Toggle Main Menu Toggle Search

Open Access padlockePrints

PrivGait: An Energy-Harvesting-Based Privacy-Preserving User-Identification System by Gait Analysis

Lookup NU author(s): Dr Bo WeiORCiD

Downloads


Licence

This is the authors' accepted manuscript of an article that has been published in its final definitive form by Institute of Electrical and Electronics Engineers Inc., 2022.

For re-use rights please refer to the publisher's terms and conditions.


Abstract

© 2014 IEEE.Smart space has emerged as a new paradigm that combines sensing, communication, and artificial intelligence technologies to offer various customized services. A fundamental requirement of these services is person identification. Although a variety of person-identification approaches has been proposed, they suffer from several limitations in practical applications, such as low energy efficiency, accuracy degradation, and privacy issue. This article proposes an energy-harvesting-based privacy-preserving gait recognition scheme for smart space, which is named PrivGait. In PrivGait, we extract discriminative features from 1-D gait signal and design an attention-based long short-term memory (LSTM) network to classify different people. Moreover, we leverage a novel Bloom filter-based privacy-preserving technique to address the privacy leakage problem. To demonstrate the feasibility of PrivGait, we design a proof-of-concept prototype using off-the-shelf energy-harvesting hardware. Extensive evaluation results show that the proposed scheme outperforms state of the art by 6%-10% and incurs low system cost while preserving user's privacy.


Publication metadata

Author(s): Xu W, Xue W, Lin Q, Lan G, Feng X, Wei B, Luo C, Li W, Zomaya AY

Publication type: Article

Publication status: Published

Journal: IEEE Internet of Things Journal

Year: 2022

Volume: 9

Issue: 22

Pages: 22048-22060

Print publication date: 15/11/2022

Online publication date: 15/06/2021

Acceptance date: 07/06/2021

Date deposited: 29/06/2023

ISSN (electronic): 2327-4662

Publisher: Institute of Electrical and Electronics Engineers Inc.

URL: https://doi.org/10.1109/JIOT.2021.3089618

DOI: 10.1109/JIOT.2021.3089618


Altmetrics

Altmetrics provided by Altmetric


Share