College of Information and Computer, Taiyuan University of Technology

【目的】抑郁症分类诊断研究中,特征选择扮演了重要角色。【方法】针对现有超图正则化特征选择缺失组效应信息问题,提出基于组套索的超图正则化特征选择方法。首先,对抑郁症功能磁共振影像(functionalmagneticresonanceimaging,fMRI)数据集进行预处理。其次,基于预处理后的功能磁共振数据,构建5个不同尺度的脑网络模型并计算拓扑属性提取特征。基于提取的特征,利用组套索方法构建超图,利用超图正则化特征选择方法进行特征选择。最后,使用支持向量机构建分类模型并评估分类性能。此外,还在UCI数据集中验证了所提方法的有效性。【结果】所提方法在5个不同节点定义模板下,均高于传统的特征选择方法。此外,在模板的节点数量相似的情况下,此方法有更高的分类诊断性能。

【Purposes】 In the research of depression classification and diagnosis, feature selec-tion plays a crucial role. 【Methods】 To address the issues of missing group effect information in existing hypergraph regularized feature selection methods, the group lasso-based hypergraph reg-ularized feature selection approach is proposed. Specifically, the functional magnetic resonance imaging (fMRI) dataset is preprocessed first for depression. Second, on the basis of the prepro-cessed fMRI data, five brain network models under different scales are constructed and the topol-ogical attributes are calculated to extract features. After feature extracting, the group lasso method is introduced to build hypergraph and the hypergraph regularized feature selection method is employed to select features. At last, classification model is constructed by using support vector machine (SVM) and its performance is evaluated. Additionally, the effectiveness of the proposed method is validated on UCI datasets. 【Findings】 The demonstrate that the proposed method outperforms traditional feature selection methods across five different node templates. Moreover, for similar numbers of nodes in different templates, superior classification diagnostic performance is achieved.

国家自然科学基金资助项目(61672374,61873178,61976150);山西省科技厅应用基础研究项目青年面上基金资助项目(201801D121135);教育部赛尔网络下一代互联网技术创新项目(NGII20170712);山西省重点研发计划项目(201803D31043);国家留学基金资助出国留学项目(201708140216)

郭冬喜,李瑶,陈俊杰.组套索超图正则化特征选择方法及抑郁症分类研究[J].太原理工大学学报,2023,54(5):838-845.

GUO Dongxi,LI Yao,CHEN Junjie.Research on feature selection method of group lasso hypergraph regulariza-tion and depression classification[J].Journal of Taiyuan University of Technology,2023,54(5):838-845.