Earticle

A hybrid kernel function of support vector machine is proposed to improve the classification performance of power quality disturbances. The kernel function mathematical model of support vector machine directly affects the classification performance. Different types of kernel functions have different generalization ability and learning ability. The single kernel function cannot have better ability both in learning and generalization. To overcome this problem, we propose a hybrid kernel function that is composed of two single kernel functions to improve both the ability in generation and learning. In simulations, we respectively used the single and multiple power quality disturbances to test classification performance of support vector machine algorithm with the proposed hybrid kernel function. Compared with other support vector machine algorithms, the improved support vector machine algorithm has better performance for the classification of power quality signals with single and multiple disturbances.

One-class support vector machine (OCSVM) is an important and efficient classifier used when only one class of data is available while others are too expensive or difficult to collect. It uses vector as input data, and trains a linear or nonlinear decision function in vector space. However, the traditional vector-based classifiers may fail when input is matrix. Therefore, it makes sense to study matrixzed classifiers which can make use of the structural information presented in the data. In this paper we propose a matrix-based one-class classification algorithm named Kernel-based Matrixzed One-class Support Vector Machine (KMatOCSVM). It aims to convert the OCSVM to suit for matrix representation data and to deal with nonlinear one-class classification problems. The efficiency and validity of the proposed method is illustrated by four real-world matrix-based human face datasets.

The relationship between the nuclear parameters and model performance is complex, which is from relevance vector machine (RVM) regression model based on Gaussian radial basis kernel function. Aiming at the problem of how to determine the kernel parameters of RVM, a method to selecting kernel parameter of RVM based on AIC criterion is proposed. Firstly, a novel of statistic Q is proposed based on “Akaike” Information Criterion (AIC), while the Q is as a fitness function. Secondly, we use the differential evolution algorithm (Differential Evolution Algorithm, DE) to find the best kernel parameter, in order to choose determine the kernel parameters. Finally, a RVM regression model mode is established and it is used in predicting gold price. Experimental results show that the prediction model has higher precision and better fitting the generalization ability than the traditional method, which demonstrates the AIC-based criteria for selecting RVM kernel parameter method is effective and feasible.

The existing trustworthiness attestation methods are not only difficult to be applied to the embedded system because they are mainly based on virtual machine technology, but have some problems such shat evidence is not obtained in time, protecting the privacy need trusted third party and trust measurement efficiency is low. In this paper, an embedded system dynamic trustworthiness attestation method based on dual-kernel (super kernel and normal kernel) operating system architecture is proposed. Super kernel is non-changeable, and it verifies the integrity of the critical data structures and kernel file in normal kernel. Super kernel can serve as a trusted third party which can dynamically verify whether the code segment changes in runtime. A system implementation is given in this paper, and the experimental data show that the behavior of the system can dynamically verify the behavior of program whether meets embedded trusted application demand or not.

The research work in this paper is in the field, the moving target detection spatiotemporal correlation and difference contour tracking algorithm based on a fixed background. The algorithm in the background under the condition of fixed to pay a smaller time complexity, the target detection and tracking has a good effect, so it has higher application value. This paper mainly focuses on the study of motion estimation and compensation algorithm to eliminate the temporal redundancy. Algorithm of detection and tracking of video moving object is a core subject in computer vision field, but also the key technology of intelligent video surveillance system. It combines the research achievements of artificial intelligence and other fields of pattern recognition, image processing, has been widely used in every field of security monitoring, intelligent weapons, video conference, video retrieval. Therefore, detection and tracking algorithm research has the extremely important theory significance and practical value. The starting point of this article is the subjective quality of image reconstruction of how to improve the accuracy of motion estimation and compensation after, to reduce the computation complexity of motion estimation algorithms, to improve the efficiency of motion estimation. This paper makes some studies on the redundant wavelet domain block matching motion estimation and compensation, then the video image for non-translational motion, the DT triangular mesh motion estimation and compensation in the redundant wavelet domain to do related research.

With the development of artificial intelligence and pattern recognition technology, more and more research related to human face is constantly developing in all walks of life. At the present stage, the traditional face recognition algorithm based on LBP and SVM is not good, and the process of feature extraction and feature classification are deeply studied in this paper. For feature extraction, the authors put forward an improved CS-LBP texture feature; for feature classification, the author uses the histogram intersection (HIK) kernel function to classify the features which has high efficiency and good effect. Subsequently, experiments are carried out on the Yale data set and the ORL data set. Experimental results show that the proposed algorithm has a significant improvement on the face recognition effect of face direction change, and the illumination change is slightly improved. In the natural environment, most face recognition has the influence of human face direction and noise, and the effect of noise is a hot direction of face recognition research in the future.

Because of the feature points can describe the local characteristics of the image in a reasonable manner, effective use of feature point of content based image retrieval become the current hot issues in the field of computer vision. Aiming at this problem, we put forward a kind of combination clustering based on feature points, a new method of image retrieval. The method includes the combination of feature point clustering algorithm and based on the algorithm of local color histogram construction strategy. With the existing and local color histogram retrieval method based on feature points, compared to the method can effectively solve the current method of feature point location information and feature point center relying too much on the problem. Subjectivity and as a result of the manual annotation image accuracy, the traditional image retrieval methods cannot meet the needs of the user. Multidimensional indexing technology is only from the perspective of how to improve the indexing algorithm to adapt to the large-scale database to consider a problem, in content-based image retrieval. Our research combines the advantages of the semantic analysis and kernel clustering which will enhance the performance of the traditional image retrieval methods and strengthen the feasibility of the algorithm.

It is well known that each kernel function defines primal-dual interior-point method (IPM). Most of polynomial-time interior-point algorithms for linear optimization (LO) are based on the logarithmic kernel function ([9]). In this paper we define new eligible kernel function and propose a new search direction and proximity function based on this function for LO problems. We show that the new algorithm has $\mathcal{O}(({\log}\;p)^{\frac{5}{2}}\sqrt{n}{\log}\;n\;{\log}\frac{n}{\epsilon})$ and $\mathcal{O}(q^{\frac{3}{2}}({\log}\;p)^3\sqrt{n}{\log}\;\frac{n}{\epsilon})$ iteration complexity for large- and small-update methods, respectively. These are currently the best known complexity results for such methods.

The censored regression model generally assumes the logarithm of survival time is modelled linearly in the covariates. In this study a censored varying coefficient regression model is proposed to consider situations in which the regression coefficients are not constant and change as the relevant smoothing variables change. Using the formulation of weighted least squares support vector machine with jumps of the Kaplan-Meier estimator of the empirical distribution of function of residuals similar to Miller’s estimation for censored regression, we can easily obtain the estimators of the proposed model through simple linear equations, and can also easily derive a generalized cross validation function. The proposed method is evaluated through simulated and real data sets.

Change point testing problem is considered. Kernel density estimators are used for constructing proposed change point test statistics. The proposed method can be used to the hypothesis testing of not only parameter change but also distributional change. Bootstrap method is applied to get the sampling distribution of proposed test statistic. Small sample Monte Carlo Simulation were also conducted in order to show the performance of proposed method.

신분위장공격 탐지는 오랫동안 연구되어 왔지만 실제 시스템에 적용되어 사용되기에는 여전이 높은 오탐지율(false alarm)과 낮은 탐지력(detecion rate)이 가장 큰 문제였다. 유닉스 시스템에서 신분위장공격을 탐지하기 위하여 사용자의 유닉스 명령어 행위를 프로파일링하고 정상 프로파일링에서 벗어난 권한 도용을 탐지하는 방법을 사용한다. 본 연구에서는 신분위장공격 탐지 시스템의 탐지력을 높이기 위하여 순서 정보를 반영한 SVM 커널 기법을 고찰하고 실험 결과를 정리하였다.

신분위장공격 탐지는 오랫동안 연구되어 왔지만 실제 시스템에 적용되어 사용되기에는 여전이 높은 오탐지율(false alarm)과 낮은 탐지력(detecion rate)이 가장 큰 문제였다. 유닉스 시스템에서 신분위장공격을 탐지하기 위하여 사용자의 유닉스 명령어 행위를 프로파일링하고 정상 프로파일링에서 벗어난 권한 도용을 탐지하는 방법을 사용한다. 본 연구에서는 신분위장공격 탐지 시스템의 탐지력을 높이기 위하여 순서 정보를 반영한 SVM 커널 기법을 고찰하고 실험 결과를 정리하였다.

SVDD(support vector data description)는 one-class 서포트 벡터 학습 방법론 중 하나로 비정상 물체에서 정상 데이터를 구분하기 위해서 특징 공간에서 정의된 구를 이용하는 전략을 쓰는 방법론이다. 본 논문에서는 SVDD를 이용해서 노이즈가 섞인 비정상 데이터를 노이즈가 제거된 정상 데이터로 복원하는 방법에 대해서 논한다. 그리고 저해상도의 이미지를 고해상도의 이미지로 복원함으로써 본 논문의 방법론이 어떻게 실용적으로 적용되는지에 대해서 다룬다.

스마트폰은 주로 사용되고 있는 안드로이드 OS는 다양한 악성코드로 인해 금전적 피해, 데이터 유출 및 통제권한 상실 등과 같은 많은 피해를 당하고 있다. 침해 위협을 가중시키고 있는 모바일 악성코드 중 심각한 피해를 유발하는 커널 기반의 루팅(Rooting) 악성코드는 일반적인 탐지 방법으로는 찾아낼 수 없는 어려움이 있다. 본 논문에서는 커널 기반에서 동작하는 루팅(Rooting) 악성코드를 탐지하기 위한 방법을 제안한다. 스마트폰 어플리케이션이 실행될 때마다 생성되는 모든 프로세스의 UID를 확인하여 비정상적으로 사용자(User) 권한에서 관리자(Root) 권한으로 변환되는지를 확인하는 방법이다. 제안하는 방법을 활용하여 알려지지 않은 악성코드로 인한 안드로이드 OS의 피해를 최소화할 수 있을 것으로 기대된다.

커널 함수는 데이터를 high dimension 상의 속성 공간으로 mapping함으로써 복잡한 분포를 가지는 데이터에 대하여 기존의 선형 분류 알고리즘들의 성능을 향상시킬 수 있다. 본 논문에서는 기존의 유클리디안 거리측정방법 대신에 커널 함수에 의한 속성 공간의 거리측정방법을 fuzzy K-nearest neighbor 알고리즘에 적용한 fuzzy kernel K-nearest neighbor(FKKNN) 알고리즘을 제안한다. 제시한 알고리즘은 데이터에 대한 적절한 커널 함수의 선택으로 기존 알고리즘의 성능을 향상 시킬 수 있다. 제시한 알고리즘의 타당성을 보이기 위하여 여러 데이터 집합에 대한 실험결과를 분석한다.

본 논문에서는 커널 백피팅 알고리즘에 가중 ${\beta}$-지수승 최소평균제곱오차 추정방식(weighted ${\beta}$-order minimum mean square error: WbE)을 적용한 보컬음 분리 방식에 대해 제안한다. 음성 향상 방식에서, WbE는 진폭 성분 기반 MMSE(Minimum Mean Square Error) 추정방식, 로그 스펙트럼 진폭 기반 MMSE 추정방식 등과 같은 기존의 베이지안(Bayesian) 기반의 추정방식들 보다 객관적 및 주관적 측면에서 모두 보다 높은 성능을 나타내는 방식으로 잘 알려져 있다. 이에 본 논문에서는 기본적인 반복적 커널 백피팅 알고리즘에 WbE를 적용하여 음악 신호에서의 보컬음 분리 성능을 향상시키고자 하였다. 실험결과는 본 논문에서 제안한 방식이 기존의 분리 방식보다 분리 성능이 더 뛰어나다는 것을 보인다.

In this paper, we propose a vocal separation method using weighted ${\beta}$-order minimum mean wquare error estimation (WbE) based on kernel back-fitting algorithm. In spoken speech enhancement, it is well-known that the WbE outperforms the existing Bayesian estimators such as the minimum mean square error (MMSE) of the short-time spectral amplitude (STSA) and the MMSE of the logarithm of the STSA (LSA), in terms of both objective and subjective measures. In the proposed method, WbE is applied to a basic iterative kernel back-fitting algorithm for improving the vocal separation performance from monaural music signal. The experimental results show that the proposed method achieves better separation performance than other existing methods.

Recently, demands of information devices are increasing as we can find so many information devices around us such as smartphone, MID(Mobile Internet Device), Tablet. These characteristics of information devices services should support soft real-time based time guaranteed multimedia services and control internet appliances. In this situation, soft real-time supported system should be developed to consider as a total aspect of hardware, kernel, middleware, application. But this paper will describe soft real-time supporting and evaluation methods for information device as an aspect of only kernel.

Workers in nuclear power plants are likely to be exposed to radiation from variousgeometrical sources. In order to evaluate the exposure level, the point-kernel method can be utilized. In order to perform a dose assessment based on this method, the radiation source should be dividedinto point sources, and the number of divisions should be set by the evaluator. However, for the generalpublic, there may be difficulties in selecting the appropriate number of divisions and performing anevaluation. Therefore, the purpose of this study is to develop an algorithm for dose assessment forarbitrary shaped sources based on the point-kernel method. For this purpose, the point-kernel methodwas analyzed and the main factors for the dose assessment were selected. Subsequently, based onthe analyzed methodology, a dose assessment algorithm for arbitrary shaped sources was developed. Lastly, the developed algorithm was verified using Microshield. The dose assessment procedure of thedeveloped algorithm consisted of 1) boundary space setting step, 2) source grid division step, 3) the setof point sources generation step, and 4) dose assessment step. In the boundary space setting step, theboundaries of the space occupied by the sources are set. In the grid division step, the boundary space isdivided into several grids. In the set of point sources generation step, the coordinates of the point sourcesare set by considering the proportion of sources occupying each grid. Finally, in the dose assessmentstep, the results of the dose assessments for each point source are summed up to derive the dose rate. In order to verify the developed algorithm, the exposure scenario was established based on the standardexposure scenario presented by the American National Standards Institute. The results of the evaluationwith the developed algorithm and Microshield were compare. The results of the evaluation with thedeveloped algorithm showed a range of 1.99×10-1~9.74×10-1 μSv hr-1, depending on the distance and theerror between the results of the developed algorithm and Microshield was about 0.48~6.93%. The errorwas attributed to the difference in the number of point sources and point source distribution between thedeveloped algorithm and the Microshield. The results of this study can be utilized for external exposureradiation dose assessments based on the point-kernel method.