Multi-Label Classification with Optimal Thresholding for Multi-Composition Spectroscopic Analysis

Files

Gan_Luyun_MachLearnKnowlExtra_2019.pdf (1.56 MB)

Date

2019

Authors

Gan, Luyun
Yuen, Brosnan
Lu, Tao

Journal Title

Journal ISSN

Volume Title

Publisher

Machine Learning & Knowledge Extraction

Abstract

In this paper, we implement multi-label neural networks with optimal thresholding to identify gas species among a multiple gas mixture in a cluttered environment. Using infrared absorption spectroscopy and tested on synthesized spectral datasets, our approach outperforms conventional binary relevance-partial least squares discriminant analysis when the signal-to-noise ratio and training sample size are sufficient.

Description

Keywords

multi-label classification, infrared absorption spectroscopy, supervised learning, feedforward neural networks, binary relevance

Citation

Gan, L. & Yuen, B. & Lu, T. (2019). Multi-Label Classification with Optimal Thresholding for Multi-Composition Spectroscopic Analysis. Machine Learning & Knowledge Extraction, 1(4), 1084-1099. https://doi.org/10.3390/make1040061

URI

https://doi.org/10.3390/make1040061
 http://hdl.handle.net/1828/11389

Collections

Faculty Publications (Engineering)
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.