改进的粒子群算法优化的特征选择方法

被引:79
作者
李炜 [1 ]
巢秀琴 [2 ]
机构
[1] 安徽大学计算机科学与技术学院
[2] 安徽大学计算智能与信号处理教育部重点实验室
关键词
二进制粒子群优化算法; 特征聚类; 交互操作; 粒子密度; 群智能算法;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
特征选择是数据挖掘中数据预处理的一个重要步骤,因此选择出最优的特征子集可有效地降低学习算法的数据维度和计算成本。采用二进制粒子群优化算法(binary particle swarm optimization algorithm,BPSO)来对特征选择过程进行优化。提出基于特征聚类信息进行种群初始化的策略,其中特征的聚类由社团划分算法完成,并根据划分后的信息,在初始化过程中减少信息冗余,提高初始化种群的质量。提出一种基于决策空间相似性的自适应局部搜索策略,其中粒子的相似性指数由粒子在决策空间中的相似性确定。进化过程中,自适应地调整粒子进行局部搜索,避免算法早熟。最后,选择三种代表性的优化算法分别在11个UCI数据集上进行对比实验。实验结果表明,改进后的BPSO算法得到的特征选择结果在降低特征数目方面明显优于其他对比算法,且分类精度也有显著提高。
引用
收藏
页码:990 / 1004
页数:15
相关论文
共 23 条
[1]
机器学习中的特征选择 [J].
张丽新 ;
王家钦 ;
赵雁南 ;
杨泽红 .
计算机科学, 2004, (11) :180-184
[2]
Feature selection using particle swarm optimization-based logistic regression model.[J].Omar Saber Qasim;Zakariya Yahya Algamal.Chemometrics and Intelligent Laboratory Systems.2018,
[3]
Optimizing Multi-objective PSO based feature selection method using a feature elitism mechanism.[J].Maryam Amoozegar;Behrouz Minaei-Bidgoli.Expert Systems With Applications.2018,
[4]
Five discrete symbiotic organisms search algorithms for simultaneous optimization of feature subset and neighborhood size of KNN classification models.[J].T.W. Liao;R.J. Kuo.Applied Soft Computing.2018,
[5]
An opinion formation based binary optimization approach for feature selection.[J].Homayoun Hamedmoghadam;Mahdi Jalili;Xinghuo Yu.Physica A: Statistical Mechanics and its Applications.2018,
[6]
PSO-based feature selection and neighborhood rough set-based classification for BCI multiclass motor imagery task [J].
Kumar, S. Udhaya ;
Inbarani, H. Hannah .
NEURAL COMPUTING & APPLICATIONS, 2017, 28 (11) :3239-3258
[7]
A BPSO-SVM algorithm based on memory renewal and enhanced mutation mechanisms for feature selection.[J].Jiaxuan Wei;Ruisheng Zhang;Zhixuan Yu;Rongjing Hu;Jianxin Tang;Chun Gui;Yongna Yuan.Applied Soft Computing.2017,
[8]
A new hybrid feature selection approach using feature association map for supervised and unsupervised classification.[J].Amit Kumar Das;Saptarsi Goswami;Amlan Chakrabarti;Basabi Chakraborty.Expert Systems With Applications.2017,
[9]
A hybrid particle swarm optimization for feature subset selection by integrating a novel local search strategy.[J].Parham Moradi;Mozhgan Gholampour.Applied Soft Computing.2016,
[10]
Opposition chaotic fitness mutation based adaptive inertia weight BPSO for feature selection in text clustering.[J].Kusum Kumari Bharti;Pramod Kumar Singh.Applied Soft Computing.2016,