Journal of Ambient Intelligence and Humanized Computing
Gait based biometric personal authentication by using MEMS inertial
· Xiaowei Zhang
· Huaying Cai
· Zeping Lv
· Caiyou Hu
· Haiqun Xie
Received: 30 November 2017 / Accepted: 24 May 2018
© Springer-Verlag GmbH Germany, part of Springer Nature 2018
Walking is one of the major human activities, and walking pattern is unique for each individual. Thus, human gait can be
applied in biometric personal authentication. The traditional method for gait recognition is based on one or multiple cameras.
With the rapid development of Micro-Electro-Mechanical System (MEMS), small light inertial sensors have been used for
human identiﬁcation so far. In this study, a gait based personal authentication method is proposed using MEMS inertial sen-
sors. They are ﬁxed in the smart shoes, collecting motion signals and transmitting them to the server. Then, gait parameters
such as step length, cadence, stance phase, swing phase and the pitch angular are calculated and used as features for personal
identiﬁcation. A probabilistic neural network is proposed as a classiﬁcation mechanism to uniquely identify diﬀerent users.
Experiments are conducted to validate the proposed method. By using two cross-validation techniques, the overall mean
classiﬁcation rate for 22 persons is up to 85.3 and 85.7% respectively, which demonstrates the eﬀectiveness of the method.
Keywords Personal authentication · Inertial sensors · Gait parameters · Probabilistic neural network · Classiﬁcation rate
With the rapid development of Micro-Electro-Mechanical
System (MEMS) and wireless communication technology,
the inertial sensor has been used in many ﬁelds, including
activity recognition (Chen et al. 2012, 2014; Skillen et al.
2012; Godfrey et al. 2011; Gao et al. 2014; Preece et al.
2009), pedestrian navigation (Alvarez et al. 2012; Han and
Wang 2011; Yun and Bachmann 2006), gait analysis (Sala-
rian et al. 2013; Mariani et al. 2012), fall detection (Gjoreski
et al. 2012; Wu and Xue 2008) and personal authentica-
tion (Derawi et al. 2010; Hoang et al. 2013; Ngo et al.
2014). In recent years, research on personal authentication
has received more and more attention. The authentication
methods include face recognition, ﬁngerprint recognition,
iris recognition and gait recognition. As a novel biometric
authentication method, the gait-based authentication rec-
ognizes people by way of walking. Compared with other
methods, the main advantages of gait recognition lie in the
non-contact and long-distance identiﬁcation.
* Shuai Tao
* Zeping Lv
Dalian University, Dalian 116622, China
China-UK Institute of Gait and Health Innovation, Dalian
Qianhan Technology Co. Ltd., Dalian 116085, China
Department of Neurology, School of Medicine, Sir Run Run
Shaw Hospital, Zhejiang University, Hangzhou 310016,
National Research Center for Rehabilitation Technical
Aids, Rehabilitation Hospital, Beijing Key Laboratory
of Rehabilitation Technical Aids for Old-Age Disability,
Key Laboratory of Intelligent Control and Rehabilitation
Technology of the Ministry of Civil Aﬀairs, Beijing 100176,
Guangxi Jiangbin Hospital, Nanning 530021, China
Foshan First People’s Hospital, Foshan 528000, China