• Journal of the Korea Society for Simulation
• /
• v.23 no.4
• /
• pp.111-119
• /
• 2014

The cloud environment need resource management method that to enable the big data issue and data analysis technology. Existing resource management uses the limited calculation method, therefore concentrated the resource bias problem. To solve this problem, the resource management requires the learning-based scheduling using resource history information. In this paper, we proposes the ART (Adaptive Resonance Theory)-based adaptive resource management. Our proposed method assigns the job to the suitable method with the resource monitoring and history management in cloud computing environment. The proposed method utilizes the unsupervised learning method. Our goal is to improve the data processing and service stability with the adaptive resource management. The propose method allow the systematic management, and utilize the available resource efficiently.

• Journal of Korea Multimedia Society
• /
• v.21 no.3
• /
• pp.369-381
• /
• 2018

Nowadays a personalization algorithm is gaining huge attention. It gives users selective information which is helpful and interesting in a deluge of information based on their past behavior on the internet. However there is also a fatal side effect that the user can only get restricted information on restricted topics selected by the algorithm. Basically, the personalization algorithm makes users have a narrower perspective and even stronger bias because users have less chances to get views of opponent. Eli Pariser called this problem the 'filter bubble' in his book. It is important to understand exactly what a filter bubble is to solve the problem. Therefore, this paper shows how much Google's personalized search algorithm influences search result through an experiment with deep neural networks acting like users. At the beginning of the experiment, two Google accounts are newly created, not to be influenced by the Google's personalized search algorithm. Then the two pure accounts get politically biased by two methods. We periodically calculate the numerical score depending on the character of links and it shows how biased the account is. In conclusion, this paper shows the formation process of filter bubble by a personalization algorithm through the experiment.

• The Korean Journal of Applied Statistics
• /
• v.4 no.1
• /
• pp.1-11
• /
• 1991

It is of great interest to consider the homogeniety of covariance matrices in MANOVA of discriminant analysis. If we lock at the problem of testing hypothesis, H : $\Sigma_1 = \Sigma_2$ from an invariance point of view where $\Sigma_i$ are the covariance matrix of two independent p-variate distribution, the testing problem is invariant under the group of nonsingular transformations and the hypothesis becomes H : $\delta_1 = \delta_2 = \cdots = \delta_p = 1$ where $\delta = (\delta_1, \delta_2, \cdots, \delta_p)$ is a vector of latent roots of $\Sigma$. Bias-corrected estimators of eigenvalues and sampling distribution of the test statistics proposed are obtained. Pooled-bootstrap method also considered for Bartlett's modified likelihood ratio statistics.

• International Journal of Human Ecology
• /
• v.4 no.2
• /
• pp.77-87
• /
• 2003

This paper tried to construct statistical and econometric models on the basis of economic theory in order to discuss the issue of statistical efficiency and unbiasedness including the sample selection bias correcting problem. Comparative analytical tool were one stage Tobit of Maximum Likelihood estimation and Heckman's two-step Tobit of Ordinary Least Squares. The results showed that the adequacy of model for the analysis on demand and choice, we believe that there is no big difference in explanatory variables between the first selection model and the second linear probability model. Since the Lambda, the self- selectivity correction factor, in the Type II Tobit is not statistically significant, there is no self-selectivity in the Type II Tobit model, indicating that Type I Tobit model would give us better explanation in the demand for and choice which is less complicated statistical method rather than type II model.

• Communications for Statistical Applications and Methods
• /
• v.21 no.1
• /
• pp.1-9
• /
• 2014

This paper discusses the problem of estimation of finite population mean in double sampling for stratification. In fact, ratio and product type exponential estimators of population mean are proposed in double sampling for stratification. The biases and mean squared errors of proposed estimators are obtained upto the first degree of approximation. The proposed estimators have been compared with usual unbiased estimator, ratio and product estimators in double sampling for stratification. To judge the performance of the proposed estimators an empirical study has been carried out.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.4
• /
• pp.96-99
• /
• 1995

Under signal range mismatch, the LCMV beamformer has the performance degradation to cancel a desired signal. Using the eigenstructure properties of the array covariance matrix, we investigate the cause of this problem. From this investigation, a robust beamformer to source range mismatch is presented. The proposed beamformer has the maximum output signal-to-noise ration (SNR). When a desired signal is in a far field, the weight vector of the proposed beamformer is not biased.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2627-2647
• /
• 2016

With the rapid growth of microblog, expert identification on microblog has been playing a crucial role in many applications. While most previous expert identification studies only assess global authoritativeness of a user, there is no way to differentiate the authoritativeness in a particular aspect of topics. In this paper, we propose a novel model, which jointly models text and following relationship in the same generative process. Furthermore, we integrate a similarity-based weight scheme into the model to address the popular bias problem, and use followee topic distribution as prior information to make user's topic distribution more precisely. Our empirical study on two large real-world datasets shows that our proposed model produces significantly higher quality results than the prior arts.

• Communications for Statistical Applications and Methods
• /
• v.15 no.5
• /
• pp.709-717
• /
• 2008

The difference of two one-sided kernel estimators is usually used to detect the location of the discontinuity points of regression function. The large absolute value of the statistic imply discontinuity of regression function, so we may use the difference of two one-sided kernel estimators as the test statistic for testing null hypothesis of a smooth regression function. The problem is, however, we only know the asymptotic distribution of the test statistic under $H_0$ and we hardly expect the good performance of test if we rely solely on the asymptotic distribution for determining the critical points. In this paper, we show that if we adjust the bias of test statistic properly, the asymptotic rules hold for even small sample size situation.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.91-94
• /
• 2001

Recently a constant-norm constraint equation-error method was proposed to solve the bias problem in adaptive IIR filtering. However, the method adopts a fixed step-size and thus results in slow convergence for a small step-size and significant misadjustment error for a largestep-size. In this paper, we propose a variable step-size (VSS) algorithm that greatly improves convergence properties of the constant-norm constraint equation-error method. The analysis and the simulation results show that the proposed method indeed achieves both fast convergence and small misadjustment error.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.65-68
• /
• 2000

It is well-known that the decision rule in the mini-mum mean-squares-error decision feedback equalizer(MMSE-DFE) is biased, and therefore suboptimum with respect to error probability. We present a new family of algorithms that solve the bias problem in the adaptive DFE. A novel constraint, called the constant-norm con-straint, is introduced unifying the quadratic constraint and the monic one. A new cost function based on the constant-norm constraint and Lagrange multiplier is defined. Minimizing the cost function gives birth to a new family of unbiased adaptive DFE. The simula-tion results demonstrate that the proposed method in-deed produce unbiased solution in the presence of noise while keeping very simple both in computation and im-plementation.