Optimal deployment of face recognition solutions in a heterogeneous IoT platform for secure elderly care applications

Autor:	Nerea Aranjuelo, Jon Goenetxea, Luis Unzueta, Ignacio Arganda-Carreras, Unai Elordi, Alvaro Bertelsen
Rok vydání:	2021
Předmět:	Authentication Edge device Computer science business.industry Distributed computing Elderly care Encryption Facial recognition system Variety (cybernetics) General Earth and Planetary Sciences Inference engine business Internet of Things General Environmental Science
Zdroj:	KES 25th International Conference on Knowledge-Based and Intelligent Information & Engineering (KES 2021)
ISSN:	1877-0509
Popis:	Face recognition provides a desirable solution for authentication and surveillance in Internet of Things platforms for elderly care. However, its inclusion is challenging because of the possibly reduced interaction capabilities of users, the high variety of interaction devices, and the need of managing biometric data securely. Our approach relies on lightweight deep neural networks for secure recognition and to guide users during interaction. An automated procedure selects the appropriate inference engine, model configurations, and batch size, based on edge device characteristics. Biometric data is homomorphically encrypted to preserve privacy. An evaluation with respect to state-of-the-art alternatives shows its potential.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90efa58fecf29e1e7897033cdad036d2 https://doi.org/10.1016/j.procs.2021.09.093 Zobrazit plný text záznamu