[1]侯晓丽,赵雅,严慧深,等.基于深度LSTM残差网络的帕金森症诊断方法[J].中国医学物理学杂志,2023,40(5):609-615.[doi:DOI:10.3969/j.issn.1005-202X.2023.05.014]
　HOU Xiaoli,ZHAO Ya,YAN Huishen,et al.Diagnosis of Parkinsons disease based on deep LSTM residual network[J].Chinese Journal of Medical Physics,2023,40(5):609-615.[doi:DOI:10.3969/j.issn.1005-202X.2023.05.014]
点击复制

基于深度LSTM残差网络的帕金森症诊断方法()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
40卷
期数:
2023年第5期
页码:
609-615
栏目:
医学信号处理与医学仪器
出版日期:
2023-05-26

文章信息/Info

Title:
Diagnosis of Parkinsons disease based on deep LSTM residual network
文章编号:
1005-202X（2023）05-0609-07
作者:
侯晓丽1; 赵雅2; 严慧深1; 程宏2
1.扬州市职业大学医学院， 江苏 扬州 225000； 2.扬州大学医学院， 江苏 扬州 225000
Author(s):
HOU Xiaoli1;  ZHAO Ya2;  YAN Huishen1;  CHENG Hong2
1. Medical School, Yangzhou Polytechnic College, Yangzhou 225000, China 2. Medical School, Yangzhou University, Yangzhou 225000, China
关键词:
帕金森症; 长短期记忆网络; 残差网络; 帕金森症元音集
Keywords:
Keywords: Parkinsons disease?ong short-term memory network?esidual network?arkinsons disease vowel set
分类号:
R318；TP181
DOI:
DOI:10.3969/j.issn.1005-202X.2023.05.014
文献标志码:
A
摘要:
语音特征分类下的帕金森症诊断方法具有无创、高效、准确、远程与成本低等特点，本研究提出一种基于深度长短期记忆网络（LSTM）残差网络的帕金森症诊断方法。分析帕金森症语音信号特点和LSTM残差模型，基于深度LSTM残差网络的帕金森症诊断模型分成3个部分：语音信号预处理网络、深度LSTM残差语音诊断网络和GAP-ELM帕金森症分类网络。该模型能实现帕金森语音信号的深层特征提取，通过LSTM结构的遗忘门和记忆门得到帕金森语音信号随时间变化的状态，最后通过帕金森症元音集完成帕金森症诊断测试。结果表明本文方法在各类信噪比环境中的帕金森症识别准确度均较高，并可在较少的轮次中完成训练，达到较优的稳定性和较小的损失值。
Abstract:
Abstract: Parkinsons disease (PD) diagnosis method based on speech feature classification has the characteristics of non-invasive, efficient, accurate, remote and low-cost. A PD diagnosis method based on deep long short-term memory (LSTM) residual network is proposed.?he characteristics of speech signal in PD patients and deep LSTM residual model are analyzed, and the PD diagnosis model based on deep LSTM residual network is divided into 3 parts, namely speech signal pre-processing network, deep LSTM residual network for speech diagnosis and GAP-ELM network for PD classification. The proposed model can realize the extraction of deep features of PD speech signal, and obtain the time-changing state of PD speech signal through the forgetting gate and memory gate of LSTM structure. PD diagnostic test is completed using PD vowel set. The experimental results demonstrate the proposed method has a higher recognition accuracy for PD in various signal-to-noise ratio environments, and it can complete the training in fewer epochs, and achieve better stability and smaller loss value.?/html>

相似文献/References:

[1]周杰,杨国雨,徐涛. 基于空间频率与时间序列信息的多类运动想象脑电分类[J].中国医学物理学杂志,2019,36(1):81.[doi:DOI:10.3969/j.issn.1005-202X.2019.01.016]
　ZHOU Jie,YANG Guoyu,XU Tao. Classification of multi-class motor imagery EEG data based on spatial frequency and time-series information[J].Chinese Journal of Medical Physics,2019,36(5):81.[doi:DOI:10.3969/j.issn.1005-202X.2019.01.016]
[2]张乙鹏,孙文慧,陈扶明.基于小波变换和CNN-LSTM的肺音分类算法[J].中国医学物理学杂志,2024,41(3):356.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.014]
　ZHANG Yipeng,SUN Wenhui,et al.Lung sound classification algorithm based on wavelet transform and CNN-LSTM[J].Chinese Journal of Medical Physics,2024,41(5):356.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.014]
[3]李刚,高广帅,张珍珍,等.基于连续小波变换和高阶统计量的心律失常识别算法[J].中国医学物理学杂志,2024,41(3):365.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.015]
　LI Gang,GAO Guangshuai,ZHANG Zhenzhen,et al.Arrhythmia identification algorithm based on continuous wavelet transform and higher-order statistics[J].Chinese Journal of Medical Physics,2024,41(5):365.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.015]

备注/Memo

备注/Memo:
【收稿日期】2022-12-03 【基金项目】江苏省自然科学基金（BK20201434）；中国高等教育学会职业技术教育分会课题（GZYYB2018030）；扬州市职业大学自然科学科科研项目（2017ZR16） 【作者简介】侯晓丽，硕士，讲师，研究方向：帕金森症诊断、神经药理学，E-mail: houxiaoli2010_1987@163.com 【通信作者】程宏，博士，副教授，研究方向：神经退行性疾病的保护作用，E-mail: hcheng@yzu.edu.cn
更新日期/Last Update: 2023-05-26