• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.336-338
• /
• 2012

본 연구에서는 고차 데이터 분류를 위해 순차적 베이지만 샘플링 기반의 진화연산 기법을 이용한 하이퍼네트워크 모델의 학습 알고리즘을 제시한다. 제시하는 방법에서는 모델의 조건부 확률의 사후(posterior) 분포를 최대화하도록 학습이 진행된다. 이를 위해 사전(prior) 분포를 문제와 관련된 사전지식(prior knowledge) 및 모델 복잡도(model complexity)로 정의하고, 측정된 모델의 분류성능을 우도(likelihood)로 사 용하며, 측정된 사전분포와 우도를 이용하여 모델의 적합도(fitness)를 정의한다. 이를 통해 하이퍼네트워크 모델은 고차원 데이터를 효율적으로 학습 가능할 뿐이 아니라 모델의 학습시간 및 분류성능이 개선될 수 있다. 또한 학습 시에 파라미터로 주어지던 하이퍼에지의 구성 및 모델의 크기가 학습과정 중에 적응적으로 결정될 수 있다. 제안하는 학습방법의 검증을 위해 본 논문에서는 약 25,000개의 유전자 발현정보 데이터셋에 대한 분류문제에 모델을 적용한다. 실험 결과를 통해 제시하는 방법이 기존 하이퍼네트워크 학습 방법 뿐 아니라 다른 모델들에 비해 우수한 분류 성능을 보여주는 것을 확인할 수 있다. 또한 다양한 실험을 통해 사전분포로 사용된 사전지식이 모델 학습에 끼치는 영향을 분석한다.

• The KIPS Transactions:PartA
• /
• v.17A no.1
• /
• pp.33-44
• /
• 2010

We present a pipeline monitoring system based on bio-memetic robot in this paper. A bio-memetic robot exploring pipelines measures temperature, humidity, and vibration. The principal function of pipeline monitoring robot for the exploring pipelines is to recognize the shape of pipelines. We use infrared distance sensor to recognize the shape of pipelines and potentiometer to measure the angle of motor mounting infrared distance sensor. For the shape recognition of pipelines, the number of detected pipelines is used during only one scanning of distance. Three fuzzy classifiers are used for the number of detected pipelines, and the classifying results are presented in this paper.

• Journal of Information Processing Systems
• /
• v.9 no.3
• /
• pp.395-404
• /
• 2013

In order to classify a web page as being benign or malicious, we designed 14 basic and 16 extended features. The basic features that we implemented were selected to represent the essential characteristics of a web page. The system heuristically combines two basic features into one extended feature in order to effectively distinguish benign and malicious pages. The support vector machine can be trained to successfully classify pages by using these features. Because more and more malicious web pages are appearing, and they change so rapidly, classifiers that are trained by old data may misclassify some new pages. To overcome this problem, we selected an adaptive support vector machine (aSVM) as a classifier. The aSVM can learn training data and can quickly learn additional training data based on the support vectors it obtained during its previous learning session. Experimental results verified that the aSVM can classify malicious web pages adaptively.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.26-30
• /
• 2008

Currently an automated methodology based on data mining techniques is presented for the prediction of customer load patterns in long duration load profiles. The proposed our approach consists of three stages: (i) data pre-processing: noise or outlier is removed and the continuous attribute-valued features are transformed to discrete values, (ii) cluster analysis: k-means clustering is used to create load pattern classes and the representative load profiles for each class and (iii) classification: we evaluated several supervised learning methods in order to select a suitable prediction method. According to the proposed methodology, power load measured from AMR (automatic meter reading) system, as well as customer indexes, were used as inputs for clustering. The output of clustering was the classification of representative load profiles (or classes). In order to evaluate the result of forecasting load patterns, the several classification methods were applied on a set of high voltage customers of the Korea power system and derived class labels from clustering and other features are used as input to produce classifiers. Lastly, the result of our experiments was presented.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.343-359
• /
• 2020

In this paper, a new algorithm is proposed for three-dimensional (3D) shape recognition using local features of model views and its sparse representation. The algorithm starts with the normalization of 3D models and the extraction of 2D views from uniformly distributed viewpoints. Consequently, the 2D views are stacked over each other to from view cubes. The algorithm employs the descriptors of 3D local features in the view cubes after applying Gabor filters in various directions as the initial features for 3D shape recognition. In the training stage, we store some 3D local features to build the prototype dictionary of local features. To extract an intermediate feature vector, we measure the similarity between the local descriptors of a shape model and the local features of the prototype dictionary. We represent the intermediate feature vectors of 3D models in the sparse domain to obtain the final descriptors of the models. Finally, support vector machine classifiers are used to recognize the 3D models. Experimental results using the Princeton Shape Benchmark database showed the average recognition rate of 89.7% using 20 views. We compared the proposed approach with state-of-the-art approaches and the results showed the effectiveness of the proposed algorithm.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.80-89
• /
• 2020

Out - of - distribution (OOD) samples are frequently encountered when deploying a classification model in plenty of real-world machine learning-based applications. Those samples are normally sampling far away from the training distribution, but many classifiers still assign them high reliability to belong to one of the training categories. In this study, we address the problem of removing OOD examples by estimating marginal density estimation using variational autoencoder (VAE). We also investigate other proper methods, such as temperature scaling, Gaussian discrimination analysis, and label smoothing. We use Chonnam National University (CNU) weeds dataset as the in - distribution dataset and CIFAR-10, CalTeach as the OOD datasets. Quantitative results show that the proposed framework can reject the OOD test samples with a suitable threshold.

• The Korean Journal of Applied Statistics
• /
• v.16 no.2
• /
• pp.261-271
• /
• 2003

Support Vector Machines (SVMs) provide a powerful performance of the learning system. Generally, SVMs tend to make overfitting. For the purpose of overcoming this difficulty, the definition of soft margin has been introduced. In this case, it causes another difficulty to decide the weight for slack variables reflecting soft margin classifiers. Especially, the error of soft margin algorithm can be bounded by a target margin and some norms of the slack vector. In this paper, we formulate a new soft margin algorithm considering the bound of corruption by noise in data directly. Additionally, through a numerical example, we compare the proposed method with a conventional soft margin algorithm.

• Communications for Statistical Applications and Methods
• /
• v.16 no.6
• /
• 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.

• Korean Journal of Geomatics
• /
• v.5 no.1
• /
• pp.27-34
• /
• 2005

Unsupervised classification is an important area of research in image processing because supervised classification has the disadvantages such as long task-training time and high cost and low objectivity in training information. This paper focuses on unsupervised classification, which can extract ground object information with the minimum 'Spectral Angle Distance' operation on be behalf of 'Spectral Euclidian Distance' in the clustering process. Unlike previous studies, our algorithm uses the unit vector, not the spectral distance, to compute the cluster mean, and the Single-Pass algorithm automatically determines the seed points. Atmospheric correction for more accurate results was adapted on the Hyperion data and the results were analyzed. We applied the algorithm to the Hyperion and ETM+ data and compared the results with K-Means and the former USAM algorithm. From the result, USAM classified the water and dark forest area well and gave more accurate results than K-Means, so we believe that the 'Spectral Angle' can be one of the most accurate classifiers of not only multispectral images but hyperspectral images. And also the unit vector can be an efficient technique for characterizing the Remote Sensing data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6009-6027
• /
• 2019

Support vector machine (SVM) classifiers have been widely used for object detection. These methods usually locate the object by finding the region with maximal score in an image. With bag-of-features representation, the SVM score of an image region can be written as the sum of its inside feature-weights. As a result, the searching process can be executed efficiently by using strategies such as branch-and-bound. However, the feature-weight derived by optimizing region classification cannot really reveal the category knowledge of a feature-point, which could cause bad localization. In this paper, we represent a region in an image by a collection of local feature-points and determine the object by the region with the maximum posterior probability of belonging to the object class. Based on the Bayes' theorem and Naive-Bayes assumptions, the posterior probability is reformulated as the sum of feature-scores. The feature-score is manifested in the form of the logarithm of a probability ratio. Instead of estimating the numerator and denominator probabilities separately, we readily employ the density ratio estimation techniques directly, and overcome the above limitation. Experiments on a car dataset and PASCAL VOC 2007 dataset validated the effectiveness of our method compared to the baselines. In addition, the performance can be further improved by taking advantage of the recently developed deep convolutional neural network features.