[1]邓 晶,张 倩.交通流数据自适应特征选择算法[J].计算机技术与发展,2019,29(12):76-80.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 014]
　DENG Jing,ZHANG Qian.Adaptive Feature Selection Algorithm for Traffic Flow Data[J].,2019,29(12):76-80.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 014]
点击复制

交通流数据自适应特征选择算法()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年12期
页码:
76-80
栏目:
智能、算法、系统工程
出版日期:
2019-12-10

文章信息/Info

Title:
Adaptive Feature Selection Algorithm for Traffic Flow Data
文章编号:
1673-629X(2019)12-0076-05
作者:
邓 晶; 张 倩
南京工程学院 计算机学院,江苏 南京 211167
Author(s):
DENG Jing; ZHANG Qian
School of Computer Engineering,Nanjing Institute of Engineering,Nanjing 211167,China
关键词:
特征选择; 梯度提升决策树; 分类与回归决策树; 特征重要度; 二次下降法
Keywords:
feature selection; gradient lifting decision tree; classification and regression decision tree; characteristic importance; quadraticdescent method
分类号:
TP301.6
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 12. 014
摘要:
在交通流数据挖掘领域中,交通流预测占据着相当重要的地位。 特别的,由于交通流数据具有数据量大、维度高、非线性等特征,对预测数据训练集的选取更加关键。 文中以包含多影响因子的交通流数据为研究对象,综合考虑了交通流量、天气以及日期属性等交通数据特征。 数据的特征较多,维度较高。 基于此,在对数据进行合适的数据清洗后,提出并实现了一种梯度提升决策树的自适应选择方法,对应用于动态交通流预测模型的数据集进行特征选择。 以分类和回归决策树作为基学习器,采用梯度提升决策树算法进行回归拟合。 通过迭代过程中每棵决策树产生的基尼指数和分裂特征属性的次数来计算特征重要度,并采用二次下降法对特征进行自适应选择,实现对交通流数据重要特征的自动选取。 最后,通过实验数据论证了提出的算法和模型。
Abstract:
In traffic flow data mining,traffic flow prediction plays an important role. Especially,because traffic flow data has the characteristics of large amount of data,high dimension and non-linearity,it is more critical to select the training set of prediction data.We take traffic flow data with multiple impact factors as the research object and consider traffic flow,weather and date attributes comprehensively. The data has more features and higher dimensions. Based on this,an adaptive selection method of gradient lifting decision tree is proposed and implemented after proper data cleaning. The feature selection method is applied to the data set of dynamic traffic flow prediction model. Classification and regression decision tree are used as base learners,and gradient lifting decision tree algorithm is used for regression fitting. In the iteration process,Gini index produced by each decision tree and the number of times of splitting feature attributes are used to calculate the feature importance,and the second descent method is used to select the feature adaptively to realize the automatic selection of the important features of traffic flow data. Finally,the algorithm and model proposed are demonstrated by experimental data.

相似文献/References:

[1]刘利 何先平 袁文亮.股票趋势预测中Wrapper方法的研究与应用[J].计算机技术与发展,2010,(01):209.
　LIU Li,HE Xian-ping,YUAN Wen-liang.Research and Application of Wrapper Approach to Stock Trend Prediction[J].,2010,(12):209.
[2]黄炜 黄志华.一种基于遗传算法和SVM的特征选择[J].计算机技术与发展,2010,(06):21.
　HUANG Wei,HUANG Zhi-hua.Feature Selection Based on Genetic Algorithm and SVM[J].,2010,(12):21.
[3]张家柏 王小玲.基于聚类和二进制PSO的特征选择[J].计算机技术与发展,2010,(06):25.
　ZHANG Jia-bai,WANG Xiao-ling.A Novel Algorithm Based on K-Means Clustering and Binary Particle Swarm Optimization[J].,2010,(12):25.
[4]冯甲策 叶明 王惠文.基于Gram—Schmidt过程的支持向量机降维方法[J].计算机技术与发展,2009,(11):7.
　FENG Jia-ce,YE Ming,WANG Hui-wen.Dimension Reduction Method of Support Vector Machine Based on Gram- Schmidt Process[J].,2009,(12):7.
[5]林伟 柳荣其 徐熙.邮件过滤中一种改进的特征选择方法研究[J].计算机技术与发展,2009,(01):84.
　LIN Wei,LIU Rong-qi,XU Xi.Improvement of Feature Selection Algorithm in Spam Filtering[J].,2009,(12):84.
[6]刘毅 张月琳.基于Agent的邮件过滤与个性化分类系统设计[J].计算机技术与发展,2009,(02):66.
　LIU Yi,ZHANG Yue-lin.Design of a Mail Filter and Personalized Classification System Based on Agent[J].,2009,(12):66.
[7]陈素萍 谢丽聪.一种文本特征选择方法的研究[J].计算机技术与发展,2009,(02):112.
　CHEN Su-ping,XIE Li-cong.Research on Document Feature Selection[J].,2009,(12):112.
[8]段震 王倩倩 张燕平 张铃.覆盖算法下文本分类特征选择的研究[J].计算机技术与发展,2008,(11):29.
　DUAN Zhen,WANG Qian-qian,ZHANG Yan-ping,et al.Study on Feature Selection of Text Classification in Cross Cover Algorithm[J].,2008,(12):29.
[9]王希雷.基于Rough集理论的车牌汉字特征提取[J].计算机技术与发展,2007,(06):26.
　WANG Xi-lei.Car Plate Chinese Character Feature Extraction Based on Rough Set Theory[J].,2007,(12):26.
[10]董梅 胡学钢.基于多特征选择的中文文本分类[J].计算机技术与发展,2007,(07):117.
　DONG Mei,HU Xue-gang.Text Categorization Based on Multiple Features Selection[J].,2007,(12):117.

更新日期/Last Update: 2019-12-10