An Artificial Neural Network Framework for Gait-Based Biometrics.

Yingnan Sun,Benny Lo

doi:10.1109/jbhi.2018.2860780

Abstract

As the popularity of wearable and the implantable body sensor network (BSN) devices increases, there is a growing concern regarding the data security of such power-constrained miniaturized medical devices. With limited computational power, BSN devices are often not able to provide strong security mechanisms to protect sensitive personal and health information, such as one's physiological data. Consequently, many new methods of securing wireless body area networks have been proposed recently. One effective solution is the biometric cryptosystem (BCS) approach. BCS exploits physiological and behavioral biometric traits, including face, iris, fingerprints, electrocardiogram, and photoplethysmography. In this paper, we propose a new BCS approach for securing wireless communications for wearable and implantable healthcare devices using gait signal energy variations and an artificial neural network framework. By simultaneously extracting similar features from BSN sensors using our approach, binary keys can be generated on demand without user intervention. Through an extensive analysis on our BCS approach using a gait dataset, the results have shown that the binary keys generated using our approach have high entropy for all subjects. The keys can pass both National Institute of Standards and Technology and Dieharder statistical tests with high efficiency. The experimental results also show the robustness of the proposed approach in terms of the similarity of intraclass keys and the discriminability of the interclass keys.

Highlights

R ECENT wireless communication technology advancements have facilitated the development of light-weight, low-energy, miniaturized sensor nodes to be worn on human body or implanted in the body, forming a network of body worn sensors (i.e. Body Sensor Networks (BSN)), and associated wireless networking technology which is known as the Wireless Body Area Network (WBAN) defined by the IEEE standard 802.15.6 [1]
The state-of-the-art Biometric Cryptosystems (BCS) are mainly designed based on extracting binary keys from ECG signals [5], [6] for WBAN channel encryption and authentication
To assess the performance of the proposed security scheme, we evaluated the scheme with a series of experiments, using a walking dataset containing recordings of 15 subjects from the Real World Human Activity Recognition (HAR) dataset [22]

Summary

Introduction

R ECENT wireless communication technology advancements have facilitated the development of light-weight, low-energy, miniaturized sensor nodes to be worn on human body or implanted in the body, forming a network of body worn sensors (i.e. Body Sensor Networks (BSN)), and associated wireless networking technology which is known as the Wireless Body Area Network (WBAN) defined by the IEEE standard 802.15.6 [1]. Due to the very limited computational power, the lack of an user interface, and the low battery power design of BSN sensors, security solutions for wearable and implantable sensors are required to be lightweight and robust Physiological signals, such as Electrocardiogram (ECG), Photoplethysmography (PPG), and behavioral characteristics, such as voice [3], and gait [4], can be captured by BSN sensors, providing opportunities for Biometric Cryptosystems (BCS) to be applied as channel encryption, device authentication, and key distribution methods for securing WBANs. The state-of-the-art BCSs are mainly designed based on extracting binary keys from ECG signals [5], [6] for WBAN channel encryption and authentication. Most ECG-based BCSs require high sampling frequencies to capture the fiducial points in ECG waveforms, which could drain the battery power of the BSN sensors

Methods

Results

Conclusion