• Journal of IKEEE
• /
• v.22 no.2
• /
• pp.491-494
• /
• 2018

This paper presents a similarity search method based on mixed norm for enhancing self-example-based single image super-resolution. In order to incorporate the local statistical characteristics of the patches into the super-resolution image reconstruction, we propose a method to determine the order of the norm according to the patch inclination and use it as a similarity search between patches. Experimental results demonstrate that the proposed similarity search method has the capability to improve the performance of existing search method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2101-2123
• /
• 2023

Recent studies have shown that the neural network-based binary code similarity detection technology performs well in vulnerability mining, plagiarism detection, and malicious code analysis. However, existing cross-architecture methods still suffer from insufficient feature characterization and low discrimination accuracy. To address these issues, this paper proposes a cross-architecture binary function similarity detection method based on composite feature model (SDCFM). Firstly, the binary function is converted into vector representation according to the proposed composite feature model, which is composed of instruction statistical features, control flow graph structural features, and application program interface calling behavioral features. Then, the composite features are embedded by the proposed hierarchical embedding network based on a graph neural network. In which, the block-level features and the function-level features are processed separately and finally fused into the embedding. In addition, to make the trained model more accurate and stable, our method utilizes the embeddings of predecessor nodes to modify the node embedding in the iterative updating process of the graph neural network. To assess the effectiveness of composite feature model, we contrast SDCFM with the state of art method on benchmark datasets. The experimental results show that SDCFM has good performance both on the area under the curve in the binary function similarity detection task and the vulnerable candidate function ranking in vulnerability search task.

• Journal of Fashion Business
• /
• v.6 no.4
• /
• pp.17-31
• /
• 2002

This study is, to the special company with corporate brand, to investigate the effect of its reputation, credibility and the similarity of business area on consumer's attitude toward its clothing products. It is another topic of the study to reveal statistical significance in comsumer's attitude when naming new product with two different brand strategy. The major findings of this study can be summarized as follows. First, there was positive relationship between corporate reputation and consumer's attitude toward new brand and also between corporate credibility and consumer's that. Second, corporate credibility is proven to be grown in proportion to company's reputation. In other words, a corporate credibility is grown with a corporate reputation. Third, the influence of similarity or fitness of business area has a positive effect on a attitude toward new brand. The case of use the new brand name, the variable had low effect on attitude toward new brand, comparing to the case of use the existing brand name but seems to be statistically significant. Fourth, comparing to the inclination toward company's product based on brand name, strategy of supporting brand extension is more effective than that of new brand name on evaluating company's reputation, credibility and the similarity of business area. Fifth, the similarity of business area and the interaction of brand name on the basis of the strategy of use the existing brand name(;brand extension strategy) and new one have significant effect on the inclination to a brand. When participating a new business, it is more effective that a company is extending its business where the similarity of business area is growing. For the case of low similarity, the brand-new strategy is proven to be effective.

• Journal of information and communication convergence engineering
• /
• v.10 no.1
• /
• pp.27-32
• /
• 2012

Twitter can spread and share all kinds of information such as facts, opinions, and ideas in real time. In this paper, we empirically compare and analyze the topic categories in Twitter with all top 100 users in each of geographic region. We mainly consider the relationships among regions and selected four regions: Global, Seoul, Tokyo, and Beijing. Each of the top 100 users in Twitter is classified into a specific category and then statistical analysis is conducted. Among eight topic categories, the "Arts" category is the largest and the second is "Life". The correlation between global and Seoul groups has the lowest value among the six pairs of relationships between regional groups, and this difference is statistically significant. We find that the Seoul, Tokyo, and Beijing regional Twitter groups, all in East Asia, have high topical similarity. Based on the correlation analysis, Seoul and Tokyo saliently show a sticky trend. The correlation coefficient presents very a strong positive correlation between Seoul and Tokyo. The correlation between the global group and the East Asian groups is relatively lower than that among the East Asian groups.

• Communications for Statistical Applications and Methods
• /
• v.19 no.4
• /
• pp.547-558
• /
• 2012

Social network analysis is a graphical technique to search the relationships and characteristics of nodes (people, companies, and organizations) and an important node for positioning a visualized social network figure; however, it is difficult to characterize nodes in a social network figure. Therefore, their relationships and characteristics could be presented through an application of correspondence analysis to an affiliation matrix that is a type of similarity matrix between nodes. In this study, we provide the relationships and characteristics around authors and keywords in the JKSS(Journal of the Korean Statistical Society) of the Korean Statistical Society through the use of social network analysis and correspondence analysis.

• Communications for Statistical Applications and Methods
• /
• v.9 no.3
• /
• pp.649-663
• /
• 2002

We consider an unlimited fluid queueing model which has Fractional Brownian motion(FBM) as an input and a single server of constant service rate. By using the result of Duffield and O'Connell(6), we investigate the asymptotic tail-distribution of the stationary work-load. When there are multiple homogeneous FBM inputs, the workload distribution is similar to that of the queue with one FBM input; whereas for the heterogeneous sources the asymptotic work-load distributions is dominated by the source with the largest Hurst parameter.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.1-8
• /
• 2003

The traffic patterns of today's IP networks exhibit two important properties: self-similarity and long-range dependence. The fractional Brownian motion is widely used for representing the traffic model with the properties. We consider a single server fluid queueing system with input process of a fractional Brownian motion type. Formulas for effective bandwidth are derived in a single source and multiple source cases.

• Journal of Families and Better Life
• /
• v.18 no.3 s.47
• /
• pp.129-146
• /
• 2000

The purpose of this study was to investigation the variables that affected the generational transmission of household work form mothers to their married daughter. The subjects were 415 married daughters and their mothers living in Seoul and metropolitan areas. Statistical techniques used for this study included descriptive statistics and multiple regression analysis. The results of this study were as follows : First, married daughters; value of household work was significantly affected by total periods of marriage of daughters, daughter's perceived similarity to their mothers' household work. Second, married daughters' preference for household work was significantly affected by mother's occupation (managerialㆍprofessional), mother's perceived similarity, daughter's experience of living with mother-in-law, daughter's sex-role attitude, and daughter's perceived similarity. Third, married daughters' ability to do household work was significantly affected by total periods of marriage for mothers, mother's perceived similarity, and daughter's perceived similarity. Fourth, married daughters' standard of household work was significantly affected by mother's perceived similarity, daughter's occupation (techniciansㆍclerk), daughter's monthly income, and daughter's perceived similarity. Fifth, married daughters' usage level of home equipments was significantly affected by mother's birth order, mother's education, mother's occupation (managerialㆍprofessional), daughter's birth order, daughter's education, and daughter's monthly income. Sixth, Mother related variables had greater power than daughter related ones in explaining daughters' values and preference for household work value and preferences and usage of home equipments. In conclusion, married daughter's consciousness and performance of household work were significantly influenced by their mothers. It was especially so in daughter's usage level of hoe equipments. Accordingly, the results of this study support the existence of generational transmission of household work from mothers to their married daughters with regard to its consciousness and performance. Findings of this study have implications for counsellors, practitioners and educators.

• Journal of Korea Multimedia Society
• /
• v.14 no.10
• /
• pp.1252-1261
• /
• 2011

In this paper, we propose the comparison method of pattern similarity for video segmentation algorithm. The shot boundary type is categorized as 2 types, abrupt change and gradual change. The representative examples of gradual change are dissolve, fade-in, fade-out or wipe transition. The proposed method consider the problem to detect shot boundary as 2-class problem. We concentrated if the shot boundary event happens or not. It is essential to define similarity between frames for shot boundary detection. We proposed 2 similarity measures, within similarity and between similarity. The within similarity is defined by feature comparison between frames belong to same shot. The between similarity is defined by feature comparison between frames belong to different scene. Finally we calculated the statistical patterns comparison between the within similarity and between similarity. Because this measure is robust to flash light or object movement, our proposed algorithm make contribution towards reducing false positive rate. We employed color histogram and mean of sub-block on frame image as frame feature. We performed the experimental evaluation with video dataset including set of TREC-2001 and TREC-2002. The proposed algorithm shows the performance, 91.84% recall and 86.43% precision in experimental circumstance.

• Journal of Environmental Impact Assessment
• /
• v.18 no.6
• /
• pp.401-409
• /
• 2009

Multivariate statistical approaches to classify sampling sites with measuring their similarity by water quality data and understand the characteristics of classified clusters have been discussed for the optimal water quality monitering network. For empirical study, data of two years (2005, 2006) at the 9 sampling sites with the combination of 2 depth levels and 7 important variables related to water quality is collected in Yongdam reservoir. The similarity among sampling sites is measured with Euclidean distances of water quality related variables and they are classified by hierarchical clustering method. The clustered sites are discussed with principal component variables in the view of the geographical characteristics of them and reducing the number of measuring sites. Nine sampling sites are clustered as follows; One cluster of 5, 6, and 7 sampling sites shows the characteristic of low water depth and main stream of water. The sites of 2 and 4 are clustered into the same group by characteristics of hydraulics which come from that of main stream. But their changing pattern of water quality looks like different since the site of 2 is near to dam. The sampling sites of 3, 8, and 9 are individually positioned due to the different tributary.