Discrimination between Cynomolgus Monkey (Macaca Fascicularis) and Humans using Machine Learning and Heart Rate Variability Indices

Abstract

In recent years, from the viewpoint of privacy protection policy, research on the personal identification of human bio-signals has been prominent. However, it is not well known whether indices obtained from biological time series data, such as ECGs, have personal identifiability, and it is not clear and can they be discriminated from animal ECGs. In this study, we visualized Heart Rate Variability (HRV) indices data of a cynomolgus monkey (Macaca Fascicularis) and a newborn using T-SNE, which is often used for data dimensionality compression in unsupervised learning, and UMAP, which is a new method. As a result, it was difficult to discriminate between cynomolgus monkey and newborn HRV indices.