Apple Inc.

Princeton University

Tejal Bhamre

Vinay R Majjigi

Hung A Pham

Karthik Jayaraman Raghuram

Stephen P Jackson

Yann Jerome Julien Renard

Sunny Kai Pang Chow

Mrinal Agarwal

Parisa Dehleh Hossein Zadeh

Sriram Venkateswaran

Henry Choi

Amit Singer

Omar Aziz

Alexandru Popovici

Teng Zhang

Yi Wen Liao

Paul D Bryan

Ethan Goolish

Alvaro J Melendez Hasbun

Tianye Sun

Richard G Liu

David Ojeda Avellaneda

Lauren Schutz

Pedro O Varangot

Rebecca L Clarkson

Aniket Aranake

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.

Crash detection on mobile device

Methods and systems are described for digitally reconstructing an unknown 3D structure of a target molecule using orthogonal extension. A plurality of 2D images of the target molecule are captured by an imaging system. An estimated low-order moment of the unknown 3D structure (e.g., a covariance matrix) is calculated based on the 2D images. A homologous molecule having a known 3D structure is identified and at least one expansion coefficient of the known structure of the homologous molecule is determined. At least one estimated expansion coefficient for the unknown structure is calculated based at least in part on the estimated low order moment of the unknown structure and the at least one expansion coefficient of the known structure. An estimated 3D reconstruction of the target molecule is then generated based on the at least one estimated expansion coefficient for the unknown structure of the target molecule.

Anisotropic twicing for single particle reconstruction using autocorrelation analysis

Growing community of inventors

Mountain View, CA, United States of America

Tejal Bhamre