• 首页
  • 期刊简介
  • 编委会
  • 投稿指南
  • 收录情况
  • 杂志订阅
  • 联系我们
引用本文:朱永梁,朱耀东,唐 敏,胡 蝶.基于复杂特征的心动周期检测算法[J].软件工程,2024,(8):1-6.【点击复制】
【打印本页】   【下载PDF全文】   【查看/发表评论】  【下载PDF阅读器】  
←前一篇|后一篇→ 过刊浏览
分享到: 微信 更多
基于复杂特征的心动周期检测算法
朱永梁1, 朱耀东2, 唐 敏1, 胡 蝶1
(1.浙江理工大学信息科学与工程学院, 浙江 杭州 310018;
2.嘉兴大学信息科学与工程学院, 浙江 嘉兴 314001)
khakiman@163.com; zhuyaodong@163.com; 1401357810@qq.com; 1536172206@qq.com
摘 要: 为了解决传统算法应用于心冲击信号(Ballistocardiogram,BCG)心动周期检测时容易受到干扰导致准确率不高的问题,提出了一种基于复杂特征检测BCG 心动周期的算法。该算法通过同步采集的心电图信号(Electrocardiogram,ECG)将BCG信号划分为若干子序列,提取每段子序列信号的Shapelet,利用Shapelet变换将BCG子序列与其Shapelet映射到同一空间中,将Shapelet与BCG子序列的距离作为特征。同时,提取BCG子序列的小波变换特征,将两种特征融合后,使用人工神经网络(ANN)进行心动周期的检测,并且与传统分类器进行比较。实验结果表明,提出的算法在心动周期检测方面准确率提升了2.69百分点,证明了该算法在实际检测中的可行性。
关键词: 心冲击信号;Shapelet;小波变换;人工神经网络
中图分类号: TP389.1    文献标识码: A
基金项目: 浙江省医学电子与数字健康重点实验室开放课题(MEDH202206)项目;浙江省重点研发计划项目(2017C01043)
Cardiac Cycle Detection Algorithm Based on Complex Features
ZHU Yongliang1, ZHU Yaodong2, TANG Min1, HU Die1
(1.School of In f ormation Science and Engineering, Zhejiang Sci-Tech University, Zhejiang 310018, China;
2.School of In f ormation Science and Engineering, Jiaxing University, Jiaxing 314001, China)
khakiman@163.com; zhuyaodong@163.com; 1401357810@qq.com; 1536172206@qq.com
Abstract: In order to solve the problem that the traditional algorithm is easily interfered with in the detection of BCG (Ballistocardiogram)signal cardiac cycle, resulting in low accuracy, this paper proposes an algorithm for detecting BCG cardiac cycle based on complex features detection. This algorithm divides the BCG signal into several subsequences through the synchronously collected ECG (Electrocardiogram) signal, extracts the Shapelet of each subsequence signal, and maps the BCG subsequence and its Shapelet to the same space through Shapelet transformation, using the distance between the Shapelet and the BCG subsequence as a feature. At the same time, the wavelet transform features of the BCG subsequence are extracted, and after the fusion of the two features, the cardiac cycle is detected using an Artificial Neural Network (ANN), and compared with traditional classifiers. Experimental results show that the accuracy of the proposed algorithm in cardiac cycle detection improves by 2.69 percentage points, proving the feasibility of the algorithm in practical detection.
Keywords: BCG; Shapelet; wavelet transform; ANN


版权所有:软件工程杂志社
地址:辽宁省沈阳市浑南区新秀街2号 邮政编码:110179
电话:0411-84767887 传真:0411-84835089 Email:semagazine@neusoft.edu.cn
备案号:辽ICP备17007376号-1
技术支持:北京勤云科技发展有限公司

用微信扫一扫

用微信扫一扫