• Journal of the Korean Data and Information Science Society
• /
• 제24권1호
• /
• pp.189-200
• /
• 2013

In this paper, it will be assumed that there are two distinct populations which are multivariate normal with equal covariance matrix. We also assume that the two populations are equally likely and the costs of misclassification are equal. The classification rule depends on the situation whether the training samples include missing values or not. We consider the conditional bootstrap confidence intervals for classification error rate when a block of observation is missing.

• Journal of the Korean Data and Information Science Society
• /
• 제21권3호
• /
• pp.589-595
• /
• 2010

In discriminant analysis, we consider an intraclass correlation pattern by principal component analysis. We assume that the two populations are equally likely and the costs of misclassification are equal. In this situation, we consider two procedures, i.e., the test and proportion procedures, for selecting the principal components in classifica-tion. We compare the regular classification method and the proposed two procedures. We consider two methods for estimating error rate, i.e., the leave-one-out method and the bootstrap method.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.878-885
• /
• 2022

Research in the field of computer vision based on deep learning is being actively conducted. However, deep learning-based models have vulnerabilities in adversarial attacks that increase the model's misclassification rate by applying adversarial perturbation. In particular, in the case of FGSM, it is recognized as one of the effective attack methods because it is simple, fast and has a considerable attack success rate. Meanwhile, as one of the efforts to visualize deep learning models, Grad-CAM enables visual explanation of convolutional neural networks. In this paper, I propose a method to generate adversarial examples with high attack success rate by applying Grad-CAM to FGSM. The method chooses fixels, which are closely related to labels, by using Grad-CAM and add perturbations to the fixels intensively. The proposed method has a higher success rate than the FGSM model in the same perturbation for both targeted and untargeted examples. In addition, unlike FGSM, it has the advantage that the distribution of noise is not uniform, and when the success rate is increased by repeatedly applying noise, the attack is successful with fewer iterations.

• Communications for Statistical Applications and Methods
• /
• 제16권6호
• /
• pp.1005-1012
• /
• 2009

The area under the curve(AUC) is commonly used as a measure of the receiver operating characteristic(ROC) curve which displays the performance of a set of binary classifiers for all feasible ratios of the costs associated with true positive rate(TPR) and false positive rate(FPR). In the bipartite ranking problem where one has to compare two different observations and decide which one is "better", the AUC measures the quantity that ranking score of a randomly chosen sample in one class is larger than that of a randomly chosen sample in the other class and hence, the function which maximizes an AUC of bipartite ranking problem is different to the function which maximizes (minimizes) accuracy (misclassification error rate) of binary classification problem. In this paper, we develop a way to construct the unified framework for AUC maximizer including support vector machines based on maximizing large margin and logistic regression based on estimating posterior probability. Moreover, we develop an efficient algorithm for the proposed unified framework. Numerical results show that the propose unified framework can treat various methodologies successfully.

• Communications for Statistical Applications and Methods
• /
• 제17권5호
• /
• pp.679-688
• /
• 2010

Lee (2010) developed a confidence interval for the difference of binomial proportions in two doubly sampled data subject to false-positive errors. The confidence interval seems to be adequate for a general double sampling model subject to false-positive misclassification. However, in many applications, the false-positive error rates could be the same. On this note, the construction of asymptotic confidence interval is considered when the false-positive error rates are common. The coverage behaviors of nine likelihood based confidence intervals are examined. It is shown that the confidence interval based Rao score with the expected information has good performance in terms of coverage probability and expected width.

• 전자공학회논문지B
• /
• 제31B권3호
• /
• pp.115-122
• /
• 1994

The problems in back-propagation(BP) generally are learning speed and misclassification due to lacal minimum. In this paper, to solve these problems, the classical modified methods of BP are reviewed and an extension of the BP to compensate the sigmoide-prime function around the extremity where the actual output of a unit is close to zero or one is proposed. The proposed method is not onlu faster than the conventional methods in learning speed but has an advantage of setting variables easily because it shows good classification results over the vast and uncharted space about the variations of learning rate, etc.. And it is simple for hardware implementation.

• 대한음성학회지:말소리
• /
• 제56호
• /
• pp.195-206
• /
• 2005

Discrimination between speech and music is important in many multimedia applications. In this paper, focusing on the spectral change characteristics of speech and music, we propose a new method of speech/music discrimination based on cepstral distance. Instead of using cepstral distance between the frames with fixed interval, the minimum of cepstral distances among neighbor frames is employed to increase discriminability between fast changing music and speech. And, to prevent misclassification of speech segments including short pause into music, short pause segments are excluded from computing cepstral distance. The experimental results show that proposed method yields the error rate reduction of$68\%$, in comparison with the conventional approach using cepstral distance.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.273-276
• /
• 1996

We propose a new method to extract valid lines from a visual image. Unsupervised clustering method is used to assign each line to any of the line groups according to its orientation. During the low-level image processing we use an adaptive threshold method to reduce human supervision and to automate the processing sequence. To reduce the misclassification rate and to suppress the superiors line support regions at the clustering stage, the adaptive threshold method is consistently applied. Performing principal component analysis on each line support region provides an efficient method of obtaining line equation. Finally we adopt the theory of robust statistics to guarantee the quality of each extracted line and to eliminate the lines of poor quality. We present the experimental results to verify our method. With the proposed method, one can extract the lines according to the internal orientation similarities and integrate the whole process into one adaptive procedure.

• 전자공학회논문지C
• /
• 제35C권2호
• /
• pp.48-55
• /
• 1998

Structural learning methods of MLP classifiers for a given application using genetic algorithms have been studied. In the methods, however, the search space for an optimal structure is increased exponentially for the physical application of high diemension-multi calss. In this paperwe propose a method of MLP classifiers using species genetic algorithm(SGA), a modified GA. In SGA, total search space is divided into several subspaces according to the number of hidden units. Each of the subdivided spaces is called "species". We eliminate low promising species from the evoluationary process in order to reduce the search space. experimental results show that the proposed method is more efficient than the conventional genetic algorithm methods in the aspect of the misclassification ratio, the learning rate, and the structure.structure.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.282-285
• /
• 2009

This paper proposes a flame verification algorithm using motion and spatial persistency. Most previous vision-based methods using color information and temporal variations of pixels produce frequent false alarms due to the use of many heuristic features. To solve these problems, we used a Bayesian Networks. In addition, since the shape of flame changes upwards irregularly due to the airflow caused by wind or burning material, we distinct real flame from moving objects by checking the motion orientation and temporal persistency of flame regions to remove the misclassification. As a result, the use of two verification steps and a Bayesian inference improved the detection performance and reduced the missing rate.