检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:成谢锋 单煦 佘辰俊 CHENG Xiefeng;SHAN Xu;SHE Chenjun(College of Electronic and Optical Engineering&College of Microelectronics,Nanjing Universityof Posts and Telecommunications,Nanjing 210023,China)
机构地区:[1]南京邮电大学电子与光学工程学院、微电子学院,江苏南京210023
出 处:《南京邮电大学学报(自然科学版)》2020年第2期13-19,共7页Journal of Nanjing University of Posts and Telecommunications:Natural Science Edition
基 金:国家自然科学基金(61271334,61373065)资助项目。
摘 要:心音信号作为一种生物特征已成为身份识别研究领域的新热点,并且已经有大量研究结果证明心音应用于身份识别技术是可行的,然而不同听诊位置采集到的心音信号具有一定的差异性,因此文中研究这种差异性对身份识别的影响。首先利用自制的4通道同步心音传感器记录来自二尖瓣、三尖瓣、肺动脉瓣、主动脉瓣的心音信号,然后对原始心音进行去噪和分段预处理,再通过线性预测编码(LPC)的方法提取S1和S2的共振峰频率作为心音识别的特征向量,并结合欧氏距离度量样本之间的相似性,分别对四个听诊位置进行身份识别实验。实验结果表明,不同听诊位置的识别率略有差异:在肺动脉瓣获得的识别率为92.5%,主动脉瓣的识别率为90%,二尖瓣和三尖瓣的识别率分别为87.5%和85%,并且肺动脉瓣获得的心音信号与实验对象的性别基本无关。这为心音采集与识别提供了一种有实用价值的参考。Heart sound signal as a biological feature has become a new hotspot in the field of identity recognition,and a large number of research results have proved that heart sound is applicable to identity recognion technology.However,heart sound signals collected at different auscultation locations have certain differences,so this article studies the impact of this difference on identity recognition.Firstly,a self-made 4-channel synchronous heart sound sensor is used to record the heart sound signals from the mitral valve,tricuspid valve,pulmonary valve,and aortic valve,and then the original heart sound is denoised and segmented prep-rocessed,and then linear prediction coding(LPC)is performed.The method uses the formant frequencies of S1 and S2 as the feature vectors for heart sound recognition,and combines the Euclidean distance to measu-re the similarity between samples,respectively to four auscultation location identification experiments.The experimental results show that the recognition rate is slightly different at different auscultation positions;the recognition rate obtained at the pulmonary valve is 92.5%,the recognition rate at the aortic valve is 90%,and the recognition rates at the mitral and tricuspid valves are 87.5%and 85%,and the heart sound signal obtained from the pulmonary valve was basically independent of the gender of the test subject.This provides a practical reference for heart sound collection and recognition.
分 类 号:TN911.7[电子电信—通信与信息系统] R318.04[电子电信—信息与通信工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.117