• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.615-621
• /
• 2020

In this paper, we propose a multi-site based earthquake event classification method using graph convolution networks. In the traditional earthquake event classification methods using deep learning, they used single-site observation to estimate seismic event class. However, to achieve robust and accurate earthquake event classification on the seismic observation network, the method using the information from the multi-site observations is needed, instead of using only single-site data. Firstly, our proposed model employs convolution neural networks to extract informative embedding features from the single-site observation. Secondly, graph convolution networks are used to integrate the features from several stations. To evaluate our model, we explore the model structure and the number of stations for ablation study. Finally, our multi-site based model outperforms up to 10 % accuracy and event recall rate compared to single-site based model.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.1_2
• /
• pp.86-94
• /
• 2004

In this paper, we show that $ G(2^m, 4), m{\geq}3$with at most m-2 faulty elements has a fault-free cycle of length 1 for every ${\leq}1{\leq}2^m-f_v$ is the number of faulty vertices. To achieve our purpose, we define a graph G to be k-fault hypohamiltonian-connected if for any set F of faulty elements, G- F has a fault-free path joining every pair of fault-free vertices whose length is shorter than a hamiltonian path by one, and then show that$ G(2^m, 4), m{\geq}3$ is m-3-fault hypohamiltonian-connected.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3211-3230
• /
• 2014

Recently, sparse coding has achieved remarkable success in image representation tasks. In practice, the performance of clustering can be significantly improved if limited label information is incorporated into sparse coding. To this end, in this paper, a novel semi-supervised algorithm, called constrained sparse concept coding (CSCC), is proposed for image representation. CSCC considers limited label information into graph embedding as additional hard constraints, and hence obtains embedding results that are consistent with label information and manifold structure information of the original data. Therefore, CSCC can provide a sparse representation which explicitly utilizes the prior knowledge of the data to improve the discriminative power in clustering. Besides, a kernelized version of our proposed CSCC, namely kernel constrained sparse concept coding (KCSCC), is developed to deal with nonlinear data, which leads to more effective clustering performance. The experimental evaluations on the MNIST, PIE and Yale image sets show the effectiveness of our proposed algorithms.

• The KIPS Transactions:PartA
• /
• v.9A no.3
• /
• pp.333-340
• /
• 2002

Embedding is a mapping an interconnection network G to another interconnection network H. If a network G can be embedded to another network H, algorithms developed on G can be simulated on H. In this paper, we first propose a method to embed between Hierarchical Cubic Network HCN(n, n) and Hierarchical Folded-hypercube Network HFN(n, n). HCN(n, n) and HFN(n, n) are graph topologies having desirable properties of hypercube while improving the network cost, defined as degree${\times}$diameter, of Hypercube. We prove that HCN(n, n) can be embedded into HFN(n, n) with dilation 3 and congestion 2, and the average dilation is less than 2. HFN(n, n) can be embedded into HCN(n, n) with dilation 0 (n), but the average dilation is less than 2. Finally, we analyze the fault tolerance of HCN(n, n) and prove that HCN(n, n) is maximally fault tolerant.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.5
• /
• pp.335-343
• /
• 2009

The crossed cube has received great attention because it has equal or superior properties compared to the hypercube that is widely known as a versatile parallel processing system. It has been known that disjoint two copies of a mesh of size $4{\times}2^m$ or disjoint four copies of a mesh of size $8{\times}2^m$ can be embedded into a crossed cube with dilation 1 and expansion 1 [Dong, Yang, Zhao, and Tang, 2008]. However, it is not known that disjoint multiple copies of a mesh with more than eight rows and columns can be embedded into a crossed cube with dilation 1 and expansion 1. In this paper, we show that disjoint $2^{n-1}$ copies of a mesh of size $2^n{\times}2^m$ can be embedded into a crossed cube with dilation 1 and expansion 1 where $n{\geq}1$ and $m{\geq}3$. Our result is optimal in terms of dilation and expansion that are important measures of graph embedding. In addition, our result is practically usable in allocating multiple jobs of mesh structure on a parallel computer of crossed cube structure.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.2
• /
• pp.125-134
• /
• 2012

In this paper, we propose a method to analyze M:N corresponding relations in semantic matching, especially focusing on feature class matching. Similarities between any class pairs are measured by spatial objects which coexist in the class pairs, and corresponding classes are obtained by clustering with these pairwise similarities. We applied a graph embedding method, which constructs a global configuration of each class in a low-dimensional Euclidean space while preserving the above pairwise similarities, so that the distances between the embedded classes are proportional to the overall degree of similarity on the edge paths in the graph. Thus, the clustering problem could be solved by employing a general clustering algorithm with the embedded coordinates. We applied the proposed method to polygon object layers in a topographic map and land parcel categories in a cadastral map of Suwon area and evaluated the results. F-measures of the detected class pairs were analyzed to validate the results. And some class pairs which would not detected by analysis on nominal class names were detected by the proposed method.

• Journal of the Korean Mathematical Society
• /
• v.53 no.4
• /
• pp.795-834
• /
• 2016

The main purpose of this paper is to propose a scheme of a proof of the nonsimpleness of the group $Homeo^{\Omega}$ ($D^2$, ${\partial}D^2$) of area preserving homeomorphisms of the 2-disc $D^2$. We first establish the existence of Alexander isotopy in the category of Hamiltonian homeomorphisms. This reduces the question of extendability of the well-known Calabi homomorphism Cal : $Diff^{\Omega}$ ($D^1$, ${\partial}D^2$)${\rightarrow}{\mathbb{R}}$ to a homomorphism ${\bar{Cal}}$ : Hameo($D^2$, ${\partial}D^2$)${\rightarrow}{\mathbb{R}}$ to that of the vanishing of the basic phase function $f_{\underline{F}}$, a Floer theoretic graph selector constructed in [9], that is associated to the graph of the topological Hamiltonian loop and its normalized Hamiltonian ${\underline{F}}$ on $S^2$ that is obtained via the natural embedding $D^2{\hookrightarrow}S^2$. Here Hameo($D^2$, ${\partial}D^2$) is the group of Hamiltonian homeomorphisms introduced by $M{\ddot{u}}ller$ and the author [18]. We then provide an evidence of this vanishing conjecture by proving the conjecture for the special class of weakly graphical topological Hamiltonian loops on $D^2$ via a study of the associated Hamiton-Jacobi equation.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.2
• /
• pp.53-60
• /
• 2020

Sentiment analysis is the automated process of understanding attitudes and opinions about a given topic from written or spoken text. One of the sentiment analysis approaches is a dictionary-based approach, in which a sentiment dictionary plays an much important role. In this paper, we propose a method to automatically generate Korean sentiment lexicon from the well-known English sentiment lexicon called VADER (Valence Aware Dictionary and sEntiment Reasoner). The proposed method consists of three steps. The first step is to build a Korean-English bilingual lexicon using a Korean-English parallel corpus. The bilingual lexicon is a set of pairs between VADER sentiment words and Korean morphemes as candidates of Korean sentiment words. The second step is to construct a bilingual words graph using the bilingual lexicon. The third step is to run the label propagation algorithm throughout the bilingual graph. Finally a new Korean sentiment lexicon is generated by repeatedly applying the propagation algorithm until the values of all vertices converge. Empirically, the dictionary-based sentiment classifier using the Korean sentiment lexicon outperforms machine learning-based approaches on the KMU sentiment corpus and the Naver sentiment corpus. In the future, we will apply the proposed approach to generate multilingual sentiment lexica.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.3
• /
• pp.417-430
• /
• 2024

As modern technology advances and the proliferation of the internet continues, cyber threats are also on the rise. To effectively counter these threats, the importance of utilizing Cyber Threat Intelligence (CTI) is becoming increasingly prominent. CTI provides information on new threats based on data from past cyber incidents, but the complexity of data and changing attack patterns present significant analytical challenges. To address these issues, this study aims to utilize graph data that can comprehensively represent multidimensional relationships. Specifically, the study constructs a heterogeneous graph based on malware data, and uses the metapath2vec node embedding technique to more effectively identify cyber attack groups. By analyzing the impact of incorporating topology information into traditional malware data, this research suggests new practical applications in the field of cyber security and contributes to overcoming the limitations of CTI analysis.