Gait fingerprinting-based user identification on smartphones

Mobile Information Systems

et al. 2018

Self Cite

Smartphones are ubiquitously integrated into our home and work environment and users frequently use them as the portal to cloud-based secure services. Since smartphones can easily be stolen or coopted, the advent of smartwatches provides an intriguing platform legitimate user identification for applications like online banking and many other cloud-based services. However, to access security-critical online services, it is highly desirable to accurately identifying the legitimate user accessing such services and data whether coming from the cloud or any other source. Such identification must be done in an automatic and non-bypassable way. For such applications, this work proposes a two-fold feasibility study; (1) activity recognition and (2) gait-based legitimate user identification based on individual activity. To achieve the above-said goals, the first aim of this work was to propose a semicontrolled environment system which overcomes the limitations of users’ age, gender, and smartwatch wearing style. The second aim of this work was to investigate the ambulatory activity performed by any user. Thus, this paper proposes a novel system for implicit and continuous legitimate user identification based on their behavioral characteristics by leveraging the sensors already ubiquitously built into smartwatches. The design system gives legitimate user identification using machine learning techniques and multiple sensory data with 98.68% accuracy.

Section: Introductionmentioning

confidence: 94%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Smartwatch-Based Legitimate User Identification for Cloud-Based Secure Services

Alqarni

Mobile Information Systems

et al. 2018

Self Cite

“…In recent years, several feature selection algorithms have been proposed, including the filter based approach, the wrapper method, the principal components analysis (PCA), the linear discriminant analysis (LDA) [33], KLDA a kernelized version of the LDA [35] and SWLDA a stepwise linear discriminant analysis method [4].…”

Section: Feature Selectionmentioning

confidence: 99%

“…In the literature hereby referred to, several solutions were proposed addressing implicit user identification without involving the user, such as keystroke-based user identification [54], touch screen biometrics [22,28], application set fingerprints [2], hybrid user identification methods-such as accelerometers and gyroscopes [6,14,52], and gait based user identification [4,43]. However, these solutions only discuss one aspect of user identification, either software or hardware.…”

Section: Introductionmentioning

confidence: 99%

Extended sammon projection and wavelet kernel extreme learning machine for gait-based legitimate user identification

Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing

Mazzara

Distefano

et al. 2019

Self Cite

Smartphones have ubiquitously integrated into our home and work environments, however, the user normally relies on explicit but inefficient identification processes in a controlled environment. Therefore, when the device is stolen, the attacker can have access to the user's personal information and services against the stored password/s. As a result of this potential scenario, this work demonstrates the possibilities of legitimate user identification in a semicontrolled environment through the built-in smartphones motion dynamics captured by two different sensors. This is a two-fold process, sub-activity recognition based user identification using the wavelet kernel extreme learning machine (KELM) to first recognize the performed activity and then identifies whether the recognized activity is performed by the legitimate user or impostor. Prior to the identification; Extended Sammon Projection (ESP) method has been deployed to reduce the redundancy between the features. To validate the proposed system, we first collected data from 20 users walking with their device freely placed in one of their pants pockets (front right, front left, back right and back left pocket). Through extensive experimentation's using overall and averageone-subject-cross-validation, we demonstrate that together time and frequency domain features optimized by ESP to train the KELM is an effective system to identify the legitimate user or an impostor with 97 − 98% overall accuracy.

Seeking Optimum System Settings for Physical Activity Recognition on Smartwatches

Advances in Intelligent Systems and Computing

Mazzara

Distefano

2019

Self Cite

Physical activity recognition using wearable devices can provide valued information regarding an individual's degree of functional ability and lifestyle. Smartphone-based physical activity recognition is a well-studied area. However, research on smartwatch-based physical activity recognition, on the other hand, is still in its infancy. Through a largescale exploratory study, this work aims to investigate the smartwatchbased physical activity recognition domain. A detailed analysis of various feature banks and classification methods are carried out to find the optimum system settings for the best performance of any smartwatch-based physical activity recognition system for both personal and impersonal models in real life scenarios. To further validate our hypothesis for both personal and impersonal models, we tested single subject out cross validation process for smartwatch-based physical activity recognition.