請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/64540
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 魏志平(Chih-Ping Wei) | |
dc.contributor.author | Tai-Ying Guo | en |
dc.contributor.author | 郭岱茵 | zh_TW |
dc.date.accessioned | 2021-06-16T17:53:23Z | - |
dc.date.available | 2013-08-19 | |
dc.date.copyright | 2012-08-19 | |
dc.date.issued | 2012 | |
dc.date.submitted | 2012-08-13 | |
dc.identifier.citation | [1] Cory, K. A., Discovering Hidden Analogies in an Online Humanities Database, Computers and the Humanities, 31: 1–12, 1997.
[2] Baker, N.C., Hemminger, B.M., Mining Connections between Chemicals, Proteins, and Diseases Extracted from MEDLINE Annotations, Journal of Biomedical Informatics 43:510–519, 2010. [3] Frijters R., et al, Literature Mining for the Discovery of Hidden Connections between Drugs, Genes and Diseases, PLoS Computational Biology, 6(9), 2010. [4] Gordon, M.D., Dumais, S., Using Latent Semantic Indexing for Literature Based Discovery, Journal of the American Society for Information Science, 49(8) 674–685, 1998. [5] Gordon, M.D., Lindsay, R.K., Toward Discovery Support Systems: A Replication, Re-examination, and Extension of Swanson's Work on Literature-based Discovery of A Connection between Raynaud's and Fish Oil, Journal of the American Society for Information Science, 47 (2) 116–128, 1996. [6] Gordon, M.D., Lindsay, R.K., Literature-Based Discovery by Lexical Statistics, Journal of the American Society for Information Science, 50(7) 574–587, 1999. [7] Gordon, M.D., Lindsay, R.K., Fan, W., Literature-Based Discovery on the World Wide Web, ACM Transactions on Internet Technology, 2(4):261–275, 2002. [8] Hettne, K. M., et al, Automatic Mining of the Literature to Generate New Hypotheses for the Possible Link between Periodontitis and Atherosclerosis: Lipopolysaccharide As A Case, Journal of Clinical Periodontology, 34: 1016–1024, 2007. [9] Hristovski, D., Peterlin, B., Mitchell, J.A., Humphrey, S.M., Using Literature-based Discovery to Identify Disease Candidate Genes, International Journal of Medical Informatics, 74: 289–298, 2005. [10] Huang, W., Nakamoria, Y., Wang S., and Ma, T., Mining Scientific Literature to Predict New Relationships, Intelligent Data Analysis 9:219–234, 2005. [11] Medical Subject Headings. Available from: http://www.nlm.nih.gov/pubs/factsheets/mesh.html http://www.nlm.nih.gov/mesh/intro_record_types.html [12] National Library of Medicine. MEDLINE. Available from: http://www.nlm.nih.gov/pubs/factsheets/medline.html [13] National Library of Medicine. Unified Medical Language System fact sheet .Available from: http://www.nlm.nih.gov/pubs/factsheets/umls.html [14] Resnik, P., Using Information Content to Evaluate Semantic Similarity in A Taxonomy. In Proceedings of the 14th International Joint Conference on Artificial Intelligence, 448–453, 1995 [15] Srinivasan, P., Text Mining: Generating Hypotheses From MEDLINE, Journal of the American Society for Information Science and Technology, 55(5):396–413, 2004. [16] Srinivasan, P., Libbus, B., Mining MEDLINE for Implicit Links between Dietary Substances and Diseases, Bioinformatics, 20(1):i290–i296, 2004. [17] Swaminathan, R., Sharma, A., Yang, H., Opinion Mining for Biomedical Text Data: Feature Space Design and Feature Selection, Computer and Information Science, 2010. [18] Swanson, D.R., Fish oil, Raynaud’s Syndrome, and Undiscovered Public Knowledge. Perspectives in biology and medicine, 30:7–18, 1986. [19] Swanson, D.R., Migraine and Magnesium: Eleven Neglected Connections. Perspectives in Biology and Medicine, 31:526–557, 1988. [20] Swanson, D.R., Smalheiser, N.R., and Bookstein, A., Information Discovery from Complementary Literatures: Categorizing Viruses as Potential Weapons. Journal of the American Society for Information Science, 52:797–812, 2001. [21] Swanson, D.R., Smalheiser, N.R., Ranking Indirect Connections in Literature-Based Discovery: The Role of Medical Subject Headings. Journal of the American Society for Information Science, 57(11):1427–1439, 2006. [22] Weeber. M., Klein. H., den Berg LTW., VOS. R., Using Concepts in Literature-based Discovery: Simulating Swanson’s Raynaud-Fish Oil and Migraine-Magnesium Discoveries, Journal of the American Society for Information Science and Technology, 52(7):548–557, 2001. [23] Weeber, M., Klein, H., VOS, R., et al., Generating Hypotheses by Discovering Implicit Associations in the Literature: A Case Report of a Search for New Potential Therapeutic Uses for Thalidomide, Journal of the American Medical Informatics Association, 10(3):252–259, 2003. [24] Wren, JD., Extending the Mutual Information Measure to Rank Inferred Literature Relationship, BMC Bioinform, 5:145, 2004. [25] Yetisgen-Yildiz, M., Pratt, W., Using Statistical and Knowledge-based Approaches for Literature-based Discovery, Journal of Biomedical Informatics 39:600–611, 2006. [26] Yetisgen-Yildiz, M., Pratt, W., A New Evaluation Methodology for Literature-based Discovery Systems, Journal of Biomedical Informatics, 42:633–643. 2009. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/64540 | - |
dc.description.abstract | 近幾年科學文獻快速的成長,使得想要了解醫學資訊的人很難在大量的文獻中找到他們所想要資訊或者是潛藏的醫學上的關係,而Swanson於1986年提出了文獻探勘的方法來協助研究者找出潛在的醫學上的關係,之後其他的研究者也提出許多方法想要改善Swanson所提出的方法。
透過文獻探勘能夠縮短尋找潛在醫學上的關係的時間,但是無法提供更多的資訊,例如魚油能夠降低血漿濃度這種上升、下降影響的關係。因此,本研究基於文獻探勘的概念,提出影響效果探勘的方法,能夠找出醫學上關係上升、下降影響來幫助使用者或者是專家們在面臨大量資料時,透過這個方法所提供的上升、下降的圖形與排名更容易分析。我們會先透過文獻探勘找出相關的醫學概念,接著利用我們所提出的方法來找出醫學交互關係影響,最後再利用排序的方法來對產生的結果建立排名。 我們建立兩個實驗情境來評估影響效果探勘方法的結果,「疾病─化合物與藥情境」。在疾病─化合物與藥的情境中,通常較會注意哪種藥可以治療哪一種病,我們提出的方法能夠有效地將能治療疾病的藥排序在前面,並且能夠將正確的藥放在較高的排名。而在「藥─化合物與藥情境」之下,儘管實驗結果沒有疾病─化合物與藥的情境明顯,但是仍然可以看出我們所提出的方法能夠有效地提供較佳的結果給研究者。而對於研究者,通常較會注意前面一百名或是三百名的結果,而本研究所提出的方法能提供一個更好的結果讓想要了解醫學資訊不論是有醫學背景或是無醫學背景的人更容易了解。 | zh_TW |
dc.description.abstract | Scientific literature has growth rapidly in the past century, and a great deal of knowledge can support medical researchers to keep up with up-to-date information. This large volume of data is difficult to discover hidden relationships. To overcome this problem, Swanson proposed a method called literature-based discovery in 1986 to support researchers an effective way to uncovering new, potentially meaningful relationships. After Swanson proposed this method, other researchers also try to improve the result from literature-base discovery or develop new method to improve.
Researchers could employ literature-based discovery to support them reduce the time of discovering hidden relationships. But literature-based discovery method could not provide more information such as fish oil and blood viscosity is a suppressing relationship because fish oil can decrease blood viscosity. The kind of relationship we defined as impact relationship. Therefore, this study proposed a LBD (Impact) technique which is based on the concept of literature-based discovery and this technique can extract impact relationship to support researchers easier to analyze large volume of data. First, we apply literature-based discovery to retrieve related medical concepts. Subsequently, we use our proposed technique to extract impact relationship then order medical concepts in an appropriate way. We construct two scenarios to evaluate our proposed LBD (Impact) technique, disease-chemicals and drugs scenario and drug-chemicals and drugs scenario. In disease-chemicals and drugs scenario, researchers usually focus on which drug can cure disease. And our proposed technique can rank drugs that can cure disease at higher rank. In the other scenario, drug-chemicals and drugs scenario, although the experiment result is not better than disease-chemicals and drugs scenario, we still can provide a better result to researchers. For researchers, they usually pay more attention on top 100 or 300. In this study, our proposed technique can provide a better result for researchers. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T17:53:23Z (GMT). No. of bitstreams: 1 ntu-101-R99725043-1.pdf: 1328244 bytes, checksum: 9d87a6bf7398184313cb0af3d32020f0 (MD5) Previous issue date: 2012 | en |
dc.description.tableofcontents | 誌謝 i
中文摘要 ii Abstract iii Chapter 1 Introduction 1 1.1 Background 1 1.2 Research Motivation and Objectives 4 Chapter 2 Literature Review 8 2.1 Brief Overview of Literature-based Discovery 8 2.2 Term Selection and Filtering 10 2.3 Link Weighting 11 2.3.1 Association Rule 11 2.3.2 Term Frequency-Inverse Document Frequency (TF-IDF) 13 2.3.3 Z-score 13 2.3.4 Mutual Information Measure (MIM) 15 2.4 Target Term Ranking 16 2.4.1 Average Minimum Weight (AMW) 16 2.4.2 Linking Term Count with Average Minimum Weight (LTC-AMW) 17 2.5 Summary 18 Chapter 3 Design of LBD-Impact Technique 19 3.1 Term Selection (B and C) and Link Weighting (A-B and B-C) 20 3.2 Impact Mining 21 3.2.1 Relationship Patterns and Seed Terms for Impact Relationship Detection 23 3.2.2 Impact Relationship Detection (Sentence-level) 25 3.3 Target Term Ranking 28 Chapter 4 Evaluation Design and Results 33 4.1 Data Collection 33 4.2 Evaluation Procedure and Criteria 39 4.3 Performance Benchmark and Experiment Scenarios 41 4.4 Parameter-Tuning Experiment and Results 42 4.5 Experiment Results 44 4.5.1 Disease-Chemicals and Drugs Scenario 45 4.5.2 Drug-Chemicals and Drugs Scenario 47 Chapter 5 Conclusion 50 References 52 Appendix 56 MeSH introduction 56 | |
dc.language.iso | zh-TW | |
dc.title | 利用影響效果探勘協助文獻探勘 | zh_TW |
dc.title | Impact Mining for Supporting Literature-based Discovery | en |
dc.type | Thesis | |
dc.date.schoolyear | 100-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 李彥賢,楊錦生,楊傳智 | |
dc.subject.keyword | 文獻探勘,影響效果探勘,醫學文獻探勘, | zh_TW |
dc.subject.keyword | Literature-based discovery,Impact mining,Medical literature mining, | en |
dc.relation.page | 57 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2012-08-13 | |
dc.contributor.author-college | 管理學院 | zh_TW |
dc.contributor.author-dept | 資訊管理學研究所 | zh_TW |
顯示於系所單位: | 資訊管理學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-101-1.pdf 目前未授權公開取用 | 1.3 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。