• Journal of Korea Multimedia Society
• /
• v.12 no.7
• /
• pp.1032-1042
• /
• 2009

This research is for early extraction and utilization of semantic information from the tags in tagged Web image retrieval. Generally, users attach a tag to a Web image with little thought of the order, up to over 100 ones. In this paper, we suggest a method of selecting prior tags based on their importance when tagged images are uploaded, and using them in image retrieval. Ideas came from the recognition of the important tags which give a better description of the image as the tags sharing more semantic information with other tags of the same image. This method includes calculation of relation scores between tags based on WordNet and multilevel search of tagged images with the scores. For evaluation, we compared the suggested method and other retrieval methods searching images with simple matching of tags to a given keyword. As the results, we found the superiority of our method in precision and recall rate.

• The Journal of Korean Medical History
• /
• v.30 no.2
• /
• pp.45-61
• /
• 2017

Objectives : This research aims to investigate the consumer's interest in the Korean Medicine (KM) industry by using Google-trends and Naver-Data lab. A quick and uncomplicated way for those who are already involved with KM industry but do not have expertise in utilizing Big-data searches, is introduced. Methods : 'Direct keyword' was set by FGI (Focus Group Interview) and 'Detailed keyword' was set by using relevant word search and autocomplete search functions in the search engine. By inquiring Naver-Data lab, keyword search volumes are compared by age and sex, date range, and originating region of the researcher. It is possible to determine whether the data is reliable or authentic through examining the associated query. Selected direct keywords used through FGI (Focus Group Interview) were 'Acupuncture', 'Herbal Medicine', 'Cupping', 'Musculoskeletal Disease', 'Diet', and 'Stemina'. Based on these keywords, the following results were derived from the keyword analysis. Results : From August 2016, there was a noticeable surge of interest in men's 'Cupping'. The search for 'Diet' increased in the second quarter of 2016 from all ages. The search volume of 'Stemna' for individuals in their 20s is higher than that of those in their 30s or 40s'. Researchers from the region of Chungcheongbuk-do had a higher level of interest in analgesics and less interest in Korean Medicine. There is a greater interest in the KM market from European countries and America, than from Korea, China, and other Asian countries. Discussion : Despite the limitations of the research, it is meaningful to introduce a quick and easy data search method to compare information by age, sex, and region. Conclusion : The future of research into Korea Medicine and this market is confirmed by our data results which indicate interest from Europe, the United States, and other western countries, but less interest from Korea, China and other Asian countries.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.317-322
• /
• 2010

This paper proposes how to improve performance of the Korean document sentiment-classification system using semantic properties of the sentiment words. A sentiment word means a word with sentiment, and sentiment features are defined by a set of the sentiment words which are important lexical resource for the sentiment classification. Sentiment feature represents different sentiment intensity in general field and in specific domain. In general field, we can estimate the sentiment intensity using a snippet from a search engine, while in specific domain, training data can be used for this estimation. When the sentiment intensity of the sentiment features are estimated, it is called semantic orientation and is used to estimate the sentiment intensity of the sentences in the text documents. After estimating sentiment intensity of the sentences, we apply that to the weights of sentiment features. In this paper, we evaluate our system in three different cases such as general, domain-specific, and general/domain-specific semantic orientation using support vector machine. Our experimental results show the improved performance in all cases, and, especially in general/domain-specific semantic orientation, our proposed method performs 3.1% better than a baseline system indexed by only content words.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.40 no.2
• /
• pp.74-85
• /
• 2012

As competition increases, ski resort managers need to search for ways to attract previous visitors or to gain new visitors through word-of-mouth. This study examined the impact of skiers' perceived value, satisfaction and self-congruity on the revisit intention and the positive word-af-mouth intention. Total respondents were also segmented into a promotion-focus and prevention-focus individuals then later examined the differences in the effect of independent variables between groups in order to suggest a managerial direction that will enhance business competency of ski resorts. Results from regression analysis showed that all independent variables utilized in this study were good predictors of two dependent variables. Specially, satisfaction was a highly significant predictor. Promotion and prevention-focused individuals were also differed in evaluating the importance of independent variables for their revisit and word-of-mouth intention. It means that self-regulatory focus is an effective variable for segmentation. More specifically, satisfaction was the only variable influencing the revisit intention for promotion-focused individuals; whereas both satisfaction and self-congruity had significant effects on the revisit intention for prevention-focused individuals. All independent variables had significant effects on the word-of-mouth intention, except self-congruity for promotion-focused individuals. This research suggests several managerial implications on the findings based on the analysis and the characteristics of the visitors.

• Information Systems Review
• /
• v.22 no.1
• /
• pp.17-31
• /
• 2020

With the start of the fourth industrial revolution era, technologies of various fields are merged and new types of technologies and products are being developed. In addition, the importance of the registration of intellectual property rights and patent registration to gain market dominance of them is increasing in oversea as well as in domestic. Accordingly, the number of patents to be processed per examiner is increasing every year, so time and cost for prior art research are increasing. Therefore, a number of researches have been carried out to reduce examination time and cost for patent-pending technology. This paper proposes a method to calculate the degree of similarity among patent documents of the same priority claim when a plurality of patent rights priority claims are filed and to provide them to the examiner and the patent applicant. To this end, we preprocessed the data of the existing irregular patent documents, used Word2vec to obtain similarity between patent documents, and then proposed recommendation model that recommends a similar patent document in descending order of score. This makes it possible to promptly refer to the examination history of patent documents judged to be similar at the time of examination by the examiner, thereby reducing the burden of work and enabling efficient search in the applicant's prior art research. We expect it will contribute greatly.

• Journal of Korean Library and Information Science Society
• /
• v.40 no.3
• /
• pp.367-387
• /
• 2009

The similar bibliographic retrieval system follows whether it selects a thing of the extracted index term and or not the difference in which the similar document retrieval system There be many in the search result is generated. In this research, the method minimally making the error of the selection of the extracted candidate index term is provided In this research, the word information in which it is adjacent by using candidate index terms extracted from the similar literature and the keyword topic information were used. And by using the related author information and the reranking method of the search result, the similar bibliographic system in which an accuracy is high was developed. In this paper, we conducted experiments for similar bibliographic retrieval system on a collection of Korean journal articles of science and technology arena. The performance of similar bibliographic retrieval system was proved through an experiment and user evaluation.

• The Journal of Korean Medical History
• /
• v.23 no.2
• /
• pp.47-56
• /
• 2010

The objective of this article is to investigate and analyze the way how the suture surgery was operated in case of external wound or incision in past Korea. The method to do this study was to search the books on the website, Knowledge of Oriental Medicine Web Service, databased and serviced by Korean Institute of Oriental Medicine. The searching key word was '縫'. The results was as follows. According to the website search, ten subjects of suture surgery could be classified: sword wound(金瘡), horse bite(馬咬), intestine incision(腸肚傷), knife or ax wound(刀斧傷), larynx incision(割喉), intestine protrusion by cow collision(牛觸腸出), self-stabbing of neck(自刎), falling from tree(童稚上木墮下), lip injury(趺損唇皮) and face wound(顔面의 外傷). Furthermore, the kinds of suturing fiber, the way how to stitch, the kinds of medical care before and after the suture surgery could also be found

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.8
• /
• pp.656-661
• /
• 2013

In Guided Scrambling (GS) encoding for the holographic storage, after scrambling augmented source word into codeword, the best codeword satisfying modulation constraint is determined. Modulation constraints considered in this paper are strength which is the minimum number of transition between '0' and '1' in each row and column of codeword array and the symbol balancedness of codeword array. In this paper, we show that GS encoding procedure can be formulated as an integer programming model and develop a fast neighborhood search heuristic for fast computation of control bits. In the simulation, we compared the performance of heuristic algorithm with the integer programming model for various array and control bit size combinations.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.639-640
• /
• 2006

Many companies in mechanical engineering fields have accumulated information of design and manufacturing. The Enterprise Resource Planning (ERP) and Product Data Management (PDM) systems help information gathering and data managing. However, these systems are not flexible to support suitable functionality for specific product because these systems deal with entire enterprise resources. To cope with this issue, a web-based design support system was constructed for the design process of automotive steel pulley. This system provided 1) search service for part design with key word and clustering map, and 2) estimation service of maximum stress. These services reduced design time by reducing iterative jobs with Computer Aided Design (CAD) and Computer Aided Engineering (CAE) for stress analysis, and by enhancing search for existing data of steel pulley.

• Journal of Digital Contents Society
• /
• v.19 no.5
• /
• pp.927-933
• /
• 2018

One of the factors that have the greatest influence on the error of the question answering system that finds and provides answers to natural language questions is the step of searching for documents or passages that contain correct answers. In order to improve the retrieval performance, it is necessary to understand the characteristics of documents and passages containing correct answers. This paper experimentally analyzes how many question words appear in the correct answer documents, how the location of the question word is distributed, and how the topic of the question and the correct answer document are similar using the corpus composed of the question, the documents with correct answer, and the documents without correct answer. This study explains the causes of previous search research results for question answer system and discusses the necessary elements of effective search step.