Search for: All records

We have been witnessing an unprecedented increase in the aging population in human history. It is nontrivial to ensure the health and safety of seniors living alone. The prohibitive human labor cost necessitates more sustainable, technology oriented approaches instead of labor-intensive solutions. The raising digital healthcare services (DHS) leveraging the Internet of Medical Things (IoMT), Digital Twins (DT), and advanced fifth-generation and beyond (B5G) wireless communication technology, are widely recognized as promising solutions. By enabling a seamless interwoven of the physical world and cyberspace, Metaverse makes an ideal home for the next generation of DHS. Thanks to characteristics of decentralization, traceability, and unalterability, Blockchain is envisioned to enhance security properties in Metaverse. This paper proposes MetaSafe, a DHS architecture for seniors’ safety monitoring in Metaverse. Based on monitoring data collected by sensors, the activities and status of seniors, who are considered as the physical objects (PO), are mirrored to corresponding logical objects (LO) in a virtual community in the Metaverse, where activity recognition, potential risk prediction, and alert generation are realized. By leveraging Non-Fungible Token (NFT) technology to tokenize identities (POs and LOs) and data streams of the DHS on the blockchain, an NFT-based authentication fabric allows for verifiable ownership and traceable transferability during the data-sharing process. Specifically, an instant alerting system is introduced in this work that leverages a hybrid algorithm combining the singular spectrum analysis (SSA) approach with the long-short-term memory (LSTM) networks. Through an extensive experimental study, MetaSafe is validated as a feasible and promising approach to protect seniors living alone. 

Free-text keystroke is a form of behavioral biometrics which has great potential for addressing the security limitations of conventional one-time authentication by continuously monitoring the user's typing behaviors. This paper presents a new, enhanced continuous authentication approach by incorporating the dynamics of both keystrokes and wrist motions. Based upon two sets of features (free-text keystroke latency features and statistical wrist motion patterns extracted from the wrist-worn smartwatches), two one-vs-all Random Forest Ensemble Classifiers (RFECs) are constructed and trained respectively. A Dynamic Trust Model (DTM) is then developed to fuse the two classifiers' decisions and realize non-time-blocked real-time authentication. In the free-text typing experiments involving 25 human subjects, an imposter/intruder can be detected within no more than one sentence (average 56 keystrokes) with an FRR of 1.82% and an FAR of 1.94%. Compared with the scheme relying on only keystroke latency which has an FRR of 4.66%, an FAR of 17.92% and the required number of keystroke of 162, the proposed authentication system shows significant improvements in terms of accuracy, efficiency, and usability.