An algorithm makes it possible to identify people by their heartbeat

A study conducted by Universidad Carlos III de Madrid (UC3M) along with Iran’s Shahid Raja Teacher Training University has concluded that heartbeat can be used as a biometric tool to identify people.

Biometrics is the science that explores the identification of humans and animals through biological measures or physical characteristics, for example, fingerprints or iris. In this regard, biometric-based tools are increasingly being used in areas such as security to complement or replace password systems; and in the field of civil administration, in the registration and provision of identity documents.

This research proposes an innovative technique to identify people based on the distinctive features of their heartbeats. To do this, an electrocardiogram (ECG) is used and five musical properties are analyzed: dynamics, timbre, timbre, pitch and tonality—commonly used to characterize audio files—. Applying to the sound of the heartbeat. Thus, these five properties yield a combination of parameters, which is unique to each individual and has an accuracy rate of 96.6%.

Heartbeat - artistic impression.

Heartbeat – artistic impression. Image credit: Zorono via Pixabay, free license

“Biometric identification based on cardiac recordings has been studied for years, which has proven to be effective. The main novelty of our work is that we look at the ECG recording, which is a temporary signal, as if it were a sound wave.” From there, we analyze this sound wave using properties that are commonly used to characterize music”, explains Carmen Camara, a researcher in UC3M’s Department of Computer Science.

The main advantage of this technique is the universality of its identification, because to date, some people still cannot be identified by certain types of biometrics—in cases of injury, amputation or disabling physical features—but the heartbeat is a biometrics. is- sign that is present in all humans without exception.

Another advantage is its low cost and non-invasive operation: “Nowadays, there are already smart bracelets and watches that do ECG recording, so it would suffice to install an application on them that uses our detection algorithms”, researchers Says Pedro Paris- López, also from UC3M’s computer science department.

This technology is currently under development. Although the future of cardiac detection is promising, the researchers say they should “continue this line of research, before considering commercialisation.” One of the important aspects of this study is to analyze the behavior of the system according to the various activities performed by the individual, such as walking, running, resting, doing physical exercise or being in a stressful situation. In addition, factors such as the use of pacemakers or the effects of arrhythmias should be taken into account.

Age is also a factor to consider: “As we age, the signal changes slightly over time. This means that our systems must be updated approximately every five years”, say the researchers.

Source: Carlos III University of Madrid


Leave a Reply

Your email address will not be published.