Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing a set of design parameters. In one aspect, a method includes: obtaining a respective initial value for each design parameter, and iteratively optimizing current values of the design parameters over a sequence of optimization iterations. The method further includes, each optimization iteration: generating a representation of an initial state of an environment using the current values of the design parameters, processing an input including the representation of the initial state of the environment using a simulation neural network to generate an output that defines a simulation of the state of the environment over a sequence of one or more time steps, determining a reward, determining gradients of the reward with respect to the current values of the design parameters, and updating the current values of the design parameters using the gradients.

Abstract: A system to allow the cancellation of terrestrial interferences over aerial networks (Satellite links, and wireless communications) with the support of a canceller module to dynamically decompose wanted and unwanted signals. The invention performs interference cancellation over satellite carriers affected by terrestrial congested spectrum, including the jamming, share of frequencies, or accidental interferences for satellite communications, GPS, Galileo, GNSS or any type of satellite link. The invention provides resiliency to the communication by the regeneration of the desired signal filtering of any unwanted noise received in a terrestrial antenna without the need of any guidance by the modulation. This invention is applicable for any satellite constellation (GEO, MEO, LEO, GPS, MCODE, GNSS, or wireless connectivity, 2G, 3G, 4G, 5G, 6G, Radar, Wifi, WiMax, etc) and any type of satellite antenna (parabolic, mechanically flat panel antenna, steerable flat panel antennas, unidirectional, etc).

Abstract: In one aspect, a method to detect white blood cells and/or white blood cell subtypes from non-invasive capillary videos is featured. The method includes acquiring a first plurality of images of a region of interest including one or more capillaries of a predetermined area of a human subject from non-invasive capillary videos captured with an optical device, processing the first plurality of images to determine one or more optical absorption gaps located in said capillary, and annotating the first plurality of images with an indication of any optical absorption gap detected in the first plurality of images.

Abstract: An automated system for acquiring images of one or more capillaries in a capillary bed includes a platform for receiving a body portion of a subject, an imaging subsystem having a repositionable field of view and coupled to the platform to acquire images of at least a capillary bed of the body portion and a controller communicably coupled to the imaging subsystem to automatically reposition the field of view of the imaging subsystem to different areas of the capillary bed, and at each field of view within the capillary bed, activate the imaging subsystem to acquire images of one or more capillaries in the capillary bed.

Abstract: An automated system for acquiring images of one or more capillaries in a capillary bed includes a platform for receiving a body portion of a subject, an imaging subsystem having a repositionable field of view and coupled to the platform to acquire images of at least a capillary bed of the body portion and a controller communicably coupled to the imaging subsystem to automatically reposition the field of view of the imaging subsystem to different areas of the capillary bed, and at each field of view within the capillary bed, activate the imaging subsystem to acquire images of one or more capillaries in the capillary bed.

Abstract: A system for non-invasive hematological measurements includes a platform to receive a body portion of a user and an imaging device to acquire a set of images of a capillary bed in the body portion. For each image, a controller detects one or more capillaries in the body portion of the finger to identify a first set of capillaries by estimating one or more attributes of each capillary (e.g., structural attributes, flow attributes, imaging attributes, or combinations thereof), wherein at least one attribute of each capillary meets a predetermined criterion. The controller also identifies a second set of capillaries from the first set of capillaries such that each capillary of the second set of capillaries is visible in a predetermined number of images of the set of images.

Abstract: A method, a computer system, and a computer program product are provided for supporting data-based clinical decision-making. Medical concepts and relations between medical concepts contained in a structured medical report and/or a template for such reports are extracted. The template and/or the structured medical report comprise a data structure representing the medical concepts and relations between these medical concepts. These extracted medical concepts and relations between the medical concepts are then integrated into a graph database and weighted according to their relevance. Based on the weights one or more recommendations for actions a user may take when composing report templates and/or structured medical reports are inferred and presented to the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network that includes one or more graph neural network layers. In one aspect, a method comprises: generating data defining a graph, comprising: generating a respective final feature representation for each node, wherein, for each of one or more of the nodes, the respective final feature representation is a modified feature representation that is generated from a respective feature representation for the node using respective noise; processing the data defining the graph using one or more of the graph neural network layers of the neural network to generate a respective updated node embedding of each node; and processing, for each of one or more of the nodes having modified feature representations, the updated node embedding of the node to generate a respective de-noising prediction for the node.

Abstract: A battery module for a vehicle is disclosed. The battery module comprises a casing configured to accommodate a number of battery cells and a mounting section configured to receive a fastening element for mounting the battery module to a further component of the vehicle. The battery module comprises a thermal insulation unit positioned between the casing and the mounting section. The present disclosure further relates to a battery pack for a vehicle and a vehicle comprising a battery pack.

Abstract: A system for non-invasive hematological measurements includes a platform to receive a body portion of a user and an imaging device to acquire a set of images of a capillary bed in the body portion. For each image, a controller detects one or more capillaries in the body portion of the finger to identify a first set of capillaries by estimating one or more attributes of each capillary (e.g., structural attributes, flow attributes, imaging attributes, or combinations thereof), wherein at least one attribute of each capillary meets a predetermined criterion. The controller also identifies a second set of capillaries from the first set of capillaries such that each capillary of the second set of capillaries is visible in a predetermined number of images of the set of images.

Abstract: The present invention discloses a design for a measurement device with improved power measurement accuracy, involving the measurement of the temperature using a highly accurate device that can be installed coupled to the protectors, the device comprising: an essentially rectangular parallelepiped-shaped casing with a plurality of slots in the lateral surfaces, one or more openings, and at least one electrical connection rod; a motherboard (PCB) on the inside of the casing, comprising a first face having at least one Shunt resistor and its own power supply, and a second face, opposite the first face, having—a communication module consisting of a microcontroller that is connected to the measurement module, —a temperature sensor disposed on the second face (PCB) and on the side opposite the Shunt resistor, and—electrically isolated communication ports; and an analogue-to-digital converter.

Abstract: In one aspect, a method to detect white blood cells and/or white blood cell subtypes from non-invasive capillary videos is featured. The method includes acquiring a first plurality of images of a region of interest including one or more capillaries of a predetermined area of a human subject from non-invasive capillary videos captured with an optical device, processing the first plurality of images to determine one or more optical absorption gaps located in said capillary, and annotating the first plurality of images with an indication of any optical absorption gap detected in the first plurality of images.

Abstract: In one aspect, a method to detect white blood cells and/or white blood cell subtypes from non-invasive capillary videos is featured. The method includes acquiring a first plurality of images of a region of interest including one or more capillaries of a predetermined area of a human subject from non-invasive capillary videos captured with an optical device, processing the first plurality of images to determine one or more optical absorption gaps located in said capillary, and annotating the first plurality of images with an indication of any optical absorption gap detected in the first plurality of images.

Abstract: This specification describes a simulation system that performs simulations of physical environments using a graph neural network. At each of one or more time steps in a sequence of time steps, the system can process a representation of a current state of the physical environment at the current time step using the graph neural network to generate a prediction of a next state of the physical environment at the next time step. Some implementations of the system are adapted for hardware GLOBAL acceleration. As well as performing simulations, the system can be used to predict physical quantities based on measured real-world data. Implementations of the system are differentiable and can also be used for design optimization, and for optimal control tasks.

Abstract: A system to allow the cancellation of terrestrial interferences over aerial networks (Satellite links, and wireless communications) with the support of a canceller module to dynamically decompose wanted and unwanted signals. The invention performs interference cancellation over satellite carriers affected by terrestrial congested spectrum, including the jamming, share of frequencies, or accidental interferences for satellite communications, GPS, Galileo, GNSS or any type of satellite link. The invention provides resiliency to the communication by the regeneration of the desired signal filtering of any unwanted noise received in a terrestrial antenna without the need of any guidance by the modulation. This invention is applicable for any satellite constellation (GEO, MEO, LEO, GPS, MCODE, GNSS, or wireless connectivity, 2G, 3G, 4G, 5G, 6G, Radar, Wifi, WiMax, etc) and any type of satellite antenna (parabolic, mechanically flat panel antenna, steerable flat panel antennas, unidirectional, etc).

Abstract: The present invention discloses a smart electrical socket device enabling the detection of the temperature of the room in which it is installed; the device comprising a housing (1) essentially of a rectangular parallelepiped shape, where the front surface presents a female connection (6) enabling an external element (13) to be plugged in, and the rear surface includes pins (11) for the connection thereof to a power source; further incorporating a temperature module comprising a temperature sensor (2) disposed at the lower part of the internal metallic structure (10) and cut-outs (2.1) in the printed circuit board (PCB) (20) to isolate the heat produced by said board; a power consumption sensor circuit (4) disposed facing the printed circuit board (PCB) (20) and opposite the temperature sensor (2); a load actuator comprised of at least one relay; a power source (14); and a wireless communication module (5) disposed on the internal structure (PCB) (10).

Abstract: The present invention relates to a system that allows the temperature of water inlet and outlet tubes in a water cylinder to be measured, making it possible to estimate the energy stored in the device and to estimate the times when the hot water is being used, in addition to allowing user behaviour to be predicted, anomalies in the hot water to be detected, and the power consumption of the device to be optimised. The device comprises: a water cylinder controller (100) disposed on the case; two thermocouple cables (300) for measuring the water inlet and outlet temperature in the cylinder; and an antenna (200) coupled to an antenna connector (12) in order to connect the controller (100) to another server or to the cloud, where the information is processed.

Abstract: An automated system for acquiring images of one or more capillaries in a capillary bed includes a platform for receiving a body portion of a subject, an imaging subsystem having a repositionable field of view and coupled to the platform to acquire images of at least a capillary bed of the body portion and a controller communicably coupled to the imaging subsystem to automatically reposition the field of view of the imaging subsystem to different areas of the capillary bed, and at each field of view within the capillary bed, activate the imaging subsystem to acquire images of one or more capillaries in the capillary bed.

Abstract: A reinforcement learning system and method that selects actions to be performed by an agent interacting with an environment. The system uses a combination of reinforcement learning and a look ahead search: Reinforcement learning Q-values are used to guide the look ahead search and the search is used in turn to improve the Q-values. The system learns from a combination of real experience and simulated, model-based experience.