Abstract: Systems and methods additively manufacturing an object by applying heat to a first plurality of metallic particles in a powder bed using a first heat source, wherein the first heat source is one of multiple heat sources configured into an array, and the first heat source generates a first melt pool. Heat is simultaneously applied to a second plurality of metallic particles in the powder bed using a second heat source of the multiple heat sources in the array to generate a second melt pool. The first plurality of metallic particles are separated from the second plurality of metallic particles by a distance, wherein the distance and an amount of heat from each heat source is controlled to generate a combined melt pool that is larger in size and encompasses the first and second melt pools. The combined melt pool is allowed to solidify to form the object.

Abstract: In some examples, a structural framework component for an aerial platform comprises a body defining a cavity to receive a support system, and an arm to receive a payload, wherein the arm comprises a conduit to receive cabling linking a support system and a payload.

Abstract: Concurrent servicing of a first cable of a cable pair while a second cable of the cable pair remains operational improves multi-processor computer system availability and serviceability. A pair of processing chips in different processing drawers may continue operation by way of the second cable while the first cable is degraded or serviced. Upon the servicing of the first cable, the serviced cable may transition to a fully operational state with no interruptions to the operations between the processing drawers by way of the second cable. Since cable faults are typically more common than processing chip or processing drawer faults, identification of cable faults and the ability to maintain operations of the processing drawers connected therewith is increasingly important.

Abstract: There is a need for solutions that generates a temporally dynamic prediction for a particular prediction input. This need can be addressed by, for example, processing the prediction input using each of a plurality of temporally trained machine learning models to generate a corresponding model-specific prediction inference of a plurality of model-specific prediction inferences and processing the plurality of model-specific prediction inferences using an ensemble model to generate the temporally dynamic prediction for the prediction input.

Abstract: A method determining lung pathology severity from a subject under test includes receiving a training set comprising a plurality of breath flow signals and a plurality of audio signals for a convolutional neural network (CNN). The method includes training a convolutional neural network and creating at least one test graph using a breath flow signal and an audio signal from the subject under test. The method further includes inputting the at least one test graph associated with the subject under test into the CNN and determining an existing pathology and associated severity for the subject under test. Also, the method includes determining a prediction for a future possible condition of the subject and determining the lung pathology severity be computing a distance between the future possible condition of the subject under test and the existing pathology and associated severity.

Abstract: A computer-implemented method for determining lung pathology from audio respiratory and breath flow signals comprises receiving a plurality of breath flow signals and a plurality of audio signals comprising a training set for a convolutional neural network (CNN), wherein the plurality of breath flow signals and the plurality of audio signals are extracted from sessions with patients with known pathologies of known degrees of severity. The method also comprises analyzing the plurality of audio signals and the plurality of breath flow signals, wherein the analyzing comprises extracting a plurality of descriptors associated with the audio and breath flow signals. Further, the method comprises creating a plurality of graphs using information from the descriptors, wherein at least one of the graphs comprises a plot combining descriptors from both the audio and the breath flow signals. The method also comprises training the CNN using the plurality of graphs.

Abstract: According to an aspect of the invention, there is provided a method of triggering an explosive charge of each of a plurality of munitions, the method comprising: launching a first munition, into the air, from a first gun barrel, and into water to engage with a target location, the first munition comprising a first explosive charge and a first fuze system, adapted to trigger the first explosive charge in the water, launching a second munition, into the air, from a second gun barrel, and into water to engage with the target location, the second munition comprising an second explosive charge and a second fuze system, adapted to trigger the second explosive charge in the water, the method comprising co-ordinating the timing of the triggering of the first explosive charge and the second explosive charge to establish a co-ordinated explosive event at the target location.

Abstract: A medical device (10) includes a device housing (12). An in-line thermal mass flow sensor (26) includes a heater (28) and at least one temperature sensor (30). The in-line thermal mass flow sensor is vertically mounted on or in the device housing. The in-line thermal mass flow sensor is configured to measure a flow rate of the fluid through the medical device. At least one electronic processor (18) is programmed to: read the flow rate of the fluid measured by the in-line thermal mass flow sensor; and detect at least one bubble in the fluid based on the measured flow rate.

Abstract: A medical device (10) includes a device housing (12). An in-line thermal mass flow sensor (26) includes a heater (28) and at least one temperature sensor (30). The in-line thermal mass flow sensor is vertically mounted on or in the device housing. The in-line thermal mass flow sensor is configured to measure a flow rate of the fluid through the medical device. At least one electronic processor (18) is programmed to: read the flow rate of the fluid measured by the in-line thermal mass flow sensor, and detect at least one bubble in the fluid based on the measured flow rate.

Abstract: In one aspect of the present disclosure, a tissue marking system is provided that includes a container and an applicator. The applicator is in the container and is removable therefrom. The applicator includes a tip, a reservoir containing sterile tissue marking dye, and a valve. The valve is configured to open and permit sterile tissue marking dye to flow from the reservoir to the tip of the applicator in response to the tip being pressed against a priming surface. In one embodiment, the system includes a substrate that is removable from the container and includes the priming surface. In another embodiment, the container includes a tray having a compartment that receives the applicator. The tray includes a well that includes the priming surface.

Abstract: An infusion pump (10) includes a fluid chamber (28) having an outlet valve (34) and a piezo-stack actuator (36) comprising a stack of piezo-electric layers (38). An electronic processor (18) is programmed to operate the outlet valve and the piezo-stack actuator to pump fluid through the fluid chamber at a programmed flow rate.

Abstract: In one aspect of the present disclosure, a tissue marking system is provided that includes a container and an applicator. The applicator is in the container and is removable therefrom. The applicator includes a tip, a reservoir containing sterile tissue marking dye, and a valve. The valve is configured to open and permit sterile tissue marking dye to flow from the reservoir to the tip of the applicator in response to the tip being pressed against a priming surface. In one embodiment, the system includes a substrate that is removable from the container and includes the priming surface. In another embodiment, the container includes a tray having a compartment that receives the applicator. The tray includes a well that includes the priming surface.

Abstract: An imitation learning system may learn how to play a video game based on user interactions by a tester or other user of the video game. The imitation learning system may develop an imitation learning model based, at least in part, on the tester's interaction with the video game and the corresponding state of the video game to determine or predict actions that may be performed when interacting with the video game. The imitation learning system may use the imitation learning model to control automated agents that can play additional instances of the video game. Further, as the user continues to interact with the video game during testing, the imitation learning model may continue to be updated. Thus, the interactions by the automated agents with the video game may, over time, almost mimic the interaction by the user enabling multiple tests of the video game to be performed simultaneously.

Abstract: An infusion pump including a fluid chamber having an outlet valve and a piezo-stack actuator including a stack of piezo-electric layers. The infusion pump also includes a linear actuator to measure displacement of the piezo-stack actuator during operation. An electronic processor is programmed to operate the outlet valve and the piezo-stack actuator to pump fluid through the fluid chamber at a programmed flow rate.

Abstract: A medical device (10) for use in a Magnetic Resonance environment includes a keypad (22) having keys (24). Light sources (26) are disposed with respective keys of the keypad to illuminate the respective keys. At least one electronic processor (18) is programmed to: perform user interfacing operations in which user inputs are received via the keypad; during the user interfacing operations, control the light sources to selectively illuminate keys usable in the user interfacing operations; and controlling or configuring the medical device in accord with the user inputs received during the user interfacing operations.

Abstract: An imitation learning system may learn how to play a video game based on user interactions by a tester or other user of the video game. The imitation learning system may develop an imitation learning model based, at least in part, on the tester's interaction with the video game and the corresponding state of the video game to determine or predict actions that may be performed when interacting with the video game. The imitation learning system may use the imitation learning model to control automated agents that can play additional instances of the video game. Further, as the user continues to interact with the video game during testing, the imitation learning model may continue to be updated. Thus, the interactions by the automated agents with the video game may, over time, almost mimic the interaction by the user enabling multiple tests of the video game to be performed simultaneously.

Abstract: In one aspect, a trimming knife is provided that includes a blade and a handle. The blade has a straight leading edge, a straight trailing edge, a straight lower cutting edge, and squared leading and trailing corners between the straight leading and trailing edges and the straight lower cutting edge. The handle includes a gripping portion, a spine to receive the blade, and a blade guard configured to protect the squared trailing corner of the blade with the blade received in the spine.

Abstract: According to an aspect of the invention, there is provided a method of triggering an explosive charge of each of a plurality of munitions, the method comprising: launching a first munition, into the air, from a first gun barrel, and into water to engage with a target location, the first munition comprising a first explosive charge and a first fuze system, adapted to trigger the first explosive charge in the water, launching a second munition, into the air, from a second gun barrel, and into water to engage with the target location, the second munition comprising an second explosive charge and a second fuze system, adapted to trigger the second explosive charge in the water, the method comprising co-ordinating the timing of the triggering of the first explosive charge and the second explosive charge to establish a co-ordinated explosive event at the target location.

Abstract: According to an aspect of the invention, there is provided a system for reducing water-entry shock for a projectile entering the water, the system comprising: a first component, the first component being moveable to a target region for which water-entry shock is to be reduced, and arranged to interact with the water, for reducing water-entry shock for a second component; a second component in the form of the projectile, arranged to enter the water in the region for which water-entry shock has been reduced by the first component, functionality of the second projectile component being triggered by the water.

Abstract: There is provided an external load transport assembly for an aerial vehicle. The assembly includes a load suspension line having a first end connectable to the aerial vehicle and a second end connectable to an external load. The assembly includes a relative humidity indicator positioned to monitor moisture content of the load suspension line. The assembly includes an at least partially transparent coating encasing the load suspension line and the relative humidity indicator.