基于统计特性随机森林算法的特征选择

doi:10.11772/j.issn.1001-9081.2015.05.1459

计算机应用 ›› 2015, Vol. 35 ›› Issue (5): 1459-1461.DOI: 10.11772/j.issn.1001-9081.2015.05.1459

基于统计特性随机森林算法的特征选择

宋源, 梁雪春, 张然

南京工业大学自动化与电气工程学院, 南京 211816

收稿日期:2014-11-21 修回日期:2015-01-07 出版日期:2015-05-10 发布日期:2015-05-14
通讯作者: 梁雪春
作者简介:宋源(1989-),男,江苏南京人,硕士研究生,主要研究方向:复杂系统预测及建模; 梁雪春(1969-),女,江苏南京人,教授,博士,主要研究方向:复杂系统预测及建模; 张然(1989-),女,安徽淮南人,硕士研究生,主要研究方向:复杂系统预测及建模.
基金资助:
国家自然科学基金资助项目(51205185);江苏省普通高校研究生科研创新计划项目(KYLX_0754).

Feature selection based on statistical random forest algorithm

SONG Yuan, LIANG Xuechun, ZHANG Ran

College of Automation and Electrical Engineering, Nanjing Technology University, Nanjing Jiangsu 211816, China

Received:2014-11-21 Revised:2015-01-07 Online:2015-05-10 Published:2015-05-14

摘要/Abstract

摘要：

针对由静息态功能磁共振成像(R-fMRI)得到的脑功能连接矩阵数据运用传统特征选择方法处理的结果,存在特征冗余,无法确定最终特征维数等问题,提出一种全新的特征选择算法.该算法在随机森林(RF)算法中结合统计特性,根据袋外数据的分类效果得到保留的特征,并将其运用在对精神分裂患者与正常被试者的识别实验中.实验结果表明,与传统的主成分分析(PCA)方法相比,该算法可以有效保留重要特征,提高识别精度,且保留的特征具有很好的医学解释性.

关键词: 随机森林, 统计特性, 静息态功能磁共振成像, 脑功能连接矩阵

Abstract:

Focused on the traditional methods of feature selection for brain functional connectivity matrix derived from Resting-state functional Magnetic Resonance Imaging (R-fMRI) have feature redundancy, cannot determine the final feature dimension and other problems, a new feature selection algorithm was proposed. The algorithm combined Random Forest (RF) algorithm in statistical method, and applied it in the identification experiment of schizophrenic and normal patients, according to the features are obtained by the classification results of out of bag data. The experimental results show that compared to the traditional Principal Component Analysis (PCA), the proposed algorithm can effectively retain important features to improve recognition accuracy, which have good medical explanation.

Key words: Random Forest (RF), statistical property, Resting-state functional Magnetic Resonance Imaging (R-fMRI), brain functional connectivity matrix

中图分类号:

TP391.4

宋源, 梁雪春, 张然. 基于统计特性随机森林算法的特征选择[J]. 计算机应用, 2015, 35(5): 1459-1461.

SONG Yuan, LIANG Xuechun, ZHANG Ran. Feature selection based on statistical random forest algorithm[J]. Journal of Computer Applications, 2015, 35(5): 1459-1461.

参考文献

[1] WISNER K M, ATLURI G, LIM K O, et al. Neurometrics of intrinsic connectivity networks at rest using fMRI: retest reliability and cross-validation using a meta-level method[J]. NeuroImage, 2013, 32(6): 236-251.
[2] MEDA S A, GILL A, STEVENS M C, et al. Differences in resting-state functional magnetic resonance imaging functional network connectivity between schizophrenia and psychotic bipolar probands and their unaffected first-degree relatives[J]. Biological Psychiatry, 2012, 71(10): 881-889.
[3] ZHI L, LI Y, ZHAO S. Feature extraction of fMRI data based on discrete wavelet transform[J]. Chinese Journal of Medical Imaging Technology, 2010, 26(6): 1151-1154. (支联合, 李玉晓, 赵书俊. 基于离散小波变换的 fMRI 数据特征提取[J]. 中国医学影像技术, 2010, 26(6): 1151-1154.)
[4] LYU B, WANG H. High-dimensional data visualization based on random forest[J]. Journal of Computer Applications, 2014, 34(6): 1613-1617. (吕兵, 王华珍. 基于随机森林的高维数据可视化[J]. 计算机应用, 2014, 34(6): 1613-1617.)
[5] FAN M, WU F, ZHENG H. Study of cognitive function in ultra-high risk subjects and first episode patients with schizophrenia[J]. Journal of Clinical Psychiatry, 2014, 24(1): 11-13. (范敏珍, 吴逢春, 郑洪波. 精神分裂症超高危人群及首次发病患者的认知功能研究[J]. 临床精神医学杂志, 2014, 24(1): 11-13.)
[6] TZOURIO-MAZOYER N, LANDEAU B, PAPATHANASSIOU D, et al. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain[J]. Neuroimage, 2002, 15(1): 273-289.
[7] SURGULADZE S A, CHU E M, MARSHALL N, et al. Emotion processing in schizophrenia: fMRI study of patients treated with risperidone long-acting injections or conventional depot medication[J]. Journal of Psychopharmacology, 2011, 25(6): 722-733.
[8] LIN C, PENG G. Application of random forest on selecting evaluation index system for enterprise credit assessment[J]. Journal of Xiamen University: Natural Science, 2007, 46(2): 199-203.(林成德, 彭国兰. 随机森林在企业信用评估指标体系确定中的应用[J]. 厦门大学学报: 自然科学版, 2007, 46(2): 199-203.)
[9] BENJAMINI Y, HOCHBERG Y. Controlling the false discovery rate: a practical and powerful approach to multiple testing[J]. Journal of the Royal Statistical Society, Series B: Methodological, 1995, 57: 289-300.
[10] STIGLER S. Fisher and the 5% level[J]. Chance, 2008, 21(4): 12.
[11] KALOUSIS A, PRADOS J, HILARIO M. Stability of feature selection algorithms: a study on high-dimensional spaces[J]. Knowledge and Information Systems, 2007, 12(1): 95-116.
[12] LI Y, WANG E, ZHANG H, et al. Default mode network in primary insomnia: measured with resting state functional MRI[J]. Chinese Journal of Medical Imaging, 2014, 22(7): 481-486.(李永丽, 王恩锋, 张红菊, 等. 原发性失眠患者默认网络神经功能的静息态 MRI 研究[J]. 中国医学影像学杂志, 2014, 22(7): 481-486.)

[1]	张杨, 董士程. 面向并发程序中锁机制的智能化推荐方法[J]. 计算机应用, 2021, 41(6): 1597-1603.
[2]	余东昌, 赵文芳, 聂凯, 张舸. 基于LightGBM算法的能见度预测模型[J]. 计算机应用, 2021, 41(4): 1035-1041.
[3]	张增辉, 姜高霞, 王文剑. 基于局部概率抽样的标签噪声过滤方法[J]. 计算机应用, 2021, 41(1): 67-73.
[4]	周翔, 翟俊海, 黄雅婕, 申瑞彩, 侯璎真. 基于随机森林和投票机制的大数据样例选择算法[J]. 计算机应用, 2021, 41(1): 74-80.
[5]	肖跃雷, 张云娇. 基于特征选择和超参数优化的恐怖袭击组织预测方法[J]. 计算机应用, 2020, 40(8): 2262-2267.
[6]	聂茜婵, 张阳, 余敦辉, 张兴盛. 面向全局优化的时空众包任务分配算法[J]. 计算机应用, 2020, 40(7): 1950-1958.
[7]	余敦辉, 袁旭, 张万山, 王晨旭. 基于动态阈值的时空众包在线分配算法[J]. 计算机应用, 2020, 40(3): 658-664.
[8]	陈禹, 毛莺池. 基于随机森林和遗传算法的Ceph参数自动调优[J]. 计算机应用, 2020, 40(2): 347-351.
[9]	王治忠, 钱龙龙, 韩闯, 师丽. 基于统计特征和熵特征融合的心肌梗死辅助诊断方法[J]. 计算机应用, 2020, 40(2): 608-615.
[10]	郎大鹏, 丁巍, 姜昊辰, 陈志远. 基于多特征融合的恶意代码分类算法[J]. 计算机应用, 2019, 39(8): 2333-2338.
[11]	何新宇, 张晓龙. 基于深度神经网络的肺炎图像识别模型[J]. 计算机应用, 2019, 39(6): 1680-1684.
[12]	田臣, 周丽娟. 基于带多数类权重的少数类过采样技术和随机森林的信用评估方法[J]. 计算机应用, 2019, 39(6): 1707-1712.
[13]	李鲜, 王艳, 罗勇, 周激流. 基于随机森林特征选择算法的鼻咽肿瘤分割[J]. 计算机应用, 2019, 39(5): 1485-1489.
[14]	胡淼, 王开军. 基于双特征和松弛边界的随机森林进行异常点检测[J]. 计算机应用, 2019, 39(4): 956-962.
[15]	王鑫, 高原, 王彬, 孙婕, 相洁. 多模态网络融合在轻度认知障碍分类中的应用[J]. 计算机应用, 2019, 39(12): 3703-3708.

基于统计特性随机森林算法的特征选择

Feature selection based on statistical random forest algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics