摘要
数据挖掘是从大量数据中通过算法搜索隐藏于其中的信息,解决"数据爆炸但知识贫乏"问题。本文基于SLIQ算法展开研究。首先,研究由表示层、处理层和挖掘层构成的数据挖掘系统结构;然后,研究SLIQ算法,以算法思想为基础,设计了SLIQ算法流程,构建了Gini系数计算最佳分裂点和DML剪枝算法数学模型;最后,研究由主要常规功能和决策分析功能以及支撑数据构成的系统功能结构。本文的研究成果是软件开发的基础性工作,为软件开发提供技术支持。
Data mining is the large amount of data through the algorithm to search the information, it is hidden in the data, to solve the ＂data explosion but lack of knowledge＂ problem. The paper is studied based on SLIQ algorithm. First, researches data mining system architecture, which is composed of the presentation layer, processing layer and excavated layer; and then, researches SLIQ algorithm, which is based on the algorithm thinking, and designs SLIQ algorithm flow, constructed Gini coefficient to calculate the optimal split point and DML pruning algorithm mathematical model; Finally, researches system function structure by the major conventional functions and decision analysis capabilities and supports data constituted. The research results of this paper are the fundamental work of software development, and provide technical support for software development.
出处
《自动化技术与应用》
2016年第5期37-40,共4页
Techniques of Automation and Applications
基金
辽宁省社会科学规划基金项目(编号L13BGL013)
