基于交叉覆盖算法的成绩预测  

A Research On Prediction Of Academic Record Based On Cover Algorithm

作　　者：史科[1] 宣国庆 

机构地区：[1]安徽广播电视大学省直分校,安徽合肥230001 [2]合肥市庐阳中学,安徽合肥230001

出　　处：《中国科技信息》2012年第13期167-168,共2页China Science and Technology Information

摘　　要：本文主要利用交叉覆盖算法,通过实验找出对初中生学习影响较大的因素。交叉覆盖算法是利用了M-P神经元模型的几何意义得到的一种领域覆盖的算法,它在一定意义上考虑到了网络结构的优化问题,可以使得产生的神经网络的规模较小,而且方法实用、可行,解决了多年以来一直未能很好解决的前向网络设计问题。本文尝试将交叉覆盖算法应用到学生成绩预测上,在实验中得到较好预测结果。This paper deals with experiment-based crosscovering algorithm aiming to find the more important factors that influence middle school students＇ learning. Cross-covering algorithm is a field covering algorithm, which obtained from the geometric meaning of MP neuron model. In a sense, it takes into accounts the optimization of network structure, causing a smaller neural network and this method is practical. It solves the problem of how to design a feedforword network, and this problem has not been well solved for many years after all.

关 键 词：数据挖掘 交叉覆盖算法 综合素质评价 成绩分析 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]