Electronic nose dataset for COPD detection from smokers and healthy people through exhaled breath analysis

This dataset is related to the research paper “Wireless electronic smell system for the detection of diseases through the exhaled breath” published in chemical engineering transactions journal (available online from October 1, 2018, https://doi.org/10.3303/cet1868066), and the data paper " Electronic nose dataset for COPD detection from smokers and healthy people through exhaled breath analysis " submitted to Data in Brief journal. For more details read the mentioned articles. The data were acquired with a sampling rate of 500 samples / second and a resolution of the ADC of 24 bits, obtaining measurements of exhaled breath with a length of 4000 data points per sensor through the matrix of 8 sensors or variables (SP-3, MQ-3, TGS 822, MQ-138, MQ-137, TGS 813, TGS-800, MQ-135). In each of the measurements of the In three groups analyzed, two measurements were taken per person with the purpose to obtain a correct measurement gathering and also correlate the exhaled breath measurements of the same person (repeatability). That is the reason why a total of 78 samples were obtained (40 from COPD, 20 from control, 8 from smokers, and 10 from the air. The database is organized in three files COPD, SMOKERS, CONTROL, and AIR in .txt format; which contain the measurements in voltage units and show the characteristic response of a MOS type sensor in the presence of a gas. Additionally, a text file is attached which comprises data such as gender, age, and COPD severity level (estimated) from each person and other relevant data.本数据集关联两项学术成果：其一为发表于《化学工程汇刊》（Chemical Engineering Transactions）的研究论文《无线电子鼻系统用于呼出气检测疾病》，其英文原标题为Wireless electronic smell system for the detection of diseases through the exhaled breath，该论文可于2018年10月1日起在线获取，链接为https://doi.org/10.3303/cet1868066；其二为提交至《数据简报》（Data in Brief）的数据论文《基于呼出气分析的吸烟者与健康人群慢性阻塞性肺疾病（COPD）检测电子鼻数据集》，英文原标题为Electronic nose dataset for COPD detection from smokers and healthy people through exhaled breath analysis。如需了解更多细节，请参阅上述两篇文献。 该数据集的采样率为500样本/秒，模数转换器（ADC）分辨率为24位。通过由8个传感器（SP-3、MQ-3、TGS 822、MQ-138、MQ-137、TGS 813、TGS-800、MQ-135）组成的传感器阵列采集呼出气样本，每个传感器可获取长度为4000个数据点的测量结果。在本次分析的三个组别中，每名受试者均完成两次测量，以保障采样数据的可靠性，并实现同一受试者呼出气测量结果的相关性验证（可重复性分析）。最终共获取78组有效样本，其中慢性阻塞性肺疾病（COPD）组40组、健康对照组20组、吸烟者组8组、空白空气组10组。 该数据库以纯文本（.txt）格式存储为四个文件，分别对应COPD、SMOKERS、CONTROL及AIR组别，文件内存储以电压为单位的测量数据，可体现金属氧化物半导体（MOS）型传感器在气体环境下的特征响应曲线。此外，还附带一个文本文件，包含每名受试者的性别、年龄、估算的COPD严重程度等相关信息。