Saved in:
Bibliographic Details
Main Authors: Couchard, Darius, Olarte, Oscar, Haelterman, Rob
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.13183
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909781608890368
author Couchard, Darius
Olarte, Oscar
Haelterman, Rob
author_facet Couchard, Darius
Olarte, Oscar
Haelterman, Rob
contents Gas Chromatography coupled with Ion Mobility Spectrometry (GC-IMS) is a dual-separation analytical technique widely used for identifying components in gaseous samples by separating and analysing the arrival times of their constituent species. Data generated by GC-IMS is typically represented as two-dimensional spectra, providing rich information but posing challenges for data-driven analysis due to limited labelled datasets. This study introduces a novel method for generating synthetic 2D spectra using a deep learning framework based on Autoencoders. Although applied here to GC-IMS data, the approach is broadly applicable to any two-dimensional spectral measurements where labelled data are scarce. While performing component classification over a labelled dataset of GC-IMS records, the addition of synthesized records significantly has improved the classification performance, demonstrating the method's potential for overcoming dataset limitations in machine learning frameworks.
format Preprint
id arxiv_https___arxiv_org_abs_2502_13183
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Synthetic generation of 2D data records based on Autoencoders
Couchard, Darius
Olarte, Oscar
Haelterman, Rob
Image and Video Processing
Machine Learning
Gas Chromatography coupled with Ion Mobility Spectrometry (GC-IMS) is a dual-separation analytical technique widely used for identifying components in gaseous samples by separating and analysing the arrival times of their constituent species. Data generated by GC-IMS is typically represented as two-dimensional spectra, providing rich information but posing challenges for data-driven analysis due to limited labelled datasets. This study introduces a novel method for generating synthetic 2D spectra using a deep learning framework based on Autoencoders. Although applied here to GC-IMS data, the approach is broadly applicable to any two-dimensional spectral measurements where labelled data are scarce. While performing component classification over a labelled dataset of GC-IMS records, the addition of synthesized records significantly has improved the classification performance, demonstrating the method's potential for overcoming dataset limitations in machine learning frameworks.
title Synthetic generation of 2D data records based on Autoencoders
topic Image and Video Processing
Machine Learning
url https://arxiv.org/abs/2502.13183