Abstract: Methods, systems, and apparatuses, including computer programs encoded on a computer storage medium, for machine learning classification based on separate processing of multiple views. In some implementations, a system obtains image data for multiple images showing different views of an object. A machine learning model is used to generate a separate output based on each the multiple images individually. The outputs for the respective images are combined to generate a combined output. A predicted characteristic of the object is determined based on the combined output. An indication of the predicted characteristic of the object is provided.

Abstract: In a general aspect, integrated spatial phase imaging is described. In some aspects, an integrated imaging system includes a sensor device and one or more processors. The sensor device is configured to generate a first set of data indicative of a first set of attributes of an object and a second set of data indicative of a second set of attributes of the object. The one or more processors are configured to: generate a first set of primitives based on the first set of data; generate a second set of primitives based on the second set of data; generate a combined data set based on the first set of primitives and the second set of primitives; and determine a plurality of features of the object based on the combined data set.

Abstract: An information processing apparatus includes a processor configured to acquire biological information of plural users determined to be within a predetermined area and operate an apparatus based on the biological information of the plural users.

Abstract: The present disclosure provides methods and systems for managing safety and risk in a remote workplace. The method may comprise: collecting, via a local network, data stream from one or more sensors and a user device; transmitting the data stream to an edge computing device via the local network, wherein the data stream is stored in a local database; processing, at the edge computing device, the data stream to identify a hazardous condition and a health condition of a user associated with the user device; and automatically generating a dynamic geofencing area in the remote workplace base at least in part on the hazardous condition and the health condition.

Abstract: An x-ray source has a target assembly including a target, an electron source for generating electrons to impact the target, and a flight tube assembly separating the target assembly from the electron source and transporting a coolant to the target assembly. The flight tube assembly includes a flight tube interface ring, a target cartridge tube, and an electrical isolation ring between the flight tube interface ring and the target cartridge tube.

Abstract: Methods, systems, and apparatus for generating a recipe for a concrete mixture, comprising: obtaining an optical characterization of a set of particles; determining, based on the optical characterization, physical characteristics of the set of particles; generating a multispherical approximation of the set of particles; selecting, based on the physical characteristics of the set of particles and from a database of performance rules, performance rules applicable to the set of particles; predicting performance of a proposed recipe for a concrete mixture formed from the set of particles by: determining a wet flowability rating of the proposed recipe based on the selected performance rules; and determining a dry packing rating of the proposed recipe based on the multispherical approximation; iteratively altering the proposed recipe and predicting performance of the altered proposed recipe until the predicted performance satisfies performance criteria to obtain a final recipe; and outputting the final recipe.

Abstract: Effective delivery of an insecticide to a growing plant can sometimes be problematic. Topical delivery of an insecticide at the post-emergence stage of growth can sometimes be ineffective. It can also be difficult to deliver an insecticide to the roots of a growing plant, such as to combat a subsurface insect infestation. Accordingly, soil blends having insecticidal activity can comprise a soil medium, a porous soil additive, and an insecticide dispersed within the soil medium. Such soil blends may be used in conjunction with cultivating a variety of plants. Methods for producing the soil blends can comprise providing a soil medium and a porous soil additive, and dispersing the porous soil additive and an insecticide within the soil medium.

Abstract: Embodiments of an electric heater apparatus are disclosed. In one embodiment, an electric heater apparatus includes: (a) a first thermally conductive layer comprising an electrically insulating material; (b) one or more electrically conductive heating elements disposed in one or more grooves arranged on the top side of the first thermally conductive layer; and (c) a second thermally conductive layer disposed on the top side of the first thermally conductive layer over the one or more heating elements. The one or more heating elements include one or more refractory hard metals doped with at least one of carbon, nitrogen, aluminum, yttrium, or oxygen. The doped one or more refractory hard metals include a temperature insensitive electrical resistance over operational temperatures ranging from ambient temperature to about 850° C. as compared to undoped refractory hard metals. The one or more heating elements are independently controllable to provide one or more heating zones.

Abstract: A thermal image-based hybrid object detection method using a YOLO model and an object tracking technique includes: a) a step of obtaining a plurality of thermal image data by means of a thermal image camera; b) a step of extracting an object region from a thermal image data of the thermal image camera using an installed YOLO model and then creating an object region coordinate data by returning coordinates of the object region by means of an image processor; and c) a step of outputting a first image reflecting an object region coordinate data to each of thermal image data received from the image processor by means of an output device when the output device requests transmission of the first image.

Abstract: A system includes a vertical axis wind turbine (VAWT), a first charger connected to another device external from the system having at least one battery, a second charger connected to an on board battery pack, and at least one programmable logic controller (PLC) configured to: manage communication between the VAWT, the at least one battery, and the first charger to ensure that the at least one battery reaches a preset state of charge (SOC) comprising 90% state of charge, and manage communication between the on board battery pack and the second charger to ensure that the on board battery pack reaches the preset SOC and trigger the second charger to discontinue the charging session, manage transfer of energy from the on board battery pack to the at least one battery.

Abstract: There is provided a method of training a machine learning model, comprising: for each set of sample medical images depicting calcification within a target anatomical structure wherein each set includes non-contrast medical image(s) and contrast enhanced medical image(s), correlating between calcifications depicted in the target anatomical structure of the contrast enhanced image(s) with corresponding calcifications depicted in the target anatomical structure of the non-contrast medical image(s), computing calcification parameter(s) for calcification depicted in the respective target anatomical structure, labelling each contrast enhanced medical image with the calcification parameter(s), and training the machine learning model on a training dataset that includes the contrast enhanced medical images of the sets, each labelled with ground truth label of a respective calcification parameter(s), for generating an outcome indicative of a target calcification parameter(s) for calcification depicted in the target ana

Abstract: A system includes a first charger connected to one of an aircraft, a watercraft, and a vehicle having at least one vehicle battery, a second charger connected to an on board battery pack, and at least one programmable logic controller (PLC) to manage communication between the at least one vehicle battery and the first charger to ensure that the at least one vehicle battery reaches a preset state of charge (SOC), manage communication between the on board battery pack and the second charger to ensure that the on board battery pack reaches the preset SOC, and manage transfer of energy from the on board battery pack to the at least one vehicle battery.

Abstract: A device source wafer includes a wafer substrate, devices formed on or in the wafer substrate at a location on the wafer substrate, and test structures disposed on the wafer substrate connected to some but not all of the devices. The devices include a first device disposed at a first location and a second device disposed at a second different location on the wafer substrate. The test structures include at least a first test structure connected to the first device and a second test structure connected to the second device. The first test structure is adapted to measuring a characteristic of the first device and the second test structure is adapted to measuring the characteristic of the second device. An estimated characteristic of unmeasured devices is derived from the first and second device locations and measured characteristics and the device is selected based on the estimated characteristic.

Abstract: The present disclosure is directed to systems, apparatuses, and methods for controlling an electrical system using setpoints. Some embodiments include systems that receive a meter read schedule comprising anticipated meter read occurrences. The systems may set a demand setpoint representing a desired upper limit of demand of the electrical power system and adjust the demand setpoint during a billing period. The system may also reset the demand setpoint multiple times at different reset points around each of the anticipated meter read occurrences.

Abstract: Implementations are described herein for aggregating information responsive to a query from multiple different data feed services using machine learning. In various implementations, NLP may be performed on a natural language input comprising a query for information to generate a data feed-agnostic aggregator embedding (FAAE). A plurality of data feed services may be selected, each having its own data feed service action space that includes actions that are performable to access data via the data feed service. The FAAE may be processed based on domain-specific machine learning models corresponding to the selected data feed services. Each domain-specific machine learning model may translate between a respective data feed service action space and a data feed-agnostic semantic embedding space. Using these models, action(s) may be selected from the data feed service action spaces and performed to aggregate, from the plurality of data feed services, data that is responsive to the query.

Abstract: Aspects of the disclosure provide a method of adjusting a plurality of phase shifters of an OPA. The method may include identifying, by one or more processors, one or more first subsets of phase shifters of the plurality of phase shifters based on an orthogonal set of functions; performing, by the one or more processors, one or more first dithers on the one or more first subsets of phase shifters of the plurality of phase shifters using one or more first frequencies of a predetermined set of frequencies; determining, by the one or more processors, one or more first corrections based on a first power output of the OPA resulting from the one or more first dithers; and adjusting, by the one or more processors, the one or more first subsets using the one or more first corrections, the adjustment resulting in a first set of corrected phase shifter values.