Evaluation of deep learning models in contactless human motion detection system for next generation healthcare

Yukai Song; William Taylor; Yao Ge; Muhammad Usman; Muhammad Ali Imran; Qammer H. Abbasi

doi:10.1038/s41598-022-25403-y

Evaluation of deep learning models in contactless human motion detection system for next generation healthcare

Yukai Song, William Taylor, Yao Ge, Muhammad Usman, Muhammad Ali Imran, Qammer H. Abbasi^*

^*Corresponding author for this work

Electronic Engineering

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

7 Citations (Scopus)

97 Downloads (Pure)

Abstract

Recent decades have witnessed the growing importance of human motion detection systems based on artificial intelligence (AI). The growing interest in human motion detection systems is the advantages of automation in the monitoring of patients remotely and giving warnings to doctors promptly. Currently, wearable devices are frequently used for human motion detection systems. However, such devices have several limitations, such as the elderly not wearing devices due to lack of comfort or forgetfulness and/or battery limitations. To overcome the problems of wearable devices, we propose an AI-driven human motion detection system (deep learning-based system) using channel state information (CSI) extracted from Radio Frequency (RF) signals. The main contribution of this paper is to improve the performance of the deep learning models through techniques, including structure modification and dimension reduction of the original data. In this work, We firstly collected the CSI data with the center frequency 5.32 GHz and implemented the structure of the basic deep learning network in our previous work. After that, we changed the basic deep learning network by increasing the depth, increasing the width, adapting some advanced network structures, and reducing dimensions. After finishing those modifications, we observed the results and analyzed how to further improve the deep learning performance of this contactless AI-enabled human motion detection system. It can be found that reducing the dimension of the original data can work better than modifying the structure of the deep learning model.

Original language	English
Article number	21592
Journal	Scientific Reports
Volume	12
DOIs	https://doi.org/10.1038/s41598-022-25403-y
Publication status	Published - 14 Dec 2022

Keywords

computer science
quality of life
scientific data

ASJC Scopus subject areas

General

UN SDGs

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

Documents and Links

10.1038/s41598-022-25403-y

Song, Y. et al (2022) Evaluation of deep learning models in contactless human motion detection system for next generation healthcare
© The authors. Open Access Tis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
Final published version, 2.63 MBLicence: CC BY

Cite this

@article{d51c48af8455472db6808b7c630902bb,

title = "Evaluation of deep learning models in contactless human motion detection system for next generation healthcare",

abstract = "Recent decades have witnessed the growing importance of human motion detection systems based on artificial intelligence (AI). The growing interest in human motion detection systems is the advantages of automation in the monitoring of patients remotely and giving warnings to doctors promptly. Currently, wearable devices are frequently used for human motion detection systems. However, such devices have several limitations, such as the elderly not wearing devices due to lack of comfort or forgetfulness and/or battery limitations. To overcome the problems of wearable devices, we propose an AI-driven human motion detection system (deep learning-based system) using channel state information (CSI) extracted from Radio Frequency (RF) signals. The main contribution of this paper is to improve the performance of the deep learning models through techniques, including structure modification and dimension reduction of the original data. In this work, We firstly collected the CSI data with the center frequency 5.32 GHz and implemented the structure of the basic deep learning network in our previous work. After that, we changed the basic deep learning network by increasing the depth, increasing the width, adapting some advanced network structures, and reducing dimensions. After finishing those modifications, we observed the results and analyzed how to further improve the deep learning performance of this contactless AI-enabled human motion detection system. It can be found that reducing the dimension of the original data can work better than modifying the structure of the deep learning model.",

keywords = "computer science, quality of life, scientific data",

author = "Yukai Song and William Taylor and Yao Ge and Muhammad Usman and Imran, {Muhammad Ali} and Abbasi, {Qammer H.}",

year = "2022",

month = dec,

day = "14",

doi = "10.1038/s41598-022-25403-y",

language = "English",

volume = "12",

journal = "Scientific Reports",

issn = "2045-2322",

publisher = "Springer Nature",

}

TY - JOUR

T1 - Evaluation of deep learning models in contactless human motion detection system for next generation healthcare

AU - Song, Yukai

AU - Taylor, William

AU - Ge, Yao

AU - Usman, Muhammad

AU - Imran, Muhammad Ali

AU - Abbasi, Qammer H.

PY - 2022/12/14

Y1 - 2022/12/14

N2 - Recent decades have witnessed the growing importance of human motion detection systems based on artificial intelligence (AI). The growing interest in human motion detection systems is the advantages of automation in the monitoring of patients remotely and giving warnings to doctors promptly. Currently, wearable devices are frequently used for human motion detection systems. However, such devices have several limitations, such as the elderly not wearing devices due to lack of comfort or forgetfulness and/or battery limitations. To overcome the problems of wearable devices, we propose an AI-driven human motion detection system (deep learning-based system) using channel state information (CSI) extracted from Radio Frequency (RF) signals. The main contribution of this paper is to improve the performance of the deep learning models through techniques, including structure modification and dimension reduction of the original data. In this work, We firstly collected the CSI data with the center frequency 5.32 GHz and implemented the structure of the basic deep learning network in our previous work. After that, we changed the basic deep learning network by increasing the depth, increasing the width, adapting some advanced network structures, and reducing dimensions. After finishing those modifications, we observed the results and analyzed how to further improve the deep learning performance of this contactless AI-enabled human motion detection system. It can be found that reducing the dimension of the original data can work better than modifying the structure of the deep learning model.

AB - Recent decades have witnessed the growing importance of human motion detection systems based on artificial intelligence (AI). The growing interest in human motion detection systems is the advantages of automation in the monitoring of patients remotely and giving warnings to doctors promptly. Currently, wearable devices are frequently used for human motion detection systems. However, such devices have several limitations, such as the elderly not wearing devices due to lack of comfort or forgetfulness and/or battery limitations. To overcome the problems of wearable devices, we propose an AI-driven human motion detection system (deep learning-based system) using channel state information (CSI) extracted from Radio Frequency (RF) signals. The main contribution of this paper is to improve the performance of the deep learning models through techniques, including structure modification and dimension reduction of the original data. In this work, We firstly collected the CSI data with the center frequency 5.32 GHz and implemented the structure of the basic deep learning network in our previous work. After that, we changed the basic deep learning network by increasing the depth, increasing the width, adapting some advanced network structures, and reducing dimensions. After finishing those modifications, we observed the results and analyzed how to further improve the deep learning performance of this contactless AI-enabled human motion detection system. It can be found that reducing the dimension of the original data can work better than modifying the structure of the deep learning model.

KW - computer science

KW - quality of life

KW - scientific data

U2 - 10.1038/s41598-022-25403-y

DO - 10.1038/s41598-022-25403-y

M3 - Article

SN - 2045-2322

VL - 12

JO - Scientific Reports

JF - Scientific Reports

M1 - 21592

ER -

Evaluation of deep learning models in contactless human motion detection system for next generation healthcare

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

Documents and Links

Fingerprint

Cite this