Belief-Rule-Based System with Self-organizing and Multi-temporal Modeling for Sensor-based Human Activity Recognition

Long-Hao Yang; Fei-Fei Ye; CD Nugent; J. Liu; Ying-Ming Wang

doi:10.1109/JBHI.2024.3485871

Belief-Rule-Based System with Self-organizing and Multi-temporal Modeling for Sensor-based Human Activity Recognition

Long-Hao Yang
, Fei-Fei Ye
, CD Nugent
, J. Liu
, Ying-Ming Wang

Research output: Contribution to journal › Article › peer-review

79 Downloads (Pure)

Abstract

Smart environment is an efficient and cost-effective way to afford intelligent supports for the elderly people. Human activity recognition is a crucial aspect of the research field of smart environments, and it has attracted widespread attention lately. The goal of this study is to develop an effective sensor-based human activity recognition model based on the belief-rule-based system (BRBS), which is one of representative rule-based expert systems. Specially, a new belief rule base (BRB) modeling approach is proposed by taking into account the self- organizing rule generation method and the multi-temporal rule representation scheme, in order to address the problem of combination explosion that existed in the traditional BRB modelling procedure and the time correlation found in continuous sensor data in chronological order. The new BRB modeling approach is so called self-organizing and multi-temporal BRB (SOMT-BRB) modeling procedure. A case study is further deducted to validate the effectiveness of the SOMT-BRB modeling procedure. By comparing with some conventional BRBSs and classical activity recognition models, the results show a significant improvement of the BRBS in terms of the number of belief rules, modelling efficiency, and activity recognition accuracy.

Original language	English
Pages (from-to)	1062-1073
Number of pages	12
Journal	IEEE Journal of Biomedical and Health Informatics
Volume	29
Issue number	2
Early online date	24 Oct 2024
DOIs	https://doi.org/10.1109/JBHI.2024.3485871
Publication status	Published (in print/issue) - 6 Feb 2025

Bibliographical note

Publisher Copyright:
© 2013 IEEE.

Funding

This work was supported by the National Natural Science Foundation of China under Grant 72471061, Grant 72001043 and Grant 72301071, in part by the Natural Science Foundation of Fujian Province, China, under Grant 2022J01178, and in part by the Humanities and Social Science Foundation of the Ministry of Education, China, under Grant 24YJA630116 and Grant 22YJAZH151. This work was supported by the National Natural Science Foundation of China (Nos. 72001043 and 72301071), the Natural Science Foundation of Fujian Province, China (Nos. 2020J05122 and 2022J01178), and the Humanities and Social Science Foundation of the Ministry of Education, China (No. 20YJC630188).

Funders	Funder number
22YJAZH151, 24YJA630116, 20YJC630188
2022J01178, 2020J05122
National Natural Science Foundation of China	72001043, 72471061, 72301071
National Natural Science Foundation of China

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 8 Decent Work and Economic Growth

Keywords

Data models
Human activity recognition
Explosions
feature extraction
Correlation
Accuracy
Bioninformatics
Vectors
Robustness
Predictive models
Combination explosion problem
Time correlation
Activity recognition
Belief rule base
Sensor
combination explosion problem
time correlation
sensor
activity recognition

Access to Document

10.1109/JBHI.2024.3485871

Accepted versionAuthor Accepted Manuscript, 1.38 MBLicence: Unspecified

Cite this

@article{4c6d3d68889847e4879e12721cec6938,

title = "Belief-Rule-Based System with Self-organizing and Multi-temporal Modeling for Sensor-based Human Activity Recognition",

abstract = "Smart environment is an efficient and cost-effective way to afford intelligent supports for the elderly people. Human activity recognition is a crucial aspect of the research field of smart environments, and it has attracted widespread attention lately. The goal of this study is to develop an effective sensor-based human activity recognition model based on the belief-rule-based system (BRBS), which is one of representative rule-based expert systems. Specially, a new belief rule base (BRB) modeling approach is proposed by taking into account the self- organizing rule generation method and the multi-temporal rule representation scheme, in order to address the problem of combination explosion that existed in the traditional BRB modelling procedure and the time correlation found in continuous sensor data in chronological order. The new BRB modeling approach is so called self-organizing and multi-temporal BRB (SOMT-BRB) modeling procedure. A case study is further deducted to validate the effectiveness of the SOMT-BRB modeling procedure. By comparing with some conventional BRBSs and classical activity recognition models, the results show a significant improvement of the BRBS in terms of the number of belief rules, modelling efficiency, and activity recognition accuracy.",

keywords = "Data models, Human activity recognition, Explosions, feature extraction, Correlation, Accuracy, Bioninformatics, Vectors, Robustness, Predictive models, Combination explosion problem, Time correlation, Activity recognition, Belief rule base, Sensor, combination explosion problem, time correlation, sensor, activity recognition",

author = "Long-Hao Yang and Fei-Fei Ye and CD Nugent and J. Liu and Ying-Ming Wang",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2025",

month = feb,

day = "6",

doi = "10.1109/JBHI.2024.3485871",

language = "English",

volume = "29",

pages = "1062--1073",

journal = "IEEE Journal of Biomedical and Health Informatics",

issn = "2168-2194",

publisher = "IEEE",

number = "2",

}

TY - JOUR

T1 - Belief-Rule-Based System with Self-organizing and Multi-temporal Modeling for Sensor-based Human Activity Recognition

AU - Yang, Long-Hao

AU - Ye, Fei-Fei

AU - Nugent, CD

AU - Liu, J.

AU - Wang, Ying-Ming

PY - 2025/2/6

Y1 - 2025/2/6

N2 - Smart environment is an efficient and cost-effective way to afford intelligent supports for the elderly people. Human activity recognition is a crucial aspect of the research field of smart environments, and it has attracted widespread attention lately. The goal of this study is to develop an effective sensor-based human activity recognition model based on the belief-rule-based system (BRBS), which is one of representative rule-based expert systems. Specially, a new belief rule base (BRB) modeling approach is proposed by taking into account the self- organizing rule generation method and the multi-temporal rule representation scheme, in order to address the problem of combination explosion that existed in the traditional BRB modelling procedure and the time correlation found in continuous sensor data in chronological order. The new BRB modeling approach is so called self-organizing and multi-temporal BRB (SOMT-BRB) modeling procedure. A case study is further deducted to validate the effectiveness of the SOMT-BRB modeling procedure. By comparing with some conventional BRBSs and classical activity recognition models, the results show a significant improvement of the BRBS in terms of the number of belief rules, modelling efficiency, and activity recognition accuracy.

AB - Smart environment is an efficient and cost-effective way to afford intelligent supports for the elderly people. Human activity recognition is a crucial aspect of the research field of smart environments, and it has attracted widespread attention lately. The goal of this study is to develop an effective sensor-based human activity recognition model based on the belief-rule-based system (BRBS), which is one of representative rule-based expert systems. Specially, a new belief rule base (BRB) modeling approach is proposed by taking into account the self- organizing rule generation method and the multi-temporal rule representation scheme, in order to address the problem of combination explosion that existed in the traditional BRB modelling procedure and the time correlation found in continuous sensor data in chronological order. The new BRB modeling approach is so called self-organizing and multi-temporal BRB (SOMT-BRB) modeling procedure. A case study is further deducted to validate the effectiveness of the SOMT-BRB modeling procedure. By comparing with some conventional BRBSs and classical activity recognition models, the results show a significant improvement of the BRBS in terms of the number of belief rules, modelling efficiency, and activity recognition accuracy.

KW - Data models

KW - Human activity recognition

KW - Explosions

KW - feature extraction

KW - Correlation

KW - Accuracy

KW - Bioninformatics

KW - Vectors

KW - Robustness

KW - Predictive models

KW - Combination explosion problem

KW - Time correlation

KW - Activity recognition

KW - Belief rule base

KW - Sensor

KW - combination explosion problem

KW - time correlation

KW - sensor

KW - activity recognition

UR - https://pure.ulster.ac.uk/en/publications/4c6d3d68-8898-47e4-879e-12721cec6938

UR - https://www.scopus.com/pages/publications/85207872151

U2 - 10.1109/JBHI.2024.3485871

DO - 10.1109/JBHI.2024.3485871

M3 - Article

C2 - 39446535

SN - 2168-2194

VL - 29

SP - 1062

EP - 1073

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

IS - 2

ER -

Belief-Rule-Based System with Self-organizing and Multi-temporal Modeling for Sensor-based Human Activity Recognition

Abstract

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this