Research on Baseline Extraction Method Based on NMR Spectrogram

This paper proposes a baseline extraction method based on a nuclear magnetic resonance atlas, which uses the DBSCAN algorithm to cluster the data extracted by the nuclear magnetic resonance spectrometer and determines the baseline of the atlas according to the clustering results. In this paper, the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of physics. Conference series Ročník 2303; číslo 1; s. 12080 - 12085
Hlavní autoři: Xiong, ShiYong, Zhu, Fuli, Xu, Daoxu
Médium: Journal Article
Jazyk:angličtina
Vydáno: Bristol IOP Publishing 01.07.2022
Témata:
Algorithms
Clustering
NMR
Nuclear magnetic resonance
Outliers (statistics)
Parameters
Physics
ISSN:1742-6588, 1742-6596
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper proposes a baseline extraction method based on a nuclear magnetic resonance atlas, which uses the DBSCAN algorithm to cluster the data extracted by the nuclear magnetic resonance spectrometer and determines the baseline of the atlas according to the clustering results. In this paper, the core parameters of the DBSCAN algorithm are improved, and the Eps parameter set is selected by combining k-dist and equal interval division. The optimal number of outliers is obtained based on this set, and the baseline value range is set. Finally, the clustering quality is tested by the silhouette coefficient. The final experiment shows that the accuracy and stability of the baseline set based on the improved DBSCAN clustering algorithm are better.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2303/1/012080