• Journal of Korean Library and Information Science Society
• /
• v.50 no.4
• /
• pp.77-100
• /
• 2019

This study aims to analyze and compare centrality and brokerage measures of journal citation network focusing on textmining research. The analytic sample was 193 academic articles collected from 136 KCI journals published in 2018. The journal citation network was constructed based on citation relations. The characteristics, centralities, and brokerages of network was analyzed. The journal citation network consisted 136 nodes and 413 links with directed and weight. According to the five types of centrality(out-degree, in-degree, out-closeness, in-closeness, betweenness), journals of social sciences, engineering, and interdisciplinary research showed higher centrality. Social sciences, engineering and interdisciplinary research journals also showed higher brokerages as a result of brokerage analysis which identify five types of brokerage roles(coordinator, gatekeeper, representative, consultant, liaison). The centralities and brokerages of journals are positively correlated. This study suggested how to construct journal citation network from the articles focusing on certain topics. This was meaningful study in terms of conducting brokerage analysis and comparing it with centrality in the journal citation network.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.12
• /
• pp.511-522
• /
• 2014

During the development of the software, a variety of bugs are reported. Several bug tracking systems, such as, Bugzilla, MantisBT, Trac, JIRA, are used to deal with reported bug information in many open source development projects. Bug reports in bug tracking system would be triaged to manage bugs and determine developer who is responsible for resolving the bug report. As the size of the software is increasingly growing and bug reports tend to be duplicated, bug triage becomes more and more complex and difficult. In this paper, we present an approach to assign bug reports to appropriate developers, which is a main part of bug triage task. At first, words which have been included the resolved bug reports are classified according to each developer. Second, words in newly bug reports are selected. After first and second steps, vectors whose items are the selected words are generated. At the third step, TF-IDF(Term frequency - Inverse document frequency) of the each selected words are computed, which is the weight value of each vector item. Finally, the developers are recommended based on the similarity between the developer's word vector and the vector of new bug report. We conducted an experiment on Eclipse JDT and CDT project to show the applicability of the proposed approach. We also compared the proposed approach with an existing study which is based on machine learning. The experimental results show that the proposed approach is superior to existing method.

• Journal of Korea Technology Innovation Society
• /
• v.18 no.3
• /
• pp.387-415
• /
• 2015

In this study, we have proposed an estimation model of domestic market size using the linking between standard statistical classification systems, and reviewed the practical applicability of the model. The results of the mining and manufacturing survey of Statistics Korea conducted on the basis of KSIC (Korea Standard Industrial Classification) and Korea trade statistics based on HS (The Harmonized Commodity Description and Coding System; Harmonized System) classification were linked for the model by using the correspondence tables provided by Statistics Korea and United Nations Statistics Division. The most serious problem to adopt the integrated KSIC-ISIC-HS correspondence table for the estimation of domestic market size is the complex multiple linkages among KSIC and HS codes. In this study, we have suggested the method to divide the amount of trade corresponding to the HS codes linked to more than two ISIC codes based on the ratio of shipments corresponding to the ISIC codes as the weight. Then, it is possible to analyze the domestic market size of 125 ISIC codes in the manufacturing industry and to forecast the market size in the near future by using the model. Although the model has some limitations such as the difficulty in analysis on more subdivided items than ISIC items, the impossibility of the analysis on items in industries except for manufacturing, errors in the shipment due to some missing data, this study has significance in the sense that it provided the analysis method of domestic market size by using the most objective, reliable and sustainably useful data.

• The Journal of Society for e-Business Studies
• /
• v.22 no.1
• /
• pp.65-87
• /
• 2017

We propose a method to analyze the user reviews and ratings of the products in the online shopping mall and automatically extracts the features of the products to determine the characteristics of a product. By judging whether a rating is given by a specific feature of a product, our method distributes the score to each feature. Conventional methods force users to wastes time reading overflowing number of reviews and ratings to decide whether to buy the product or not. Moreover, it is difficult to grasp the merits and demerits of the product, because of the way reviews and ratings are provided. It is structured in a way that it is impossible to decide which rating is given to the which characteristics of the product. Therefore, in this paper, to resolve this problem, we propose a method to automatically extract the feature of the product from the user review and distribute the score to appropriate characteristics of the product by calculating the rating of each feature from the overall rating. proposed method collects product reviews and ratings, conducts morphological analysis, and extracts features and emotional words of the products. In addition, a method for determining the polarity of a sentence in which the feature appears is given a weight value for each feature. results of the experiment and the questionnaires comparing the existing methods show the usefulness of the proposed method. We also validates the results by comparing the analysis conducted by the product review experts.

• Journal of the Korea Convergence Society
• /
• v.11 no.11
• /
• pp.9-17
• /
• 2020

In this paper, we proposed an SNS review analysis method based on deep learning for user tendency. The existing SNS review analysis method has a problem that does not reflect a variety of opinions on various interests because most are processed based on the highest weight. To solve this problem, the proposed method is to extract the user's personal tendency from the SNS review for food. It performs classification using the YOLOv3 model, and after performing a sentiment analysis through the BiLSTM model, it extracts various personal tendencies through a set algorithm. Experiments showed that the performance of Top-1 accuracy 88.61% and Top-5 90.13% for the YOLOv3 model, and 90.99% accuracy for the BiLSTM model. Also, it was shown that diversity of the individual tendencies in the SNS review classification through the heat map. In the future, it is expected to extract personal tendencies from various fields and be used for customized service or marketing.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.4
• /
• pp.92-103
• /
• 2003

Great many advertisements are serviced in on-line by development of electronic commerce and internet user's rapid increase recently. However, this advertisement service is stopping in one-side service of relevant advertisement rather than doing users' inclination analysis to basis. Therefore, want advertisement service that many websites are personalized for efficient service of relevant advertisement and service through relevant server's log analysis research and enforce. Take advantage of log data of local system that this treatise is not analysis of server log data and analyze user's Preference degree and inclination. Also, try to propose advertisement system personalized by making relevant site tributary category and give weight of relevant tributary. User's preference user preference which analysis is one part of cooperation fielder ring of web personalized techniques use information in visit site tributary and suppose internet user's action in visit number of times of relevant site and try inclination analysis of mixing form. Express user's preference degree by vector, and inclination analysis result uninterrupted data that simplicity application form is not regarded and techniques that propose inclination analysis change of data since with move data use and analyze newly and proposed so that can do continuous renewal and application as feedback Sikkim. Presented method that can choose advertisements of relevant tributary through this result and provide personalized advertisement service by applying process such as user inclination analysis in advertisement chosen.

• Korean Journal of Materials Research
• /
• v.23 no.4
• /
• pp.227-232
• /
• 2013

Al-based alloys have recently attracted considerable interest as structural materials and light weight materials due to their excellent physical and mechanical properties. For the investigation of the potential of Al-based alloys, a surface porous $Al_{88}Cu_6Si_6$ eutectic alloy has been fabricated through a chemical leaching process. The formation and microstructure of the surface porous $Al_{88}Cu_6Si_6$ eutectic alloy have been investigated using X-ray diffraction and scanning electron microscopy. The $Al_{88}Cu_6Si_6$ eutectic alloy is composed of an ${\alpha}$-Al dendrite phase and a single eutectic phase of $Al_2Cu$ and ${\alpha}$-Al. We intended to remove only the ${\alpha}$-Al phase and then the $Al_2Cu$ phase would form a porous structure on the surface with open pores. Both acidic and alkaline aqueous chemical solutions were used with various concentrations to modify the influence on the microstructure and the overall chemical reaction was carried out for 24 hr. A homogeneous open porous structure on the surface was revealed via selective chemical leaching with a $H_2SO_4$ solution. Only the ${\alpha}$-Al phase was successfully leached while the morphology of the $Al_2Cu$ phase was maintained. The pore size was in a range of $1{\sim}5{\mu}m$ and the dealloying depth was nearly $3{\mu}m$. However, under an alkaline NaOH, aqueous solution, an inhomogeneous porous structure on the surface was formed with a 5 wt% NaOH solution and the morphology of the $Al_2Cu$ phase was not preserved. In addition, the sample that was leached by using a 7 wt% NaOH solution crumbled. Al extracted from the Al2Cu phase as ${\alpha}$-Al phase was dealloyed, and increasing concentration of NaOH strongly influenced the morphology of the $Al_2Cu$ phase and sample statement.

• The KIPS Transactions:PartD
• /
• v.12D no.1 s.97
• /
• pp.31-42
• /
• 2005

Generally, conventional video searching or classification methods are based on its meta-data. However, it is almost Impossible to represent the precise information of a video data by its meta-data. Therefore, a processing method of video data that is based on its meta-data has a limitation to be efficiently applied in application fields. In this paper, for efficient classification of video data, a classification method of video data that is based on its low-level data is proposed. The proposed method extracts the characteristics of video data from the given video data by clustering process, and makes the profile of the video data. Subsequently. the similarity between the profile and video data to be classified is computed by a comparing process of the profile and the video data. Based on the similarity. the video data is classified properly. Furthermore, in order to improve the performance of the comparing process, generating and comparing techniques of integrated profile are presented. A comparing technique based on a differentiated weight to improve a result of a comparing Process Is also Presented. Finally, the performance of the proposed method is verified through a series of experiments using various video data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.581-588
• /
• 2017

This study was conducted to determine which factors would predict metabolic syndrome (MetS) perception and exercise by applying a machine learning classifier, or Extreme Gradient Boosting algorithm (XGBoost) from July 2014 to December 2015. Data were obtained from the Korean Community Health Survey (KCHS), representing different community-dwelling Korean adults 19 years and older, from 2009 to 2013. The dataset includes 370,430 adults. Outcomes were categorized as follows based on the perception of MetS and physical activity (PA): Stage 1 (no perception, no PA), Stage 2 (perception, no PA), and Stage 3 (perception, PA). Features common to all questionnaires for the last 5 years were selected for modeling. Overall, there were 161 features, categorical except for age and the visual analogue scale (EQ-VAS). We used the Extreme Boosting algorithm in R programming for a model to predict factors and achieved prediction accuracy in 0.735 submissions. The top 10 predictive factors in Stage 3 were: age, education level, attempt to control weight, EQ mobility, nutrition label checks, private health insurance, EQ-5D usual activities, anti-smoking advertising, EQ-VAS, education in health centers for diabetes, and dental care. In conclusion, the results showed that XGBoost can be used to identify factors influencing disease prevention and management using healthcare bigdata.

• Korean Journal of Food Science and Technology
• /
• v.17 no.4
• /
• pp.253-257
• /
• 1985

Effects of four kinds of phosphate complex on the water holding capacity (W.H.C) and protein solubility of yellow-corvenia (Pseudosciance manchurica) and hair tail (Tichurus lepturus) meat paste were investigated. The formulations of four kinds of phosphate complex employed to this experiment were made by mixing several phosphates such as sodium polyphosphate, sodium pyro-phosphate, sodium acid pyro-phosphate, potassium pyro-phosphate, sodium tetra meta-phosphate, sodium ultra meta-phosphate and sodium hexa meta-phosphate, and monoglyceride at different mixture ratios. Among the four kinds of phosphate complex, phosphate B complex which was formulated by mixing sodium poly-phosphate 50%, sodium pyrophosphate 20%, sodium tetra meta-phosphate 20%, sodium acid pyrophosphate 5% and sodium ultra meta-phosphate 5% was most effective on enhancing the W.H.C and protein solubility of yellow corvenia meat paste, and in case of hair tail meat paste, phosphate C complex which was formulated by mining sodium poly-phosphate 40%, sodium pyro-phosphate 30%, potassium pyro-phosphate 15%, sodium tetra meta-phosphate 10%, and sodium hexa meta-phosphate 5% was more effective than other phosphate complex, and their optimum addition level was 0.4% respectively in weight of fish meat paste. Texture characteristics such as hardness, cohesiveness, and springiness value of Kamaboko (fish meat paste product) were evaluated as best when 0.3% of phosphate B complex was added. The optimum cooking condition of Kamaboko to get good texture was heating for 45 mimutes at $85^{\circ}C$.