• Communications for Statistical Applications and Methods
• /
• 제15권3호
• /
• pp.441-450
• /
• 2008

In this paper we propose a new method for solving multiclass problem with least squares support vector machine(LS-SVM) regression. This method implements one-against-all scheme which is as accurate as any other approach. We also propose cross validation(CV) method to select effectively the optimal values of hyper-parameters which affect the performance of the proposed multiclass method. Experimental results are then presented which indicate the performance of the proposed multiclass method.

• 대한수학회논문집
• /
• 제11권4호
• /
• pp.1147-1157
• /
• 1996

Nonlinear ill-posed problems arise in many application including parameter estimation and inverse scattering. We introduce a least squares regularization method to solve nonlinear ill-posed problems with constraints robustly and efficiently. The regularization method uses Trust-Region approach to handle the constraints on variables. The Generalized Cross Validation is used to choose the regularization parameter in computational tests. Numerical results are given to exhibit faster convergence of the method over other methods.

• 한국지형학회지
• /
• 제26권3호
• /
• pp.53-67
• /
• 2019

The purpose of this study is to identify the quality of landslide susceptibility in a landslide-prone area (Jinbu-myeon, Gangwon-do, South Korea) by spatial prediction modeling approach and compare the results obtained. For this goal, a landslide inventory map was prepared mainly based on past historical information and aerial photographs analysis (Daum Map, 2008), as well as some field observation. Altogether, 550 landslides were counted at the whole study area. Among them, 182 landslides are debris flow and each group of landslides was constructed in the inventory map separately. Then, the landslide inventory was randomly selected through Excel; 50% landslide was used for model analysis and the remaining 50% was used for validation purpose. Total 12 contributing factors, such as slope, aspect, curvature, topographic wetness index (TWI), elevation, forest type, forest timber diameter, forest crown density, geology, landuse, soil depth, and soil drainage were used in the analysis. Moreover, to find out the co-relation between landslide causative factors and incidents landslide, pixels were divided into several classes and frequency ratio for individual class was extracted. Eventually, six landslide susceptibility maps were constructed using the Bayesian Predictive Discriminant (BPD), Empirical Likelihood Ratio (ELR), and Linear Regression Method (LRM) models based on different category dada. Finally, in the cross validation process, landslide susceptibility map was plotted with a receiver operating characteristic (ROC) curve and calculated the area under the curve (AUC) and tried to extract success rate curve. The result showed that Bayesian, likelihood and linear models were of 85.52%, 85.23%, and 83.49% accuracy respectively for total data. Subsequently, in the category of debris flow landslide, results are little better compare with total data and its contained 86.33%, 85.53% and 84.17% accuracy. It means all three models were reasonable methods for landslide susceptibility analysis. The models have proved to produce reliable predictions for regional spatial planning or land-use planning.

• Structural Engineering and Mechanics
• /
• 제9권4호
• /
• pp.323-338
• /
• 2000

An analytical approach for the prediction of the behaviour of steel-fiber reinforced concrete beams subjected to torsion is described. The analysis method employs a special stress-strain model with a non-linear post cracking branch for the material behaviour in tension. Predictions of this model for the behaviour of steel-fiber concrete in direct tension are also presented and compared with results from tests conducted for this reason. Further in this work, the validation of the proposed torsional analysis by providing comparisons between experimental curves and analytical predictions, is attempted. For this purpose a series of 10 steel-fiber concrete beams with various cross-sections and steel-fiber volume fractions tested in pure torsion, are reported here. Furthermore, experimental information compiled from works around the world are also used in an attempt to establish the validity of the described approach based on test results of a broad range of studies. From these comparisons it is demonstrated that the proposed analysis describes well the behaviour of steel-fiber concrete in pure torsion even in the case of elements with non-rectangular cross-sections.

• Journal of Electrical Engineering and Technology
• /
• 제12권2호
• /
• pp.830-839
• /
• 2017

Support vector machine (SVM) is introduced as an effective fault diagnosis technique based on dissolved gases analysis (DGA) for oil-immersed transformers with maximum generalization ability; however, the applicability of the SVM is highly affected due to the difficulty of selecting the SVM parameters appropriately. Therefore, a novel approach combing SVM with improved imperialist competitive algorithm (IICA) for fault diagnosis of oil-immersed transformers was proposed in the paper. The improved ICA, which is proved to be an effective optimization approach, is employed to optimize the parameters of SVM. Cross validation and normalizations were applied in the training processes of SVM and the trained SVM model with the optimized parameters was established for fault diagnosis of oil-immersed transformers. Three classification benchmark sets were studied based on particle swarm optimization SVM (PSOSVM) and IICASVM with four multiple classification schemes to select the best scheme for transformer fault diagnosis. The results show that the proposed model can obtain higher diagnosis accuracy than other methods. The comparisons confirm that the proposed model is an effective approach for classification problems.

• 정보처리학회논문지B
• /
• 제17B권4호
• /
• pp.309-316
• /
• 2010

본 연구에서는 얼굴 그리드 각도를 특징공간으로 하는 새로운 모델 기반 얼굴 표정 인식 방법을 제안한다. 제안 방식은 6가지 얼굴 대표 표정을 인식하기 위해 표정 그리드를 이용하여 그리드의 각 간선과 정점이 형성하는 각도를 기반으로 얼굴 특징 공간을 구성한다. 이 방법은 다른 표정 인식 알고리즘의 정확도를 낮추는 원인인 변환, 회전, 크기변화와 같은 어파인 변환에 강건한 특징을 보인다. 또한, 본 연구에서는 각도로 특징공간을 구성하고 이 공간 내에서 Wrapper 방식으로 특징 부분집합을 선택하는 과정을 설명한다. 선택한 특징들은 SVM, 3-NN 분류기를 이용해 분류하고 분류 결과는 2중 교차검증을 통해 검증하도록 한다. 본 연구가 제안한 방법에서는 94%의 표정 인식 결과를 보였으며 특히 특징 부분집합 선택 알고리즘을 적용한 결과 전체 특징을 이용한 경우보다 약 10%의 인식율 개선 효과를 보인다.

• Journal of the Korean Data and Information Science Society
• /
• 제24권6호
• /
• pp.1113-1125
• /
• 2013

기업의 부도를 예측하는 것은 회계나 재무 분야에서 중요한 연구주제이다. 지금까지 기업 부도예측을 위해 여러 가지 데이터마이닝 기법들이 적용되었으나 주로 단일 모형을 사용함으로서 복잡한 분류 문제에의 적용에 한계를 갖고 있었다. 본 논문에서는 최근에 각광받고 있는 SVM (support vector machine) 모형들을 결합한 앙상블 SVM 모형 (ensemble SVM model)을 부도예측에 사용하고자 한다. 제안된 앙상블 모형은 v-조각 교차 타당성 (v-fold cross-validation)에 의해 얻어진 여러 가지 모형 중에서 성능이 좋은 상위 k개의 단일 모형으로 구성하고 과반수 투표 방식 (majority voting)을 사용하여 미지의 클래스를 분류한다. 본 논문에서 제안된 앙상블 SVM 모형의 성능을 평가하기 위해 실제 기업의 재무비율 자료와 모의실험자료를 가지고 실험하였고, 실험결과 제안된 앙상블 모형이 여러 가지 평가척도 하에서 단일 SVM 모형들보다 좋은 성능을 보임을 알 수 있었다.

• 분석과학
• /
• 제37권2호
• /
• pp.114-122
• /
• 2024

A transmission Raman spectroscopy-based quantitative model, which can analyze the content of a drug product containing naproxen sodium as its active pharmaceutical ingredient (API), was developed. Compared with the existing analytical method, i.e., high-performance liquid chromatography (HPLC), Raman spectroscopy exhibits high test efficiency owing to its shorter sample pre-treatment and measurement time. Raman spectroscopy is environmentally friendly since samples can be tested rapidly via a nondestructive method without sample preparation using solvent. Through this analysis method, rapid on-site analysis was possible and it could prevent the production of defective tablets with potency problems. The developed method was applied to the assays of the naproxen sodium of coated tablets that were manufactured in commercial scale and the content of naproxen sodium was accurately predicted by Raman spectroscopy and compared with the reference analytical method such as HPLC. The method validation of the new approach was also performed. Further, the specificity, linearity, accuracy, precision, and robustness tests were conducted, and all the results were within the criteria. The standard error of cross-validation and standard error of prediction values were determined as 0.949 % and 0.724 %, respectively.

• Journal of the Korean Statistical Society
• /
• 제24권2호
• /
• pp.495-506
• /
• 1995

We present formula for detecting influential observations on the smoothing parameter in smoothing spline. Further, we express them as functions of basic building blocks such as residuals and leverage, and compare it with the local influence approach by Thomas (1991). An example based on a real data set is given.

• 응용통계연구
• /
• 제25권4호
• /
• pp.669-680
• /
• 2012

Noise removal of document images is a necessary step during preprocessing to recognize characters effectively because it has influences greatly on processing speed and performance for character recognition. We have considered using the spatial filters such as traditional mean filters and Gaussian filters, and wavelet transformed based methods for noise deduction in natural images. However, these methods are not effective for the noise removal of document images. In this paper, we present noise removal of document images using support vector regression. The proposed approach consists of two steps which are SVR training step and SVR test step. We construct an optimal prediction model using grid search with cross-validation in SVR training step, and then apply it to noisy images to remove noises in test step. We evaluate our SVR based method both quantitatively and qualitatively for noise removal in Korean, English and Chinese character documents, and compare it to some existing methods. Experimental results indicate that the proposed method is more effective and can get satisfactory removal results.