KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Similarity Calculation Method Between Research Infrastructure

국가연구시설장비의 유사도 판단기법에 관한 연구

  • 김용주 (국가연구시설장비진흥센터) ;
  • 김영찬 (한밭대학교 컴퓨터공학과)
  • Received : 2018.05.14
  • Accepted : 2018.08.09
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In order to jointly utilize research infrastructure and to build efficient construction, which are essential in science and technology research and development process. Although various classification methods have been introduced for efficient utilization of registered information, functions that can be directly utilized such as similar research infrastructure search is not yet been implemented due to limitations of collection information. In this study, we analyzed the similar search technique so far, presented the methodology for the calculation of similarity of research infrastructure, and analyzed the learning result. Study suggested that a technique can be use to extract meaningful keywords from information and analyze the similarity between the research infrastructure.

연구개발과정에서의 필수요소인 연구장비의 공동활용 및 효율적인 구축을 위해 한국에서는 국가예산으로 구축된 장비정보를 필수적으로 등록하도록 하고 있다. 등록정보의 다양한 활용(중복성 검토, 성능예측, 대체장비추천)을 위해 본 연구에서는 현재 유사장비검색기법에 대해 분석하고 유사도 산출 방법을 제시하였다. 이를 통해 자연어 상태인 장비정보에서 키워드를 추출하여 LSA 기법을 적용하면 키워드간의 유사도산출 및 장비정보 간 유사도 분석이 가능함을 확인하였으며 향후 연구장비분류정보를 접목하여 적용할 경우 의미있는 유사도 산출 및 이를 활용한 다양한 서비스가 가능 할 것으로 예측된다.

Keywords

JBCRJM_2018_v7n12_469_f0001.png 이미지

Fig. 1. Analysis Procedure for Similarity

JBCRJM_2018_v7n12_469_f0004.png 이미지

Fig. 5. Examples of Word Similaruty Calculation

JBCRJM_2018_v7n12_469_f0005.png 이미지

Fig. 6. Examples of Graph

JBCRJM_2018_v7n12_469_f0006.png 이미지

Fig. 7. Analysis

JBCRJM_2018_v7n12_469_f0007.png 이미지

Fig. 8. Analysis

JBCRJM_2018_v7n12_469_f0008.png 이미지

Fig. 2. Examples of TF-IDF Calculatuon

JBCRJM_2018_v7n12_469_f0009.png 이미지

Fig. 3. Examples of SVD Calculation

JBCRJM_2018_v7n12_469_f0010.png 이미지

Fig. 4. Examples of Document Similarity Calculation

Table 1. Construction Ratio of Standard Classification

JBCRJM_2018_v7n12_469_t0001.png 이미지

Table 4. Process of Extracting Document Using the Extracted Keywords

JBCRJM_2018_v7n12_469_t0002.png 이미지

Table 2. Object noun phrase + predicate noun extraction[on]

JBCRJM_2018_v7n12_469_t0003.png 이미지

Table 3. [Adjective+tubular mother+noun phrase] Syntax extraction[jn]

JBCRJM_2018_v7n12_469_t0004.png 이미지

Table 5. Expansion of the Document by searching for and inserting the synonyms of the keywords

JBCRJM_2018_v7n12_469_t0005.png 이미지

Table 6. Test Dataset for Algorithm Performance

JBCRJM_2018_v7n12_469_t0006.png 이미지

Table 7. Reference Equipment for Comparison

JBCRJM_2018_v7n12_469_t0007.png 이미지

Table 8. Same Classification Distribution in Similar Equipment

JBCRJM_2018_v7n12_469_t0008.png 이미지

Table 9. Same or Similar Model Distribution in Similar Equipment

JBCRJM_2018_v7n12_469_t0009.png 이미지

Table 10. Ideal value type

JBCRJM_2018_v7n12_469_t0010.png 이미지

References

  1. Ministry of Science and ICT, R.O.Korea, "National Research Facilities & Equipment Trends 2016".
  2. NFEC, "A Study on the Similarity Estimation of Research Facilities and Equipments," PRISM. Polissue 14 2015.
  3. NFEC Research report(Kyung Hee University), "Research Equipment duplication and the improvement of the fair price calculation," 2014.
  4. Jeong Ok-Nam, "A Study on the Improvement of Similarity Evaluation Model for R&D Project," Ph.D. dissertation Soongsil University, 2013.
  5. Jianshan Sun, "Leveraging Content and Connections for Scientific Article Recommendation in Social Computing Contexts," The Computer Journal, Vol.57, Issue 9, Sept. 2014.
  6. DinhTuyen Hoang, "Academic event recommendation based on research similarity and exploring interaction between authors," 2016 IEEE International Conference on Systems, Man, and Cybernetics, 2016.
  7. Qamar Mahmood, Muhammad Abdul Qadir, Muhammad TanvirAfzal, "Application of COReS to Compute Research Papers Similarity," IEEE Access, 2017, Vol.5.
  8. Sukyung Kim, "Advanced Ontology Using the Seesorus and Meta Information of Research Facilities, Korea Basic Science Research Institute," Hanbat National University, 2015.
  9. K.V. Neethukrishnan, "Ontology based research paper recommendation using personal ontology similarity method," 2017 Second International Conference on Electrical,Computer and Communication Technologies (ICECCT).
  10. Qamar Mahmood, "Document similarity detection using semantic social network analysis on RDF citation," graph2013 IEEE 9th International Conference on Emerging Technologies (ICET).
  11. Presidential Decree of South Korea 28799, "Regulations on the Management of National R&D Projects," 2018.4.17.
  12. Lee Kyung Mi, Seo Dong Ryul, Choi Jin Sook, "Extract Class Composition Hierarchy Information in Semi-structured Data Processing," 1997.
  13. C. D. Manning, P. Raghavan, and H. Schutze, "Introduction to Information Retrieval," Cambridge University Press. 100-123. ISBN 9780521865715. Scoring, term weighting, and the vector space model.
  14. http://nlplab.ulsan.ac.kr/doku.php?id=utagger