Abstract
This article proposes a lightweight biometric sensing system using ubiquitous narrowband radio frequency (RF) links for path-dependent walker classification. The fluctuated received signal strength (RSS) sequence generated by human motion is used for feature representation. To capture the most discriminative characteristics of individuals, a three-layer RF sensing network is organized for building multiple sampling links at the most common heights of upper limbs, thighs, and lower legs. The optimal parameters of sensing configuration, such as the height of link location and number of fused links, are investigated to improve sensory data distinctions among subjects, and the experimental results suggest that the synergistic sensing by using multiple links can contribute a better performance. This is the new consideration of using RF links in building a biometric sensing system. In addition, two types of classification methods involving vector quantization (VQ) and hidden Markov models (HMMs) are developed and compared for closed-set walker recognition and verification. Experimental studies in indoor line-of-sight (LOS) and non-line-of-sight (NLOS) scenarios are conducted to validate the proposed method.
Highlights
Acquiring biometric information represented by the physiological and behavioral attributes of human beings has important significance in many security systems and authentication applications [1].Measurable, stable, and distinctive biometrics exhibit robust connections to individuals, and such traits are advantageous in data–object association based multiple targets tracking and behavior analysis [2,3]
We explore the novel use of multiple narrowband radio frequency (RF) links to sample biometric traits generated by walking on a constrained path
This article explores the novel use of multiple narrowband RF links to sample biometric traits generated by walking on a constrained path
Summary
Acquiring biometric information represented by the physiological and behavioral attributes of human beings has important significance in many security systems and authentication applications [1].Measurable, stable, and distinctive biometrics exhibit robust connections to individuals, and such traits are advantageous in data–object association based multiple targets tracking and behavior analysis [2,3]. Acquiring biometric information represented by the physiological and behavioral attributes of human beings has important significance in many security systems and authentication applications [1]. In the constrained sensing-based systems, the capture of physiological traits such as fingerprint [11], palm print [12], and iris [13] depends on high-quality and short-range sensors. These types of biometrics have been proven to be unique and consistent for individual matching, and some have been applied in the fields of border control and smart ID cards. With the continuing advances in sensors and pattern recognition technologies, a series of behavioral biometric sensing using wearable devices have emerged, such as electroencephalography (EEG) [14], finger-vein [15], and gait [16]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call