No Cover Image

Journal article 476 views

Deep Prediction Network Based on Covariance Intersection Fusion for Sensor Data

Hanchi Ren, Yeqing Wang, Huijun Ma Orcid Logo

ICCK Transactions on Intelligent Systematics, Volume: 1, Issue: 1, Pages: 10 - 18

Swansea University Author: Hanchi Ren

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.62762/tis.2024.136898

Abstract

To predict future trends based on the data from sensors is an important technology for many applications, such as the Internet of Things, smart cities, etc. Based on the predicted results, further decisions and system controls can be made. Raw sensor data sets are often complex non-linear data with...

Full description

Published in: ICCK Transactions on Intelligent Systematics
ISSN: 2998-3320 2998-3355
Published: Institute of Central Computation and Knowledge Inc. 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa67603
first_indexed 2024-09-06T13:59:48Z
last_indexed 2025-11-27T05:18:13Z
id cronfa67603
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-11-26T11:38:28.6989235</datestamp><bib-version>v2</bib-version><id>67603</id><entry>2024-09-06</entry><title>Deep Prediction Network Based on Covariance Intersection Fusion for Sensor Data</title><swanseaauthors><author><sid>9e043b899a2b786672a28ed4f864ffcc</sid><firstname>Hanchi</firstname><surname>Ren</surname><name>Hanchi Ren</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-09-06</date><deptcode>MACS</deptcode><abstract>To predict future trends based on the data from sensors is an important technology for many applications, such as the Internet of Things, smart cities, etc. Based on the predicted results, further decisions and system controls can be made. Raw sensor data sets are often complex non-linear data with noise, which results in the difficulty of accurate prediction. This paper proposes a distributed deep prediction network based on a covariance intersection (CI) fusion algorithm in which the deep learning networks, such as long-term and short-term memory networks (LSTM) and gated recurrent unit networks (GRU) are fused by CI fusion algorithm to effectively develop the performance of prediction. Moreover, the variance is obtained to value the prediction results. The model is validated on the real weather dataset in Beijing. The experiments show that LSTM and GRU have their pros and cons for different data, CI fusion can develop the accuracy of the final predictions, and the entire framework has robust prediction results with a reasonable estimated variance.</abstract><type>Journal Article</type><journal>ICCK Transactions on Intelligent Systematics</journal><volume>1</volume><journalNumber>1</journalNumber><paginationStart>10</paginationStart><paginationEnd>18</paginationEnd><publisher>Institute of Central Computation and Knowledge Inc.</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>2998-3320</issnPrint><issnElectronic>2998-3355</issnElectronic><keywords>Deep prediction network, covariance intersection (CI) fusion, sensor data analytics</keywords><publishedDay>25</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-05-25</publishedDate><doi>10.62762/tis.2024.136898</doi><url>https://doi.org/10.62762/tis.2024.136898</url><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders>This work was supported in part by the National Natural Science Foundation of China No. 62173002.</funders><projectreference/><lastEdited>2025-11-26T11:38:28.6989235</lastEdited><Created>2024-09-06T14:37:12.4858025</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Hanchi</firstname><surname>Ren</surname><order>1</order></author><author><firstname>Yeqing</firstname><surname>Wang</surname><order>2</order></author><author><firstname>Huijun</firstname><surname>Ma</surname><orcid>0009-0006-5003-0437</orcid><order>3</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2025-11-26T11:38:28.6989235 v2 67603 2024-09-06 Deep Prediction Network Based on Covariance Intersection Fusion for Sensor Data 9e043b899a2b786672a28ed4f864ffcc Hanchi Ren Hanchi Ren true false 2024-09-06 MACS To predict future trends based on the data from sensors is an important technology for many applications, such as the Internet of Things, smart cities, etc. Based on the predicted results, further decisions and system controls can be made. Raw sensor data sets are often complex non-linear data with noise, which results in the difficulty of accurate prediction. This paper proposes a distributed deep prediction network based on a covariance intersection (CI) fusion algorithm in which the deep learning networks, such as long-term and short-term memory networks (LSTM) and gated recurrent unit networks (GRU) are fused by CI fusion algorithm to effectively develop the performance of prediction. Moreover, the variance is obtained to value the prediction results. The model is validated on the real weather dataset in Beijing. The experiments show that LSTM and GRU have their pros and cons for different data, CI fusion can develop the accuracy of the final predictions, and the entire framework has robust prediction results with a reasonable estimated variance. Journal Article ICCK Transactions on Intelligent Systematics 1 1 10 18 Institute of Central Computation and Knowledge Inc. 2998-3320 2998-3355 Deep prediction network, covariance intersection (CI) fusion, sensor data analytics 25 5 2024 2024-05-25 10.62762/tis.2024.136898 https://doi.org/10.62762/tis.2024.136898 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University Not Required This work was supported in part by the National Natural Science Foundation of China No. 62173002. 2025-11-26T11:38:28.6989235 2024-09-06T14:37:12.4858025 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Hanchi Ren 1 Yeqing Wang 2 Huijun Ma 0009-0006-5003-0437 3
title Deep Prediction Network Based on Covariance Intersection Fusion for Sensor Data
spellingShingle Deep Prediction Network Based on Covariance Intersection Fusion for Sensor Data
Hanchi Ren
title_short Deep Prediction Network Based on Covariance Intersection Fusion for Sensor Data
title_full Deep Prediction Network Based on Covariance Intersection Fusion for Sensor Data
title_fullStr Deep Prediction Network Based on Covariance Intersection Fusion for Sensor Data
title_full_unstemmed Deep Prediction Network Based on Covariance Intersection Fusion for Sensor Data
title_sort Deep Prediction Network Based on Covariance Intersection Fusion for Sensor Data
author_id_str_mv 9e043b899a2b786672a28ed4f864ffcc
author_id_fullname_str_mv 9e043b899a2b786672a28ed4f864ffcc_***_Hanchi Ren
author Hanchi Ren
author2 Hanchi Ren
Yeqing Wang
Huijun Ma
format Journal article
container_title ICCK Transactions on Intelligent Systematics
container_volume 1
container_issue 1
container_start_page 10
publishDate 2024
institution Swansea University
issn 2998-3320
2998-3355
doi_str_mv 10.62762/tis.2024.136898
publisher Institute of Central Computation and Knowledge Inc.
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url https://doi.org/10.62762/tis.2024.136898
document_store_str 0
active_str 0
description To predict future trends based on the data from sensors is an important technology for many applications, such as the Internet of Things, smart cities, etc. Based on the predicted results, further decisions and system controls can be made. Raw sensor data sets are often complex non-linear data with noise, which results in the difficulty of accurate prediction. This paper proposes a distributed deep prediction network based on a covariance intersection (CI) fusion algorithm in which the deep learning networks, such as long-term and short-term memory networks (LSTM) and gated recurrent unit networks (GRU) are fused by CI fusion algorithm to effectively develop the performance of prediction. Moreover, the variance is obtained to value the prediction results. The model is validated on the real weather dataset in Beijing. The experiments show that LSTM and GRU have their pros and cons for different data, CI fusion can develop the accuracy of the final predictions, and the entire framework has robust prediction results with a reasonable estimated variance.
published_date 2024-05-25T17:37:56Z
_version_ 1850690792685830144
score 11.08899

Similar Items