使用神经模糊系统对主动脉瓣关闭不全和狭窄进行分类。

Classification of aorta insufficiency and stenosis using neuro-fuzzy system.

作者信息

Barşçi Necaattin, Topal Ergün, Hardalaç Firat, Güler Inan

机构信息

Department of Electronic and Computer Education, Faculty of Technical Education, Gazi University, Ankara, Turkey.

出版信息

J Med Syst. 2005 Apr;29(2):155-64. doi: 10.1007/s10916-005-3003-9.

DOI:10.1007/s10916-005-3003-9

PMID:15931801

Abstract

Cardiac Doppler signals recorded from aorta valve of 60 patients were transferred to a personal computer by using a 16 bit sound card. The fast Fourier transform (FFT) method was applied to the recorded signal from each patient. Since FFT method inherently cannot offer a good spectral resolution at jet blood flows such as cardiac Doppler signals, it sometimes causes wrong interpretation. In order to do a good interpretation and rapid diagnosis, cardiac Doppler blood flow signals were statistically arranged and then classified using neuro-fuzzy system. The NEFCLASS model, which is used to create a fuzzy classification system from data, was used. The classification results show that neuro-fuzzy system offers best results in the case of diagnosis.

摘要

使用16位声卡将60例患者主动脉瓣记录的心脏多普勒信号传输到个人计算机。对每位患者记录的信号应用快速傅里叶变换（FFT）方法。由于FFT方法本质上不能在诸如心脏多普勒信号的喷射血流处提供良好的频谱分辨率，它有时会导致错误的解释。为了进行良好的解释和快速诊断，对心脏多普勒血流信号进行统计整理，然后使用神经模糊系统进行分类。使用了用于从数据创建模糊分类系统的NEFCLASS模型。分类结果表明，神经模糊系统在诊断方面提供了最佳结果。