Abstract: Embodiments are disclosed for crash detection on one or more mobile devices (e.g., smartwatch and/or smartphone). In some embodiments, a method comprises: detecting, with at least one processor, a crash event on a crash device; extracting, with the at least one processor, multimodal features from sensor data generated by multiple sensing modalities of the crash device; computing, with the at least one processor, a plurality of crash decisions based on a plurality of machine learning models applied to the multimodal features; and determining, with the at least one processor, that a severe vehicle crash has occurred involving the crash device based on the plurality of crash decisions and a severity model.

Abstract: Provided herein is a photonic modulator and methods for controlling a photonic modulator that can control the phase and/or amplitude of photons being transmitted through the modulator to minimize photonic loss while remaining power efficient and operating at high speeds. The photonic modulator can include a substrate with a pair of piezoelectric cantilevers spaced apart from one another by a gap, with a photonic waveguide disposed in the substrate that extends across the modulator and bridges the gap between the piezoelectric cantilevers. In one or more examples, the piezoelectric cantilevers can be configured to move away from the substrate in response to an electrical signal, such that a refractive index of the photonic waveguide is altered.