In this paper, we present two approaches for identification based on biometric gait using acceleration sensor -called accelerometer. In contrast to preceding works, acceleration data are acquired from built-in sensor in mobile phone placed at the trouser pocket position. Data are then analyzed in both time domain and frequency domain. In time domain, gait templates are extracted and Dynamic Time Warping (DTW) is used to evaluate the similarity score. On the other hand, extracted features in frequency domain are classified using Support Vector Machine (SVM). With the participation of total 11 volunteers over 24 years old in our experiment, we achieved the accuracy of both methods respectively 79.1% and 92.7%.
Authentication systems using gait captured from inertial sensors have been recently developed to enhance the limitation of existing mechanisms on mobile devices and achieved promising results. However, most these systems employed pattern recognition and machine learning techniques in which biometric templates are stored insecurely, which could leave critical security and user privacy issues. Specifically, a compromise of original gait templates could result in everlasting forfeiture. In this paper, two main results will be presented. Firstly, we propose a novel gait authentication system on mobile devices in which the security and privacy are preserved by employing a fuzzy commitment scheme. Instead of storing original gait templates for user verification like in conventional approaches, we verify the user via a stored key which is biometrically encrypted by gait templates collected from a mobile accelerometer. Secondly, the discriminability of sensor-based gait templates are investigated to determine appropriate parameter values to construct an effective gait-based biometric cryptosystem. The performance of our proposed system is evaluated on the dataset including gait signals of 34 volunteers. We achieved the zero-FAR and the False Rejection Rate of approximately 16.18 % corresponding to the key length, as well as the system security level of 139 bits. The results from our experiment show that accelerometer-based gait could be further investigated to construct a biometric cryptosystem, as effective as other biometric traits such as iris, fingerprint, voice, and signature.
Summary Among existing wireless technologies, ultra‐wideband (UWB) is the most promising solution for indoor location tracking. UWB has a great multipath fading immunity; however, great multipath resolvability alone does not eliminate the effect of non‐line‐of‐sight (NLOS) and multipath propagation. NLOS and multipath propagation in indoor environments can easily produce meters of UWB ranging error. This condition gives an enormous impact on the accuracy of indoor location tracking data. To address this problem, we propose an NLOS detection method using recursive decision tree learning. Using the UWB channel quality indicators information, we develop our model with the Gini index and altered priors splitting criteria. We then validate the constructed model using the 10‐fold cross‐validation method. Our experiment shows that the constructed model has correctly detected 90% of both line‐of‐sight (LOS) and NLOS cases on the seven different indoor environments. The result of this work can be used for the UWB indoor location tracking accuracy improvement.
Abstract. In this paper, we propose a novel gait authentication mechanism by mining sensor resources on mobile phone. Unlike previous works, both built-in accelerometer and magnetometer are used to handle mobile installation issues, including but not limited to disorientation, and misplacement errors. The authentication performance is improved by executing deep examination at pre-processing steps. A novel and effective segmentation algorithm is also provided to segment signal into separate gait cycles with perfect accuracy. Subsequently, features are then extracted on both time and frequency domains. We aim to construct a lightweight but high reliable model; hence feature subsets selection algorithms are applied to optimize the dimension of the feature vectors as well as the processing time of classification tasks. Afterward, the optimal feature vector is classified using SVM with RBF kernel. Since there is no public dataset in this field to evaluate fairly the effectiveness of our mechanism, a realistic dataset containing the influence of mobile installation errors and footgear is also constructed with the participation of 38 volunteers (28 males, 10 females). We achieved the accuracy approximately 94.93% under identification mode, the FMR, FNMR of 0%, 3.89% and processing time of less than 4 seconds under authentication mode.
Abstract-Mobile authentication/identification has grown into a priority issue nowadays because of its existing outdated mechanisms, such as PINs or passwords. In this paper, we introduce gait recognition by using a mobile accelerometer as not only effective but also as an implicit identification model. Unlike previous works, the gait recognition only performs well with a particular mobile specification (e.g., a fixed sampling rate). Our work focuses on constructing a unique adaptive mechanism that could be independently deployed with the specification of mobile devices. To do this, the impact of the sampling rate on the preprocessing steps, such as noise elimination, data segmentation, and feature extraction, is examined in depth. Moreover, the degrees of agreement between the gait features that were extracted from two different mobiles, including both the Average Error Rate (AER) and Intra-class Correlation Coefficients (ICC), are assessed to evaluate the possibility of constructing a device-independent mechanism. We achieved the classification accuracy approximately 91.33 ± 0.67 % for both devices, which showed that it is feasible and reliable to construct adaptive cross-device gait recognition on a mobile phone.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.