Abstract: This disclosure relates generally to program synthesis for weakly-supervised multimodal question answering using filtered iterative back-translation (FIBT). Existing approaches for chart question answering mainly address structural, visual, relational, or simple data retrieval queries with fixed-vocabulary answers. The present disclosure implements a two-stage approach where, in first stage, a computer vision pipeline is employed to extract data from chart images and store in a generic schema. In second stage, SQL programs for Natural Language (NL) queries are generated in dataset by using FIBT. To adapt forward and backward models to required NL queries, a Probabilistic Context-Free Grammar is defined, whose probabilities are set to be inversely proportional to SQL programs in training data and sample programs from it.

Abstract: Technologies are provided for providing a dashboard interface corresponding to one or more datacenter components for information originating from one or more proprietary applications. A selection of information corresponding to the one or more datacenter components is initially received. Upon receiving the selection, an application programming interface (API) call request is made for the information corresponding to the one or more datacenter components from the one or more proprietary applications. As the information corresponding to one or more datacenter components from the one or more proprietary applications is received, it is aggregated and provided within the dashboard interface.

Abstract: A non-transitory computer readable medium (107, 127) stores: a predictive model (130) configured to generate an alert (132) predicting a failure of a component of a medical imaging device (120) by applying patterns to values of a set of features; a table (136) having records corresponding to the patterns of the predictive model; and instructions readable and executable by at least one electronic processor (101, 113) to (i) train: a sequence model (134) to receive values of the set of features for a current case and to output a most probable root cause and at least one service action for the current case, and (ii) determine a root cause and at least one recommended service action for the alert generated by the predictive model by applying the trained sequence model to the values of the set of features for the medical imaging device.

Abstract: A method (100) of determining a layout for one or more medical devices (12) in a medical facility includes: obtaining images (30) of a plurality of locations of the medical facility; mapping the obtained images to an architectural layout of the medical facility; generating a three-dimensional (3D) model of the medical facility based on the mapping; determining a recommended location for the one or more medical devices using the 3D model; determining a recommended placement of the one or more medical devices in the recommended location based on the recommended location; and outputting an image (40) showing the determined recommended placement of the medical devices in the recommended location.

Abstract: According to an aspect, there is provided a computer implemented method in a central sewer of selecting a training dataset with which to train a model using a distributed machine learning process, wherein the training dataset is to comprise medical data that satisfies one or more clinical requirements and wherein training data in the training dataset is located at a plurality of clinical sites. The method comprises requesting (302) from each of the clinical sites, metadata describing features of matching data at the respective clinical site that satisfies the one or more clinical requirements. The method then comprises determining (304), from the metadata, a measure of variation of the features of the matching data. Based on the measure of variation, the method then comprises selecting (306) training data for the training dataset from the matching data using the metadata.

Abstract: An apparatus (100) for scheduling field service for a fleet of medical imaging devices includes at least one electronic processor (101, 113) programmed to maintain a service records database (140) storing information on instances of service tasks performed on the fleet including identifiers of service completion times for the instances of service tasks; identify one or more service tasks to be performed on a medical imaging device of the fleet based on content of one or more machine and/or service logs of the medical imaging device to be serviced; optimize a service plan (130) for the upcoming field service based at least on the one or more service tasks to be performed during the upcoming field service and service completion times for instances of the one or more service tasks to be performed in the service records database; and display the service plan on a display device (105).

Abstract: The invention discloses an apparatus for stroke characterization. The apparatus comprises a processor. The processor is configured to receive image data representing a three-dimensional image of a head of a subject; identify a region within the image data corresponding to bone in the head of the subject; apply an adjustment to the image data to compensate for effects resulting from radiation scattered from the bone during acquisition of the image data; generate a two-dimensional image based on the adjusted image data; and provide the generated two-dimensional image as an input to a predictive model to identify a region of interest for stroke characterization in the two-dimensional image.

Abstract: A reactor for coating particles includes a stationary vacuum chamber to hold a bed of particles to be coated, a chemical delivery system, and a paddle assembly. The paddle assembly includes a rotatable drive shaft and a first plurality of paddles and a second plurality of paddles that extend radially from the drive shaft. The spacing, cross-sections, and oblique angles of the paddles are such that orbiting of the paddles causes the first plurality of paddles and the second plurality of paddles to displace substantially equal volumes in opposite directions in the lower portion of the stationary vacuum chamber.

Abstract: Systems for prequalifying components for a processing chamber are described. The systems may be used to clean particulates from chamber parts and concurrently quantify the cleanliness. The systems may be used to qualify replacement parts before sending to a customer site for installation. The systems have three adjacent compartments separated by impermeable barriers. All three compartments are filled with liquid while cleaning a chamber component. The center compartment contains a submerged component for cleaning and qualifying. Two compartments on either side of the center compartment are configured with submerged ultrasonic transducers to deliver ultrasonic energy to either side of the component being cleaned and prequalified. A liquid pump is connected to the cleaning tub to recirculate water from the cleaning bath and another liquid pump is configured to remove a small amount of the cleaning bath to sample particulates.

Abstract: Improved methods for chemically etching silicon are provided herein. In some embodiments, a method of etching a silicon material includes: (a) exposing the silicon material to a halogen-containing gas; (b) evacuating the halogen-containing gas from the semiconductor processing chamber; (c) exposing the silicon material to an amine vapor to etch a monolayer of the silicon material; (d) evacuating the amine vapor from the semiconductor processing chamber and; (e) optionally repeating (a)-(d) to etch the silicon material to a predetermined thickness.

Abstract: Systems for prequalifying components for a processing chamber are described. The systems may be used to clean particulates from chamber parts and concurrently quantify the cleanliness. The systems may be used to qualify replacement parts before sending to a customer site for installation. The systems have three adjacent compartments separated by impermeable barriers. All three compartments are filled with liquid while cleaning a chamber component. The center compartment contains a submerged component for cleaning and qualifying. Two compartments on either side of the center compartment are configured with submerged ultrasonic transducers to deliver ultrasonic energy to either side of the component being cleaned and prequalified. A liquid pump is connected to the cleaning tub to recirculate water from the cleaning bath and another liquid pump is configured to remove a small amount of the cleaning bath to sample particulates.

Abstract: Systems for prequalifying components for a processing chamber are described. The systems may be used to clean particulates from chamber parts and concurrently quantify the cleanliness. The systems may be used to qualify replacement parts before sending to a customer site for installation. The systems have three adjacent compartments separated by impermeable barriers. All three compartments are filled with liquid while cleaning a chamber component. The center compartment contains a submerged component for cleaning and qualifying. Two compartments on either side of the center compartment are configured with submerged ultrasonic transducers to deliver ultrasonic energy to either side of the component being cleaned and prequalified. A liquid pump is connected to the cleaning tub to recirculate water from the cleaning bath and another liquid pump is configured to remove a small amount of the cleaning bath to sample particulates.

Abstract: Systems for prequalifying components for a processing chamber are described. The systems may be used to clean particulates from chamber parts and concurrently quantify the cleanliness. The systems may be used to qualify replacement parts before sending to a customer site for installation. The systems have three adjacent compartments separated by impermeable barriers. All three compartments are filled with liquid while cleaning a chamber component. The center compartment contains a submerged component for cleaning and qualifying. Two compartments on either side of the center compartment are configured with submerged ultrasonic transducers to deliver ultrasonic energy to either side of the component being cleaned and prequalified. A liquid pump is connected to the cleaning tub to recirculate water from the cleaning bath and another liquid pump is configured to remove a small amount of the cleaning bath to sample particulates.

Abstract: Improved methods for chemically etching silicon are provided herein. In some embodiments, a method of etching a silicon material includes: (a) exposing the silicon material to a halogen-containing gas; (b) evacuating the halogen-containing gas from the semiconductor processing chamber; (c) exposing the silicon material to an amine vapor to etch a monolayer of the silicon material; (d) evacuating the amine vapor from the semiconductor processing chamber and; (e) optionally repeating (a)-(d) to etch the silicon material to a predetermined thickness.

Abstract: A terminal connector for retaining and supporting a female electrical terminal. The terminal connector is formed of an electrically insulating material and is configured such that the socket of the terminal and a portion of, but not the entire, edge of the terminal proximate said socket is exposed to allow access to the exposed portion by a probe to permit testing of the terminal.