Abstract
This paper exploits blind source separation for the purpose of multi-label classification (MLC). The proposed method addresses the multi-label classification problem in two stages, source separation of data consisting of two or more observed classes followed by a single-label classification. This method is evaluated on two data-sets: the new application to electromagnetic interference (EMI) signals that are used for high-voltage power asset condition monitoring, and overlapping handwritten digits (multi-MNIST) for further model validation. Our approach is compared to other deep neural networks such as variational auto-encoder (VAE) and capsule network (CapsNet). Results show high average precision on both data-sets and outperform in most metrics other deep auto-encoding networks that infer label decision from the latent variables distribution.
Original language | English |
---|---|
Title of host publication | 30th European Signal Processing Conference (EUSIPCO 2022): Proceedings |
Publisher | IEEE |
Pages | 1686-1690 |
Number of pages | 5 |
ISBN (Electronic) | 9789082797091 |
ISBN (Print) | 9781665467995 |
Publication status | Published - 18 Oct 2022 |
Event | 30th European Signal Processing Conference - Crowne Plaza, Belgrade, Serbia Duration: 29 Aug 2022 → 2 Sept 2022 https://2022.eusipco.org/ (Link to conference website) |
Publication series
Name | |
---|---|
ISSN (Print) | 2219-5491 |
ISSN (Electronic) | 2076-1465 |
Conference
Conference | 30th European Signal Processing Conference |
---|---|
Abbreviated title | EUSIPCO 2022 |
Country/Territory | Serbia |
City | Belgrade |
Period | 29/08/22 → 2/09/22 |
Internet address |
|
Keywords
- Multi-label classification
- source separation
- variation auto-encoder
- EMI technique
- high-voltage asset diagnosis
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering