https://github.com/airdipu/ultrasonic-flowmeter-diagnostics-kpca
Using Kernel PCA
https://github.com/airdipu/ultrasonic-flowmeter-diagnostics-kpca
Last synced: 3 months ago
JSON representation
Using Kernel PCA
- Host: GitHub
- URL: https://github.com/airdipu/ultrasonic-flowmeter-diagnostics-kpca
- Owner: airdipu
- License: gpl-3.0
- Created: 2021-10-10T09:40:51.000Z (over 3 years ago)
- Default Branch: master
- Last Pushed: 2021-10-11T11:14:39.000Z (over 3 years ago)
- Last Synced: 2025-01-03T20:42:58.469Z (5 months ago)
- Language: MATLAB
- Size: 111 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Ultrasonic-flowmeter-diagnostics-KPCA
Using Kernel PCA using different kernel like gaussian, polynomial, sigmoid, linear and laplacian kernel
# Data
Meter B contains 92 instances of diagnostic parameters for a 4-path liquid USM. It has 52 attributes and 3 classes:
Class '1' - Healthy learning |
Class '2' - Gas injection |
Class '3' - Waxing
(1) -- Profile factor
(2) -- Symmetry
(3) -- Crossflow
(4) -- Swirl angle
(5)-(8) -- Flow velocity in each of the four paths
(9) -- Average flow velocity in all four paths
(10)-(13) -- Speed of sound in each of the four paths
(14) -- Average speed of sound in all four paths
(15)-(22) -- Signal strength at both ends of each of the four paths
(23)-(26) -- Turbulence in each of the four paths
(27) -- Meter performance
(28)-(35) -- Signal quality at both ends of each of the four paths
(36)-(43) -- Gain at both ends of each of the four paths
(44)-(51) -- Transit time at both ends of each of the four paths
(52) -- Class attribute or health state of meter: 1,2,3
Relevant Papers:
K. S. Gyamfi, J. Brusey, A. Hunt, E. Gaura , “Linear dimensionality reduction for classification via a sequential Bayes error minimisation with an application to flow meter diagnostics,†Expert Systems with Applications (IF: 3.928), September 2017
Source:
Kojo Sarfo Gyamfi
Coventry University, UK
gyamfik '@' uni.coventry.ac.uk
Craig Marshall
National Engineering Laboratory, TUV-NEL, UK
Craig.Marsall '@' tuv-sud.co.uk