• Structural Engineering and Mechanics
• /
• 제83권3호
• /
• pp.293-304
• /
• 2022

In this work, a novel reliability approach for combined high and low cycle fatigue (CCF) estimation is developed by combining active learning strategy with least squares support vector machines (LS-SVM) (named as ALS-SVM) surrogate model to address the multi-resources uncertainties, including working loads, material properties and model itself. Initially, a new active learner function combining LS-SVM approach with Monte Carlo simulation (MCS) is presented to improve computational efficiency with fewer calls to the performance function. To consider the uncertainty of surrogate model at candidate sample points, the learning function employs k-fold cross validation method and introduces the predicted variance to sequentially select sampling. Following that, low cycle fatigue (LCF) loads and high cycle fatigue (HCF) loads are firstly estimated based on the training samples extracted from finite element (FE) simulations, and their simulated responses together with the sample points of model parameters in Coffin-Manson formula are selected as the MC samples to establish ALS-SVM model. In this analysis, the MC samples are substituted to predict the CCF reliability of turbine blades by using the built ALS-SVM model. Through the comparison of the two approaches, it is indicated that the reliability model by linear cumulative damage rule provides a non-conservative result compared with that by the proposed one. In addition, the results demonstrate that ALS-SVM is an effective analysis method holding high computational efficiency with small training samples to gain accurate fatigue reliability.

• Journal of the Korean Data and Information Science Society
• /
• 제21권3호
• /
• pp.561-567
• /
• 2010

Multiclassification is typically performed using voting scheme methods based on combining a set of binary classifications. In this paper we use multiclassification method with a hat matrix of least squares support vector machine (LS-SVM), which can be regarded as the revised one-against-all method. To tackle multiclass problems for large data, we use the $Nystr\ddot{o}m$ approximation and the quadratic Renyi entropy with estimation in the primal space such as used in xed size LS-SVM. For the selection of hyperparameters, generalized cross validation techniques are employed. Experimental results are then presented to indicate the performance of the proposed procedure.

• Journal of the Korean Data and Information Science Society
• /
• 제16권4호
• /
• pp.999-1012
• /
• 2005

We compare two popular algorithms in current machine learning and statistical learning areas, boosting method represented by AdaBoost and kernel based SVM (Support Vector Machine) using 13 real data sets. This comparative study shows that boosting method has smaller prediction error in data with heavy noise, whereas SVM has smaller prediction error in the data with little noise.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.347-350
• /
• 2002

This paper describes eye detection algorithm using edge information and Support Vector Machine (SVM). We adopt an edge detection and labelling algorithm to detect isolated components. Detected candidate eye pairs finally verified by SVM using Radial Basis Function (RBF) kernel. A detection rate over the test set has been achieved more than 90%, and compared with template matching method. this proposed method significantly reduced FAR.

• 대한산업공학회지
• /
• 제40권4호
• /
• pp.404-414
• /
• 2014

Yield prediction is important to manage semiconductor quality. Many researches with machine learning algorithms such as SVM (support vector machine) are conducted to predict yield precisely. However, yield prediction using SVM is hard because extremely imbalanced and big data are generated by final test procedure in semiconductor manufacturing process. Using SVM algorithm with imbalanced data sometimes cause unnecessary support vectors from major class because of unselected support vectors from minor class. So, decision boundary at target class can be overwhelmed by effect of observations in major class. For this reason, we propose a under-sampling method with minor class based SVM (MCSVM) which overcomes the limitations of ordinary SVM algorithm. MCSVM constructs the model that fixes some of data from minor class as support vectors, and they can be good samples representing the nature of target class. Several experimental studies with using the data sets from UCI and real manufacturing process represent that our proposed method performs better than existing sampling methods.

• Journal of Electrical Engineering and Technology
• /
• 제11권1호
• /
• pp.192-199
• /
• 2016

With changes in insulated defects, the environment, and so on, new partial discharge (PD) data are highly different from the original samples. It leads to a decrease in on-line recognition rate. The UHF signal and pulse current signal of four kinds of typical artificial defect models in gas insulated switchgear (GIS) are obtained simultaneously by experiment. The relationship map of ultra-high frequency (UHF) cumulative energy and its corresponding apparent discharge of four kinds of typical artificial defect models are plotted. UHF cumulative energy and its corresponding apparent discharge are used as inputs. The support vector machine (SVM) incremental method is constructed. Examples show that the PD SVM incremental method based on simulated annealing (SA) effectively speeds up the data update rate and improves the adaptability of the classifier compared with the original method, in that the total sample is constituted by the old and new data. The PD SVM incremental method is a better pattern recognition technology for PD on-line monitoring.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2010년도 춘계학술대회
• /
• pp.981-984
• /
• 2010

우리는 본 연구에서 학습방법으로서 연속음성을 초성, 중성, 종성의 음소단위로 분할하기 위하여 인공 신경회로망의 하나인 SVMs을 사용하였으며 분할한 음소단위의 음성으로 연속음성인식에 적용하여 그 성능을 살펴보았다. 음소경계는 단 구간에서의 최대 주파수를 가진 알고리듬에 의하여 결정되며 또한 음성인식처리는 CHMM에 의하여 이루어지며 목측에 의한 분할결과와도 비교하여 살펴보았다. 시뮬레이션 결과로부터 초성의 분할성능에서 제안한 SVMs를 적용한 결과가 GMMs보다 효율적인을 알 수 있었다.

• 충청수학회지
• /
• 제29권4호
• /
• pp.631-642
• /
• 2016

This article deals with one-dimension backward heat conduction problem (BHCP). A new approach based on least squares support vector machines (LS-SVM) is proposed for obtaining their approximate solutions. The approximate solution is presented in closed form by means of LS-SVM, whose parameters are adjusted to minimize an appropriate error function. The approximate solution consists of two parts. The first part is a known function that satisfies initial and boundary conditions. The other is a product of two terms. One term is known function which has zero boundary and initial conditions, another term is unknown which is related to kernel functions. This method has been successfully tested on practical examples and has yielded higher accuracy and stable solutions.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.417-420
• /
• 2002

In this paper, we propose a VLSI architecture for computation of the SVM(Support Vector Machine) that has become established as a powerful technique for solving a variety of classification, regression, and so on. When we compare the proposed systolic arrays with the conventional method, our architecture exhibits a lot of advantages in terms of latency and throughput rate.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2112-2115
• /
• 2003

The system for the real time face detection is described in this paper. For face verification, support vector machine (SVM) was utilized. Although SVM performs quit well, SVM has a drawback that the computational cost is high because all pixels in a mask are used as an input feature vector of SVM. To resolve this drawback, a method to reduce the dimension of feature vectors using the integer DCT was proposed. Also for the real time face detection applications, low-complexity methods for face candidate detection in a gray image were used. As a result, the accurate face detection was performed in real time.