scholarly journals Filter Feature Selection for Unsupervised Clustering of Designer Drugs Using DFT Simulated IR Spectra Data

ACS Omega ◽  
2021 ◽  
Author(s):  
Kedan He
Keyword(s):  
Feature Selection ◽  
Ir Spectra ◽  
Unsupervised Clustering ◽  
Designer Drugs ◽  
Selection For

Application of rough set theory to feature selection for unsupervised clustering

2002 ◽  
Vol 63 (2) ◽  
pp. 155-167 ◽  
Author(s):  
F. Questier ◽  
I. Arnaut-Rollier ◽  
B. Walczak ◽  
D.L. Massart
Keyword(s):  
Feature Selection ◽  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Unsupervised Clustering ◽  
Selection For

scholarly journals Filter feature selection for unsupervised clustering of designer drugs using DFT simulated IR spectra data

2021 ◽  
Author(s):  
Kedan He
Keyword(s):  
Feature Selection ◽  
Unsupervised Clustering ◽  
Designer Drugs ◽  
Full Spectrum ◽  
Molecular Fingerprints ◽  
Spectral Similarity ◽  
Ranking Algorithms ◽  
Statistical Measures ◽  
Selection Algorithms ◽  
Forensic Testing

The rapid emergence of novel psychoactive substances (NPS) poses new challenges and requirements for forensic testing/analysis techniques. This paper aims to explore the application of unsupervised clustering of NPS compounds' infrared spectra. Two statistical measures, Pearson and Spearman, were used to quantify the spectral similarity and to generate the affinity matrices for hierarchical clustering. The correspondence of spectral similarity clustering trees to the commonly used structural/pharmacological categorization was evaluated and compared to the clustering generated using 2D/3D molecular fingerprints. Hybrid model feature selections were applied using different filter-based feature ranking algorithms developed for unsupervised clustering tasks. Since Spearman tends to overestimate the spectral similarity based on the overall pattern of the full spectrum, the clustering result shows the highest degree of improvement from having the non-discriminative features removed. The loading plots of the first two principal components (PCs) of the optimal feature subsets confirmed that the most important vibrational bands contributing to the clustering of NPS compounds were selected using NDFS feature selection algorithms.

Chicken Algorithm Based Feature Selection For Arabic Information Searching System

2019 ◽  
pp. 389
Author(s):  
زينب عبدالأمير ◽  
علياء كريم عبدالحسن
Keyword(s):  
Feature Selection ◽  
Information Searching ◽  
Selection For

scholarly journals Fault Feature Selection for Distribution Network

2021 ◽  
Vol 1881 (2) ◽  
pp. 022080
Author(s):  
Zhiqiang Wu ◽  
Lizong Zhang ◽  
Gang Yu ◽  
Ying Wang ◽  
Tao Huang ◽  
...  
Keyword(s):  
Feature Selection ◽  
Distribution Network ◽  
Selection For
Sign in / Sign up

Export Citation Format

Share Document