• Journal of the Korean Data and Information Science Society
• /
• v.9 no.1
• /
• pp.1-9
• /
• 1998

In case of Zero-Inflated Poisson model with a change-point, likelihood ratio test statistic was used for testing hypothesis for a change-point. A change-point and several interesting parameters were estimated by using the method of moments and maximum likelihood. In order to compare the estimators, empirical mean-square-error was used. Real data for the Zero-Inflated Poisson model with a change-point and Poisson model without a change-point were examined.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.69-74
• /
• 2023

This study introduces an innovative model for zero-shot voice conversion that utilizes the capabilities of HuBERT. Zero-shot voice conversion models can transform the speech of one speaker to mimic that of another, even when the model has not been exposed to the target speaker's voice during the training phase. Comprising five main components (HuBERT, feature encoder, flow, speaker encoder, and vocoder), the model offers remarkable performance across a range of scenarios. Notably, it excels in the challenging unseen-to-unseen voice-conversion tasks. The effectiveness of the model was assessed based on the mean opinion scores and similarity scores, reflecting high voice quality and similarity to the target speakers. This model demonstrates considerable promise for a range of real-world applications demanding high-quality voice conversion. This study sets a precedent in the exploration of HuBERT-based models for voice conversion, and presents new directions for future research in this domain. Despite its complexities, the robust performance of this model underscores the viability of HuBERT in advancing voice conversion technology, making it a significant contributor to the field.

• Journal of Energy Engineering
• /
• v.27 no.4
• /
• pp.103-110
• /
• 2018

In this paper, we introduce evaluation method of time series prediction model with new approach of Mean Absolute Percentage Error(hereafter MAPE) and Symmetric Mean Absolute Percentage Error(hereafter sMAPE). There are some problems using MAPE and sMAPE. First MAPE can't evaluate Zero observation of dataset. Moreover, when the observed value is very close to zero it evaluate heavier than other methods. Finally it evaluate different measure even same error between observations and predicted values. And sMAPE does different evaluations are made depending on whether the same error value is over-predicted or under-predicted. And it has different measurement according to the each sign, even if error is the same distance. These problems were solved by Maximum Mean Absolute Percentage Error(hereafter mMAPE). we used the absolute maximum of observed value as denominator instead of the observed value in MAPE, when the value is less than 1, removed denominator then solved the problem that the zero value is not defined. and were able to prevent heavier measurement problem. Also, if the absolute maximum of observed value is greater than 1, the evaluation values of mMAPE were compared with those of the other evaluations. With Beijing PM2.5 temperature data and our simulation data, we compared the evaluation values of mMAPE with other evaluations. And we proved that mMAPE can solve the problems that we mentioned.

• Journal of Power Electronics
• /
• v.12 no.4
• /
• pp.528-537
• /
• 2012

This paper presents an interleaved resonant converter with a parallel-series transformer connection in order to achieve ripple current reduction at the output capacitor, zero voltage turn-on for the active switches, zero current turn-off for the rectifier diodes, less voltage stress on the rectifier diodes, and less current stress on the transformer primary windings. The primary windings of the two transformers are connected in parallel in order to share the input current and to reduce the root-mean-square (rms) current on the primary windings. The secondary windings of the two transformers are connected in series in order to ensure that the transformer primary currents are balanced. A full-wave diode rectifier is used at the output side to clamp the voltage stress of the rectifier diode at the output voltage. Two circuit modules are operated with the interleaved PWM scheme so that the input and output ripple currents are reduced. Based on the resonant behavior, all of the active switches are turned on under zero voltage switching (ZVS), and the rectifier diodes are turned off under zero current switching (ZCS) if the operating switching frequency is less than the series resonant frequency. Finally, experiments with a 1kW prototype are described to verify the effectiveness of the proposed converter.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.14 no.3
• /
• pp.133-141
• /
• 2006

The Low cycle fatigue behavior of 11.7Cr-1.1Mo heat-resisting steel has been investigated under strain-controlled conditions with mean stresses at room temperature and $300^{\circ}C$. For the tensile mean stress test, the initial high tensile mean stress generally relaxed to zero at room temperature, however, at $300^{\circ}C$ initial tensile mean stress relaxed to compressive mean stress. Low cycle fatigue lives under mean stress conditions are usually correlated using modifications to the strain-life approach. Based on the fatigue test results from different stain ratio of -1, 0, 0.5, and 0.75 at room temperature and $300^{\circ}C$, the fatigue damage of the steel was represented by using cyclic strain energy density. Total strain energy density considering mean stress indicated well better than not considering mean stress at $300^{\circ}C$. Predicted fatigue life using Smith-Watson-Topper's parameter correlated fairly well with the experimental life at $300^{\circ}C$.

• 전기의세계
• /
• v.28 no.3
• /
• pp.57-64
• /
• 1979

The static state estimation are divided into two groups; estimation and detection & identification. This paper centers on detection and identification algorithm. Especially, the identification of line errors is focused on and is performed by the extended W.L.S. algorithm with line swithching states. Here, line switching states mean the discrete values of line admittance which are influenced by unexpected line switching. The numerical results are obtained from the assumption that the noise vector is independent zero mean Gaussian random variables.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 1999.04a
• /
• pp.41-48
• /
• 1999

Small earthquake records with magnitude 2.7-4.8 recorded in Kyungsang Basin during 1995-1997 were analysed. Total of 87 records consisted of 16 events instrumented at 11 stations,. Mean dominant period at each station mean zero period acceleration of each component and the acceleration response spectra were analysed. Spectral value increases as magnitude increases and the predominant frequency band expands to low frequency zone as magnitude increases.

• Kyungpook Mathematical Journal
• /
• v.56 no.1
• /
• pp.273-293
• /
• 2016

In this paper, we obtain that every biharmonic non-degenerate hypersurfaces in semi-Euclidean space $E^5_s$ with constant scalar curvature of diagonal shape operator has zero mean curvature.

• Journal of Ocean Engineering and Technology
• /
• v.16 no.3
• /
• pp.8-18
• /
• 2002

Formulation of the far-field method for the prediction of time-mean hydrodynamic force and moment acting on a 3-D surface-piercing body in waves is reviewed. It is found that the inequality between the weight of the floating body and its buoyancy force permits the replacement of the fluid particles inside the control surface by the fluid particles outside the control surface. Under such circumstances, momentum exchanges across the control surface make the time-mean value of the time rate of the momentum of the fluid inside the control surface non-vanishing. It is a second-order quantity which is hard to calculate by the far-field method. The drift forces and moments on half-immersed ellipsoids are calculated by both the far-field method and the near-field method. The discrepancy between two numerical results is presented and discussed.

• The Korean Journal of Applied Statistics
• /
• v.24 no.5
• /
• pp.951-961
• /
• 2011

In this paper, we propose a Bayesian inference using the Markov Chain Monte Carlo(MCMC) method for the zero inflated negative binomial(ZINB) regression model. The proposed model allows the regression model for zero inflation probability as well as the regression model for the mean of the dependent variable. This extends the work of Jang et al. (2010) to the fully defiend ZINB regression model. In addition, we apply the proposed method to a real data example, and compare the efficiency with the zero inflated Poisson model using the DIC. Since the DIC of the ZINB is smaller than that of the ZIP, the ZINB model shows superior performance over the ZIP model in zero inflated count data with overdispersion.