工程科学学报.第42卷，第4期：441-447.2020年4月 Chinese Journal of Engineering,Vol.42,No.4:441-447,April 2020 https://doi.org/10.13374/j.issn2095-9389.2019.09.12.007;http://cje.ustb.edu.cn 基于多目标支持向量机的ADHD分类 杜海鹏，邵立珍区，张冬辉 北京科技大学自动化学院工业过程知识自动化教育部重点实验室，北京100083 ☒通信作者，E-mail:Ishao(@ustb.edu.cn 摘要注意力缺陷多动障碍(ADHD)是儿童期最常见的精神疾病之一，在大多数情况下持续到成年期.近年来，基于功能 磁共振数据的ADHD分类成为了研究热点.文献中已有的大多数分类算法均假设样本是均衡的，然而事实上，ADHD数据集 通常是不平衡的.传统的学习算法会使得分类器倾向于多数类样本，从而导致性能下降.本文研究了基于不平衡神经影像数 据的ADHD分类问题，即基于静息状态功能磁共振数据对ADHD进行分类.采用功能连接矩阵作为分类特征，提出了一种 基于多目标支持向量机的ADHD数据分类方案.该方案将不均衡数据分类问题建模为具有三个目标的支持向量机模型，其 中三个目标分别为最大化分类间隔、最小化正样本误差和最小化负样本误差，进而正负样本经验误差可以被分开处理.然后 采用多目标优化的法向量边界交叉法对模型进行求解，并给出一组代表性的分类器供决策者进行选择.该方案在ADHD- 200竞赛的五个数据集上进行测试评估，并与传统分类方法进行对比.实验结果表明本文提出的三个目标支持向量机分类方 案比传统的分类方法效果好，可以有效的从算法层面解决数据不平衡问题.该方案不仅可用于辅助ADHD诊断，还可用于阿 尔茨海默病和自闭症等疾病的辅助诊断. 关键词多目标优化：功能磁共振数据：注意力缺陷多动障碍：支持向量机：不平衡数据集 分类号TG181 ADHD classification based on a multi-objective support vector machine DU Hai-peng,SHAO Li-zher°，ZHANG Dong--hui Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education,School of Automation and Electrical Engineering, University of Science and Technology Beijing,Beijing 100083,China Corresponding author,E-mail:Ishao@ustb.edu.cn ABSTRACT Attention deficit hyperactivity disorder (ADHD)is one of the most common mental disorders during childhood,which lasts until adulthood in most cases.In recent years,ADHD classification based on functional magnetic resonance imaging (fMRI)data has become a research hotspot.Most existing classification algorithms reported in the literature assume that samples are balanced; however,ADHD data sets are usually imbalanced.Imbalanced data sets can cause the performance degradation of a classifier by imbalanced learning,which tends to overfocus on the majority class.In this study,we considered an imbalanced neuroimaging classification problem:classification of ADHD using resting state fMRI.We used the functional connection matrix of fMRI as the classification feature and proposed a multi-objective data classification scheme based on a support vector machine(SVM)to aid the diagnosis of ADHD.In this scheme,the imbalanced data classification problem is formulated as an SVM model with three objectives: maximizing the margin,minimizing the sum of positive errors,and minimizing the sum of negative errors.Accordingly,the positive and negative sample empirical errors can be separately handled.Then,the model is solved by a multi-objective optimization method,i.e., normal boundary intersection method.A set of representative classifiers are computed for selection by decision makers.The proposed scheme was tested and evaluated on five data sets from the ADHD-200 consortium and compared with traditional classification methods. Experimental results show that the proposed three-objective SVM classification scheme is better than traditional classification methods 收稿日期：2019-09-12基于多目标支持向量机的 ADHD 分类 杜海鹏，邵立珍苣，张冬辉 北京科技大学自动化学院工业过程知识自动化教育部重点实验室, 北京 100083 苣通信作者，E-mail：lshao@ustb.edu.cn 摘    要    注意力缺陷多动障碍（ADHD）是儿童期最常见的精神疾病之一，在大多数情况下持续到成年期. 近年来，基于功能 磁共振数据的 ADHD 分类成为了研究热点. 文献中已有的大多数分类算法均假设样本是均衡的，然而事实上，ADHD 数据集 通常是不平衡的. 传统的学习算法会使得分类器倾向于多数类样本，从而导致性能下降. 本文研究了基于不平衡神经影像数 据的 ADHD 分类问题，即基于静息状态功能磁共振数据对 ADHD 进行分类. 采用功能连接矩阵作为分类特征，提出了一种 基于多目标支持向量机的 ADHD 数据分类方案. 该方案将不均衡数据分类问题建模为具有三个目标的支持向量机模型，其 中三个目标分别为最大化分类间隔、最小化正样本误差和最小化负样本误差，进而正负样本经验误差可以被分开处理. 然后 采用多目标优化的法向量边界交叉法对模型进行求解，并给出一组代表性的分类器供决策者进行选择. 该方案在 ADHD- 200 竞赛的五个数据集上进行测试评估，并与传统分类方法进行对比. 实验结果表明本文提出的三个目标支持向量机分类方 案比传统的分类方法效果好，可以有效的从算法层面解决数据不平衡问题. 该方案不仅可用于辅助 ADHD 诊断，还可用于阿 尔茨海默病和自闭症等疾病的辅助诊断. 关键词    多目标优化；功能磁共振数据；注意力缺陷多动障碍；支持向量机；不平衡数据集 分类号    TG181 ADHD classification based on a multi-objective support vector machine DU Hai-peng，SHAO Li-zhen苣 ，ZHANG Dong-hui Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China 苣 Corresponding author, E-mail: lshao@ustb.edu.cn ABSTRACT    Attention deficit hyperactivity disorder (ADHD) is one of the most common mental disorders during childhood, which lasts until adulthood in most cases. In recent years, ADHD classification based on functional magnetic resonance imaging (fMRI) data has become a research hotspot. Most existing classification algorithms reported in the literature assume that samples are balanced; however, ADHD data sets are usually imbalanced. Imbalanced data sets can cause the performance degradation of a classifier by imbalanced learning, which tends to overfocus on the majority class. In this study, we considered an imbalanced neuroimaging classification problem: classification of ADHD using resting state fMRI. We used the functional connection matrix of fMRI as the classification feature and proposed a multi-objective data classification scheme based on a support vector machine (SVM) to aid the diagnosis of ADHD. In this scheme, the imbalanced data classification problem is formulated as an SVM model with three objectives: maximizing the margin, minimizing the sum of positive errors, and minimizing the sum of negative errors. Accordingly, the positive and negative sample empirical errors can be separately handled. Then, the model is solved by a multi-objective optimization method, i.e., normal boundary intersection method. A set of representative classifiers are computed for selection by decision makers. The proposed scheme was tested and evaluated on five data sets from the ADHD-200 consortium and compared with traditional classification methods. Experimental results show that the proposed three-objective SVM classification scheme is better than traditional classification methods 收稿日期: 2019−09−12 工程科学学报，第 42 卷，第 4 期：441−447，2020 年 4 月 Chinese Journal of Engineering, Vol. 42, No. 4: 441−447, April 2020 https://doi.org/10.13374/j.issn2095-9389.2019.09.12.007; http://cje.ustb.edu.cn