• Communications for Statistical Applications and Methods
• /
• v.30 no.3
• /
• pp.245-258
• /
• 2023

This study proposes a modification to the objective function of the support vector machine for the linearly non-separable case of a binary classifier y_i ∈ {-1, 1}. The modification takes into account the position of each data item x_i from its corresponding class centroid. The resulting optimization function involves the centroid mean vector, and the spread of data besides the support vectors, which should be minimized by the choice of hyper-plane β. Theoretical assumptions have been tested to derive an optimal separable hyperplane that yields the minimal misclassification rate. The proposed method has been evaluated using simulation studies and real-life COVID-19 patient outcome hospitalization data. Results show that the proposed method performs better than the classical linear SVM classifier as the sample size increases and is preferred in the presence of correlations among predictors as well as among extreme values.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.382-385
• /
• 2007

본 논문은 "X라는 인물은 누구인가?"와 같은 질의어가 주어질 때, X라는 인물에 대한 나이, 직업, 학력 또는 특정 사건에서 X라는 인물의 역할에 대한 정보를 기술하는 문장을 인식하고 추출함으로써 해당 인물에 대한 신문 기사 내용을 요약하는 방법을 제시한다. 질의어 용어에 대해 가능한 많은 관련 문장을 추출하기 위하여 중심 벡터에 기반한 통계적 방법을 적용하였으며, 정확도와 재현율 성능을 개선하기 위해 위키피디어 같은 외부 지식을 사용한 중심 단어의 개선된 가중치 측도를 적용하였다. 실험 대상인 전자신문 말뭉치 상에서 출현 빈도수가 큰 20 인의 IT 인물에 대해 제안한 방법이 개선된 성능을 보임을 알 수 있었다.

• Journal of Broadcast Engineering
• /
• v.7 no.2
• /
• pp.126-135
• /
• 2002

An image contains various features such as color, shape, texture and location information. When only one of those features is used to retrieve an image, it is difficult to acquire satisfactory retrieval efficiency. Especially, in the database with huge capacity, such phenomenon happens frequently. Therefore, by using moi·e features, efficiency of the contents-based image retrieval (CBIR) system can be improved. This paper proposes a technique to consider location information about specific color as well as color information in image using centroid situation vector. Centroid situation vectors are calculated for specific color of the query image. Then, location similarity is determined through comparing distances between extracted centroid situation vectors of query image and target image in the database. Simulation results show that the proposed method is robust in zoom-in or zoom-out processed images and improves discrimination ability in fliped or rotated images. In addition, the suggested method reduced computational complexity by overlapping information extraction, and that improved the retrieval speed using an efficient index file.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.6
• /
• pp.813-818
• /
• 2007

This paper is concerned with the problem of recognizing definition sentences. Given a definition question like "Who is the person X?", we are to retrieve the definition sentences which capture descriptive information correspond variously to a person's age, occupation, of some role a person played in an event from the collection of news articles. In order to retrieve as many relevant sentences for the definition question as possible, we adopt a centroid based statistical approach which has been applied in summarization of multiple documents. To improve the precision and recall performance, the weight measure of centroid words is supplemented by using external knowledge resource such as Wikipedia and redundant candidate sentences are removed from candidate definitions. We see some improvements obtained by our approach over the baseline for 20 IT persons who have high document frequency.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.199-209
• /
• 2022

Typical anomaly detection algorithms are trained by using prior data. Thus the batch learning based algorithms cause inevitable performance degradation when characteristics of newly incoming normal data change over time. We propose an online anomaly detection algorithm which can consider the gradual characteristic changes of incoming normal data. The proposed algorithm based on one-class classification model includes both offline and online learning procedures. In offline learning procedure, the algorithm learns the prior data to be close to centroid of the latent space and then updates the centroid of the latent space incrementally by new incoming data. In the online learning, the algorithm continues learning by using the updated centroid. Through experiments using public underwater acoustic data, the proposed online anomaly detection algorithm takes only approximately 2 % additional learning time for the incremental centroid update and learning. Nevertheless, the proposed algorithm shows 19.10 % improvement in Area Under the receiver operating characteristic Curve (AUC) performance compared to the offline learning model when new incoming normal data comes.

• Fisheries and Aquatic Sciences
• /
• v.4 no.1
• /
• pp.1-9
• /
• 2001

This paper describes a procedure extracting feature vector of a target cell more precisely in the case of identifying specified cell. The classification of object type is based on feature vector such as area, complexity, centroid, rotation angle, effective diameter, perimeter, width and height of the object So, the feature vector plays very important role in classifying objects. Because the feature vectors is affected by noises and holes, it is necessary to remove noises contaminated in original image to get feature vector extraction exactly. In this paper, we propose the following method to do to get feature vector extraction exactly. First, by Otsu's optimal threshold selection method and morphological filters such as cleaning, filling and opening filters, we separate objects from background an get rid of isolated particles. After the labeling step by 4-adjacent neighborhood, the labeled image is filtered by the area filter. From this area-filtered image, feature vector such as area, complexity, centroid, rotation angle, effective diameter, the perimeter based on chain code and the width and height based on rotation matrix are extracted. To prove the effectiveness, the proposed method is applied for yeast Zygosaccharomyces rouxn. It is also shown that the experimental results from the proposed method is more efficient in measuring feature vectors than from only Otsu's optimal threshold detection method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.3
• /
• pp.1650-1669
• /
• 2017

In this study, each pixel in an ear is used as a centroid to generate a cake. Subsequently the major axis length of this cake is computed and obtained. This obtained major axis length serves as a feature to recognize an ear. Later, the ear hole is used as a centroid and a 16-circle template is generated to extract the major axis lengths of the ear. The 16-circle template extracted signals are used to recognize an ear. In the next step, a ring-to-line mapping technique is used to map these major axis lengths to several straight-line signals. Next, the complex plane vector computing technique is used to determine the similarity of these major axis lengths, whereby a solution to the image-rotating problem is achieved. The aforementioned extracted signals are also compared to the ones that are extracted from its neighboring pixels, whereby solving the image-shifting problem. The algorithm developed in this study can precisely identify an ear image by solving the image rotation and image shifting problems.

• Journal of IKEEE
• /
• v.17 no.3
• /
• pp.254-259
• /
• 2013

The choice of labeled data in semi-supervised learning algorithm can result in effects on the performance of the resultant classifier. In order to select labeled data required for the training of a semi-supervised learning algorithm, VCNN(Vector Centroid Neural Network) is proposed in this paper. The proposed selection method of label data is evaluated on UCI dataset and caltech dataset. Experiments and results show that the proposed selection method outperforms conventional methods in terms of classification accuracy and minimum error rate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.10B
• /
• pp.1946-1952
• /
• 1999

A new image compression method to preserve edge characteristics in reconstructed images using an unsupervised learning neural is proposed in this paper. By the unsupervised competitive learning which generalizes previously proposed Centroid Neural Network(CNN) algorithm with the geometric characteristics of edge area and statistical characteristics of image data, more codevectors are allocated in the edge areas to provide the more accurate edges in reconstructed image. Experimental results show that the proposed method gives improved edge in reconstructed images when compared with SOM, Modified SOM and M/R-CNN.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.9C
• /
• pp.861-866
• /
• 2007

A clustering algorithm for Gaussian Probability Distribution Function (GPDF) data called Centroid Neural Network with a Bhattacharyya Kernel (BK-CNN) is proposed in this paper. The proposed BK-CNN is based on the unsupervised competitive Centroid Neural Network (CNN) and employs a kernel method for data projection. The kernel method adopted in the proposed BK-CNN is used to project data from the low dimensional input feature space into higher dimensional feature space so as the nonlinear problems associated with input space can be solved linearly in the feature space. In order to cluster the GPDF data, the Bhattacharyya kernel is used to measure the distance between two probability distributions for data projection. With the incorporation of the kernel method, the proposed BK-CNN is capable of dealing with nonlinear separation boundaries and can successfully allocate more code vector in the region that GPDF data are densely distributed. When applied to GPDF data in an image classification probleml, the experiment results show that the proposed BK-CNN algorithm gives 1.7%-4.3% improvements in average classification accuracy over other conventional algorithm such as k-means, Self-Organizing Map (SOM) and CNN algorithms with a Bhattacharyya distance, classed as Bk-Means, B-SOM, B-CNN algorithms.