Abstract-- The oscillations of the human heart rate are inherently complex and non-linear--they are best described by mathematical chaos, and they present a challenge when applied to the practical domain of cardiovascular health monitoring in everyday life. In this work, we study the non-linear chaotic behavior of heart rate through mutual information and introduce a novel approach for enhancing heart rate estimation in real-life conditions. Our proposed approach not only explains and handles the non-linear temporal complexity from a mathematical perspective but also improves the deep learning solutions when combined with them. We validate our proposed method on four established datasets from real-life scenarios and compare its performance with existing algorithms thoroughly with extensive ablation experiments. Our results demonstrate a substantial improvement, up to 40%, of the proposed approach in estimating heart rate compared to traditional methods and existing machine-learning techniques while reducing the reliance on multiple sensing modalities and eliminating the need for post-processing steps. Healthy biological systems exhibit complex patterns of variability that can be described by mathematical chaos [1], [2]. A healthy heart is not a metronome; instead, its complex and constantly changing oscillations enable the cardiovascular system to rapidly adjust to sudden physical and psychological challenges to homeostasis [2]. Therefore, measuring heart rate (HR) during daily life has significant importance in monitoring individuals' health.

As AI's presence in all kinds of domains becomes more obvious every day, we can no longer think of it as something completely separate from the physical world. As visionaries predicted, the digital and the material are slowly merging. And, for the team at SparkCognition, an infrastructure-focused artificial intelligence company, this means that software and hardware should also be considered as a whole, not as different components. The HyperWerx campus will do just that, as a first-of-its-kind autonomy facility where AI exploration is set to lead the way. Instead of relying only on software and theoretical tests, the engineers at SparkCognition wanted to actually see how AI and the physical systems would interact.