首页|不确定大数据流分类的决策树模型构建仿真

不确定大数据流分类的决策树模型构建仿真

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
在不确定大数据流分类过程中,受噪声和孤立点的干扰,导致处理效果和分类精度无法达到预期要求.为解决上述问题,提出一种基于决策树模型的不确定大数据流分类算法.通过采用在线字典学习算法,对不确定大数据流去噪处理,消除噪声对分类过程产生的干扰.构建决策树,在剪枝过程中通过特征过滤算法,滤除不确定大数据流中掺杂的孤立点.将去噪后的不确定大数据流,输入决策树模型中,完成分类工作.实验结果表明,所提算法处理后的不确定大数据流振幅明显减小,且分类精度高,具有一定的应用价值.
Simulation of Decision Tree Model Construction for Uncertain Big Data Flow Classification
In the process of uncertain big data stream classification,the effect and classification accuracy are una-ble to meet the expected requirements due to the interference of noise and isolated points.Therefore,an algorithm of classifying uncertain big data stream based on decision tree model was proposed.First of all,the online dictionary learning algorithm was adopted to reduce the noise from uncertain big data stream,and thus to eliminate the noise in-terference in the classification process.Moreover,a decision tree was constructed.Furthermore,feature filtering algo-rithm was adopted to filter the isolated points doped in the uncertain big data stream in the pruning process.Finally,the uncertain big data stream after denoising was input into the decision tree model,thus completing the classification.The experimental results show that the amplitude of the uncertain big data stream processed by the proposed algorithm is significantly reduced.In addition,the method has high classification accuracy and application value.

Decision tree modelOnline dictionary learning algorithmFeature filteringUncertain big data streamData classification

杨知玲、谭树杰

展开 >

华南农业大学珠江学院,广东 广州 510900

江西科技师范大学通信与电子学院,江西 南昌 330013

决策树模型 在线字典学习算法 特征过滤 不确定大数据流 数据分类

广东省教育科学规划课题(高等教育专项)(2022)广东省青年创新人才类项目(2021)北方国际大学联盟教育教学研究课题(第六期)广东省青年创新人才类项目(2021)广东省本科高等学校教学质量与教学改革工程建设项目(2022)

2022GXJK4042021WQNCX 156202106080042021WQNCX136粤教高函[2023]4号

2024

计算机仿真
中国航天科工集团公司第十七研究所

计算机仿真

CSTPCD
影响因子：0.518
ISSN：1006-9348
年,卷(期)：2024.41(5)