COPD多维特征提取与集成诊断方法  

Multidimensional feature extraction and integrated diagnosis of COPD

作　　者：房有丽 王红[1,2,3] 狄瑞彤 王露潼 宋永强 Fang Youli;Wang Hong;Di Ruitong;Wang Lutong;Song Yongqiang(School of Information Science & Engineering,Shandong Normal University,Jinan 250358,China;School of Life Science,Shandong Normal University,Jinan 250358,China;Shandong Provincial Key Laboratory of Distributed Computing Software,Jinan 250358,China)

机构地区：[1]山东师范大学信息科学与工程学院,济南250358 [2]山东师范大学生命科学学院,济南250358 [3]山东省分布式计算软件新技术重点实验室,济南250358

出　　处：《计算机应用研究》2019年第10期2925-2929,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(61672329,61373149,61472233,61572300,81273704);山东省科技计划资助项目(2014GGX101026);山东省教育科学规划资助项目(ZK1437B010);山东省泰山学者基金资助项目(TSHW201502038,20110819);山东省精品课程资助项目(2012BK294,2013BK399,2013BK402)

摘　　要：目前对慢性阻塞性肺疾病(COPD)的研究存在局限性,一方面,研究成果只利用数据分析单一特征对疾病的影响;另一方面,研究成果仅通过简单算法模型对病例数据验证,因此提出了COPD多维特征提取与集成诊断方法。首先,提出最大依赖度MDF-RS算法,提取多维特征的最优组合;其次,提出DSA-SVM集成模型,构建分类器进行诊断及预测;最后,利用交叉验证方法验证准确率等各项性能指标。通过实验对比验证了提出算法的有效性。At present,there were limitations to the study of COPD.On the one hand,the research results only used data to analyze the impact of single features on the disease,on the other hand,the research results were only verified by simple algorithm models for case data.Therefore,this paper proposed a COPD multi-dimensional feature extraction and integrated diagnosis method.First,it proposed the MDF-RS algorithm to extract the optimal combination of multi-dimensional features.Secondly,it proposed the DSA-SVM integrated model to construct the classifier for diagnosis and prediction.Finally,it used the cross-validation method to verify the accuracy and other performance indicators.The experimental comparison shows the effectiveness of the proposed algorithm.

关 键 词：慢性阻塞性肺疾病 多维特征 集成方法 交叉验证 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]