Cargando…

A Novel Conflict Management Method Based on Uncertainty of Evidence and Reinforcement Learning for Multi-Sensor Information Fusion

Dempster–Shafer theory (DST), which is widely used in information fusion, can process uncertain information without prior information; however, when the evidence to combine is highly conflicting, it may lead to counter-intuitive results. Moreover, the existing methods are not strong enough to proces...

Descripción completa

Detalles Bibliográficos
Autores principales: Huang, Fanghui, Zhang, Yu, Wang, Ziqing, Deng, Xinyang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8469061/
https://www.ncbi.nlm.nih.gov/pubmed/34573847
http://dx.doi.org/10.3390/e23091222
_version_ 1784573833666101248
author Huang, Fanghui
Zhang, Yu
Wang, Ziqing
Deng, Xinyang
author_facet Huang, Fanghui
Zhang, Yu
Wang, Ziqing
Deng, Xinyang
author_sort Huang, Fanghui
collection PubMed
description Dempster–Shafer theory (DST), which is widely used in information fusion, can process uncertain information without prior information; however, when the evidence to combine is highly conflicting, it may lead to counter-intuitive results. Moreover, the existing methods are not strong enough to process real-time and online conflicting evidence. In order to solve the above problems, a novel information fusion method is proposed in this paper. The proposed method combines the uncertainty of evidence and reinforcement learning (RL). Specifically, we consider two uncertainty degrees: the uncertainty of the original basic probability assignment (BPA) and the uncertainty of its negation. Then, Deng entropy is used to measure the uncertainty of BPAs. Two uncertainty degrees are considered as the condition of measuring information quality. Then, the adaptive conflict processing is performed by RL and the combination two uncertainty degrees. The next step is to compute Dempster’s combination rule (DCR) to achieve multi-sensor information fusion. Finally, a decision scheme based on correlation coefficient is used to make the decision. The proposed method not only realizes adaptive conflict evidence management, but also improves the accuracy of multi-sensor information fusion and reduces information loss. Numerical examples verify the effectiveness of the proposed method.
format Online
Article
Text
id pubmed-8469061
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-84690612021-09-27 A Novel Conflict Management Method Based on Uncertainty of Evidence and Reinforcement Learning for Multi-Sensor Information Fusion Huang, Fanghui Zhang, Yu Wang, Ziqing Deng, Xinyang Entropy (Basel) Article Dempster–Shafer theory (DST), which is widely used in information fusion, can process uncertain information without prior information; however, when the evidence to combine is highly conflicting, it may lead to counter-intuitive results. Moreover, the existing methods are not strong enough to process real-time and online conflicting evidence. In order to solve the above problems, a novel information fusion method is proposed in this paper. The proposed method combines the uncertainty of evidence and reinforcement learning (RL). Specifically, we consider two uncertainty degrees: the uncertainty of the original basic probability assignment (BPA) and the uncertainty of its negation. Then, Deng entropy is used to measure the uncertainty of BPAs. Two uncertainty degrees are considered as the condition of measuring information quality. Then, the adaptive conflict processing is performed by RL and the combination two uncertainty degrees. The next step is to compute Dempster’s combination rule (DCR) to achieve multi-sensor information fusion. Finally, a decision scheme based on correlation coefficient is used to make the decision. The proposed method not only realizes adaptive conflict evidence management, but also improves the accuracy of multi-sensor information fusion and reduces information loss. Numerical examples verify the effectiveness of the proposed method. MDPI 2021-09-17 /pmc/articles/PMC8469061/ /pubmed/34573847 http://dx.doi.org/10.3390/e23091222 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Huang, Fanghui
Zhang, Yu
Wang, Ziqing
Deng, Xinyang
A Novel Conflict Management Method Based on Uncertainty of Evidence and Reinforcement Learning for Multi-Sensor Information Fusion
title A Novel Conflict Management Method Based on Uncertainty of Evidence and Reinforcement Learning for Multi-Sensor Information Fusion
title_full A Novel Conflict Management Method Based on Uncertainty of Evidence and Reinforcement Learning for Multi-Sensor Information Fusion
title_fullStr A Novel Conflict Management Method Based on Uncertainty of Evidence and Reinforcement Learning for Multi-Sensor Information Fusion
title_full_unstemmed A Novel Conflict Management Method Based on Uncertainty of Evidence and Reinforcement Learning for Multi-Sensor Information Fusion
title_short A Novel Conflict Management Method Based on Uncertainty of Evidence and Reinforcement Learning for Multi-Sensor Information Fusion
title_sort novel conflict management method based on uncertainty of evidence and reinforcement learning for multi-sensor information fusion
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8469061/
https://www.ncbi.nlm.nih.gov/pubmed/34573847
http://dx.doi.org/10.3390/e23091222
work_keys_str_mv AT huangfanghui anovelconflictmanagementmethodbasedonuncertaintyofevidenceandreinforcementlearningformultisensorinformationfusion
AT zhangyu anovelconflictmanagementmethodbasedonuncertaintyofevidenceandreinforcementlearningformultisensorinformationfusion
AT wangziqing anovelconflictmanagementmethodbasedonuncertaintyofevidenceandreinforcementlearningformultisensorinformationfusion
AT dengxinyang anovelconflictmanagementmethodbasedonuncertaintyofevidenceandreinforcementlearningformultisensorinformationfusion
AT huangfanghui novelconflictmanagementmethodbasedonuncertaintyofevidenceandreinforcementlearningformultisensorinformationfusion
AT zhangyu novelconflictmanagementmethodbasedonuncertaintyofevidenceandreinforcementlearningformultisensorinformationfusion
AT wangziqing novelconflictmanagementmethodbasedonuncertaintyofevidenceandreinforcementlearningformultisensorinformationfusion
AT dengxinyang novelconflictmanagementmethodbasedonuncertaintyofevidenceandreinforcementlearningformultisensorinformationfusion