Signal Separation Based on Knowledge Representation

The separation of mixed signals typically requires appropriate prior assumptions, while traditional signal separation methods struggle to describe the differences in separation targets with significant features. This paper proposes a signal separation framework based on knowledge representation, whe...

Full description

Saved in:
Bibliographic Details
Main Authors: Cai Lu, Xuyang Zou, Jingjing Zong
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/6/3319
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343385760956416
author Cai Lu
Xuyang Zou
Jingjing Zong
author_facet Cai Lu
Xuyang Zou
Jingjing Zong
author_sort Cai Lu
collection DOAJ
description The separation of mixed signals typically requires appropriate prior assumptions, while traditional signal separation methods struggle to describe the differences in separation targets with significant features. This paper proposes a signal separation framework based on knowledge representation, where separation targets are represented with knowledge, guiding the branches of autoencoders for signal separation. Firstly, under the proposed knowledge representation framework, corresponding knowledge representations are obtained based on observed mixed signals. Secondly, the number of branches of the autoencoder is determined based on the number of separation target signals. Then, utilizing the results of knowledge representation, a branch autoencoder network is constructed, with branches guided by knowledge to achieve the separation of target sub-signals. Finally, a self-encoding network architecture is constructed with a combination of observation signal reconstruction error and knowledge-guided error constraints. Through numerical simulations on a layered velocity model, the Marmousi-II geological model, and the MNIST dataset, the proposed method is validated by comparing the numerical energy differences between predictions and ground truths, demonstrating its effectiveness under both limited and ample data conditions.
format Article
id doaj-art-3d53b87d50524c90b09a02f85b918310
institution Kabale University
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-3d53b87d50524c90b09a02f85b9183102025-08-20T03:43:01ZengMDPI AGApplied Sciences2076-34172025-03-01156331910.3390/app15063319Signal Separation Based on Knowledge RepresentationCai Lu0Xuyang Zou1Jingjing Zong2School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, ChinaThe separation of mixed signals typically requires appropriate prior assumptions, while traditional signal separation methods struggle to describe the differences in separation targets with significant features. This paper proposes a signal separation framework based on knowledge representation, where separation targets are represented with knowledge, guiding the branches of autoencoders for signal separation. Firstly, under the proposed knowledge representation framework, corresponding knowledge representations are obtained based on observed mixed signals. Secondly, the number of branches of the autoencoder is determined based on the number of separation target signals. Then, utilizing the results of knowledge representation, a branch autoencoder network is constructed, with branches guided by knowledge to achieve the separation of target sub-signals. Finally, a self-encoding network architecture is constructed with a combination of observation signal reconstruction error and knowledge-guided error constraints. Through numerical simulations on a layered velocity model, the Marmousi-II geological model, and the MNIST dataset, the proposed method is validated by comparing the numerical energy differences between predictions and ground truths, demonstrating its effectiveness under both limited and ample data conditions.https://www.mdpi.com/2076-3417/15/6/3319signal separationknowledge representationdeep learning
spellingShingle Cai Lu
Xuyang Zou
Jingjing Zong
Signal Separation Based on Knowledge Representation
Applied Sciences
signal separation
knowledge representation
deep learning
title Signal Separation Based on Knowledge Representation
title_full Signal Separation Based on Knowledge Representation
title_fullStr Signal Separation Based on Knowledge Representation
title_full_unstemmed Signal Separation Based on Knowledge Representation
title_short Signal Separation Based on Knowledge Representation
title_sort signal separation based on knowledge representation
topic signal separation
knowledge representation
deep learning
url https://www.mdpi.com/2076-3417/15/6/3319
work_keys_str_mv AT cailu signalseparationbasedonknowledgerepresentation
AT xuyangzou signalseparationbasedonknowledgerepresentation
AT jingjingzong signalseparationbasedonknowledgerepresentation