帕金森病（PD）生物医学语音数据集

该数据集是由牛津大学的Max Little与丹佛科罗拉多语音和语音中心合作录制的。最初的研究发表了针对一般语音障碍的特征提取方法。 Data Set Information: 该数据集由31人的一系列生物医学语音测量组成，其中23人患有帕金森病（PD）。表中的每一列都是一个特定的语音测量值，每一行对应这些人195个语音记录中的一个（“名称”列）。数据的主要目的是根据“状态”栏区分健康人和帕金森病患者，健康状态栏设置为0，帕金森病状态栏设置为1。 数据为ASCII CSV格式。CSV文件的行包含对应于一个语音录制的实例。每位患者大约有六次录音，患者姓名在第一列中。有关更多信息或评论，请联系Max Little（littlem'@'robots.ox.ac.uk）。 更多详细信息包含在以下参考中——如果您使用此数据集，请引用：Max A.Little，Patrick E.McSharry，Eric J.Hunter，Lorraine O.Ramig（2008），“帕金森病远程监测中发音困难测量的适用性”，IEEE生物医学工程学报（即将出版）。 Attribute Information: 矩阵列条目（属性）： 名称-ASCII主题名称和记录编号 MDVP:Fo（Hz）-平均人声基频 MDVP:Fhi（Hz）-最大人声基频 MDVP:Flo（Hz）-最低人声基频 MDVP:Jitter（%），MDVP:Jitter（Abs），MDVP:RAP，MDVP:PPQ，Jitter:DDP-基频变化的几种度量 MDVP:Shimmer，MDVP:Shimmer（dB），Shimmer:APQ3，Shimmer:APQ5，MDVP:APQ，Shimmer:DDA-振幅变化的几种度量 NHR，HNR-声音中噪音与音调成分之比的两种测量方法 状态-受试者的健康状态（一）-帕金森病（零）-健康RPDE，D2-两个非线性动力学复杂性度量信号分形标度指数展布1、展布2、PPE-基频变化的三种非线性测量 Relevant Papers: N/A Citation Request: If you use this dataset, please cite the following paper: 'Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection', Little MA, McSharry PE, Roberts SJ, Costello DAE, Moroz IM. BioMedical Engineering onLine 2007, 6:23 (26 June 2007)

This dataset was recorded in collaboration between Max Little of the University of Oxford and the Colorado Center for Speech and Voice in Denver. The original study published feature extraction methods for general voice disorders.

**Data Set Information:**
This dataset comprises a series of biomedical voice measurements from 31 participants, 23 of whom have been diagnosed with Parkinson's Disease (PD). Each column in the table represents a specific voice measurement, while each row corresponds to one of the 195 voice recordings from these individuals (identified via the "name" column). The primary objective of this dataset is to differentiate between healthy controls and Parkinson's patients using the "status" column, where a value of 0 indicates a healthy individual and 1 indicates a Parkinson's patient.

The data is provided in ASCII CSV format. Each row in the CSV file corresponds to an instance of a single voice recording. Each patient has approximately six recordings, with the patient's name listed in the first column. For additional information or comments, please contact Max Little at littlem'@'robots.ox.ac.uk.

Further details are available in the following reference; please cite this work if you use this dataset: Max A. Little, Patrick E. McSharry, Eric J. Hunter, Lorraine O. Ramig (2008), "Feasibility of Voice Measures for Remote Monitoring of Parkinson's Disease", *IEEE Transactions on Biomedical Engineering* (in press).

**Attribute Information:**
Matrix column entries (attributes):
- **name**: ASCII subject name and recording number
- **MDVP:Fo(Hz)**: Average vocal fundamental frequency
- **MDVP:Fhi(Hz)**: Maximum vocal fundamental frequency
- **MDVP:Flo(Hz)**: Minimum vocal fundamental frequency
- **MDVP:Jitter(%), MDVP:Jitter(Abs), MDVP:RAP, MDVP:PPQ, Jitter:DDP**: Several measures of variation in fundamental frequency
- **MDVP:Shimmer, MDVP:Shimmer(dB), Shimmer:APQ3, Shimmer:APQ5, MDVP:APQ, Shimmer:DDA**: Several measures of variation in amplitude
- **NHR, HNR**: Two measures of the ratio of noise to tonal components in the voice
- **status**: Health status of the subject (1 = Parkinson's Disease, 0 = Healthy)
- **RPDE, D2**: Two nonlinear dynamical complexity measures
- **Signal fractal scaling exponent, Spread 1, Spread 2, PPE**: Three nonlinear measures of fundamental frequency variation

**Relevant Papers:** N/A

**Citation Request:** If you use this dataset, please cite the following paper: 'Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection', Little MA, McSharry PE, Roberts SJ, Costello DAE, Moroz IM. *BioMedical Engineering Online* 2007, 6:23 (26 June 2007)

搜集汇总

背景与挑战

背景概述

该数据集包含31人的生物医学语音测量数据，其中23人为帕金森病患者，旨在通过语音特征区分健康与患病状态。数据以CSV格式存储，包含多种语音测量指标，适用于帕金森病的语音障碍研究。