摘要
心血管疾病的患病率和死亡率逐年上升，是当今世界头号致死疾病。心音信号可以反应心脏的结构和状态信息，在心血管疾病的诊断上有着重要的意义。在心音智能诊断方面，有少量产品已经问世，但是由于受到算法性能的限制，这些产品只能分辨心音正常与否，需要医生来确诊异常心音的类别，存在着诊断滞后、成本高的问题。本文针对以上问题，根据心音的特点，提出了基于深度学习与集成学习的心音分类算法，并研发了智能听诊系统，具体工作如下： （1）构建了基于深度学习的心音分类网络（Heart Sound Net，HSNet）：HSNet为本文从经典卷积神经网络结构AlexNet和VGGNet出发，根据心音时域和频域的特点构建的一种心音分类网络。本文利用公开数据集进行实验，并与相关文献中的分类结果进行对比分析。HSNet在正常心音和异常心音的二分类任务中达到了97.32%的准确率，较改进的AlexNet高0.27%，且HSNet预处理过程简单，易于工程实现。验证HSNet的有效性后，本文将HSNet用于本实验室自主研发的电子听诊器所采集的心音数据集，在正常心音、房性早搏、室间隔缺损和其他类别的四分类任务中达到98.72%的准确率。
（2）提出了基于深度学习和集成学习的心音网络提升算法（Heart Sound Net Boosting，HSNBoost）：针对HSNet调优后性能达到瓶颈的问题，HSNBoost使用深度学习模型HSNet作为特征提取器，并使用集成学习模型XGBoost（eXtreme Gradient Boosting）对提取特征后的心音进行分类，在公开数据集和自建数据集上的分类准确率较HSNet分别提高了1.68%和2.33%。
（3）研发了智能听诊系统：本文研发了智能听诊系统的用户端及服务端。在用户端实现了用户注册和登录、用户个人信息管理、心音录制和用户问诊的功能。服务端实现了用户信息管理、HSNBoost预测与结果整合、半监督心音标注和HSNBoost模型更新的功能。
关键词：心音分类；深度学习；集成学习；智能听诊系统
论述领导艺术的主要内容
Abstract
The prevalence and mortality of cardiovascular diseases are increasing year by year, making it the number one deadly disease in the world today. Heart sound signals can reflect the structure and state of the heart and have important implications for the diagnosis of cardiovascular disease. In the intelligent diagnosis of heart sounds, some products have been introduced, but due to the limitations of algorithm performance, these products can only distinguish whether the heart sounds are normal or not. They need doctors to diagnose the abnormal heart sounds precisely, and there are problems of diagnosis delay and high cost. Based on the above characteristics, this paper presents a heart sound classification algorithm based on deep learning and ensemble learning, and builds an intelligent auscultation system. The specific work is as follows:
(1)Heart Sound Network (HSNet) based on convolutional neural network was constructed. Based on
the classical convolutional neural network structure AlexNet and VGGNet, this paper constructs a heart sound classification network based on the characteristics of heart sound time domain and frequency domain. In this paper, the public data set is used for experiments, and the classification results in the relevant literature are compared and analyzed. HSNet achieved an accuracy of 97.32% in the normal classification of heart sounds and abnormal heart sounds, 0.27% higher than the modified Alex Net, and the HSNet preprocessing process is simple and easy to implement. After verifying the effectiveness of HSNet, this paper train HSNet with self-built datasets, achieving 98.72% accuracy in normal heart sounds, atrial premature beats, ventricular septal defects, and other categories.
(2)Heart Sound Net Boosting (HSNBoost) based on deep learning and ensemble learning was proposed. HSNBoost uses the deep learning model HSNet as the feature extractor, and uses the ensemble learning model XGBoost(eXtreme Gradient Boosting)to classify the heart sounds after extracting features. The classification accuracy on the public dataset and self-built dataset is 1.68% and 2.33% higher than HSNet respectively.
(3)Intelligent auscultation system was developed. This paper develops the user client and server of the intelligent auscultation system. The functions of user registration and login, user personal inform
ation management, heart sound recording and user inquiry are implemented on the user client. The server implements the functions of user information management, HSNBoost prediction and result integration, semi-supervised heart sound label and HSNBoost model update.
Key words: Heart Sound Classification，Deep Learning，Ensemble Learning，Intelligent Auscultation System
目录
摘要............................................................................................................................................. I ABSTRACT .............................................................................................................................. II 第一章绪论 (1)
1.1 研究背景及意义 (1)
1.2 心音分类算法的国内外研究现状 (2)
1.3 远程智能医疗的国内外研究现状 (4)
1.4 本文主要的工作内容 (6)
拉弥亚
1.5 论文结构 (6)
第二章心音特征与卷积神经网络简介 (8)
2.1 心音相关知识简介 (8)
2.1.1 心音的产生过程 (8)
2.1.2 心音信号的组成部分 (8)
2.1.3 心音的频域特征 (9)
2.2 卷积神经网络简介 (10)
2.2.1 人工神经网络 (10)
2.2.2 激活函数 (11)
2.2.3 卷积神经网络（CNN）模型 (14)
2.3 本章小节 (15)
第三章基于深度学习的心音分类器HSNET (16)
3.1 概述 (16)
3.2 经典的卷积神经网络结构 (16)
3.2.1 LeNet (16)
3.2.2 VGGNet (17)
3.3 HSNet 网络结构 (18)
3.4 实验设计与初步实验结果 (19)
17作业网英语3.4.1 实验环境介绍 (19)
3.4.2 实验数据集介绍 (19)
广西北部湾新闻
3.4.3 心音信号预处理 (21)
3.4.4 数据集划分 (24)
3.4.5 决策规则 (25)
3.4.6 初步实验结果分析 (25)
3.5 HSNet网络参数优化方法研究 (26)
3.5.1 随机梯度下降法 (26)
异乡人的花园
3.5.2 自适应梯度算法 (27)
3.5.3 均方根支撑算法 (28)
3.5.4 自适应动量估计算法 (29)
3.5.5 优化方法实验结果分析 (30)
3.6 HSNet模型性能优化研究 (31)
3.6.1 抗过拟合 (31)
3.6.2 加快收敛速度 (32)
3.7 实验结果对比与分析 (34)
3.8 本章小节 (35)
第四章基于集成学习的心音分类器HSNBOOST (36)
4.1 概述 (36)
4.2 集成学习介绍 (36)
周洋感谢门4.3 XGBoost介绍 (36)
4.4 基于HSNBoost的心音识别算法设计 (39)
4.5 HSNBoost模型的参数优化研究 (40)
4.5.1 特征维度调优 (40)
4.5.2 最大树深度与最小叶子权重调优 (41)
4.5.3 采样比例调优 (42)
4.5.4 gamma系数调优 (44)
4.5.5 学习率调优 (45)
4.6 实验结果分析 (46)
4.7 本章小节 (47)
第五章智能听诊系统的设计与实现 (48)
5.1 智能听诊系统的总体设计 (48)
5.2 服务端 (48)
5.2.1 数据库的设计与实现 (49)
豫公网安备41160202000603
站长QQ:729038198
关于我们
投诉建议