Data Fusion for Human Activity Recognition Based on RF Sensing and IMU Sensor

Zheqi Yu; Adnan Zahid; William Taylor; Hasan Abbas; Hadi Heidari; Muhammad A. Imran; Qammer H. Abbasi

doi:10.1007/978-3-030-95593-9_1

Data Fusion for Human Activity Recognition Based on RF Sensing and IMU Sensor

Zheqi Yu^*, Adnan Zahid, William Taylor, Hasan Abbas, Hadi Heidari, Muhammad A. Imran, Qammer H. Abbasi

^*Corresponding author for this work

School of Engineering & Physical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

This paper proposes a new data fusion method, which uses the designed construction matrix to fuse sensor and USRP data to realise Human Activity Recognition. At this point, Inertial Measurement Unit sensors and Universal Software-defined Radio Peripherals are used to collect human activities signals separately. In order to avoid the incompatibility problem with different collection devices, such as different sampling frequency caused inconsistency time axis. The Principal Component Analysis processing the fused data to dimension reduction without time that is performed to extract the time unrelated 5 × 5 feature matrix to represent corresponding activities. There are explores data fusion method between multiple devices and ensures accuracy without dropping. The technique can be extended to other types of hardware signal for data fusion.

Original language	English
Title of host publication	Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. BODYNETS 2021
Editors	Masood Ur Rehman, Ahmed Zoha
Publisher	Springer
Pages	3-14
Number of pages	12
ISBN (Electronic)	9783030955939
ISBN (Print)	9783030955922
DOIs	https://doi.org/10.1007/978-3-030-95593-9_1
Publication status	Published - 11 Feb 2022
Event	16th EAI International Conference on Body Area Networks 2021 - Virtual, Online Duration: 25 Dec 2021 → 26 Dec 2021

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering
Volume	420
ISSN (Print)	1867-8211
ISSN (Electronic)	1867-822X

Conference

Conference	16th EAI International Conference on Body Area Networks 2021
Abbreviated title	BODYNETS 2021
City	Virtual, Online
Period	25/12/21 → 26/12/21

Keywords

Artificial intelligence
Data fusion
Human activity recognition
Signal processing

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1007/978-3-030-95593-9_1

Cite this

Yu, Z., Zahid, A., Taylor, W., Abbas, H., Heidari, H., Imran, M. A., & Abbasi, Q. H. (2022). Data Fusion for Human Activity Recognition Based on RF Sensing and IMU Sensor. In M. Ur Rehman, & A. Zoha (Eds.), Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. BODYNETS 2021 (pp. 3-14). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering; Vol. 420). Springer. https://doi.org/10.1007/978-3-030-95593-9_1

Yu, Zheqi ; Zahid, Adnan ; Taylor, William et al. / Data Fusion for Human Activity Recognition Based on RF Sensing and IMU Sensor. Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. BODYNETS 2021. editor / Masood Ur Rehman ; Ahmed Zoha. Springer, 2022. pp. 3-14 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering).

@inproceedings{fe96598db15c4008aaefc9a562e152e6,

title = "Data Fusion for Human Activity Recognition Based on RF Sensing and IMU Sensor",

abstract = "This paper proposes a new data fusion method, which uses the designed construction matrix to fuse sensor and USRP data to realise Human Activity Recognition. At this point, Inertial Measurement Unit sensors and Universal Software-defined Radio Peripherals are used to collect human activities signals separately. In order to avoid the incompatibility problem with different collection devices, such as different sampling frequency caused inconsistency time axis. The Principal Component Analysis processing the fused data to dimension reduction without time that is performed to extract the time unrelated 5 × 5 feature matrix to represent corresponding activities. There are explores data fusion method between multiple devices and ensures accuracy without dropping. The technique can be extended to other types of hardware signal for data fusion.",

keywords = "Artificial intelligence, Data fusion, Human activity recognition, Signal processing",

author = "Zheqi Yu and Adnan Zahid and William Taylor and Hasan Abbas and Hadi Heidari and Imran, {Muhammad A.} and Abbasi, {Qammer H.}",

note = "Funding Information: Acknowledgements. Zheqi Yu is funded by Joint industrial scholarship (Ref:308987) between the University of Glasgow and Transreport London Ltd. Authors would also like to thank Francesco Fioranelli and Haobo Li for supporting Human Activities Dataset. Publisher Copyright: {\textcopyright} 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.; 16th EAI International Conference on Body Area Networks 2021, BODYNETS 2021 ; Conference date: 25-12-2021 Through 26-12-2021",

year = "2022",

month = feb,

day = "11",

doi = "10.1007/978-3-030-95593-9_1",

language = "English",

isbn = "9783030955922",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering",

publisher = "Springer",

pages = "3--14",

editor = "{Ur Rehman}, Masood and Ahmed Zoha",

booktitle = "Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. BODYNETS 2021",

}

Yu, Z, Zahid, A, Taylor, W, Abbas, H, Heidari, H, Imran, MA & Abbasi, QH 2022, Data Fusion for Human Activity Recognition Based on RF Sensing and IMU Sensor. in M Ur Rehman & A Zoha (eds), Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. BODYNETS 2021. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, vol. 420, Springer, pp. 3-14, 16th EAI International Conference on Body Area Networks 2021, Virtual, Online, 25/12/21. https://doi.org/10.1007/978-3-030-95593-9_1

Data Fusion for Human Activity Recognition Based on RF Sensing and IMU Sensor. / Yu, Zheqi; Zahid, Adnan; Taylor, William et al.
Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. BODYNETS 2021. ed. / Masood Ur Rehman; Ahmed Zoha. Springer, 2022. p. 3-14 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering; Vol. 420).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Data Fusion for Human Activity Recognition Based on RF Sensing and IMU Sensor

AU - Yu, Zheqi

AU - Zahid, Adnan

AU - Taylor, William

AU - Abbas, Hasan

AU - Heidari, Hadi

AU - Imran, Muhammad A.

AU - Abbasi, Qammer H.

N1 - Funding Information: Acknowledgements. Zheqi Yu is funded by Joint industrial scholarship (Ref:308987) between the University of Glasgow and Transreport London Ltd. Authors would also like to thank Francesco Fioranelli and Haobo Li for supporting Human Activities Dataset. Publisher Copyright: © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

PY - 2022/2/11

Y1 - 2022/2/11

N2 - This paper proposes a new data fusion method, which uses the designed construction matrix to fuse sensor and USRP data to realise Human Activity Recognition. At this point, Inertial Measurement Unit sensors and Universal Software-defined Radio Peripherals are used to collect human activities signals separately. In order to avoid the incompatibility problem with different collection devices, such as different sampling frequency caused inconsistency time axis. The Principal Component Analysis processing the fused data to dimension reduction without time that is performed to extract the time unrelated 5 × 5 feature matrix to represent corresponding activities. There are explores data fusion method between multiple devices and ensures accuracy without dropping. The technique can be extended to other types of hardware signal for data fusion.

AB - This paper proposes a new data fusion method, which uses the designed construction matrix to fuse sensor and USRP data to realise Human Activity Recognition. At this point, Inertial Measurement Unit sensors and Universal Software-defined Radio Peripherals are used to collect human activities signals separately. In order to avoid the incompatibility problem with different collection devices, such as different sampling frequency caused inconsistency time axis. The Principal Component Analysis processing the fused data to dimension reduction without time that is performed to extract the time unrelated 5 × 5 feature matrix to represent corresponding activities. There are explores data fusion method between multiple devices and ensures accuracy without dropping. The technique can be extended to other types of hardware signal for data fusion.

KW - Artificial intelligence

KW - Data fusion

KW - Human activity recognition

KW - Signal processing

UR - http://www.scopus.com/inward/record.url?scp=85125283398&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-95593-9_1

DO - 10.1007/978-3-030-95593-9_1

M3 - Conference contribution

AN - SCOPUS:85125283398

SN - 9783030955922

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering

SP - 3

EP - 14

BT - Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. BODYNETS 2021

A2 - Ur Rehman, Masood

A2 - Zoha, Ahmed

PB - Springer

T2 - 16th EAI International Conference on Body Area Networks 2021

Y2 - 25 December 2021 through 26 December 2021

ER -

Yu Z, Zahid A, Taylor W, Abbas H, Heidari H, Imran MA et al. Data Fusion for Human Activity Recognition Based on RF Sensing and IMU Sensor. In Ur Rehman M, Zoha A, editors, Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. BODYNETS 2021. Springer. 2022. p. 3-14. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering). doi: 10.1007/978-3-030-95593-9_1

Data Fusion for Human Activity Recognition Based on RF Sensing and IMU Sensor

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this