Abstract: Example methods, apparatus, and articles of manufacture to classify labels based on images using artificial intelligence are disclosed. An example apparatus includes a regional proposal network to determine a first bounding box for a first region of interest in a first input image of a product; and determine a second bounding box for a second region of interest in a second input image of the product; a neural network to: generate a first classification for a first label in the first input image using the first bounding box; and generate a second classification for a second label in the second input image using the second bounding box; a comparator to determine that the first input image and the second input image correspond to a same product; and a report generator to link the first classification and the second classification to the product.

Abstract: A method of artificial-intelligence-based robotic pipetting for spermatozoa preparation includes positioning a vessel containing a semen sample on a staging mechanism, wherein the staging mechanism includes at least one motor to position the vessel at a specified orientation, using an artificial intelligence/machine learning (AI/ML system) system. The method includes confirming a position of the vessel, using the AI/ML system. The method includes directing a robotic pipettor to place a pipette tip within the semen sample at a position specified by the AI/ML system. The method includes aspirating and mixing the semen sample using the robotic pipettor. The method includes receiving an image object from an imaging system that includes a microscopy system, a camera system, and a lighting system. The method includes determining a semen liquefaction state of the semen sample based at least in part on the image object, using the AI/ML system.

Abstract: There is provided a formatting module configured to format spaces in an electronic character sequence. The formatting module supports at least one language and comprises a language identifier configured to identify whether the electronic character sequence is written in a supported language, and a character identifier configured to identify a particular character or a particular sequence of characters in the electronic character sequence. The formatting module is configured to format spaces in the electronic character sequence on the basis of the language identified and the particular character identified or the particular sequence of characters identified, when a supported language is identified. A system and method for formatting text are also provided.

Abstract: A method of artificial-intelligence-based robotic pipetting for spermatozoa preparation includes positioning a vessel containing a semen sample on a staging mechanism, wherein the staging mechanism includes at least one motor to position the vessel at a specified orientation, using an artificial intelligence/machine learning (AI/ML system) system. The method includes confirming a position of the vessel, using the AI/ML system. The method includes directing a robotic pipettor to place a pipette tip within the semen sample at a position specified by the AI/ML system. The method includes aspirating and mixing the semen sample using the robotic pipettor. The method includes receiving an image object from an imaging system that includes a microscopy system, a camera system, and a lighting system. The method includes determining a semen liquefaction state of the semen sample based at least in part on the image object, using the AI/ML system.

Abstract: A vehicle control system may include a first friction brake member that rotates with a wheel of the vehicle, a second friction brake member that is displaced from an initial position to initiate contact with the first friction brake member to apply braking torque to the wheel, a displacement assembly operably coupled to the second friction brake member to move the second friction brake member responsive to a brake torque request, a sensor network to measure displacement information of the displacement assembly from the initial position to a point of contact between the first and second friction brake members, and a control module operably coupled to the sensor network to record the displacement information to define recorded displacement information, and to determine tapering of the second friction brake member based on the recorded displacement information.

Abstract: A power conversion system includes a high voltage (HV) switchgear; a solid-state transformer; and a low voltage (LV) switchgear. The HV switchgear connects to and disconnects from a HV network. The HV switchgear connects to an input of the solid-state transformer, which comprises first and second modules. The first module converts an HV alternating current (AC) signal into a HV DC signal, and the first module converts an HV DC signal into an HV AC signal. The second module converts an HV DC signal into at least one LV DC signal, and the second module converts at least one LV DC signal into an HV DC signal. The LV switchgear connects to an output of the solid-state transformer. The LV switchgear connects to a plurality of applications or devices and disconnects from the plurality of applications or devices.

Abstract: A power conversion system includes a high voltage (HV) switchgear; a solid-state transformer; and a low voltage (LV) switchgear. The HV switchgear connects to and disconnects from a HV or medium voltage (MV) network. The HV switchgear connects to an input of the solid-state transformer. The solid-state transformer comprises a first module and a second module. The first module converts a HV alternating current (AC) signal into a HV direct current (DC) signal. The second module connects to an output of the first module and converts the HV DC signal from the first module into at least one LV DC signal. The second module comprises at least one sub-module that converts the HV DC signal from the first module into a LV DC signal. The LV switchgear connects to an output of the solid-state transformer.

Abstract: Systems and methods for providing an artificial intelligence-based solution in a dynamic environment that requires models with varying degrees of nuance and specialization. One such dynamic environment relates to generating dynamic human-like conversational responses based on complex data. In particular, systems and methods recite generating dynamic human-like conversational responses using a modular architecture featuring layered data models with gated neural networks. The modular architecture compartmentalizes the various components and functions of an application. That is, the architecture may support multiple layers, each featuring models performing specific functions and/or having been trained on using specific data and/or algorithms.

Abstract: A computer includes a processor and a memory, and the memory stores instructions executable by the processor to receive sensor data indicating an environment around a vehicle while the vehicle is traveling forward along a driving surface; generate a map of the environment from the sensor data, the map including at least one elevation drop; and generate a planned trajectory for the vehicle to travel in reverse and avoid the at least one elevation drop based on the map.

Abstract: A source of a login attempt to a user account can be classified using machine learning. For example, a computing system can input user activity observations associated with one or more login attempts to one or more user accounts into a trained machine learning model. One or more distinguishing factors for the one or more login attempts can be received from the trained machine learning model. The computing system can determine a source of a current login attempt by applying a clustering algorithm to current values of the one or more distinguishing factors. The current values may be derived from current user activity observations associated with the current login attempt. The computing system can determine an authentication level for the current login attempt to the user account based on the source of the current login attempt.

Abstract: A technique may include receiving, by a management service a plurality of instance configurations from a client device. The technique may then include receiving, by the management service, information identifying a launch request for a compute instance. The technique may include determining, by the management service, one or more candidate shapes for the compute instance based at least in part on the plurality of instance configurations. The technique may include selecting, by the management service and from the one or more candidate shapes, a launch shape for the compute instance and launching the compute instance using the launch shape. The technique may then include providing, the client device access to the compute instance, launched based on the launch shape.

Abstract: The present invention relates to a wind turbine rotor blade spacer, a transportation and storage system for wind turbine rotor blades and a related method that prevent the vertical flexion of each one of the blades assemblies, minimizing the stresses and avoiding the contact between vertically and/or horizontally adjacent blades, and in consequence, blade damage. Also, the overall occupied surface by the system once assembled is minimised.

Abstract: Described are various embodiments of a method for managing crop irrigation, and system using same.

Abstract: Systems and methods for providing an artificial intelligence-based solution in a dynamic environment that requires models with varying degrees of nuance and specialization. One such dynamic environment relates to generating dynamic human-like conversational responses based on complex data. In particular, systems and methods recite generating dynamic human-like conversational responses using a modular architecture featuring layered data models with gated neural networks. The modular architecture compartmentalizes the various components and functions of an application. That is, the architecture may support multiple layers, each featuring models performing specific functions and/or having been trained on using specific data and/or algorithms.

Abstract: A system (700) for using a vapor pressure to determine a concentration of a component in a multi-component fluid is provided. The system (700) includes an electronics (710) communicatively coupled to a transducer (720) configured to sense a multi-component fluid. The electronics (710) is configured to determine a first vapor pressure, the first vapor pressure being a vapor pressure of a first component of the multi-component fluid, determine a second vapor pressure, the second vapor pressure being a vapor pressure of a second component of the multi-component fluid, and determine a multi-component vapor pressure, the multi-component vapor pressure being a vapor pressure of the multi-component fluid. The electronics (710) is also configured to determine a concentration of at least one of the first component and the second component based on the multi-component vapor pressure, the first vapor pressure, and the second vapor pressure.

Abstract: Embodiments of the present disclosure relate to learning digital twins of radio environments. Differentiable ray tracing may be used to refine the scene geometry of the physical environment, to learn or optimize the scene properties of objects in the scene, to learn or optimize the scene properties of antennas, and to learn or optimize antenna patterns, array geometries, and orientations and positions of transmitters and receivers. Once scene properties have been learned or optimized, the differentiable ray tracer may further be used to simulate radio wave propagation to simulate the performance of different configurations of the scene geometry and radio devices, such as antennas. In an embodiment, one or more of the scene geometry, scene properties, and antenna characteristics are computed by a differentiable parametric function, such as a neural network, etc. and parameters of the differentiable parametric function are learned using the differentiable ray tracing.

Abstract: A RF power generation system includes a power source configured to generate a periodic waveform applied to a load and a controller configured to receive at least one of a voltage signal or a current signal indicating a respective voltage and current applied to an electrode of the load. The controller determines a surface potential of a workpiece in the load in accordance with the at least one of the voltage signal or the current signal and a series capacitance of the electrode. The controller further determines an ion potential in accordance with an approximation of the surface potential. The periodic waveform may be one of a pulsed DC waveform, a RF waveform, or a pulsed RF waveform.

Abstract: A return spring assembly for a door handle of a door lock is provided. According to some embodiments, the return spring assembly may include a spring cartridge and a hub plate. The hub plate may be removably connected to the spring cartridge and configured to rehand the lock by reorienting the hub plate on the spring cartridge. A method of rehanding such a lock is also provided.

Abstract: A method includes: identifying marking parameters associated with performance of dental appliance etching; includes identifying a first segment of marking data to be etched onto a dental appliance; causing, via dental appliance marking equipment based on the marking parameters, etching of the first segment on the dental appliance; capturing image data associated with the etching of the first segment; and causing the marking parameters to be updated based on the image data. A method includes: subsequent to dental appliances being simultaneously thermoformed via a thermoforming system in a single batch, determining dental appliance data and laser tool data; determining, based on the dental appliance data and the laser tool data, global plan data for performing laser operations of the dental appliances via laser tools; and causing, based on the global plan data via the laser tools, the laser operations of the dental appliances.

Abstract: A meter electronics (20) for using a density measurement of a fluid to verify a vapor pressure is provided. The meter electronics (20) includes a processing system (200) communicatively coupled to a meter assembly (10) having the fluid, the processing system (200) is configured to determine a vapor pressure of the fluid by detecting a phase change of the fluid in the meter assembly (10), measure a density of the fluid based on a resonant frequency of the meter assembly (10), derive a vapor pressure from the measured density, and compare the determined vapor pressure with the derived vapor pressure.