A New Diagnosis Method for Heart Valve Disease by Using Antibody Memory Clone Clustering Algorithm based on Supervised Gath-Geva Algorithm
In order to discriminate normal and abnormal heart sounds (HSs) accurately and effectively, a new method for clinical diagnosis of the heart valve diseases is proposed. The method is composed of three stages. The first stage is the pre-processing stage. During the pre-processing stage, the improved wavelet threshold shrinkage denoising algorithm is used for the noise reduction of the measured HSs. In the feature extraction stage, the normalized average Shannon energy theorem and wavelet transform are used to extract the time-frequency feature of the HSs. In the classification stage, the proposed Antibody Memory Clone Clustering Algorithm (AMCCA) based on Supervised Gath-Geva algorithm is used. To test the correct classification rate of the proposed method, 110 data (60 normal, SO abnormal) of the aortic heart valve and 120 data (60 normal, 60 abnormal,) of the mitral heart valve are collected and analyzed, the accuracy performances are achieved by 96.2％, 100％, 96％ and 96.4％ respectively. Furthermore, Sammon mapping algorithm is used to project the four-dimensional feature data of HSs into a lower two-dimensional data to achieve the visualization of the classification results. The experimental results indicate that the proposed method achieves high classification accuracy, and has strong clinical application value.
Heart Sounds Noise Reduction the normalized average Shannon energy Wavelet Transform Antibody Memory clone Supervised Gath-Geva Sammon mapping
Yan Wang Haibin Wang Lihan Liu Yu Fang Jinbao Zhang
School of Electrical and Information Engineering Xihua University Chengdu China Cardiothoracic Surgery Chengdu Military General Hospital of PLA Chengdu China
国际会议
成都
英文
150-154
2010-07-07（万方平台首次上网日期，不代表论文的发表时间）