Datasets
Standard Dataset
Electronic nose dataset for recognition of eight liquor types
- Citation Author(s):
-
Qing-HaoMeng
Institute of Robotics and Autonomous Systems, School of Electrical and Information Engineering, Tianjin UniversityHui-RangHouInstitute of Robotics and Autonomous Systems, School of Electrical and Information Engineering, Tianjin University - Submitted by:
- Hui-Rang Hou
- Last updated:
- Tue, 05/17/2022 - 22:18
- DOI:
- 10.21227/7zch-5585
- Research Article Link:
- License:
535 Views- Categories:
Abstract
The data set collected using a self-designed electronic nose (e-nose) involved eight Chinese liquor types, which are LanJinJiu with 38% alcohol concentration (LJJ38), LanJinJiu with 48% alcohol concentration (LJJ48), DaoHuaXiang with 42% alcohol concentration (DHX), LuZhouLaoJiao with 38% alcohol concentration (LZLJ), MianZhuDaQu with 38% alcohol concentration (MZDQ), QingJiu with 38% alcohol concentration (QJ), ShiLiXiang (SLX) with 40% alcohol concentration and BianFengHu with 40% alcohol concentration (BFH).
Type and number of the used gas sensors: 10 metal oxide sensors (MOS), namely TGS2602, TGS2611, TGS2620, TGS880, MiCS-5121, MiCS-5521, MiCS-5524, MiCS-5526, MP502 and WSP2110
Sampling rate: 1k Hz
Sampling time: 360 s
Sample size: Each type of liquor contains 30 samples, and there are 240 (30×8) samples for 8 liquor types in total.
Each liquor sample occupies a ‘.TXT’ file, and the size of a liquor sample is 360000 (number of sampling points) × 10 (number of sensors).
Comments
Good dataset
good