• ETRI Journal
• /
• 제38권3호
• /
• pp.510-517
• /
• 2016

Recent developments in the field of separation of mixed signals into music/voice components have attracted the attention of many researchers. Recently, iterative kernel back-fitting, also known as kernel additive modeling, was proposed to achieve good results for music/voice separation. To obtain minimum mean square error (MMSE) estimates of short-time Fourier transforms of sources, generalized spatial Wiener filtering (GW) is typically used. In this paper, we propose an advanced music/voice separation method that utilizes a generalized weighted ${\beta}$-order MMSE estimation (WbE) based on iterative kernel back-fitting (KBF). In the proposed method, WbE is used for the step of mixed music signal separation, while KBF permits kernel spectrogram model fitting at each iteration. Experimental results show that the proposed method achieves better separation performance than GW and existing Bayesian estimators.

• 한국음향학회지
• /
• 제30권6호
• /
• pp.330-336
• /
• 2011

본 논문에서는 supervector linear kernel SVM을 사용한 화자식별 시스템의 성능을 개선하는 방법을 제안하였다. 제안한 방법은 긴 학습 데이터를 여러 개의 짧은 학습 데이터로 분할하는 것을 기본 아이디어로 하고 있다. 제안한 방법의 성능을 평가하기 위해 서로 다른 4가지 데이터베이스에 PCA, GKPCA, KMDA를 사용하여 특징 강화를 하고 실험한 뒤 결과를 분석하였다. 실험 결과 제안한 방법이 supervector linear kernel SVM을 사용한 화자 식별 성능을 향상 시키는 것을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.983-986
• /
• 2002

Support Vector Machine (SVM) is one of the methods of pattern recognition that separate input data using hyperplane. This method has high capability of pattern recognition by using the technique, which says kernel trick, and the Radial basis function (RBF) kernel is usually used as a kernel function in kernel trick. In this paper we propose using the q-normal distribution to the kernel function, instead of conventional RBF, and compare two types of the kernel function.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.702-723
• /
• 2020

The application of machine learning (ML) in intrusion detection has attracted much attention with the rapid growth of information security threat. As an efficient multi-label classifier, kernel extreme learning machine (KELM) has been gradually used in intrusion detection system. However, the performance of KELM heavily relies on the kernel selection. In this paper, a novel multiple kernel extreme learning machine (MKELM) model combining the ReliefF with nature-inspired methods is proposed for intrusion detection. The MKELM is designed to estimate whether the attack is carried out and the ReliefF is used as a preprocessor of MKELM to select appropriate features. In addition, the nature-inspired methods whose fitness functions are defined based on the kernel alignment are employed to build the optimal composite kernel in the MKELM. The KDD99, NSL and Kyoto datasets are used to evaluate the performance of the model. The experimental results indicate that the optimal composite kernel function can be determined by using any heuristic optimization method, including PSO, GA, GWO, BA and DE. Since the filter-based feature selection method is combined with the multiple kernel learning approach independent of the classifier, the proposed model can have a good performance while saving a lot of training time.

• Journal of the Korean Statistical Society
• /
• 제29권3호
• /
• pp.307-313
• /
• 2000

Suppose we have a set of data X1, ···, Xn and employ kernel density estimator to estimate the marginal density of X. in this article bandwith selection problem for kernel density estimator is examined closely. In particular the Kullback-Leibler method (a bandwith selection methods based on average square error (ASE)) is considered.

• 한국지능시스템학회논문지
• /
• 제22권4호
• /
• pp.454-459
• /
• 2012

Wenner의 4전극법으로 측정한 겉보기 대지저항률을 이용하여 대지저항률의 Kernel 함수를 추정할 수 있다. 이 때 커널함수를 추정하는 것은 비선형시스템을 푸는 과정으로 유도된다. 그러나 변수가 많은 비선형시스템은 해를 구하기가 쉽지 않다. 본 논문은 이 비선형시스템을 선형화하여 커널함수를 추정하는 방법을 제시한다. 마지막으로 제안한 방법을 평가하기 위하여 다양한 구조로 된 대지모델들을 시뮬레이션의 예로 사용한다.

• 한국수자원학회논문집
• /
• 제41권6호
• /
• pp.559-564
• /
• 2008

본 연구에서는 복합 강우사상으로부터 단위도와 S-곡선을 도출하는 실용적인 방법을 강구하였다. 이 연구에서 이용된 단위핵함수는 단위도와 S-곡선을 유도하는데 있어서 기존의 방법보다 편리하다. 그러나 실제 자료를 분석할 때 단위핵함수는 진동을 보이고 불안정하기 때문에 단위도와 S-곡선 도출에 있어서 장애가 있다. 그런데 단위핵함수의 요소인 Nash 의 순간단위도를 추정함에 있어서 Laplacian 행렬을 이용한 능형회귀분석을 이용하면 사상에 대한 평균적인 단위핵함수를 구하는데 유익함을 발견하였다. 또한 이를 이용하여 단위도의 지속기간 변경도 가능하였다. 이 연구에서 제시된 방법론은 단위도 제작에 적지 않은 도움이 될 것으로 기대한다.

• International Journal of Reliability and Applications
• /
• 제1권2호
• /
• pp.133-143
• /
• 2000

Data from weighted distributions appear, among other situations, when some of the data are missing or are damaged, a case that is important in reliability and life testing. The kernel method for hazard rate estimation is discussed for these data where the basic large sample properties are given. As a by product, the basic properties of the kernel estimate of the distribution function for data from weighted distribution are presented.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1327-1334
• /
• 2008

Mixed effect binomial regression models are widely used for analysis of correlated count data in which the response is the result of a series of one of two possible disjoint outcomes. In this paper, we consider kernel extensions with nonparametric fixed effects and parametric random effects. The estimation is through the penalized likelihood method based on kernel trick, and our focus is on the efficient computation and the effective hyperparameter selection. For the selection of hyperparameters, cross-validation techniques are employed. Examples illustrating usage and features of the proposed method are provided.

• Journal of applied mathematics & informatics
• /
• 제12권1_2호
• /
• pp.165-182
• /
• 2003

Toeplitz matrix method and the product Nystrom method are described for mixed Fredholm-Volterra singular integral equation of the second kind with Carleman Kernel and logarithmic kernel. The results are compared with the exact solution of the integral equation. The error of each method is calculated.