• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2013, Vol. 35 ›› Issue (8): 163-167.

• 论文 • 上一篇    下一篇

围网渔情预报中强影响因子的挖掘技术研究

李慧,胡云,王霞   

  1. (1.淮海工学院计算机工程学院, 江苏 连云港 222002;
    2.淮海工学院江苏省海洋资源开发研究院,江苏 连云港 222002)
  • 收稿日期:2012-08-13 修回日期:2013-01-17 出版日期:2013-08-25 发布日期:2013-08-25
  • 基金资助:

    江苏省海洋资源研究院科技开放基金资助项目(JSIMR11B12)

Research on mining technique of
high effect factors in purse seine fishery prediction        

LI Hui,HU Yun,WANG Xia   

  1. (1.Department of Computer Science,Huaihai Institute of Technology,Lianyungang 222002;
    2.Jiangsu Province R&D Institute of Marine Resources,Huaihai Institute of Technology,Lianyungang 222002,China)
  • Received:2012-08-13 Revised:2013-01-17 Online:2013-08-25 Published:2013-08-25

摘要:

针对传统围网渔业渔情预测方法的缺点,综合多种类型海洋环境因子,采用粗糙集理论中的属性约简方法,获得多种类型因子中的约简属性,即影响围网产量的强影响因子。该技术首先对渔情监测数据进行缺失值的填补,再利用可辨识矩阵进行属性约简,从而构建出强影响因子的核心属性集。该算法有效解决了渔情监测数据的稀疏性问题,提高了渔情预测的准确性。

关键词: 粗糙集理论, 围网, 数据挖掘, 渔情预测

Abstract:

Firstly, a new algorithm based on attribute frequency in the discernibility matrix is used to get the coreattribute of attribute reduction. Secondly, considering the effect of different kinds of marine environment factors, an effective prediction model is established to confirm the coreattribute to be the high effect factors of purse seine outputs. This method addresses the issue by automatically filling vacant item of the fishery monitor data set, and then to take a attribute deduction using the discernibility matrix to get the coreattribute to be the high effect factors of purse seine. The experiment results show that the algorithm efficiently improves sparsity of date set , and promises to make prediction more accurately .

Key words: rough set theory;purse seine;data mining;fishery prediction