Data Mining in the Presence of Quantitatively and Qualitatively Diverse Information

存在定量和定性多样化信息的数据挖掘

• 批准号: 0415190
• 负责人: Anne Denton
• 金额: $ 27.26万
• 依托单位: North Dakota State University Fargo
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2005
• 资助国家: 美国
• 起止时间: 2005-07-01 至 2009-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0415190&HistoricalAwards=false
• 关键词: Data; Mining; Presence; Quantitatively; Qualitatively

Real data often show a more complex structure than is assumed in much of statistics, machine learning, or data mining. Objects may be characterized by diverse types of information such as numerical quantities, text, and properties of a network neighborhood. The goal of the project is to develop techniques to integrate information components that differ both quantitatively and qualitatively. Classification algorithms that are based on homogeneous attributes can be evaluated exclusively by their overall classification quality. In the presence of qualitatively and quantitatively diverse information, the search space of all possible combinations of techniques and parameters is too large to be evaluated by any reasonable amount of test data. Three goals are pursued: (1) defining intermediate, homogeneous attributes that allow effective use of uniform classification and clustering techniques; (2) developing robust criteria that allow identification of suitable intermediate attributes and do not exclusively rely on overall classification accuracy; and (3) developing efficient and effective approaches to generate intermediate attributes from data with network connectivity, time-dependent data, text and other types of data. Starting with a specific classification problem in bioinformatics, the project attempts to find solutions that are applicable to a wide range of data mining problems. The work is ideally suited to teach students a broad range of research activities from fundamental concepts to applications, both in thesis and course work. Results will be of relevance to a large number of practical applications in bioinformatics and other sciences. The project Web site (http://www.cs.ndsu.nodak.edu/~adenton/IDM/) is used for dissemination of up-to-date results, including software, demonstration of newly developed techniques, comprehensive examples based on biological data to benefit researchers from biological sciences, and generally understandable examples (such as for a movie database) will enhance outreach, and demonstrate generality of results.

实际数据通常显示出比大部分统计，机器学习或数据挖掘中所假设的更复杂的结构。对象的特征是不同类型的信息，例如网络社区的数值，文本和属性。 该项目的目的是开发技术以整合数量和定性上不同的信息组件。 基于同质属性的分类算法可以通过其整体分类质量来评估。 在定性和定量多样的信息的存在下，所有可能的技术和参数组合的搜索空间太大，无法通过任何合理数量的测试数据来评估。 实现了三个目标：（1）定义中间的均质属性，以有效利用统一分类和聚类技术； （2）制定允许识别合适的中间属性的强大标准，并且不仅依赖整体分类精度； （3）开发有效有效的方法来从具有网络连接，时间依赖于时间的数据，文本和其他类型的数据的数据中生成中间属性。从生物信息学中的特定分类问题开始，该项目试图找到适用于广泛数据挖掘问题的解决方案。 这项工作非常适合教学学生从基本概念到论文和课程工作的应用。 结果将与生物信息学和其他科学中的大量实际应用有关。项目网站（http://www.cs.ndsu.nodak.edu/~adenton/idm/）用于传播最新结果，包括软件，新开发的技术，基于生物学科学的生物学数据的全面示例，以使生物学的研究人员受益于生物学的示例，以及通常可以理解的示例（例如，将其供您的电影录取范围）增强了电影的范围，并且会增强电影的范围。