Indoor Human Localization and Gait Analysis using Machine Learning for In-home Health Monitoring.

Homes equipped with ambient sensors can measure physiological signals correlated with the resident's health without requiring a wearable device. Gait characteristics may reveal physical imbalances or recognize changes in cognitive health. In this paper, we use the physical interactions with floor to both localize the resident and monitor their gait. Accelerometers are placed at the corners of the room for sensing. Gradient boosting regression was used to perform localization with an accuracy of 82%, reasonably accounting for inhomogeneity in the floor with just 3 sensors. A method using step time variance is proposed to detect gait imbalances; results on induced limps are presented.

Light Has Diverse Spatiotemporal Molecular Changes in the Mouse Suprachiasmatic Nucleus.

To be physiologically relevant, the period of the central circadian pacemaker, located in the suprachiasmatic nucleus (SCN), has to match the solar day in a process known as circadian photoentrainment. However, little is known about the spatiotemporal molecular changes that occur in the SCN in response to light. In this study, we sought to systematically characterize the circadian and light effects on activity-dependent markers of transcriptional (cFos), translational (pS6), and epigenetic (pH3) activities in the mouse SCN. To investigate circadian versus light influences on these molecular responses, we harvested brains from adult wild-type mice in darkness at different circadian times (CT) or from mice exposed to a 15-min light pulse at the middle of the subjective day (CT6, no phase shifts), early subjective night (CT14, large phase delays), or late subjective night (CT22, small phase advances). We found that cFos and pS6 exhibited rhythmic circadian expression in the SCN with distinct spatial rhythms, whereas pH3 expression was undetectable at all circadian phases. cFos rhythms were largely limited to the SCN shell, whereas pS6 rhythms encompassed the entire SCN. pH3, pS6, and cFos showed gating in response to light; however, we were surprised to find that the expression levels of these markers were not higher at phases when larger phase shifts are observed behaviorally (CT14 versus CT22). We then used animals lacking melanopsin (melanopsin knockout [MKO]), which show deficits in phase delays, to further investigate whether changes in these molecular markers correspond to behavioral phase shifts. Surprisingly, only pS6 showed deficits in MKOs at CT14. Therefore, our previous understanding of the molecular pathways that lead to circadian photoentrainment needs to be revised.