• Speech Sciences
• /
• v.10 no.2
• /
• pp.77-84
• /
• 2003

In this research, we seek the beginning of the speech and detect the stationary speech region using lip information. Performing running average of the estimated speech signal in the stationary region, we reduce the effect of musical noise which is inherent to the conventional MlMSE (Minimum Mean Square Error) speech enhancement algorithm. In addition to it, SFM (Spectral Flatness Measure) is incorporated to reduce the speech signal estimation error due to speaking habit and some lacking lip information. The proposed algorithm with Wiener filtering shows the superior performance to the conventional methods according to MOS (Mean Opinion Score) test.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.13-16
• /
• 1999

Many of the currently used PN code acquisition algorithms detect the phase of the incoming PN signal on the basis of ML estimation principle and utilize statistics grounded in taking inner products. As an extension of PN code acquisition algorithm using one auxiliary code introduced by Salih in 1996, we propose a more and optimal (hardware / time / space complexity wise) algorithm by using a vector space approach. We outline some important differences between our algorithm and that introduced by Salih and in the process point out some advantages of our algorithm.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.569-572
• /
• 1999

In this paper we present a color image segmentation algorithm based on statistical models. A novel deterministic annealing Expectation Maximization(EM) formula is derived to estimate the parameters of the Gaussian Mixture Model(GMM) which represents the multi-colored objects statistically. The experimental results show that the proposed deterministic annealing EM is a global optimal solution for the ML parameter estimation and the image field is segmented efficiently by using the parameter estimates.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.851-859
• /
• 2006

The family income distributions of NLSY97 and CPS youth data are compared by using the generalized beta distribution of the second kind. The null hypothesis that the two data sets represent the same underlying population is rejected. The ML estimation suggests that NLSY97 data are oversampled in an income group of $11,308 or less, by about 15.7% compared to CPS data.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.1021-1028
• /
• 2006

We shall propose ML, ordinary jackknife and biased reducing estimators of the parameter in the right truncated exponential distribution with an unidentified uniform outlier when the truncated point is unknown and their biases and MSE's are compared numerically each other in the small sample sizes.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.36 no.4
• /
• pp.64-70
• /
• 2013

Estimation approaches for casual relation model with high-order factors have strict restrictions or limits. In the case of ML (Maximum Likelihood), a strong assumption which data must show a normal distribution is required and factors of exponentiation is impossible due to the uncertainty of factors. To overcome this limitation many PLS (Partial Least Squares) approaches are introduced to estimate the structural equation model including high-order factors. However, it is possible to yield biased estimates if there are some differences in the number of measurement variables connected to each latent variable. In addition, any approach does not exist to deal with general cases not having any measurement variable of high-order factors. This study compare several approaches including the repeated measures approach which are used to estimate the casual relation model including high-order factors by using PLS (Partial Least Squares), and suggest the best estimation approach. In other words, the study proposes the best approach through the research on the existing studies related to the casual relation model including high-order factors by using PLS and approach comparison using a virtual model.

• Journal of Korean Institute of Industrial Engineers
• /
• v.27 no.1
• /
• pp.111-117
• /
• 2001

Most of the techniques for the performance estimation of unit-load AS/RS are a static model or computer simulation. Especially, their models have been developed under the assumption that the Storage/Retrieval (S/R) machine performs either single command(SC) or dual command(DC) only. In reality, depending on the operating policy and the status of the system at a particular time, the S/R machine performs a SC or a DC, or becomes idle. In order to resolve this weak point, we propose a stochastic model for the performance estimation of unit-load ASIRS by using a M/G/1 queueing model with a single server and two queues. Server utilization, expected numbers of waiting storage and retrieval commands and mean time spent in queue and system are found.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.99-106
• /
• 2015

In this study, we propose Radial basis function Neural Network(RBFNN) using Recursive Weighted Least Square Estimation(RWLSE) to effectively deal with big data class meteorological radar data. In the condition part of the RBFNN, Fuzzy C-Means(FCM) clustering is used to obtain fitness values taking into account characteristics of input data, and connection weights are defined as linear polynomial function in the conclusion part. The coefficients of the polynomial function are estimated by using RWLSE in order to cope with big data. As recursive learning technique, RWLSE which is based on WLSE is carried out to efficiently process big data. This study is experimented with both widely used some Machine Learning (ML) dataset and big data obtained from meteorological radar to evaluate the performance of the proposed classifier. The meteorological radar data as big data consists of precipitation echo and non-precipitation echo, and the proposed classifier is used to efficiently classify these echoes.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.7
• /
• pp.72-85
• /
• 1998

In this paper, we propose a new method that sequentially estimates TDOA(Time Delay Of Arrival) and FDOA(Frequency Delay Of Arrival) for extracting the information about the bearing and relative velocity of a target in passive radar or sonar arrays. The objective is to efficiently estimate the TDOA and FDOA between two sensor signal measurements, corrupted by correlated Gaussian noise sources in an unknown way. The proposed method utilizes the one dimensional slice function of the third order cumulants between the two sensor measurements, by which the effect of correlated Gaussian measurement noises can be significantly suppressed for the estimation of TDOA. Because the proposed sequential algoritjhm uses the one dimensional complex ambiguity function based on the TDOA estimate from the first step, the amount of computations needed for accurate estimationof FDOA can be dramatically reduced, especially for the cases where high frequency resolution is required. It is demonstrated that the proposed algorithm outperforms existing TDOA/FDOA estimation algorithms based on the ML(maximum likelihood) criterionandthe complex ambiguity function of the third order cumulant as well, in the MSE(mean squared error) sense and computational burden. Various numerical resutls on the detection probability, MSE and the floatingpoint computational burden are presented via Monte-Carlo simulations for different types of noises, different lengths of data, and different signal-to-noise ratios.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.1
• /
• pp.275-277
• /
• 2012

Objective: The objective of our present study was to assess the efficacy of carcinoembryonic antigen (CEA) for differentiating and diagnosis of pancreatic and liver diseases in Pokhara valley. Materials and methods: A hospital based retrospective study was carried out using data retrieved from the register maintained in the Department of Biochemistry of the Manipal Teaching Hospital, Pokhara, Nepal between 1st January, 2011 and 31st October, 2011. Estimation of CEA was performed by ELISA reader for all cases. Approval for the study was obtained from the institutional research ethical committee. Results: Of the 771 subjects, 208 (27%), 60(7.8%), 240(31.1%), 54(7.0%), 75(9.7%), 59(7.7%), 75(9.7%) cases were of active chronic hepatitis, cryptogenic cirrhosis, alcoholic cirrhosis, primary biliary cirrhosis, hepatoma, acute or chronic pancreatitis, carcinoma of pancreas respectively. The majority of cases (104) of active chronic hepatitis had CEA levels <5ng/ml(50%). CEA levels were found to be increased in cases of alcoholic cirrhosis with maximum number of cases (106) in range of 10 to 20 ng/ml (44%). There were no cases having more than 20ng/ml of CEA in primary biliary cirrhosis and acute or chronic pancreatitis. In cases of pancreatic cancer, maximum number of cases (35) were having CEA >20ng/ml(47%). Conclusion: High levels of CEA are associated with advanced stage of disease. CEA can thus provide an important improvement in the diagnosis by differentiating pancreatic cancer especially from chronic pancreatitis when there is a high suspicion of malignancy. Increased CEA levels may also signify progression from benign to malignant transformation in the liver.