• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.387-399
• /
• 2009

Mobile wireless networks continue to be plagued by theft of identify and intrusion. Both problems can be addressed in two different ways, either by misuse detection or anomaly-based detection. In this paper, we propose a dissimilarity-based anomaly detection method which can effectively identify abnormal behavior such as mobility patterns of mobile wireless networks. In the proposed algorithm, a normal profile is constructed from normal mobility patterns of mobile nodes in mobile wireless networks. From the constructed normal profile, a dissimilarity is computed by a weighted dissimilarity measure. If the value of the weighted dissimilarity measure is greater than the dissimilarity threshold that is a system parameter, an alert message is occurred. The performance of the proposed method is evaluated through a simulation. From the result of the simulation, we know that the proposed method is superior to the performance of other anomaly detection methods using dissimilarity measures.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.2
• /
• pp.21-28
• /
• 2010

This paper reports an experimental result on optimizing dissimilarity-based classification(DBC) by simultaneously using a dynamic time warping(DTW) and a multiple fusion strategy(MFS). DBC is a way of defining classifiers among classes; they are not based on the feature measurements of individual samples, but rather on a suitable dissimilarity measure among the samples. In DTW, the dissimilarity is measured in two steps: first, we adjust the object samples by finding the best warping path with a correlation coefficient-based DTW technique. We then compute the dissimilarity distance between the adjusted objects with conventional measures. In MFS, fusion strategies are repeatedly used in generating dissimilarity matrices as well as in designing classifiers: we first combine the dissimilarity matrices obtained with the DTW technique to a new matrix. After training some base classifiers in the new matrix, we again combine the results of the base classifiers. Our experimental results for well-known benchmark databases demonstrate that the proposed mechanism achieves further improved results in terms of classification accuracy compared with the previous approaches. From this consideration, the method could also be applied to other high-dimensional tasks, such as multimedia information retrieval.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1964-1967
• /
• 2003

워터쉐드 알고리즘에 의해 과분할 된 영상은 이후 영상의 이해 및 분석 작업의 편의성을 위하여 영역 병합 작업이 필요하다. 본 논문에서는 유사한 색상을 갖는 영역의 경계선을 보다 잘 유지할 수 있도록 통합 비유사도를 정의하고, 이를 이용한 영역 병합 방법을 제안한다. 통합 비유사도는 영역의 색상 정보, 인접한 두 영역 사이의 평균 그래디언트 값 정보, 두 영역 사이의 인접한 픽셀 수 정보를 이용하여 정의된다. 영역 병합과정에서는 영역 면적의 크기와 영역간 통합 비유사도를 고려한 3 단계 영역 병합 방법을 수행한다. 자연 영상에 대한 실험 결과 제안한 방법이 기존의 방법보다 경계선 정보를 보다 잘 유지하고 사람이 느끼기에 보다 정확한 영역 병합 결과를 나타냄을 확인하였다.

• The Korean Journal of Applied Statistics
• /
• v.5 no.2
• /
• pp.211-227
• /
• 1992

In this paper we consider the definition and mathematical properties of similarity or dissimilarity which have often used in clust analysis, and we apply a hierarchical agglomerative cluster algorithm to a dissimilarity metrx generated by these distance. Here we investigate the effect of relation between distance function and cluster algorithm on the retrieval ability of natural clusters. We present an empirical results for qualitative data as well as quantitative data.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.59-66
• /
• 2016

This paper presents an empirical evaluation on dimensionality reduction strategies by which dissimilarity-based classifications (DBC) can be implemented efficiently. In DBC, classification is not based on feature measurements of individual objects (a set of attributes), but rather on a suitable dissimilarity measure among the individual objects (pair-wise object comparisons). One problem of DBC is the high dimensionality of the dissimilarity space when a lots of objects are treated. To address this issue, two kinds of solutions have been proposed in the literature: prototype selection (PS)-based methods and dimension reduction (DR)-based methods. In this paper, instead of utilizing the PS-based or DR-based methods, a way of performing DBC in Eigen spaces (ES) is considered and empirically compared. In ES-based DBC, classifications are performed as follows: first, a set of principal eigenvectors is extracted from the training data set using a principal component analysis; second, an Eigen space is expanded using a subset of the extracted and selected Eigen vectors; third, after measuring distances among the projected objects in the Eigen space using $l_p$-norms as the dissimilarity, classification is performed. The experimental results, which are obtained using the nearest neighbor rule with artificial and real-life benchmark data sets, demonstrate that when the dimensionality of the Eigen spaces has been selected appropriately, compared to the PS-based and DR-based methods, the performance of the ES-based DBC can be improved in terms of the classification accuracy.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.877-879
• /
• 2005

장면전환의 검출은 비디오 브라우징, 검색, 요약 등에 관한 많은 응용에 유용하다. 본 논문에서는 점진적 장면전환 검출을 위해 정의된 N-길이 로컬 윈도우 내에서 비유사도 분포가 갖는 최소값만큼 상승하여 형성되는 분포를 구하고, 분포의 상단이 이루는 비유사도 값을 누적하여 설정된 임계값보다 클 경우 점진적 장면전환으로 판단하는 방법을 제안한다. 장면전환 구간에서 이루는 영역의 누적값은 최소-최대 분포를 이용하여 구할 수 있다. 실험에서 기존의 제안된 방법과 비교를 하였고 그 결과 제안된 방법에서 올바른 장면전환 검출 성능은 낮았으나 잘못 검출되는 장면전환 수는 적은 결과를 보였다. 제안된 방법은 점진적 장면전환 검출을 위한 임계값의 선택이 쉬우며, 장면전환 길이에 크게 의존하지 않는 장점이 있고 수행속도가 높아 실시간으로 처리하는데 적합하다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.15-24
• /
• 2008

For high-dimensional classification tasks, such as face recognition, the number of samples is smaller than the dimensionality of the samples. In such cases, a problem encountered in linear discriminant analysis-based methods for dimension reduction is what is known as the small sample size (SSS) problem. Recently, to solve the SSS problem, a way of employing a dissimilarity-based classification(DBC) has been investigated. In DBC, an object is represented based on the dissimilarity measures among representatives extracted from training samples instead of the feature vector itself. In this paper, we propose a new method of optimizing DBCs using multi-level fusion strategies(MFS), in which fusion strategies are employed to represent features as well as to design classifiers. Our experimental results for benchmark face databases demonstrate that the proposed scheme achieves further improved classification accuracies.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.1 s.307
• /
• pp.9-16
• /
• 2006

RDA(Relational Discriminant Analysis) is a way of finding classifiers based on the dissimilarity measures among the prototypes extracted from feature vectors instead of the feature vectors themselves. Therefore, the accuracy of the RDA classifier is dependent on the methods of selecting prototypes and measuring proximities. In this paper we propose to utilize PRS(Prototype Reduction Schemes) and Mahalanobis distances to devise a method of increasing classification accuracies. Our experimental results demonstrate that the proposed mechanism increases the classification accuracy compared with the conventional approaches for samples involving real-life data sets as well as artificial data sets.

• Journal of KIISE:Software and Applications
• /
• v.26 no.9
• /
• pp.1114-1124
• /
• 1999

클러스터링은 동일한 클러스터에 속하는 데이타들 간에는 유사도가 크도록 하고 다른 클러스터에 속하는 데이타들 간에는 유사도가 작도록 주어진 데이타를 몇 개의 클러스터로 묶는 것이다. 어떤 대상을 기술하는 데이타는 수치 속성뿐만 아니라 정성적인 비수치 속성을 갖게 되고, 이들 속성값은 관측 오류, 불확실성, 주관적인 판정 등으로 인해서 정확한 값으로 주어지지 않고 애매한 값으로 주어지는 경우가 많다. 본 논문에서는 애매한 값을 퍼지값으로 표현하는 수치 속성과 비수치 속성을 포함한 데이타에 대한 비유사도 척도를 제안하고, 이 척도를 이용하여 퍼지값을 포함한 데이타에 대하여 퍼지 클러스터링하는 방법을 소개한 다음, 이를 이용한 실험 결과를 보인다. Abstract The objective of clustering is to group a set of data into some number of clusters in a way to minimize the similarity between data belonging to different clusters and to maximize the similarity between data belonging to the same cluster. Many data for real world objects consist of numeric attributes and non-numeric attributes whose values are fuzzily described due to observation error, uncertainty, subjective judgement, and so on. This paper proposes a dissimilarity measure applicable to such data and then introduces a fuzzy clustering method for such data using the proposed dissimilarity measure. It also presents some experiment results to show the applicability of the proposed clustering method and dissimilarity measure.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.6
• /
• pp.1125-1136
• /
• 2010

Lately there exist increasing demands for online abnormality monitoring over trajectory stream, which are obtained from moving object tracking devices. This problem is challenging due to the requirement of high speed data processing within limited space cost. In this paper, we present a FADA (Fuzzy Anomaly Detection Algorithm) which constructs normal profile by computing mobility feature information from the GPS (Global Positioning System) logs of mobile devices in MANETs (Mobile Ad-hoc Networks), computes a fuzzy dissimilarity between the current mobility feature information of the mobile device and the mobility feature information in the normal profile, and detects effectively the anomaly behaviors of mobile devices on the basis of the computed fuzzy dissimilarity. The performance of proposed FADA is evaluated through simulation.