摘要
自动的心电异常识别是一个多标签分类问题,多通过对每个标签训练一个二分类器来实现异常识别。由于异常数目多,特征和异常间以及不同异常间的相关性复杂,自动检测的效果并不理想。为了充分利用异常和特征间的依存关系,提出了一种基于异常标签共现和特征局部相关(Label Co-occurrence and Feature’s local Pertinence,LCFP)的心电异常识别方法。首先,根据标签共现性和特征局部相关性,为标签构建包含宏特征和微特征的联合特征空间。宏特征采用狄利克雷过程混合模型聚类构建,以区分不同的共现标签集;微特征是原始特征空间的一个子集,用于区分共现标签集中的各个标签。进而,在联合特征空间为每个异常训练一个一对多(One-Versus-All)的概率分类器。其次,为充分利用异常的关联,提出在概率分类器排序基础上区分相关和非相关标签,采用Beta分布自适应地学习锚阈值和相关度阈值,以确定实例的相关标签集。LCFP是一种检测多种心电异常的通用方法,提高了心电异常识别的精度。在两个真实数据集上,F1指标分别提高了4%和22.4%,验证了所提方法的有效性。
Automatic electrocardiogram(ECG)abnormality detection is a multi-label classification problem,which is commonly solved by training a binary-relevance classifier for each abnormality.Due to the large number of abnormalities,the complex correlations between features and abnormalities,and those among different abnormalities,existing methods’performance is not satis-fying.To make full use of the dependencies between features and abnormalities,this paper proposes a novel abnormality detection method based on label co-occurrence and feature local pertinence(LCFP).Firstly,we set up a consolidated feature space consisting of both the macro-features and micro-features based on the label co-occurrence and features’pertineance.The macro-features are constructed with a clustering approach based on Dirichlet process mixture model(DPMM),thus distinguishing different co-occurrence label sets.The micro-features are a subset of primitive features,which serves to distinguish between the labels in the same labelset.Next,we train a one-versus-all classifier which returns a relevance probability.Secondly,to make use of the diffe-rent correlation degrees among different abnormalities,we propose to differ the relevant labels from the irrelevant ones based on the sorting according to the probabilities given by the classifiers.In particular,we propose to exploit the Beta distribution to adaptively learn the anchor thresholds and correlation thresholds,thus determining the relevant labels of an instance.Our LCFP me-thod is a universal way to detect every possible ECG abnormalities,which effectively improves the detection accuracy.The results on two real datasets show that our method can achieves an improvement of 4%and 22.4%,respectively,in terms of F1,which proves the effectiveness of our method.
作者
韩京宇
钱龙
葛康
毛毅
HAN Jingyu;QIAN Long;GE Kang;MAO Yi(School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Jiangsu Key Laboratory of Big Data Security&Intelligent Processing,Nanjing 210023,China)
出处
《计算机科学》
CSCD
北大核心
2023年第3期139-146,共8页
Computer Science
基金
国家自然科学基金(62002174)。
关键词
心电异常
多标签分类
标签共现
狄利克雷过程混合模型
BETA分布
锚阈值
Electrocardiogram abnormality
Multi-label classification
Label co-occurrence
Dirichlet process mixture model
Beta distribution
Anchor thresholds