Abstract: Described herein are techniques for identifying biological structures using a cryogenic electron microscopy (cryo-EM). In some embodiments, first images captured at a first magnification level may be received depicting cryo-EM grid units. Using a first ML model, one or more cryo-EM grid units may be detected based on the first images. Second images of each cryo-EM grid unit captured at a second magnification level may be received and, using a second ML model, one or more apertures within the cryo-EM grid may be detected based on the second images. One or more images captured at a third magnification level of depicting at least one of ice or a biological structure suspended within each aperture may be received and a Fourier transformation may be generated. Using a third ML model, at least one image depicting the biological structure from the images may be identified based on the Fourier transformations.

Abstract: An improved method and apparatus for embedding a real-time multi-tasking kernel in a non-real-time operating system is disclosed. Through encapsulating a real-time kernel into the interrupt handling environment of a non-real-time operating system, such as Windows.RTM., the method of the present invention allows for an entire real-time environment to be supported within the operating system. The scheduler of the real-time kernel supports multiple threads of execution all running at higher priority than the application tasks. By using synchronization mechanisms of the operating system, e.g. VxD events in enhanced mode Windows.RTM., the real-time tasks are able to make use of system services of the operating system. Real-time tasks not requiring system services execute more quickly from interrupt mode. Real-time tasks requiring system services execute partially from interrupt mode and partially from event mode.