Machine Learning Based Flow Regime Identification using Ultrasonic Doppler Data and Feature Relevance Determination

•An objective flow regime classifier was constructed from the discrete wavelet transform of ultrasonic data.•Anisotropic Kernel PCA feature extraction was optimized with genetic algorithm.•Explainability is improved by revealing the most significant input features and visualizing results as virtual...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Digital Chemical Engineering Jg. 3; S. 100024
Hauptverfasser:	Roxas  II, Ricardo, Evangelista, Matthew Angelo, Sombillo, Jalen Aeron, Nnabuife, Somtochukwu Godfrey, Pilario, Karl Ezra
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.06.2022 Elsevier
Schlagworte:	Clustering Discrete Wavelet Transform Feature Relevance Genetic Algorithm Kernel PCA Virtual Flow Regime Map Virtual Flow Regime Map Kernel PCA Clustering Discrete Wavelet Transform Feature Relevance Genetic Algorithm
ISSN:	2772-5081, 2772-5081
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!