Intruder recognition using ECG signal

Abstract

The electrocardiogram (ECG) is becoming a promising technology for biometric human identification. Usually ECG is used for health measurements and this is useful for biometric applications to state that the subject under analysis is live. But an individual identification shouldn't require a classical ECG clinical analysis where several contacts are applied to the person to be identified. In literature, ECG biometric recognition is usually studied for the recognition of a subject within a group of known subjects. In this paper, a new approach is considered. The aim of our embedded wearable controller is to authorize a subject or to reject him, labeling as an intruder unknown to the system. The study used 40 healthy subjects: two authorized and 38 intruders. A one-lead ECG trace has been recorded from the wrists of subjects, features have been extracted using a combination of Autocorrelation and Discrete Cosine Transform (AC/DCT) and then classified using a Multilayer Perceptron. Results show that intruder recognition can be performed with a success rate equal to 100%.

A Wearable Smart Device to Monitor Multiple Vital Parameters—VITAL ECG

“…VITAL-ECG is a smart wristband developed by the Neuronica Lab of the Politecnico di Torino based on another device, previously designed in the same laboratory, called ECG-WATCH [29][30][31], which handles electrocardiograms. Section 2 presents the state of the art.…”

Effect of attacker characterization in ECG-based continuous authentication mechanisms for Internet of Things

“…However, while 112 subjects take part in the evaluation of [60], just 30 subjects along 30 sin [61 ]. Pasero et al [62] use neural networks to classify ECG and discriminate between users of a given system and attackers -40 subjects take part in the experiments and they get the maximum possible success rate. By contrast, support vector machines are applied in [63,64] for ECG data classification.…”

A Survey of Wearable Biometric Recognition Systems

“…As opposed to chest straps, wristband ECGs cannot be used to obtain a continuous signal without interfering with daily activities. The unique features of each persons' heart are captured by the ECG signal, providing a physiological signal that has been used in several biometric studies [Derawi 2015;Pasero et al 2015;Sidek et al 2014;Camara et al 2015a]. However, it remains an open challenge to validate if these features remain constant over long periods of time or change due to ageing.…”

“…Artificial neural networks have been used in both wearable and hybrid biometric systems. Pasero et al [2015] used ANN to verify the identity of 40 subjects, achieving an accuracy of 80% with no false positives. Lee and Kim [2015] used a similar approach to verify identities based on the subject PPG signal.…”