16. 数据库中知识发现 (Knowledge Discovery in Database,KDD)
数据库
是20世纪80年代末兴起的一种信息技术,是人工智能与数据库、
中的知
统计学、机器学习等技术的交叉产物,是从海量数据中获取有效、
识发现
新颖、有潜在应用价值和最终可理解模式的过程。
KDD is the nontrivial process of identifying valid, novel,
potentially useful, and ultimately understandable patterns
in data (KDD是从海量数据中获取有效、新颖、有潜在应
用价值和最终可理解模式的过程).
Data mining is a step in the KDD process that consists of
applying data analysis and discovery algorithms that, under
acceptable computational efficiency limitations, produce
a particular enumeration of patterns (or models) over the
data (数据挖掘是KDD过程中的一步,即通过使用各种
数据分析和发现算法,在可以接受的时间内产生模式).
17. The KDD process involves using the database along with
any required selection, preprocessing, subsampling, and
transformations of it; applying data-mining methods
(algorithms) to enumerate patterns from it; and evaluating
the products of data mining to identify the subset of the
enumerated patterns deemed knowledge.
25. 研究思路:基于语义Web的知识发现
博士阶段研究语义Web技术及其在中医药等领域的应用,5年语义Web软
工作基础
件和系统开发经验,发表论文10余篇,撰写《面向语义Web的设计模式
名录》等技术报告,以及语义Web在生物医学领域的应用综述。
Semantic Web Meets Integrative Biology: A Survey. In Briefings in
Bioinformatics (SCI, IF=9.283) (Publication in progress)
… We provide insight into how Semantic Web technologies can be used
Abstract to build open, standardized, and interoperable solutions for
interdisciplinary integration on a global basis. We present a rich set of
case studies in system biology, integrative neuroscience, bio-
pharmaceutics, and translational medicine, to highlight the technical
features and benefits of Semantic Web applications in integrative
biology…
Reviewer 1: “ … an excellent paper that does a very nice job
surveying the ways in which semantic web technology is being used
Feedbacks beneficially in bioinformatics…”
Reviewer 2: ”…The overall framework the authors set up for this
review is an interesting one, and could be quite compelling to some
readers of the Journal…”
Reviewer 3: ”… Overall this is a well-written article, with a very
useful list of references.”
48. 调研了面向华人的Web本体的发展策略、技术方案和应用前景,讨
前期工作
论了语义电子科学环境的最新进展和发展趋势,参与了中医药数据
库集成平台和语义搜索引擎的开发工作。
Semantic Web Development for Traditional Chinese Medicine. AAAI 2008 (EI)
… we present the first systematic adoption of the state-of-the-art Semantic
Abstract Web technologies in the codification, management, and utilization of TCM
information and knowledge resources…
Information retrieval and knowledge discovery on the semantic web of traditional
chinese medicine. WWW 2008 (EI)
Abstract … The platform and underlying methodology are proved effective in
TCM-related drug usage, discovery, and safety analysis...…
Intelligent search on integrated knowledge base of traditional Chinese medicine.
Journal of Southeast University (English Edition) (EI)
Abstract TCMSearch,a deployed intelligent search engine for
traditional Chinese medicine(TCM).is presented..…
51. 语义图挖掘 基于语义Web技术,提出一种新颖的知识发现框架,即语义图挖
掘。将领域本体、机器推理与图挖掘相结合,支持复杂网络分析。
Semantic web for integrated network analysis in biomedicine. In Briefings in
Bioinformatics (SCI, IF=9.283)
…… We introduce a new conceptual framework, semantic graph mining,
Abstract to enable researchers to integrate graph mining with ontology reasoning
in network data analysis…
…
56. 前期工作 提出基于多代理的语义关联发现方法,能从文本中挖掘语义关系,
实现语义关系的表示、推理和传播。发表多篇SCI,EI检索的论文。
A Multi-Agent Framework for Mining Semantic Relations from the Linked Data. In
Journal of Zhejiang University-SCIENCE C (Computers & Electronics) (SCI)
… Here, we present a multi-agent framework for mining hypothetical
Abstract semantic relations from the Linked Data, in which the discovery,
management, and validation of relations can be carried out
independently by different agents..…
59. 基于中医药领域知识库,搭建了中医百科系统,实现语义浏览、语
前期工作
义查询、语义搜索等功能,为各类用户和应用提供知识服务。相关
成果发表于SCI检索期刊。
DartWiki: A Semantic Wiki for Ontology-Based Knowledge Integration in the
Biomedical Domain. In Current Bioinformatics (SCI, IF=0.976)
… In this paper, we present a semantic wiki, named DartWiki, to build ontology-
Abstract based digital encyclopedia for the biomedicine domain. DartWiki provides a
Web-based interface for accessing knowledge artifacts in both per-artifact and
per-concept mode…