram and quantify its impact on velocity estimation. The estimated velocity from the tomogram with higher spatial resolution was improved significantly, and with around 2 micron spatial resolution, the calculated velocity was very close to the lab measurement. In conclusion, the resolution of pore micro-structure is the most important parameter for accurate estimation of velocity using pore-scale simulation techniques. Also the estimation can be incrementally improved if combined with image processing techniques during the pore-grain classification.