Real-time electrocardiogram streams for continuous authentication

Carmen Camara, Pedro Peris-Lopez*, Lorena Gonzalez-Manzano, Juan Tapiador

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

26 Citations (Scopus)

Abstract

Security issues are becoming critical in modern smart systems. Particularly, ensuring that only legitimate users get access to them is essential. New access control systems must rely on continuous authentication (CA) to provide higher security level. To achieve this, recent research has shown how biological signals, such as electroencephalograms (EEGs) or electrocardiograms (ECGs), can be useful for this purpose. In this paper, we introduce a new CA scheme that, contrarily to previous works in this area, considers ECG signals as continuous data streams. The data stream paradigm is suitable for this scenario since algorithms tailored for data streams can cope with continuous data of a theoretical infinite length and with a certain variability. The proposed ECG-based CA system is intended for real-time applications and is able to offer an accuracy up to 96%, with an almost perfect system performance (kappa statistic >80%).

Original languageEnglish
Pages (from-to)784-794
JournalApplied Soft Computing Journal
Volume68
DOIs
Publication statusPublished - Jul 2018
MoE publication typeA1 Journal article-refereed

Keywords

  • Datastreams
  • Electrocardiogram
  • Healthcare
  • Identification

Fingerprint

Dive into the research topics of 'Real-time electrocardiogram streams for continuous authentication'. Together they form a unique fingerprint.

Cite this