Zhou Peng

Sichuan University, Chengdu, Sichuan Sheng, China

Are you Zhou Peng?

Claim your profile

Publications (3)0 Total impact

  • Zhou Peng, Li Zhishu, Huang Zhiguo
    [Show abstract] [Hide abstract]
    ABSTRACT: The attribute reduction based on information entropy is different to that based on positive region in inconsistent information system. The problem of discernibility matrix in algebra view is analyzed, and an new discernibility matrix based on information entropy is proposed in this paper. This algorithm considers whether the objects compared are consistent, analyses in detail the degree of inconsistency and the distributing proportion of their conditional equivalent classes in decision classes, and the reduction based on information entropy is acquired finally. The theoretic analysis and simulation instance shows that this algorithm is feasible and effective in practice.
    Information Management and Engineering (ICIME), 2010 The 2nd IEEE International Conference on; 05/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: High dimension and hard describing of cluster are the primary problems of clustering algorithm based on vector model. The conditional probability combined with rough set is introduced in this paper, and a information retrieval model based on fuzzy rough set is proposed, finally its document clustering algorithm is designed in detail. Especially the description and updating of cluster is studied in this paper.
    Communication Software and Networks, 2009. ICCSN '09. International Conference on; 03/2009
  • Zhou Peng, Li Zhishu, Huang Zhiguo
    [Show abstract] [Hide abstract]
    ABSTRACT: The relation among data objects is not strictly symmetric and transitive in data grid environment, so it is rather difficult to compare their relativity. Combining membership with rough set and introducing them into information retrieval, this paper proposes a fuzzy rough set retrieval model. First the relationship between two classes is considered sufficiently to construct similarity relationship for classifying index space, then the membership of index word in regard to data object is designed with fuzzy set as theoretical principle, and lower and upper approximation of data object with respect to index space is defined with rough set as theoretical principle, finally the retrieval result is ranked and outputted. Experiment emulation shows the feasibility and validity of this algorithm.
    Computational Intelligence and Design, 2008. ISCID '08. International Symposium on; 11/2008