Abstract: Techniques are described for selective extraction of color attributes from digital images that overcome the challenges experienced in conventional systems for color extraction. In an implementation, a user applies a region selector to a source image to select a portion of the source image for color attribute extraction. A graphics editing system identifies a selected region of the source image as well as visual objects of the source image included as part of the selected region. The graphics editing system iterates through the selected visual objects and extracts color attributes from the visual objects, such as color values, patterns, gradients, gradient stops, opacity, color area, and so forth. The graphics editing system then generates a color palette that includes the extracted color attributes, and the color palette is able to be utilized for various image editing tasks, such as digital image creation and transformation.

Abstract: A method of generating a correction plan for correcting a deformed bone includes inputting to a computer system a first image of the deformed bone in a first plane and inputting to the computer system a second image of the deformed bone in a second plane. Image processing techniques are employed to identify a plurality of anatomical landmarks of the deformed bone in the first image. The first image of the deformed bone is displayed on a display device. A graphical of the deformed bone is autonomously generated and graphically overlaid on the first image of the deformed bone on the display device, the graphical template including a plurality of lines, each line connected at each end to a landmark point corresponding to one of the anatomical landmarks. A model of the deformed bone may be autonomously generated based on the graphical template.

Abstract: A system and method monitor operation of a compressor, determine whether the operation of the compressor is outside of a designated range of values, and, responsive to determining that the operation of the compressor is outside of the designated range of values, one or more of (a) prevent communication of a signal to a system controller that controls operation of the compressor, (b) direct a gas from a reservoir to a pressure sensor used by the system controller to determine a gas pressure generated by the compressor, and/or (c) communicate the signal to the system controller that controls operation of the compressor.

Abstract: A system and method performs speech command verification to determine if audio data includes a representation of a speech command. A first neural network may process portions of the audio data before and after a representation of a wake trigger in the audio data. A second neural network may process the audio data using a recurrent neural network to determine if the audio data includes a representation of a wake trigger.

Abstract: A light detection and ranging (LIDAR) system includes an automatic gain control (AGC) unit to reduce the dynamic range, reducing processing power and saving circuit area and cost. The system detects a return beam of a light signal transmitted to a target, having a first dynamic range in a time domain. An analog to digital converter (ADC) generates a digital signal based on the return beam. A processor can perform time domain processing on the digital signal, convert the digital signal from the time domain to a frequency domain, and perform frequency domain processing on the digital signal in the frequency domain. The AGC unit can measure a power of the return beam, and apply variable gain in the frequency domain to reduce a dynamic range of the return beam to a second dynamic range lower than the first dynamic range.

Abstract: Examples include a method of live migrating a virtual device by creating a virtual device in a virtual machine, creating first and second interfaces for the virtual device, transferring data over the first interface, detecting a disconnection of the virtual device from the virtual machine, switching data transfers for the virtual device from the first interface to the second interface, detecting a reconnection of the virtual device to the virtual machine, and switching data transfers for the virtual device from the second interface to the first interface.

Abstract: An illustrative method of making a fuel cell component includes obtaining at least one blank plate including graphite and a polymer; establishing a temperature of the blank that is sufficient to maintain the polymer in an at least partially molten state; and applying a compression molding force to the blank until the polymer is essentially solidified to form a plate including a plurality of channels on at least one side of the plate. The blank plate has a central area having a first thickness. The blank plate also has two generally parallel edges on opposite sides of the central area. The edges have a second thickness that is greater than the first thickness.

Abstract: The present disclosure is directed to an agent automation framework that is capable of extracting meaning from user utterances and suitably responding using a search-based natural language understanding (NLU) framework. The NLU framework includes a meaning extraction subsystem capable of detecting multiple alternative meaning representations for a given natural language utterance. Furthermore, the NLU framework includes a meaning search subsystem that enables elastic confidence thresholds (e.g., elastic beam-width meaning searches), forced diversity, and cognitive construction grammar (CCG)-based predictive scoring functions to provide an efficient and effective meaning search. As such, the disclosed meaning extraction subsystem and meaning search subsystem improve the performance, the domain specificity, the inference quality, and/or the efficiency of the NLU framework.

Abstract: An electronic device, computer program product, and method manage presenting and pausing of media content in response to locally detected visual and aural interruptions. The electronic device is configured to determine, using one or more sensors from among: (i) an image capturing device positioned to have a field of view of a monitored area and (ii) a microphone positioned to detect sounds in or near the monitored area. A consumer is in the monitored area during presenting of media content by a media output device. The electronic device is configured to monitor the one or more sensors to determine whether an interruption is occurring that can degrade consumer experience relative to the presenting of the media content. In response to determining that the interruption is occurring, the electronic device is configured to pause the presenting of the media content on the media output device.

Abstract: Systems, computer program products, and methods are described herein for information transfer between communication channels. The present invention is configured to electronically receive, via a first communication channel associated with an entity, information associated with a transfer of resources from a user at a first time; initiate one or more machine learning algorithms at on the information associated with the transfer of resources at the first time; generate, using the one or more machine learning algorithms, a summary of the information associated with the transfer of resources; electronically receive an indication that the user wishes to transfer to a second communication channel; and initiate a communication channel transfer protocol to transmit the summary of the information associated with the transfer of resources to the second communication channel.

Abstract: A perfusion container for directly administering to patients a dose of an antineoplastic drug calculated according to a patient's parameter, wherein the first perfusion container comprises a solution of antineoplastic drug at a concentration and volume such that the amount of antineoplastic drug in the container is equal to the calculated dose for one patient but less than the calculated dose for a second patient, the calculated dose is provided to first patient within 5% variance by directly administering the full volume of the solution of antineoplastic drug from the first perfusion container, further the first perfusion container is accompanied by a second top-up perfusion container comprising a solution of antineoplastic drug at a concentration and volume such that the calculated dose is provided within 5% variance by directly administering the full volume of the solution of antineoplastic drug from the first perfusion container and the second top-up container to the second patient.

Abstract: The present technology discloses methods and systems for receiving a security profile request from an integrity verifier, the request including a nonce; requesting, from a trusted platform module, a new nonce, wherein the new nonce is generated at least in part by the nonce and a current timestamp from a clock in the trusted platform module; receiving, from the trusted platform module, the new nonce; requesting, from a cryptoprocessor, a set of platform configuration registers; receiving, from the cryptoprocessor, the set of platform configuration registers; and sending a response to the integrity verifier, the response including the new nonce and the set of platform configuration registers to verify a security status of the trusted platform module and the cryptoprocessor.

Abstract: Disclosed examples determine a duplicated audience size representative of panelists exposed to television media and digital media; determine a panel duplication reach based on the duplicated audience size and a panelist population; determine a did-not-view reach based on a television audience size, a digital audience size, the duplicated audience size, and the panelist population; obtain an overlap multiplier as a ratio of (1) a product of the panel duplication reach and the did-not-view reach and (2) a product of a television panel reach and a digital panel reach; determine a duplication factor for a media item based on a television audience reach, a digital audience reach, and the overlap multiplier; and determine a total audience for the media item based on the television audience reach, the digital audience reach, and the duplication factor.

Abstract: A method, a computer program product, and a computer system for classifying bacteria. The method comprises extracting a morphology signature corresponding to one or more bacteria and extracting a motility signature corresponding to the one or more bacteria. The method further comprises merging the morphology signature and the motility signature into a merged vector signature and classifying the one or more bacteria based on the merged vector signature.

Abstract: A planar member for a stator stack comprises a stator yoke defining a central longitudinal axis, a first surface facing radially outward, and a second surface facing radially inward, a tooth extending radially inwards from the second surface, a first tooth tip extending circumferentially from a radially inward end of the tooth, a second tooth tip extending circumferentially from the radially inward end of the tooth, a first slot portion defined between the first tooth tip and the second surface, a second slot portion defined between the second tooth tip and the second surface, and a slot cooling fin extending radially from the stator yoke into the first slot portion.

Abstract: A method for awarding blockchain mining fees based on recycling efforts includes: receiving recycling data for each of a plurality of mining systems including an amount of recycled materials associated with the respective mining system; receiving validation data for each mining system from third party entities including, for each mining system, a confirmation of the amount of recycled materials for the respective recycling data; selecting one of the mining systems, which is weighted based on the amount of recycled materials for the respective mining system compared to a total amount of recycled materials for all mining systems; and receiving a new block generated by the selected mining system including a block header and a plurality of blockchain data values including a blockchain data value corresponding to a blockchain transaction for payment of mining fees for the new block to a wallet associated with the selected mining system.

Abstract: Some implementations of the disclosure are directed to receiving, at an authentication server system, a distributed ledger address transmitted by a client device to identify itself during an authentication process for accessing a network, where the distributed ledger address corresponds to a distributed ledger network; transmitting an authentication challenge message from the authentication server to the client device; in response to transmitting the authentication challenge message from the authentication server to the client device, receiving at the authentication server, a response to the challenge message including a signature; and using at least the distributed ledger network to determine if the signature used to sign the response to the challenge message is associated with the distributed ledger address transmitted by the client device.

Abstract: Systems, methods, and computer-readable media analyzing memory usage in a network node. A network assurance appliance may be configured to query a node in the network fabric for a number of hardware level entries, stored in memory for the node, that are associated with a concrete level network rule. The network assurance appliance may identify a logical level network intent associated with the concrete level network rule, identify a logical level component of the logical level network intent, and attribute the number of hardware level entries to the logical level component.

Abstract: An apparatus and method for joining an Internet of Things (IoT) network are provided, the apparatus including a communicator configured to receive, from an electronic device, an encrypted auto-onboard configuration data associated with the IoT network, a sensor configured to detect a user command, and at least one processor configured to generate a decryption key based on features extracted from the user command, decrypt the encrypted auto-onboard configuration data using the decryption key, and join the IoT network.

Abstract: Systems and methods for operating an autonomous vehicle. The methods comprising: obtaining, by a computing device, loose-fit cuboids overlaid on 3D graphs so as to each encompass LiDAR data points associated with a given object; defining, by the computing device, an amodal cuboid based on the loose-fit cuboids; using, by the computing device, the amodal cuboid to train a machine learning algorithm to detect objects of a given class using sensor data generated by sensors of the autonomous vehicle or another vehicle; and causing, by the computing device, operations of the autonomous vehicle to be controlled using the machine learning algorithm.