• Phonetics and Speech Sciences
• /
• v.7 no.3
• /
• pp.131-138
• /
• 2015

In this paper, we propose L1-norm regularization for state vector adaptation of subspace Gaussian mixture model (SGMM). When you design a speaker adaptation system with GMM-HMM acoustic model, MAP is the most typical technique to be considered. However, in MAP adaptation procedure, large number of parameters should be updated simultaneously. We can adopt sparse adaptation such as L1-norm regularization or sparse MAP to cope with that, but the performance of sparse adaptation is not good as MAP adaptation. However, SGMM does not suffer a lot from sparse adaptation as GMM-HMM because each Gaussian mean vector in SGMM is defined as a weighted sum of basis vectors, which is much robust to the fluctuation of parameters. Since there are only a few adaptation techniques appropriate for SGMM, our proposed method could be powerful especially when the number of adaptation data is limited. Experimental results show that error reduction rate of the proposed method is better than the result of MAP adaptation of SGMM, even with small adaptation data.

• The Korean Journal of Applied Statistics
• /
• v.25 no.6
• /
• pp.925-932
• /
• 2012

The article introduces a method to estimate a cointegrated vector autoregressive model, using mixed-frequency data, in terms of a state-space representation of the vector error correction(VECM) of the model. The method directly estimates the parameters of the model, in a state-space form of its VECM representation, using the available data in its mixed-frequency form. Then it allows one to compute in-sample smoothed estimates and out-of-sample forecasts at their high-frequency intervals using the estimated model. The method is applied to a mixed-frequency data set that consists of the quarterly real gross domestic product and three monthly coincident indicators. The result shows that the method produces accurate smoothed and forecasted estimates in comparison to a method based on single-frequency data.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.475-478
• /
• 2015

The objective of this study is to apply a hybrid model for estimating solar radiation and investigate their accuracy. A hybrid model is wavelet-based support vector machines (WSVMs). Wavelet decomposition is employed to decompose the solar radiation time series into approximation and detail components. These decomposed time series are then used as inputs of support vector machines (SVMs) modules in the WSVMs model. Results obtained indicate that WSVMs can successfully be used for the estimation of daily global solar radiation at Champaign and Springfield stations in Illinois.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1400-1418
• /
• 2020

In the development of commercial promotion, chatbot is known as one of significant skill by application of natural language processing (NLP). Conventional design methods are using bag-of-words model (BOW) alone based on Google database and other online corpus. For one thing, in the bag-of-words model, the vectors are Irrelevant to one another. Even though this method is friendly to discrete features, it is not conducive to the machine to understand continuous statements due to the loss of the connection between words in the encoded word vector. For other thing, existing methods are used to test in state-of-the-art online corpus but it is hard to apply in real applications such as telemarketing data. In this paper, we propose an improved chatbot design way using hybrid bag-of-words model and skip-gram model based on the real telemarketing data. Specifically, we first collect the real data in the telemarketing field and perform data cleaning and data classification on the constructed corpus. Second, the word representation is adopted hybrid bag-of-words model and skip-gram model. The skip-gram model maps synonyms in the vicinity of vector space. The correlation between words is expressed, so the amount of information contained in the word vector is increased, making up for the shortcomings caused by using bag-of-words model alone. Third, we use the term frequency-inverse document frequency (TF-IDF) weighting method to improve the weight of key words, then output the final word expression. At last, the answer is produced using hybrid retrieval model and generate model. The retrieval model can accurately answer questions in the field. The generate model can supplement the question of answering the open domain, in which the answer to the final reply is completed by long-short term memory (LSTM) training and prediction. Experimental results show which the hybrid word vector expression model can improve the accuracy of the response and the whole system can communicate with humans.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.3
• /
• pp.401-412
• /
• 2011

This study uses a vector error correction model to analyze the daily time series data of the spot price of EUA (European Union Allowance). As endogenous variables, five variables are considered for the analysis, including prices of crude oil, natural gas, electricity and coal in addition to carbon price. Data period is Phase 2 period (April 21, 2008 to March 31, 2010) to avoid Phase 1 period (2005-2007) where the EUA prices were distorted. Unit-root and cointegration test results reveal that all variables have a unit root and cointegration vectors exist, so a vector error correction model is adopted instead of a vector autoregressive model.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.5
• /
• pp.879-886
• /
• 2009

The purpose of this article is to present the application of Least Squares Support Vector Machine in analyzing the existing structure of brand. We estimate the parameters of the Market Share Attraction Model using a non-parametric technique for function estimation called Least Squares Support Vector Machine, which allows us to perform even nonlinear regression by constructing a linear regression function in a high dimensional feature space. Estimation by Least Squares Support Vector Machine technique makes it a good candidate for solving the Market Share Attraction Model. To illustrate the performance of the proposed method, we use the car sales data in South Korea's car market.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.831-839
• /
• 2010

Least squares support vector machine (LS-SVM) is a kernel trick gaining a lot of popularities in the regression and classification problems. We use LS-SVM to propose a iterative algorithm for a nonlinear generalized autoregressive conditional heteroscedasticity model in the mean (GARCH-M) model to estimate the mean and the conditional volatility of stock market returns. The proposed method combines a weighted LS-SVM for the mean and unweighted LS-SVM for the conditional volatility. In this paper, we show that nonlinear GARCH-M models have a higher performance than the linear GARCH model and the linear GARCH-M model via real data estimations.

• Journal of Ocean Engineering and Technology
• /
• v.37 no.5
• /
• pp.198-204
• /
• 2023

In response to the complexity and time demands of conventional methods for estimating the hydrodynamic coefficients, this study aims to revolutionize ship maneuvering analysis by utilizing automatic identification system (AIS) data and the Support Vector Regression (SVR) algorithm. The AIS data were collected and processed to remove outliers and impute missing values. The rate of turn (ROT), speed over ground (SOG), course over ground (COG) and heading (HDG) in AIS data were used to calculate the rudder angle and ship velocity components, which were then used as training data for a regression model. The accuracy and efficiency of the algorithm were validated by comparing SVR-based estimated hydrodynamic coefficients and the original hydrodynamic coefficients of the Mariner class vessel. The validated SVR algorithm was then applied to estimate the hydrodynamic coefficients for real ships using AIS data. The turning circle test wassimulated from calculated hydrodynamic coefficients and compared with the AIS data. The research results demonstrate the effectiveness of the SVR model in accurately estimating the hydrodynamic coefficients from the AIS data. In conclusion, this study proposes the viability of employing SVR model and AIS data for accurately estimating the hydrodynamic coefficients. It offers a practical approach to ship maneuvering prediction and control in the maritime industry.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.467-474
• /
• 2006

In this paper we present a weighted support vector machine(SVM) and a weighted least squares support vector machine(LS-SVM) for the prediction in the heteroscedastic regression model. By adding weights to standard SVM and LS-SVM the better fitting ability can be achieved when errors are heteroscedastic. In the numerical studies, we illustrate the prediction performance of the proposed procedure by comparing with the procedure which combines standard SVM and LS-SVM and wild bootstrap for the prediction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.7
• /
• pp.1569-1574
• /
• 2005

In this paper, I propose an intelligent credit rating system using a bankruptcy prediction model based on support vector machines (SVMs). SVMs are promising methods because they use a risk function consisting of the empirical error and a regularized term which is derived from the structural risk minimization principle. This study examines the feasibility of applying SVM in Predicting corporate bankruptcies by comparing it with other data mining techniques. In addition. this study presents architecture and prototype of intelligeht credit rating systems based on SVM models.