Gait Recognition as an Authentication Method for Mobile Devices

With the rate at which smartphones are currently evolving, more and more of human life will be contained in these devices. At a time when data privacy is extremely important, it is crucial to protect one’s mobile device. In this paper, we propose a new non-intrusive gait recognition based mechanism...

Full description

Bibliographic Details
Main Authors: Matei-Sorin Axente, Ciprian Dobre, Radu-Ioan Ciobanu, Raluca Purnichescu-Purtan
Format: Article
Language:English
Published: MDPI AG 2020-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/20/15/4110
id doaj-7f51f7ce91db45fea997fcc24c661eec
record_format Article
spelling doaj-7f51f7ce91db45fea997fcc24c661eec2020-11-25T03:39:20ZengMDPI AGSensors1424-82202020-07-01204110411010.3390/s20154110Gait Recognition as an Authentication Method for Mobile DevicesMatei-Sorin Axente0Ciprian Dobre1Radu-Ioan Ciobanu2Raluca Purnichescu-Purtan3Faculty of Automatic Control and Computers, University Politehnica of Bucharest, RO-060042 Bucharest, RomaniaFaculty of Automatic Control and Computers, University Politehnica of Bucharest, RO-060042 Bucharest, RomaniaFaculty of Automatic Control and Computers, University Politehnica of Bucharest, RO-060042 Bucharest, RomaniaDepartment of Mathematical Methods and Models, University Politehnica of Bucharest, RO-060042 Bucharest, RomaniaWith the rate at which smartphones are currently evolving, more and more of human life will be contained in these devices. At a time when data privacy is extremely important, it is crucial to protect one’s mobile device. In this paper, we propose a new non-intrusive gait recognition based mechanism that can enhance the security of smartphones by rapidly identifying users with a high degree of confidence and securing sensitive data in case of an attack, with a focus on a potential architecture for such an algorithm for the Android environment. The motion sensors on an Android device are used to create a statistical model of a user’s gait, which is later used for identification. Through experimental testing, we prove the capability of our proposed solution by correctly classifying individuals with an accuracy upwards of 90% when tested on data recorded during multiple activities. The experiments, conducted on a low sampling rate and at short time intervals, show the benefits of our solution and highlight the feasibility of an efficient gait recognition mechanism on modern smartphones.https://www.mdpi.com/1424-8220/20/15/4110mobile devicessmartphonesauthenticationprivacygait detection
collection DOAJ
language English
format Article
sources DOAJ
author Matei-Sorin Axente
Ciprian Dobre
Radu-Ioan Ciobanu
Raluca Purnichescu-Purtan
spellingShingle Matei-Sorin Axente
Ciprian Dobre
Radu-Ioan Ciobanu
Raluca Purnichescu-Purtan
Gait Recognition as an Authentication Method for Mobile Devices
Sensors
mobile devices
smartphones
authentication
privacy
gait detection
author_facet Matei-Sorin Axente
Ciprian Dobre
Radu-Ioan Ciobanu
Raluca Purnichescu-Purtan
author_sort Matei-Sorin Axente
title Gait Recognition as an Authentication Method for Mobile Devices
title_short Gait Recognition as an Authentication Method for Mobile Devices
title_full Gait Recognition as an Authentication Method for Mobile Devices
title_fullStr Gait Recognition as an Authentication Method for Mobile Devices
title_full_unstemmed Gait Recognition as an Authentication Method for Mobile Devices
title_sort gait recognition as an authentication method for mobile devices
publisher MDPI AG
series Sensors
issn 1424-8220
publishDate 2020-07-01
description With the rate at which smartphones are currently evolving, more and more of human life will be contained in these devices. At a time when data privacy is extremely important, it is crucial to protect one’s mobile device. In this paper, we propose a new non-intrusive gait recognition based mechanism that can enhance the security of smartphones by rapidly identifying users with a high degree of confidence and securing sensitive data in case of an attack, with a focus on a potential architecture for such an algorithm for the Android environment. The motion sensors on an Android device are used to create a statistical model of a user’s gait, which is later used for identification. Through experimental testing, we prove the capability of our proposed solution by correctly classifying individuals with an accuracy upwards of 90% when tested on data recorded during multiple activities. The experiments, conducted on a low sampling rate and at short time intervals, show the benefits of our solution and highlight the feasibility of an efficient gait recognition mechanism on modern smartphones.
topic mobile devices
smartphones
authentication
privacy
gait detection
url https://www.mdpi.com/1424-8220/20/15/4110
work_keys_str_mv AT mateisorinaxente gaitrecognitionasanauthenticationmethodformobiledevices
AT cipriandobre gaitrecognitionasanauthenticationmethodformobiledevices
AT raduioanciobanu gaitrecognitionasanauthenticationmethodformobiledevices
AT ralucapurnichescupurtan gaitrecognitionasanauthenticationmethodformobiledevices
_version_ 1724539468780666880