Deep residual networks for user authentication via hand-object manipulations

6Citations
Citations of this article
15Readers
Mendeley users who have this article in their library.

Abstract

With the ubiquity of wearable devices, various behavioural biometrics have been exploited for continuous user authentication during daily activities. However, biometric authentication using complex hand behaviours have not been sufficiently investigated. This paper presents an implicit and continuous user authentication model based on hand-object manipulation behaviour, using a finger-and hand-mounted inertial measurement unit (IMU)-based system and state-of-the-art deep learning models. We employed three convolutional neural network (CNN)-based deep residual networks (ResNets) with multiple depths (i.e., 50, 101, and 152 layers) and two recurrent neural network (RNN)-based long short-term memory (LSTMs): simple and bidirectional. To increase ecological validity, data collection of hand-object manipulation behaviours was based on three different age groups and simple and complex daily object manipulation scenarios. As a result, both the ResNets and LSTMs models acceptably identified users’ hand behaviour patterns, with the best average accuracy of 96.31% and F1-score of 88.08%. Specifically, in the simple hand behaviour authentication scenarios, more layers in residual networks tended to show better performance without showing conventional degradation problems (the ResNet-152 > ResNet-101 > ResNet-50). In a complex hand behaviour scenario, the ResNet models outperformed user authentication compared to the LSTMs. The 152-layered ResNet and bidirectional LSTM showed an average false rejection rate of 8.34% and 16.67% and an equal error rate of 1.62% and 9.95%, respectively.

References Powered by Scopus

Deep residual learning for image recognition

174360Citations
N/AReaders
Get full text

Representation learning: A review and new perspectives

9844Citations
N/AReaders
Get full text

Learning Long-Term Dependencies with Gradient Descent is Difficult

6590Citations
N/AReaders
Get full text

Cited by Powered by Scopus

An Internet-of-Disease System for COVID-19 Testing Using Saliva by an AI-Controlled Microfluidic ELISA Device

6Citations
N/AReaders
Get full text

Immunity testing against COVID-19 from blood by an IoT-enabled and AI-controlled multiplexed microfluidic platform

3Citations
N/AReaders
Get full text

Evaluating deep learning techniques for identifying tongue features in subthreshold depression: a prospective observational study

1Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Choi, K., Ryu, H., & Kim, J. (2021). Deep residual networks for user authentication via hand-object manipulations. Sensors, 21(9). https://doi.org/10.3390/s21092981

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 4

100%

Readers' Discipline

Tooltip

Engineering 2

67%

Neuroscience 1

33%

Save time finding and organizing research with Mendeley

Sign up for free