基于单层感知器的数据挖掘分类的设计和实现  

Design and Implementation of Classification Mining Based on Single-Layer Perceptron Artificial Neural Network

作　　者：王必强[1] 毕硕本[1] 董学士[1] 

机构地区：[1]南京信息工程大学计算机与软件学院,江苏南京210044

出　　处：《计算机技术与发展》2010年第9期111-114,共4页Computer Technology and Development

基　　金：中国气象局公益性行业科研专项经费资助项目(GYHY200806017)

摘　　要：数据挖掘是指从大型数据库或数据仓库中提取人们感兴趣的知识,这些知识是潜在有用信息。分类是数据挖掘重要研究方向之一,其目的就是分析输入数据,通过分析在训练集中的数据表现出来的特性,为每一个类找到一种准确的描述或者模型。怎样用科学合适的方式来解决分类问题,是数据挖掘研究领域的一个热点和难点。通过构造一种单层感知器神经网络的分类方法,对其进行设计分析和仿真实验,用图文并貌的界面形象直观地展示了分类效果,实验表明单层感知器神经网络可有效地进行数据挖掘分类。Data mining is to extract the interested potential knowledge from the large database and data warehouse.Classification is one of the most important research directions of data mining,which aims to find an accurate description or model for each category by analyzing the characteristics of data in the training set.How to solve the problem of classification in a scientific way is a hot spot and difficulty in the field of data mining research.In this paper,propose a data mining classification method based on the single-layer perceptron neural network.Some simulation experiments are made to verify the effectiveness and the feasibility of the proposed methods,and the classification results are graphically displayed and demonstrate that the single-layer perceptron neural network can be used to solve the problem of classification data mining effectively.

关 键 词：单层感知器 神经网络 分类 数据挖掘 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]