• ETRI Journal
• /
• 제33권5호
• /
• pp.712-719
• /
• 2011

In this paper, we study the problem of domain adaptation for structural support vector machines (SVMs). We consider a number of domain adaptation approaches for structural SVMs and evaluate them on named entity recognition, part-of-speech tagging, and sentiment classification problems. Finally, we show that a prior model for structural SVMs outperforms other domain adaptation approaches in most cases. Moreover, the training time for this prior model is reduced compared to other domain adaptation methods with improvements in performance.

• Asia pacific journal of information systems
• /
• 제21권2호
• /
• pp.43-58
• /
• 2011

Support vector machines (SVMs), a machine learning technique, has been applied to not only binary classification problems such as bankruptcy prediction but also multi-class problems such as corporate credit ratings. However, in general, the performance of SVMs can be easily worse than the best alternative model to SVMs according to the selection of predictors, even though SVMs has the distinguishing feature of successfully classifying and predicting in a lot of dichotomous or multi-class problems. For overcoming the weakness of SVMs, this study has proposed an approach for selecting features for multi-class SVMs that utilize the impurity measures of classification trees. For the selection of the input features, we employed the C4.5 and CART algorithms, including the stepwise method of discriminant analysis, which is a well-known method for selecting features. We have built a multi-class SVMs model for credit rating using the above method and presented experimental results with data regarding S&P 500 companies.

• 한국산학기술학회논문지
• /
• 제18권11호
• /
• pp.778-784
• /
• 2017

참굴(Crassostrea gigas)의 패각운동을 이용하여 Alexandrium 속의 조기 출현모니터링 가능성을 고찰하였다. 지구규모에서 패류독화를 발생시키는 A. fundyense와 잠재적 유독종으로 알려진 A. affine를 이용하여 홀 소자센서(Hall element sensor)를 사용하여 참굴의 패각운동(SVMs)을 측정하였다. 참굴은 Isocrysis galbana를 먹이생물로 하여 안정화 시킨 다음 3일간 절식 시킨 후 실험에 제공하였다. 결과 참굴은 A. fundyense에 대해 세포밀도 20 cells/mL에서 SVMs 횟수가 $10.5{\pm}1.2times/hr$로 증가하여 민감하게 반응하였고, 세포밀도 500 cells/mL에서 재차 $14.1{\pm}5.7times/h$, 5,000 cells/mL에서 $27.9{\pm}11.1times/hr$로 SVMs가 급격한 증가를 보였다. 그러나 A. affine에 대해서는 세포밀도가 300 cells/mL까지 $6.7{\pm}3.9times/hr$로 기준 SVMs와 유사하였고, 세포밀도 1,000 cells/mL 이상에서 $15.3{\pm}10.8times/hr$로 급격히 증가하였다. 즉 A. fundyense는 20 cells/mL에서부터 참굴의 SVMs가 민감하게 반응하였지만, A. affine는 높은 1,000 cells/mL의 세포밀도에서 SVMs가 반응하였다. 이러한 결과에서 유독와편모조에 대한 참굴의 SVMs는 종에 따른 차이가 있어, A. fundyense의 초기발생 예보에는 유용하게 활용 가능하지만, A. affine에 응용하는 것은 어렵다는 결론을 얻었다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2006년도 추계학술대회논문집
• /
• pp.401-406
• /
• 2006

This paper presents the fault diagnosis of induction motor based on support vector machine(SVMs). SVMs are well known as intelligent classifier with strong generalization ability. Application SVMs using kernel function is widely used for multi-class classification procedure. In this paper, the algorithm of SVMs will be combined with feature extraction and reduction using component analysis such as independent component analysis, principal component analysis and their kernel(KICA and KPCA). According to the result, component analysis is very useful to extract the useful features and to reduce the dimensionality of features so that the classification procedure in SVM can perform well. Moreover, this method is used to induction motor for faults detection based on vibration and current signals. The results show that this method can well classify and separate each condition of faults in induction motor based on experimental work.

• 대한전자공학회논문지SP
• /
• 제41권6호
• /
• pp.43-49
• /
• 2004

기존의 다중 클래스 SVMs은 클래스의 개수가 증가되면, 이진 클래스 SVMs의 수도 증가되어 분류를 위해 많은 시간이 요구된다. 본 논문에서는 분류 시간을 줄이기 위하여, PCA+LDA 특징 부 공간에서 NNR을 적용하여 클래스의 개수를 줄이는 방법을 제안한다. 제안된 방법은 PCA+LDA 특징 부 공간에서 간단한 NNR을 사용하여, 입력된 테스트 특징 데이터와 근접된 얼굴 클래스들을 추출함으로서 얼굴 클래스의 개수를 줄이는 방법이다. 클래스 개수를 줄임으로, 본 방법은 기존의 다중 클래스 SVMs에 비하여 훈련 횟수와 비교 횟수를 줄일 수 있고, 결과적으로 하나의 테스트 영상을 위한 분류 시간을 크게 줄일 수 있다. 또한 실험 결과, 제안된 방법은 NNC 기법보다 낮은 에러 율을 가지며, 기존의 다중 클래스 SVMs보다 동일한 에러 율을 갖지만, 보다 빠른 분류시간을 가짐을 확인할 수 있었다.

• 인지과학
• /
• 제21권4호
• /
• pp.655-667
• /
• 2010

개체명 인식은 정보 추출의 한 단계로서 정보검색 분야 뿐 아니라 질의응답과 요약 분야에서 매우 유용하게 사용되고 있다. 본 논문에서는 structural Support Vector Machines(structural SVMs) 및 수정된 Pegasos 알고리즘을 이용한 한국어 개체명 인식 시스템에 대하여 기술하고 기존의 Conditional Random Fields(CRFs)를 이용한 시스템과의 성능을 비교한다. 실험결과 structural SVMs과 수정된 Pegasos 알고리즘이 기존의 CRFs 보다 높은 성능을 보였고(신뢰도 99%에서 통계적으로 유의함), structural SVMs과 수정된 Pegasos 알고리즘의 성능은 큰 차이가 없음(통계적으로 유의하지 않음)을 알 수 있었다. 특히 본 논문에서 제안하는 수정된 Pegasos 알고리즘을 이용한 경우 CRFs를 이용한 시스템보다 높은 성능(TV 도메인 F1=85.43, 스포츠 도메인 F1=86.79)을 유지하면서 학습 시간은 4%로 줄일 수 있었다.

• 산경연구논집
• /
• 제13권10호
• /
• pp.1-8
• /
• 2022

Purpose: Support vector machines (SVMs) ensemble has been proposed to improve classification performance of Credit risk recently. However, currently used fusion strategies do not evaluate the importance degree of the output of individual component SVM classifier when combining the component predictions to the final decision. To deal with this problem, this paper designs a support vector machines (SVMs) ensemble method based on fuzzy integral, which aggregates the outputs of separate component SVMs with importance of each component SVM. Research design, data, and methodology: This paper designs a personal credit risk evaluation index system including 16 indicators and discusses a support vector machines (SVMs) ensemble method based on fuzzy integral for designing a credit risk assessment system to discriminate good creditors from bad ones. This paper randomly selects 1500 sample data of personal loan customers of a commercial bank in China 2015-2020 for simulation experiments. Results: By comparing the experimental result SVMs ensemble with the single SVM, the neural network ensemble, the proposed method outperforms the single SVM, and neural network ensemble in terms of classification accuracy. Conclusions: The results show that the method proposed in this paper has higher classification accuracy than other classification methods, which confirms the feasibility and effectiveness of this method.

• ETRI Journal
• /
• 제32권1호
• /
• pp.120-128
• /
• 2010

In this paper, we describe a modified fixed-threshold sequential minimal optimization (FSMO) for 1-slack structural support vector machine (SVM) problems. Because the modified FSMO uses the fact that the formulation of 1-slack structural SVMs has no bias, it breaks down the quadratic programming (QP) problems of 1-slack structural SVMs into a series of smallest QP problems, each involving only one variable. For various test sets, the modified FSMO is as accurate as existing structural SVM implementations (n-slack and 1-slack SVM-struct) but is faster on large data sets.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.496-499
• /
• 2003

Support Vector Machines (SVMs) is applied to a practical problem as one of standard tools for machine learning. The application of Reinforcement Learning (RL) and SVMs in action of mobile robot is investigated. A technique to decide the action of autonomous mobile robot in practice is explained in the paper, The proposed method is to find n basis for good action of the system under unknown environment. In multi-dimensional sensor input, the most reasonable action can be automatically decided in each state by RL. Using SVMs, not only optimal decision policy but also generalized state in unknown environment is obtained.

• Journal of the Korean Data and Information Science Society
• /
• 제27권3호
• /
• pp.827-833
• /
• 2016

In this paper, we propose a deep least squares support vector machine (LS-SVM) for regression problems, which consists of the input layer and the hidden layer. In the hidden layer, LS-SVMs are trained with the original input variables and the perturbed responses. For the final output, the main LS-SVM is trained with the outputs from LS-SVMs of the hidden layer as input variables and the original responses. In contrast to the multilayer neural network (MNN), LS-SVMs in the deep LS-SVM are trained to minimize the penalized objective function. Thus, the learning dynamics of the deep LS-SVM are entirely different from MNN in which all weights and biases are trained to minimize one final error function. When compared to MNN approaches, the deep LS-SVM does not make use of any combination weights, but trains all LS-SVMs in the architecture. Experimental results from real datasets illustrate that the deep LS-SVM significantly outperforms state of the art machine learning methods on regression problems.