Abstract: A device context of a device is identified based on device data including a current state of the device, and a user context of a user is identified based on user data including user interaction with a user interface for the device. A current task that the user is performing on the device in relation to the current state of the device is identified, and knowledge regarding how the user is performing the current task using the user interface is extracted, using an artificial intelligence technique with respect to the identified device context and the identified user context. The extracted knowledge for the identified current task is stored within a knowledge base, and can be used to adapt the user interface for another user performing the current task on the device in the current state.

Abstract: An in-memory computing architecture is disclosed that can evaluate the transitive closure of graphs using the natural parallel flow of information in 3-D nanoscale crossbars. The architecture can be implemented using 3-D crossbar architectures with as few as two layers of 1-diode 1-resistor (1D1R) interconnects. The architecture avoids memory-processor bottlenecks and can hence scale to large graphs. The approach leads to a runtime complexity of O(n2) using O(n2) memristor devices. This compares favorably to conventional algorithms with a time complexity of O((n3)/p+(n2) log p) on p processors. The approach takes advantage of the dynamics of 3-D crossbars not available on 2-D crossbars.

Abstract: A technical validation mechanism is described that includes the use of facial feature recognition and tokenization technology operating in combination with machine learning models can be used such that specific facial or auditory characteristics of how an originating script is effectuated can be used to train the machine learning models, which can then be used to validate a video or a particular dynamically generated passphrase by comparing overlapping phonemes or phoneme transitions between the originating script and the dynamically generated passphrase.

Abstract: There are provided systems and methods for dynamic node insertion of secondary services for high-availability during main decision failure at runtime. A service provider, such as an electronic transaction processor for digital transactions, may utilize different decision services that implement rules and/or artificial intelligence models for decision-making of data including data in production computing environment. A main decision service may normally be used for data processing and decision-making. However, at certain times, the main decision service may fail, such as if a data processing node fails to process data or times out while processing a data processing request, such as during electronic transaction processing. During this runtime, a dynamic injection processor may dynamically inject a node that performs a call to a secondary service to process the data on behalf of the node and/or main decision service so that a response is provided to the data processing request.

Abstract: An LED luminaire including an outer LED support member having a plurality of LED arrays positioned on a lower side thereof, an LED driver housing centrally located within an interior of the outer LED support member, wherein the outer LED support member is secured to the LED driver housing with a plurality of attachment arms that extend from inner surface of the outer LED support member to the LED driver housing, such that are open spaces between the plurality of attachment arms and between the inner surface of outer LED support member and the LED driver housing, and a plurality of heat dissipating fins positioned on an upper surface of the outer LED support member extending towards the LED driver housing.

Abstract: Systems and methods are provided for new network device provisioning without Internet access. One method may include a method of network device provisioning without Internet access, the method including entering a pre-shared key (PSK) in a dynamic host configuration protocol (DHCP) message, obtaining the PSK from a set of DHCP message options by an onboarding network device requesting to join a private network, presenting the PSK, by the onboarding network device, to a network management system (NMS) of the private network, validating the PSK by the NMS, and updating an inventory list of the NMS to include the onboarding network device in the inventory list.

Abstract: Systems, methods, and computer media are described for user risk assessment using similarity analysis. Records of transactions performed by a user while in previous enhanced application access sessions can be evaluated against records of transactions performed by other users in previous sessions. The more similar a user is to other users, the more likely it is the user was acting in a typical manner, and the less likely the user poses a security risk. A similarity analysis can be performed using a bipartite graph linking a group of users and a group of application transactions. By examining an edge between a user and a performed transaction, other edges (and corresponding other users) can be identified that also performed the transaction. A similarity score can be calculated based on the bipartite graph and can be used to determine a risk classification and allow or deny an enhanced application access session request.

Abstract: An encapsulated LED engine having a printed circuit board, a plurality of LED arrays, each of said LED arrays mounted on said printed circuit board, and electrically connected to each other, an encapsulation layer comprising a pre-molded optic positioned over and adhered to the printed circuit board, and a frame positioned over the LED arrays and secured to the printed circuit board. A method of forming an encapsulated LED engine is also provided.

Abstract: In some examples, an electronic device comprises a multiplexer, a first device interface coupled to the multiplexer, a second device interface coupled to the multiplexer, a storage controller coupled to the multiplexer, and a controller coupled to the first device interface. The storage controller is to control a storage device. The controller is to determine a mode based on a command for the controller to access the storage controller and, based on the mode, cause the multiplexer to adjust access of the second device interface to the storage controller.

Abstract: Systems, devices, methods, and computer readable media are provided in various embodiments relating to generating a dynamic challenge passphrase data object. The method includes establishing, a plurality of data record clusters, representing a mutually exclusive set of structured data records of an individual, ranking the plurality of feature data fields based on a determined contribution value of each feature data field relative to the establishing of the data record cluster, and identifying, using the ranked plurality of feature data fields, a first and a second feature data field of the plurality of feature data fields. The method includes generating the dynamic challenge passphrase data object, wherein the first or the second feature data field is used to establish a statement string portion, and a remaining one of the first or the second feature data field is used to establish a question string portion and a correct response string.

Abstract: This disclosure enables various technologies for tracking various objects (e.g., mammals, animals, humans, pets) within various defined areas (e.g., rooms, apartments, residences, vehicles, tents) to determine whether those objects satisfy or do not satisfy various criteria, signatures, or thresholds, which may relate to health, safety, or security of those objects within those defined areas. These technologies may be enabled via various radars (e.g., time-of-flight radars, Doppler radars) positioned within those defined areas to track those objects therein. For example, some of such radars may operate in a Ku-band inclusively between about 12 GHz and about 18 GHz, a K-band inclusively between about 18 GHz and about 27 GHz, or a Ka-band inclusively between about 26.5 GHz and about 40 GHz, each of which has been unexpectedly found to be technologically beneficial for tracking those objects within those defined areas.

Abstract: Systems and techniques that facilitate on-the-fly reorganization of directed acyclic graph nodes of a computing service for high integration flexibility are provided. In various embodiments, an input component can receive from a computing client a requested response time to be satisfied by a computing service. In various embodiments, a node property component can access an execution matrix. In various cases, the execution matrix can list execution properties of a plurality of nodes corresponding to the computing service. In various instances, the plurality of nodes can respectively perform a plurality of sub-operations associated with the computing service. In various aspects, the plurality of nodes can include one or more multi-level-of-execution subsets of nodes. In various cases, each multi-level-of-execution subset can contain at least two nodes that facilitate a same sub-operation at different levels of resource utilization.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model to segment magnified images of tissue samples. The method includes obtaining a magnified image of a tissue sample; processing an input comprising: the image, features derived from the image, or both, in accordance with current values of model parameters of a machine learning model to generate an automatic segmentation of the image into a plurality of tissue classes; providing, to a user through a user interface, an indication of: (i) the image, and (ii) the automatic segmentation of the image; determining an edited segmentation of the image, comprising applying modifications specified by the user to the automatic segmentation of the image; and determining updated values of the model parameters of the machine learning model based the edited segmentation of the image.

Abstract: In various examples, end of speech (EOS) for an audio signal is determined based at least in part on a rate of speech for a speaker. For a segment of the audio signal, EOS is indicated based at least in part on an EOS threshold determined based at least in part on the rate of speech for the speaker.

Abstract: A method for troubleshooting and resolving access point device uplink failures. The method includes detecting an unresponsive access point on a wired computer network. In addition, the method includes retrieving a record of peer access points to determine the peer access points for the unresponsive access point. Further, the method proceeds to sending a first request to a peer access point of the unresponsive access point to query the unresponsive access point for a response over a wireless network. In response to the query, the network management system sends a notification that the unresponsive access point has a cable malfunction if the unresponsive access point responds to the query. Furthermore, the method includes, in response to the query, sending a notification to the network management system to inform that the unresponsive access point has a power malfunction if the unresponsive access point fails to respond to the query.

Abstract: A method for use in managing a networked computing system includes: receiving a trigger for a migration of a plurality of local migration artifacts from a first deployment state associated with an on-premises network management system to a second deployment state; and migrating the plurality of local migration artifacts from the first deployment state associated with the on-premises network management system to the second deployment state associated with the cloud-based provisioning system. The migration is seamless and includes reconciling at least one local migration artifact of the plurality of local migration artifacts with a plurality of remote migration artifacts maintained by the cloud-based provisioning system.

Abstract: A method and an electronic device for managing artifacts of an image includes: receiving an input image and extracting multiple features from the input image. The multiple features include a texture of the input image, a color composition of the input image and edges in the input image. Further, the method includes determining a region of interest (RoI) in the input image including an artifact based on the features and generating an intermediate output image by removing the artifact using multiple generative adversarial networks (GANs). Further, the method includes generating a binary mask using the intermediate output image, the input image, an image illustrating edges in the input image and an image illustrating edges in the intermediate output image and obtaining a final output image by applying the generated binary mask to the input image.

Abstract: There are provided systems and methods for hardening of rule data object version for smart deployment. A service provider, such as an electronic transaction processor for digital transactions, may utilize different decision services that implement rules for decision-making of data including real-time data in production computing environments. Rules may correspond to coded statements that perform an automated decision-making service for the computing services and platforms of the service provider. When writing rules different variables for data objects are used, which are updated over time. Thus, a rule authoring application may be updated over time to have more and newer variables, which requires updating of the decision services. To optimize updating of the decision services when deploying new rules, the service provider may determine compatible versions of specifications for the variables. Thereafter, the service provider may determine whether a device service's variable specification requires updating.

Abstract: An imaging system includes a microscope to generate magnified images of regions of interest of a tissue sample, a camera to capture and store the magnified images, and a controller. The controller is configured to, for each magnification level in a sequence of increasing magnification levels, image one or more regions of interest of the tissue sample at the current magnification level. For each region of interest, data is generated defining one or more refined regions of interest based on the magnified image of the region of interest of the tissue sample at the current magnification level. Each refined region of interest corresponds to a proper subset of the tissue sample, and the refined regions of interest of the tissue sample provide the regions of interest to be imaged at a next magnification level from the sequence of increasing magnification levels.

Abstract: This specification describes an adaptive robotic nursing assistant for physical tasks and patient observation and feedback. In some examples, the adaptive robotic nursing assistant includes an omni-directional mobile platform; a footrest on the omni-directional mobile platform; a handlebar located above the footrest such that a user standing on the footrest can grasp the handlebar; a display above the handlebar and at least one user input device; a robot manipulator comprising a robotic arm and an end effector on the robotic arm; and a control system coupled to the omni-directional mobile platform, the control system comprising at least one processor and memory storing executable instructions for the at least one processor to control the omni-directional mobile platform.