• ETRI Journal
• /
• v.44 no.5
• /
• pp.769-779
• /
• 2022

Spectral clustering has become a typical and efficient clustering method used in a variety of applications. The critical step of spectral clustering is the similarity measurement, which largely determines the performance of the spectral clustering method. In this paper, we propose a novel spectral clustering algorithm based on the local similarity measure of shared neighbors. This similarity measurement exploits the local density information between data points based on the weight of the shared neighbors in a directed k-nearest neighbor graph with only one parameter k, that is, the number of nearest neighbors. Numerical experiments on synthetic and real-world datasets demonstrate that our proposed algorithm outperforms other existing spectral clustering algorithms in terms of the clustering performance measured via the normalized mutual information, clustering accuracy, and F-measure. As an example, the proposed method can provide an improvement of 15.82% in the clustering performance for the Soybean dataset.

• Honam Mathematical Journal
• /
• v.41 no.1
• /
• pp.67-87
• /
• 2019

The main aim of this study is to characterize new classes of multicone graphs which are determined by their adjacency spectra, their Laplacian spectra, their complement with respect to signless Laplacian spectra and their complement with respect to their adjacency spectra. A multicone graph is defined to be the join of a clique and a regular graph. If n is a positive integer, a friendship graph $F_n$ consists of n edge-disjoint triangles that all of them meet in one vertex. It is proved that any connected graph cospectral to a multicone graph $F_n{\nabla}F_n=K_2{\nabla}nK_2{\nabla}nK_2$ is determined by its adjacency spectra as well as its Laplacian spectra. In addition, we show that if $n{\neq}2$, the complement of these graphs are determined by their adjacency spectra. At the end of the paper, it is proved that multicone graphs $F_n{\nabla}F_n=K_2{\nabla}nK_2{\nabla}nK_2$ are determined by their signless Laplacian spectra and also we prove that any graph cospectral to one of multicone graphs $F_n{\nabla}F_n$ is perfect.

• Bulletin of the Korean Mathematical Society
• /
• v.59 no.4
• /
• pp.1045-1067
• /
• 2022

Given a graph G, a {1, 3, …, 2n-1}-factor of G is a spanning subgraph of G, in which each degree of vertices is one of {1, 3, …, 2n-1}, where n is a positive integer. In this paper, we first establish a lower bound on the size (resp. the spectral radius) of G to guarantee that G contains a {1, 3, …, 2n-1}-factor. Then we determine an upper bound on the distance spectral radius of G to ensure that G has a {1, 3, …, 2n-1}-factor. Furthermore, we construct some extremal graphs to show all the bounds obtained in this contribution are best possible.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.613-619
• /
• 2006

This study proposed an unsupervised image classification through the dendrogram of agglomerative clustering as a higher stage of image segmentation in image processing. The proposed algorithm is a hierarchical clustering which includes searching a set of MCSNP (Mutual Closest Spectral Neighbor Pairs) based on the data structures of RAG(Regional Adjacency Graph) defined on spectral space and Min-Heap. It also employes a multi-window system in spectral space to define the spectral adjacency. RAG is updated for the change due to merging using RNV (Regional Neighbor Vector). The proposed algorithm provides a dendrogram which is a graphical representation of data. The hierarchical relationship in clustering can be easily interpreted in the dendrogram. In this study, the proposed algorithm has been extensively evaluated using simulated images and applied to very large QuickBird imagery acquired over an area of Korean Peninsula. The results have shown it potentiality for the application of remotely-sensed imagery.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.9
• /
• pp.1939-1946
• /
• 2011

Expander graphs are useful in the design and analysis of communication networks. Mukhopadhyay et. al introduced a method to generate a family of expander graphs based on nongroup two predecessor single attractor CA(Cellular Automata). In this paper we propose a method to generate a family of expander graphs based on 60/102 Null boundary CA(NBCA) which is a group CA. The spectral gap generated by our method is larger than that of Mukhopadhyay et. al [12]. As an application we give an algorithm which generate one-way functions whose security lies on the combinatorial properties of our expander graphs. the one-way function using d-regular graph generated by the 60/102 NBCA is based on the Goldreich's construction [5].

• Bulletin of the Korean Mathematical Society
• /
• v.58 no.1
• /
• pp.31-46
• /
• 2021

Let a and b be positive integers, and let V (G), ��(G), and ��2(G) be the vertex set of a graph G, the minimum degree of G, and the minimum degree sum of two non-adjacent vertices in V (G), respectively. An even [a, b]-factor of a graph G is a spanning subgraph H such that for every vertex v ∈ V (G), dH(v) is even and a ≤ dH(v) ≤ b, where dH(v) is the degree of v in H. Matsuda conjectured that if G is an n-vertex 2-edge-connected graph such that $n{\geq}2a+b+{\frac{a^2-3a}{b}}-2$, ��(G) ≥ a, and ${\sigma}_2(G){\geq}{\frac{2an}{a+b}}$, then G has an even [a, b]-factor. In this paper, we provide counterexamples, which are highly connected. Furthermore, we give sharp sufficient conditions for a graph to have an even [a, b]-factor. For even an, we conjecture a lower bound for the largest eigenvalue in an n-vertex graph to have an [a, b]-factor.

• Progress in Medical Physics
• /
• v.6 no.2
• /
• pp.103-109
• /
• 1995

Power spectral analysis of spontaneous heart rate fluctuations were assessed by use of autooic blocking agents and changes in posture. The total power spectral range of interest is divided amongst the various experiments so that each respiratory pattern contributes a spectral ratio of interval to respiration only over a group of frequencies for which the specific respiratory pattern has substantial, and roughly constant, spectral magnitudes. System hardware is consisted ECG preamplifier, respiratory fluctuation detect, interval time generator and IBC 486PC. High frequency fluctuation, at the respiratiory frequency, are decreased by standing and are mediated solely by the parasympathetic system. Power spectral analysis is a powerful nonivsve tool for quantitying autonomic nervous system activity.

• The Korean Journal of Applied Statistics
• /
• v.33 no.2
• /
• pp.115-122
• /
• 2020

K-means clustering uses a spherical or elliptical metric to group data points; however, it does not work well for non-convex data such as the concentric circles. Spectral clustering, based on graph theory, is a generalized and robust technique to deal with non-standard type of data such as non-convex data. Results obtained by spectral clustering often outperform traditional clustering such as K-means. In this paper, we review spectral clustering and show important issues in spectral clustering such as determining the number of clusters K, estimation of scale parameter in the adjacency of two points, and the dimension reduction technique in clustering high-dimensional data.

• ETRI Journal
• /
• v.35 no.2
• /
• pp.311-320
• /
• 2013

In most spectral clustering approaches, the Gaussian kernel-based similarity measure is used to construct the affinity matrix. However, such a similarity measure does not work well on a dataset with a nonlinear and elongated structure. In this paper, we present a new similarity measure to deal with the nonlinearity issue. The maximum flow between data points is computed as the new similarity, which can satisfy the requirement for similarity in the clustering method. Additionally, the new similarity carries the global and local relations between data. We apply it to spectral clustering and compare the proposed similarity measure with other state-of-the-art methods on both synthetic and real-world data. The experiment results show the superiority of the new similarity: 1) The max-flow-based similarity measure can significantly improve the performance of spectral clustering; 2) It is robust and not sensitive to the parameters.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.9
• /
• pp.853-859
• /
• 2013

The purpose of this study was to identify the correlation between electroencephalography (EEG) and strength, using grip strength. 64-channel EEG data were recorded from five healthy subjects in tasks requiring handgrip contractions of nine levels of MVC (Maximal Voluntary Contraction). We found the ERS (Event-Related Synchronization)/ERD (Event-Related Desynchronization) at the measured EEG data using STFT (Short-Time Furier Transform) and spectral power in the EEG of each frequency range displayed in the graph. In this paper, we identified that the stronger we contracted, the greater the spectral power was increased in the ${\beta}$, ${\gamma}$ wave.