pulse dataset

The formation and changes of the pulse wave areaffected by the functional status of the heart, blood, and arterial vessels. The pulse signal covers pathological information in the cardiovascular system, and the doctor of traditional Chinese medicine (TCM) can diagnose diseases by feeling the pulse. The diagnosis of diseases through feeling the pulse of TCM primarily relies on the doctor’s feelings and subjective experience, and it lacks objectified data. In this work, pulse signals were collected digitally by designing pulse sensors and pulse acquisition systems in accordance with the feel pulse habits of TCM. The pulse rate variability was used to characterize the functional state of the heart. The average magnitude difference function (AMDF) fuzzy entropy method was proposed to investigate the change in pulserate. A total of 77 volunteers with different heart health conditions were recruited for the collection of the pulse signal. Results showed that the AMDF fuzzy entropy can distinguish clearly among knotted pulse, regular intermittent pulse, and normal pulse. Therefore, this method has potential application value to realize cardiac-function state analysis and abnormal recognition.脉搏波的形成与变化受心脏、血液及动脉血管的功能状态影响。脉搏信号蕴含心血管系统的病理信息，传统中医（Traditional Chinese Medicine，TCM）医师可通过脉诊诊断疾病。传统中医脉诊主要依赖医师的主观触感与临床经验，缺乏客观化数据支撑。本研究依据中医脉诊手法习惯，设计脉搏传感器与脉搏采集系统，对脉搏信号进行数字化采集。本研究采用心率变异性指标表征心脏功能状态，提出平均幅值差函数（Average Magnitude Difference Function，AMDF）模糊熵方法，用于探究脉率变化规律。本研究共招募77名心脏健康状况各异的志愿者开展脉搏信号采集工作。研究结果表明，AMDF模糊熵可清晰区分结脉、规则间歇脉与正常脉象。因此，该方法在心脏功能状态分析与异常识别领域具有潜在应用价值。

搜集汇总

背景与挑战

背景概述

该数据集是一个基于中医脉诊原理的脉搏信号数据集，通过数字化采集系统收集了77名志愿者的脉搏信号，旨在研究脉搏波变化与心脏功能状态的关系。数据用于分析脉搏率变异性，并采用平均幅度差函数（AMDF）模糊熵方法，结果显示该方法能有效区分结脉、规律间歇脉和正常脉，具有心脏功能状态分析和异常识别的应用潜力。