The heartbeat, with its unique characteristics, can be used as a biometric tool to identify people, according to researchers from the Universidad Carlos III de Madrid (UC3M) and the Shahid Rajaee Teacher Training University of Iran.

To develop an algorithm that helps to identify people via heartbeat, researchers used electrocardiograms (ECG) to analyze five musical qualities — dynamics, rhythm, timbre, pitch and tonality. This analysis, which tends to be used for characterizing audio files, was applied to heartbeats, wherein parameters were extracted from the five qualities that are unique for each individual. According to the researchers, this approach has an identification accuracy rate of 96.6%.

"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 characterize music," explained Carmen Cámara, a researcher from UC3M's Computer Science Department.

Setting this biometric apart from other commonly used biometric forms of identification is that the heartbeat is present in all humans, whereas some people might not be identified via certain other types of biometrics including fingerprinting and retinal scans.

The study, ECGsound for human identification, appears in the journal Biomedical Signal Processing and Control.

To contact the author of this article, email mdonlon@globalspec.com