Feature extraction and classification for spoken letter recognition using locality preserving partial least squares discriminant analysis

2019 ◽  
Author(s):  
Muhammad Aminu ◽  
Noor Atinah Ahmad ◽  
Norhashidah Awang
Keyword(s):  
Feature Extraction ◽  
Discriminant Analysis ◽  
Least Squares ◽  
Partial Least Squares ◽  
Letter Recognition ◽  
Locality Preserving

Sparse Partial-least-squares Discriminant Analysis for Different Geographical Origins of Salvia miltiorrhiza by 1 H-NMR-based Metabolomics

2013 ◽  
Vol 25 (1) ◽  
pp. 50-58 ◽  
Author(s):  
Miaomiao Jiang ◽  
Chunhua Wang ◽  
Yu Zhang ◽  
Yifan Feng ◽  
Yuefei Wang ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Least Squares ◽  
Partial Least Squares ◽  
Salvia Miltiorrhiza ◽  
H Nmr

scholarly journals 1H-NMR spectroscopy identifies potential biomarkers in serum metabolomic signatures for early stage esophageal squamous cell carcinoma

PeerJ ◽  
2019 ◽  
Vol 7 ◽  
pp. e8151 ◽  
Author(s):  
Yan-Yan Liu ◽  
Zhong-Xian Yang ◽  
Li-Min Ma ◽  
Xu-Qing Wen ◽  
Huan-Lin Ji ◽  
...  
Keyword(s):  
Squamous Cell Carcinoma ◽  
Discriminant Analysis ◽  
Nmr Spectroscopy ◽  
Esophageal Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Least Squares ◽  
Partial Least Squares ◽  
Early Stage ◽  
H Nmr ◽  
Potential Biomarkers

Background Esophageal squamous cell carcinoma (ESCC) is one of the most prevalent types of upper gastrointestinal malignancies. Here, we used 1H nuclear magnetic resonance spectroscopy (1H-NMR) to identify potential serum biomarkers in patients with early stage ESCC. Methods Sixty-five serum samples from early stage ESCC patients (n = 25) and healthy controls (n = 40) were analysed using 1H-NMR spectroscopy. We distinguished between different metabolites through principal component analysis, partial least squares-discriminant analysis, and orthogonal partial least squares-discriminant analysis (OPLS-DA) using SIMCA-P+ version 14.0 software. Receiver operating characteristic (ROC) analysis was conducted to verify potential biomarkers. Results Using OPLS-DA, 31 altered serum metabolites were successfully identified between the groups. Based on the area under the ROC curve (AUROC), and the biomarker panel with AUROC of 0.969, six serum metabolites (α-glucose, choline, glutamine, glutamate, valine, and dihydrothymine) were selected as potential biomarkers for early stage ESCC. Dihydrothymine particularly was selected as a new feasible biomarker associated with tumor occurrence. Conclusions 1H-NMR spectroscopy may be a useful tumour detection approach in identifying useful metabolic ESCC biomarkers for early diagnosis and in the exploration of the molecular pathogenesis of ESCC.

Sign in / Sign up

Export Citation Format

Share Document