基于记忆抗体克隆聚类算法的心音分类研究

Research on Classification of Heart Sound by Using Antibody Memory Clone Clustering Algorithm

为快速、准确地判断心音的正常与否,提出了一种记忆抗体克隆聚类算法。该方法将克隆选择算法和监督Gath-Geva算法相结合对心音信号进行识别与分类,并运用Sammon映射算法将高维心音特征数据映射成二维实现分类效果的可视化。试验中,首先对临床采集的主动脉听诊区的心音数据110组(60组正常,50组异常)和二尖瓣听诊区的心音数据100组(60组正常,40组异常)进行预处理和特征提取,然后采用提出的记忆抗体克隆聚类算法对提取的心音特征数据进行识别与分类,平均分类准确率分别达到98.1%和96.2%。

In order to discriminate normal and abnormal （HS） Heart Sound accurately and effectively, （AMCCA） Anti- body Memory Clone Clustering Algorithm is proposed. The elonal selection algorithm and supervised Gath-Geva algorithm are used to do recognition and classification of HS, and then Sammon mapping algorithm is used to project the muhi-dimensional feature data of HS into a lower two-dimensional data to achieve the visualization of the classification results~ In the experiment, 110 data （60 normal, 50 abnormal） of the aortic heart valve and 100 data （60 normal, 40 abnormal） of the mitral heart valve are collected for preprocessing and feature extraction, and then the feature data are classified by using AMCCA, the average accuracy performances are achieved by 98.1% and 96.2%, respectively.