The Inducing of Classification Rules Based on Parallel ECL

摘要：

Inducing of classification rules is a research areaof machine learning and data mining that has receiveda lot of attention in recentyears. The ID3 and C4.5 arethe well-known algorithms for mining classificationrules. However, The rules induced by ID3 are notoptimal. Thus, Hu X.G propose a novel approach thatinducing classification rules in Extended ConceptLattice (ECL) which improve Concept Lattice byintroducing the equivalent intent. The approach issuperior to ID3 and C4.5. But the new features ofdatabase such as the high-dimensionality andheterogeneity make the parallel/distributed data mininga hot research domain. Under this circumstance, wepropose the parallel ECL for data mining from largescale database. In this paper, inducing classificationrules in parallel ECL is investigated both theoreticallyand experimentally.

作者: Yuhong Zhang Xuegang Hu

作者单位: Hefei University of Technology,Hefei 230009

会议类型: 国际会议

会议名称: The 8th International Conference on Computer Supported Cooperative Work in Design(第八届计算机支持的协同工作设计国际会议)(CSCWD2004)

会议地点: 厦门

会议语种:英文

页码: 759-764

在线出版日期: 2004-05-26（万方平台首次上网日期，不代表论文的发表时间）