A heart can hide many things. But can it hide your identity? According to a new study, the answer is likely ‘no’ — your heartbeat may contain enough information for smart algorithms to identify you based on it.
Biometrics is the science that deals with identifying people based on their physical characteristics, such as iris, face, fingerprints, etc. Biometric identification systems have proven to be more secure than traditional systems, which use a password or a token. This is because passwords can be stolen by others, while our individual features are unique and non-transferable.
Think of it this way: your body emits bio-signals that are unique to you. But these biosignals, which are the result of your biophysical activity, can be recorded by specialized devices.
In a new study, researchers have described a way through which they can use electrocardiograms (ECGs) to recognize a person by their heartbeat alone.
Heartbeat as a biometric tool
An ECG is a linear representation of myocardial movements. The myocardium (the muscular layer of the heart) contracts and relaxes regularly and, as a result, it causes a cellular oscillation. An ECG converts electrical signals from cells into a graphic that can be decoded by specialists. This type of test can offer valuable information regarding heart disease, heart attack, and a number of abnormalities regarding heart rhythms that may cause heart failure.
To use cardiac recordings for human identification, the received signals must be cleared, by removing unwanted noise components and adjusting the frequency. When extracting the information from an ECG, specialists take into account five elements, usually associated with music and sounds: dynamics, rhythm, timbre, pitch, and quality, essentially treating it as a sound wave. In this way, ECGs are transformed into audio files that can be used to identify a person and distinguish them from other individuals.
“Biometric identification based on cardiac recording has been studied for years, proving 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 the qualities that are commonly used to characterise music”, explains Carmen Cámara, a researcher from UC3M’s Computer Science Department, in a statement.
As with any biometric identification method, the algorithm must work with a database that contains information about the hearts of thousands of people. Pedro Peris-López, a researcher from UC3M’s Computer Science Department and one of the study co-authors, says that this kind of information should be easily obtained because there are already many smartwatches and bracelets that record the heart activity easily and with people’s consent. He added that the best solution would be to install a special app on this type of device.
Uses and limitations
Biometric identification systems that use heartbeats can have two purposes: authentication or identification, the study writes. The authentication mode is used to verify a person’s identity; the system checks if that person is who they say they are. The identification method compares the features of an individual with those stored in the database to find out who that individual is. These systems are useful in various areas such as security (in companies), civil administration, police (to identify criminals), transportation, and more recently, they are used as a payment method.
Ultimately, with this type of method, the heartbeat could be a better biometric identification tool than fingerprints, facial features, eyes, or other methods currently in use. After all, everyone has a heart, but the same cannot be said of other parts of the body. Some people are disabled, others have suffered an injury that has led to the amputation of a part of the body or the deformation of their facial features.
However, the accuracy of using the heartbeat as an authentication method has its own limitations. There are a number of medical, physical, and psychological factors that can modify the heart rate. For instance, various arrhythmias can cause tachycardia, the condition when the heart rate is over 100. Another disease that influences the heartbeat is cardiomyopathy, which is the heart having difficulty pumping blood throughout the body.
Pregnancy is also likely to alter the normal rhythm of the myocardium. The body undergoes changes to adapt to the baby. There is an increase of up to 50% in blood volume and the heart rate increases. During labor, the heart is also overworked, as the blood flow and pressure suddenly change.
Heartbeats can be influenced by daily activities, like running, exercising, sleeping or even strong emotions, like anger, stress or anxiety. Age should also be considered, because as you get older, the heart rate changes, so your biological information should be constantly updated in the system.
Biometric identification systems have been used for a long time, providing safety and efficiency. It seems that the heartbeat has begun to gain ground in this domain and has become the latest tool for identification. It is still being tested, but experts believe the approach will pay off in the long run.