透過您的圖書館登入
IP:18.218.129.100
  • 學位論文

開發以語意網技術為基礎的藥物知識系統

Developing a Drug Knowledge System based on Sematic Web Technology

指導教授 : 戚玉樑

摘要


本研究以混搭(mash-up)鏈結資料為基礎,並以藥品資料集為核心,建置鏈結化國內藥物查詢系統,再透過知識模型的建立,提供更進一步的藥物查詢,例如可替代藥品。我國民眾在醫療上,常有看診次數及服用藥物上都有浮濫現象,而在藥品的使用上,會因資訊的不對稱,使得民眾在自我藥療(Self-medication)上具備高風險。因此本研究透過語意網技術整合國內藥品資料集,並進一步與鏈結開放藥物資料(Linking Open Drug Data, LODD)進行鏈結,補充不足的藥品資訊。本研究設計方法包括:(1) 轉換RDF-based,進行資源描述框架(Resource Description Framework, RDF)的資料形式轉換;(2) 建置鏈結資料,建立語意網的鏈結資料(Linked Data, LD)技術;(3) 發展資料網絡,建立推論知識的描述邏輯,擴展應用系統的知識推理能力。研究結果顯示,本研究所建立的鏈結開放資料,除了具有國內相關藥品資訊網站(國家網路醫藥網站)的功能外,更藉由鏈結資料混搭國外藥品資訊,提供更詳細的藥品資訊,另外具有知識模型與推論後,使得應用系統達到知識共享。換言之,利用語意網技術,可以在資料整合上更有效率,並在資料層上發展知識推論,使網路能智慧化,達到資料網絡(Web of Data)。

並列摘要


This study develops a drug inquiry systems based on the integration of linked open data. The system involves domestic open data and foreign data sets to complement necessary information for public. The therapy behavior of Taiwan citizen is used to visit clinic and take medicine too much. Moreover, some people are running self-medication by taking medicine without professional guidance. Some organizations and government agency have built Web site to provide drug information. However, drug knowledge such as toxic and medicine interactions are incomplete. Therefore, this study aim to build a knowledge-based system based on linked data and semantic web technologies. Major research design components of this study include: (1) transforming open data into Resource Description Framework (RDF) format. (2) producing Linked Data with technique of Semantic Web; (3) developing Web of Data within establishing knowledge model, expanding reasoning abilities of knowledge on application systems. The experiment results show that the Knowledge-based Systems can provide a better inquiry of drug knowledge by integrating drug detailed specification, medical interaction and potential toxic issues. Consequently, the OWL-based KBS can achieve accurate problem solving reasoning while maintaining knowledge base shareability and extensibility

參考文獻


Méndez, E., & Greenberg, J. (2012). Linked data for open vocabularies and HIVE’s global framework. El Profesional de La Informacion, 21(3), 236–244. https://doi.org/10.3145/epi.2012.may.03
Alvarez-Rodríguez, J. M., Labra-Gayo, J. E., & de Pablos, P. O. (2014). New trends on e-Procurement applying semantic technologies: Current status and future challenges. Computers in Industry, 65(5), 800-820. doi:10.1016/j.compind.2014.04.005
Aoki-Kinoshita, K. F., Kinjo, A. R., Morita, M., Igarashi, Y., Chen, Y. A., Shigemoto, Y., . . . Ogishima, S. (2015). Implementation of linked data in the life sciences at BioHackathon 2011. J Biomed Semantics, 6, 3. doi:10.1186/2041-1480-6-3
Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., & Ives, Z. G. (2007). DBpedia: A Nucleus for a Web of Open Data.
Ayvaz, S., Horn, J., Hassanzadeh, O., Zhu, Q., Stan, J., Tatonetti, N. P., . . . Boyce, R. D. (2015). Toward a complete dataset of drug-drug interaction information from publicly available sources. J Biomed Inform, 55, 206-217. doi:10.1016/j.jbi.2015.04.006

延伸閱讀