期刊文献+

基于机器学习的花卉分类算法研究 被引量:4

Research on Flowers Classification Algorithm Based on Machine Learning
下载PDF
导出
摘要 介绍数据挖掘和机器学习基础知识,通过使用统计分类算法:分类和回归决策树、朴素贝叶斯分类器、神经网络、支持向量机,对UCI数据库上的花卉数据集进行分类,得到各种算法的分类性能评价指标并详细分析算法影响分类准确度的原因。 Introduces the basis of data mining and machine learning. The iris data set taken from the UCI machine learning database are classified by several commonly used algorithm, including classi- fication and regression tree (CART), naive bayes classifier, neural network and support vector machines (SVM). Carries out performance evaluation of the classification algorithms and analy- ses the effects of algorithms on classification accuracy in details.
出处 《现代计算机》 2013年第9期21-24,共4页 Modern Computer
关键词 机器学习 决策树 朴素贝叶斯 神经网络 Machine Learning Decision Tree Naive Bayes Neural Network(NN)
  • 相关文献

参考文献1

二级参考文献12

  • 1范洁,杨岳湘.决策树后剪枝算法的研究[J].湖南广播电视大学学报,2005(1):54-56. 被引量:9
  • 2季桂树,陈沛玲,宋航.决策树分类算法研究综述[J].科技广场,2007(1):9-12. 被引量:39
  • 3Hunt E B, Krivanek J. The effects of pentylenetatrazole and methyl-phenoxy propane on discrimination learning[J]. Psychopharmacologia, 1966(9): 1-16.
  • 4Quinlan J R. Induction of decision trees[J]. Machine Learning, 1986(4): 81-106.
  • 5Quinlan J R. C4.5: Programs for machine learning[J]. Morgan Kaufman, 1993: 81-106.
  • 6Mehta M, Agrawal R, Rissanen J. SLIQ: A fast scalable classifier for data mining[C]//Proc Int Conf Extending Database Technology, Avignon, France, 1996: 18-32.
  • 7Shafer J, Agrawal R. A scalable parallel classifier for data mining[C]//Proc 1996 Int Conf Very Large Data Bases Bombay, India, 1996: 544-555.
  • 8Rastogi R, Shim K. Public: A decision tree classifier that integrates building and pruning[C]//Proc 1998 Int Conf Very Large Data Bases, New York, 1998: 404-415.
  • 9Quinlan J R."C5" [EB/OL). http://rulequest.com, 2007.
  • 10Quinlan J R. Bagging, boosting, and C4.5[C]//Proc of 14th National Conference on Artificial Intelligence, Portland, Oregon, 1996: 725-730.

共引文献53

同被引文献92

引证文献4

二级引证文献41

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部