Search for: All records

Biometric authentication systems are increasingly needed across a broad range of applications including in smart city environments (e.g., entering hotels), and in smart home environments (e.g., controlling smart devices). Traditional methods, such as face-based and fingerprint-based authentication, usually incur high costs to be installed in all this kind of environments. In this paper, we develop a ubiquitous low-effort user authentication approach, mmPalm, based on palm recognition using millimeter wave (mmWave) signals. mmWave technology has been adopted by WiGig and 5G, making mmPalm a low-cost solution that can be widely adopted in public places. In addition, the high resolution of mmWave signals allows mmPalm to extract detailed palm characteristics (e.g., palm geometry, skin thickness, and texture) that can assemble distinctive palmprints for user authentication. Our innovative virtual antennas design further increases the spatial resolution of a commercial mmWave device, enabling it to fully capture the comprehensive palmprint features. Moreover, to address the challenge of small-scale environmental changes (e.g., variations in palm-device distances and palm orientations), we design a novel palm profile augmentation method, utilizing a Conditional Generative Adversarial Network (cGAN) to generate synthetic palm profiles for mitigating palm instability. Furthermore, we design a cross-environment adaptation framework based on transfer learning to address the challenge of large-scale environmental changes, including multipath variations introduced by human bodies and nearby furniture. Extensive experiments with 30 participants through 6 months demonstrate that mmPalm achieves 99% authentication accuracy with resilience against different types of attacks, including random, impersonation, and counterfeit. 

Abstract Most existing diagnostic models are developed to detect whether students have mastered a set of skills of interest, but few have focused on identifying what scientific misconceptions students possess. This article developed a general dual‐purpose model for simultaneously estimating students' overall ability and the presence and absence of misconceptions. The expectation‐maximization algorithm was developed to estimate the model parameters. A simulation study was conducted to evaluate to what extent the parameters can be accurately recovered under varied conditions. A set of real data in science education was also analyzed to examine the viability of the proposed model in practice.