Distinguishing Hearts: How Machine Learning identifies People based on their Heartbeat

Christoph Lipps; Lea Bergkemper; Hans Dieter Schotten

In: Sixth International Conference on Advances in Biomedical Engineering. International Conference on Advances in Biomedical Engineering (ICABME-2021), October 7-9, Islamic University of Lebanon, Lebanon, IEEE, 10/2021.


Though biometrics are moving into a recent focus,they are actually the oldest form of identification. Humans, andeven some animals, recognize each other by their voice, bodyshape and face. But with the emergence of sensors close to thebody combined with the possibilities of Artificial Intelligence (AI),other factors such as the gait and behaviorals are also becomingof increasingly interest.Therefore, this paper illustrates how individuals, supportedby Machine Learning (ML) methods, can be distinguishedbased on their Electrocardiogram (ECG) signals. ECG valuesrecorded with an Microcontroller Unit (MCU) are used andthe applicability of three different ML methods -K-NearestNeighbor (KNN), Support Vector Machine (SVM) and GaussianNaive Bayes (GNB)- are compared. The results also indicate thepotential of ML in terms of applications in (tele)medicine anddisease prevention.


Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence