Abstract: A computer-implemented method of reviewing digital pathology data may include receiving a digital pathology image into a digital storage device, the digital pathology image being associated with a patient, providing for display the digital pathology image on a display, pairing the digital pathology image with a physical token of the digital pathology image in an interactive system, receiving one or more commands from the interactive system, determining one or more manipulations or modifications to the displayed digital pathology image based on the one or more commands, and providing for display a modified digital pathology image on the display according to the determined one or more manipulations or modifications.

Abstract: A message addressed to a user is received. A first model is applied to the message to produce a first output indicative of whether the message is representative of a non-malicious message. The first model is trained using past messages that have been verified as non-malicious messages. It is determined, based on the first output, that the message is potentially a malicious message. Responsive to determining that the message is potentially a malicious email based on the first output, apply a second model to the message to produce a second output indicative of whether the message is representative of a given type of attack. The second model is one of a plurality of models. At least one model included in the plurality of models is associated with characterizing a goal of the malicious message. An action is performed with respect to the message based on the second output.

Abstract: A multi-level rotor for a coolant flow control valve assembly, which accommodates an increased number of inlet ports, outlet ports, and flow channels using a single rotor located in a housing, enabling a larger number of flow configurations. The housing includes nine ports which may function as an inlet or an outlet, which facilitates different flow configurations. For a thermal management system, reduced cost and less space utilization is achieved by a reduced number of valves, where the multi-level rotor is able to fluidically connect multiple inlets/outlets. This enables different flow configurations, depending on the degree of rotation. The channels at different levels are sealed from each other within the housing. The flow channels are manufactured into a single entity, therefore always having the same positional accuracy relative to each other when the rotor is repositioned.

Abstract: A cutting guide apparatus for guiding placement of bore holes in a door may include a first leg configured to be disposed along a first face of the door, a second leg configured to be disposed along a second face of the door opposite the first face, and a spacing element disposed between the first and second legs. At least one of the first leg or the second leg may include a handle hole guide structure and the spacing element may include an edge bore guide structure. A first portion of the handle hole guide structure that is proximate to the first or second face of the door may be undercut relative to a second portion of the handle hole guide structure that is opposite the first portion.

Abstract: An in-line surface drain may comprise a cylindrical frame and a plurality of concentric rings coupled to the cylindrical frame. The plurality of concentric rings may be configured to protrude outward from a bottom external surface of the cylindrical frame, and the diameters of the plurality of concentric rings may be different. At least one of the plurality of concentric rings may be configured to detachably accommodate a riser pipe.

Abstract: Conventional email filtering services are not suitable for recognizing sophisticated malicious emails, and therefore may allow sophisticated malicious emails to reach inboxes by mistake. Introduced here are threat detection platforms designed to take an integrative approach to detecting security threats. For example, after receiving input indicative of an approval from an individual to access past email received by employees of an enterprise, a threat detection platform can download past emails to build a machine learning (ML) model that understands the norms of communication with internal contacts (e.g., other employees) and/or external contacts (e.g., vendors). By applying the ML model to incoming email, the threat detection platform can identify security threats in real time in a targeted manner.

Abstract: A cutting guide apparatus for guiding placement of bore holes in a door may include an engagement interface and a backset assembly. The engagement interface is configured to retain the apparatus proximate to an edge of a door and center an edge bore guide between an inside face and an outside face of the door. The engagement interface includes a first arm and a second arm that are each operably coupled to a common pivot axis. The backset assembly is operably coupled to the engagement interface to enable an amount of backset from the edge of the door to a center of a handle hole guide to be adjusted. The backset assembly includes a first mounting bracket operably coupled to a first portion of the first arm and a first portion of the second arm, and a second mounting bracket operably coupled to a second portion of the first arm.

Abstract: A cutting guide apparatus for guiding placement of bore holes in a door may include an engagement interface and a backset assembly. The engagement interface may be configured to retain the apparatus proximate to an edge of a door. The engagement interface may include a handle hole guide structure and an edge bore guide structure. The backset assembly may be operably coupled to the engagement interface to enable an amount of backset from the edge of the door to a center of the handle hole guide structure to be adjusted. The engagement interface may include a first leg configured to be disposed along a first face of the door, and a second leg configured to be disposed along a second face of the door. The backset assembly may be configured to engage the edge of the door at a variable location between the first and second legs.

Abstract: Systems and techniques for computing cluster configuration standardization are described herein. Configuration data obtained for a plurality of computing systems may be evaluated. A first computing cluster may be identified based on first configuration data for a first set of computing systems. A second computing cluster may be identified based on second configuration data for a second set of computing systems. A score may be calculated for the second computing cluster based on an evaluation of the second configuration data using the first configuration data. The second computing cluster may be associated with the first computing cluster based on the score. A standard configuration may be selected to be applied to the first set of computing systems and the second set of computing systems using the first configuration data.

Abstract: This invention relates to both process and tooling for machining exemplary Hamilton Sundstrand 7111 and 7121 aircraft propeller blade taper bores, or equivalent to comply with government and or industry standards or specifications for such refurbishment. The tooling and process invented are an Improvement over previous and current taper bore machining methods in improved repeatability and cost effectiveness, as this machining method can quickly and repeatedly machine propeller blades to meet fit, form, and function requirements. The process makes use of a specially constructed horizontal mill, specially constructed blade-holding fixture, specially constructed probing system, specially constructed reamers, and specially constructed air gauges. A blade holding fixture assembly including a base plate, a blade holding fixture and a blade alignment fixture hold an aircraft propeller blade in a horizontal milling machine for refurbishment of the taper bores.

Abstract: Examples of techniques for extracting hydrocarbons from a subterranean hydrocarbon reservoir based on an artificial lift plan are disclosed. In one example implementation according to aspects of the present disclosure, a method includes performing, by a processing device, an evaluation of an artificial lift approach that can be operated at a well having a subterranean hydrocarbon reservoir, the evaluation being based at least in part on a static factor associated with operating the artificial lift approach in the well and a dynamic factor associated with operating the artificial lift approach at a operating condition. The method further includes generating, by the processing device, an artificial lift plan based at least in part on the evaluation. The method further includes extracting the hydrocarbons from the subterranean hydrocarbon reservoir based on the artificial lift plan by operating, at the well, the artificial lift approach.

Abstract: Systems and methods are described herein for processing electronic medical images to predict one or more donor recipients for a patient. For example, a digital medical image of the patient may be received, wherein the patient is in need of a transplant. A trained machine learning system may be determined. The digital medical image may be provided into the trained machine learning system, the trained machine learning system determining a patient embedding. Using the patient embedding, a subset of donor recipients may be determined. Based on the subset of donor recipients a recommendation of optimal donors may be determined.

Abstract: Systems and methods are described herein for processing electronic medical images to predict one or more histological morphologies. For example, one or more digital medical images may be received, the one or more digital medical images being of at least one pathology specimen associated with a patient. Patient clinical data for the patient may be received. A trained machine learning system may be determined. The patient clinic data and one or more digital medical images may be provided to the trained machine learning system. A histological morphology prediction of the patient may be determined, using the trained machine learning system. The histological morphology prediction may be output to a user and/or storage.

Abstract: This disclosure describes techniques and systems for encoding instructions in audio data that, when output on a speaker of a first device in an environment, cause a second device to output content in the environment. In some instances, the audio data has a frequency that is inaudible to users in the environment. Thus, the first device is able to cause the second device to output the content without users in the environment hearing the instructions. In some instances, the first device also outputs content, and the content output by the second device is played at an offset relative to a position of the content output by the first device.

Abstract: Systems and methods are described herein for processing electronic medical images. For example, one or more digital medical images of at least one pathology specimen, the pathology specimen being associated with a patient may be received. Additionally, an external designation of the one or more digital medical images may be received. The one or more digital medical images may be provided to one or more machine learning systems, the one or more machine learning systems each having been trained to analyze medical images using one of a plurality of versions of a protocol. The one or more machine learning systems, may determine machine learning system designations for the one or more digital medical images. The external designation may be compared to the machine learning system designations and, based on the comparison, determining whether the external designation matches a predetermined protocol.

Abstract: Systems and methods are described herein for processing electronic medical images. The method may include determining, using an automated routine, whether a pathology protocol is accessible; determining a first set of one or more training images, the first set of one or more training images comprising digital medical images annotated utilizing the pathology protocol; and providing the training images to a machine learning model capable of analyzing digital medical images according to the pathology protocol or guideline. The providing may further include determining a starting model, splitting the first set of one or more training images into a training set A and an evaluation set B of digital medical images, fine tuning the starting model with the training set A to determine the machine learning model, evaluating the machine learning model with the training set B, and upon receiving a passing evaluation, saving the determined machine learning model.

Abstract: Systems and techniques for computing infrastructure standards assay are described herein. A set of existing configurations may be obtained of an existing software application executing on a set of computing systems operating in the computing infrastructure. The set of existing configurations may be evaluated using artificial intelligence to identify the standard configuration. The standard configuration may include a set of configuration options that appear most often in the set of existing configurations. A score may be generated for each existing configuration of the set of existing configurations based on deviation between the existing configuration and the standard configuration. A notification may be transmitted to an administrator based on the score. The notification may include an indication of options of the standard configuration that differ from options of the existing configuration.

Abstract: A system including a point monitor case including a point monitoring case port electrically coupled to a confined space monitoring device for acquiring monitoring data from a confined space. A centralized monitoring station cabinet communicatively connected to the point monitor case includes a display device, a processor, and a centralized monitoring application. The centralized monitoring application executes instructions on the processor to display: a number of workers in proximity to the confined space, a camera feed from a camera located at a confined space, a control button configured to control the confined space monitoring device, and gas sensor indicators. A hub is communicatively interposed between the point monitor case and the centralized monitoring station cabinet. The hub includes a cableless access point, an aggregator, and a graphical user interface configured to display an aggregated current state of the confined space, including a combination of data streams aggregated by the aggregator.

Abstract: A computer-implemented method for processing electronic medical images, the method including receiving one or more digital medical images of at least one pathology specimen, the pathology specimen being associated with a patient and receiving one or more search criteria. One or more machine learning systems may be determined based on the one or more search criteria. The one or more machine learning systems may be output to a user, wherein outputting the one or more machine learning system includes applying the one or more machine learning systems to the one or more received medical images, and displaying the one or more digital medical images after the machine learning system performed analysis on the digital medical images. A selection from a user may be received, the selection corresponding to a first machine learning system from the one or more machine learning systems. The first machine learning system may be output.

Abstract: Systems and techniques for computing cluster configuration standardization are described herein. Configuration data obtained for a plurality of computing systems may be evaluated. A first computing cluster may be identified based on first configuration data for a first set of computing systems. A second computing cluster may be identified based on second configuration data for a second set of computing systems. A score may be calculated for the second computing cluster based on an evaluation of the second configuration data using the first configuration data. The second computing cluster may be associated with the first computing cluster based on the score. A standard configuration may be selected to be applied to the first set of computing systems and the second set of computing systems using the first configuration data.