Search for: All records

Circadian rhythms play a vital role in maintaining a person’s well-being but remain difficult to quantify accurately. Numerous approaches exist to measure these rhythms, but they often suffer from performance issues on the individual level. This work implements a Steady-State Kalman Filter as a method for estimating the circadian phase shifts from biometric signals. Our framework can automatically fit the filter’s parameters to biometric data obtained for each individual, and we were able to consistently estimate the phase shift within 1 hour of melatonin estimates on 100% of all subjects in this study. The estimation method opens up the possibility of real-time control and assessment of the circadian system, as well as chronotherapeutic intervention. 

Datasets involving multivariate event streams are prevalent in numerous applications. We present a novel framework for modeling temporal point processes called clock logic neural networks (CLNN) which learn weighted clock logic (wCL) formulas as interpretable temporal rules by which some events promote or inhibit other events. Specifically, CLNN models temporal relations between events using conditional intensity rates informed by a set of wCL formulas, which are more expressive than related prior work. Unlike conventional approaches of searching for generative rules through expensive combinatorial optimization, we design smooth activation functions for components of wCL formulas that enable a continuous relaxation of the discrete search space and efficient learning of wCL formulas using gradient-based methods. Experiments on synthetic datasets manifest our model's ability to recover the ground-truth rules and improve computational efficiency. In addition, experiments on real-world datasets show that our models perform competitively when compared with state-of-the-art models.