Abstract: Methods, apparatus, systems, and articles of manufacture to predict outputs of electronic design automation (EDA) tools using machine learning are disclosed. An example apparatus includes memory; machine readable instructions; and programmable circuitry to at least one of instantiate or execute the machine readable instructions to: access circuit design data to be optimized by an EDA tool as part of a circuit design process for an integrated circuit; extract features from the circuit design data; apply a machine learning model to the features to estimate an output of the EDA tool, the estimated output determined without execution of the EDA tool; and provide results of the estimated output.

Abstract: The present disclosure relates to a system, a method and a computer-readable medium for recommendation. The method includes obtaining viewer interaction data of a plurality of content types; determining distance values between different content types according to the viewer interaction data; determining a first viewer and a second viewer to have viewed a same content type; determining a distance value between a first content type viewed by the first viewer and a second content type viewed by the second viewer according to the distance values; and determining whether or not to recommend a stream corresponding to the first content type to the second viewer according to the distance value.

Abstract: Systems and methods can utilize a conformer model to process a data set for various data processing tasks, including, but not limited to, speech recognition, sound separation, protein synthesis determination, video or other image set analysis, and natural language processing. The conformer model can use feed-forward blocks, a self-attention block, and a convolution block to process data to learn global interactions and relative-offset-based local correlations of the input data.

Abstract: Pole management is described for installation of network elements based on latitude and longitude values. Pole data having latitude and longitude values is obtained from a plurality of sources. The pole data from the plurality of sources is stored in a central pole database. Poles associated with at least a portion of the pole data is presented on a map in a graphical user interface based at least on the latitude and longitude values. A first pole is selected on the map for consideration for installing a network element for providing wireless services. A geographic boundary is presented on the map relative to the first pole, the geographic boundary encompassing candidate poles. A pole is selected from the candidate poles within the geographic boundary to install the network element to provide the wireless services.

Abstract: A method for e-AC flight dispatch is disclosed, in accordance with one or more embodiments of the present disclosure. The method may include receiving a set of training data. The method may include training a machine learning algorithm of an electric flight dispatch module based on the received set of training data. The method may include receiving one or more sets of real-time data, the one or more sets of real-time data including at least one of airport infrastructure data, airline information data, or battery management data. The method may include generating a set of output data for dispatching an electric aircraft using the trained machine learning algorithm of the electric flight dispatch module.

Abstract: A storage management system is described that calculates a dynamic cache limit for a computing device application on an application-specific basis. The storage management system calculates the dynamic cache limit automatically and independent of user input, based on usage of the application at a computing device, conditions of the computing device, or a combination thereof. Example parameters considered in computing the dynamic cache limit include usage frequency of the application, minimum data retention requirements for the application, available computing device storage, a storage consumption rate of the application, storage consumption by the application relative to at least one other application, size of digital content created or consumed by the application, data download frequency, frequently used digital content, and so forth. The dynamic cache limit is periodically modified and enforced to prevent an application from consuming more computing device storage than permitted by the dynamic cache limit.

Abstract: Disclosed is system and method for allocating vehicles to ride requests. A ride request comprising information indicative of a pickup location and a drop location of a given ride is received. Vehicle information of a plurality of currently-available vehicles, driver information of respective drivers of the plurality of currently-available vehicles and fuel-station information of the one or more of the plurality of fuel stations is accessed. A distance to empty for each of the plurality of currently-available vehicles is predicted based on the vehicle information. One or more eligible vehicles that satisfy eligibility criteria are selected from amongst the plurality of currently-available vehicles. A vehicle from amongst the one or more eligible vehicles that is nearest to the pickup location is allocated.

Abstract: Various embodiments for an alarm performance optimizer are disclosed. An embodiment operates by receiving information about a status of each of a plurality of alarm configurations monitored by a control system. Calculating one or more alarm configuration health metrics based on the received information. The calculated one or more alarm configuration health metrics are displayed in a user interface. A first action that will increase a value of a first alarm metric of the one or more alarm configuration health metrics is identified. The first action is displayed on the user interface. A selection of the first action is received via the user interface. The user interface is updated to display additional details about a subset of the plurality of alarm configurations associated with the first action.

Abstract: Methods and systems for data processing and troubleshooting at a query management service are described. The query management service may receive, via a proxy between the query management service and a communication service, an indication of a query from a user of the communication service. The query management service may determine an intent of the query based on using a third-party natural language processing (NLP) model and customized logic to analyze the query. The query management service may obtain query results based on executing, within a distributed computing environment that includes the query management service and a set of multi-substrate network security services, a sequence of actions, that correspond to the intent of the query. The query management service may transmit an indication of the query results to the communication service, where the query results are rendered according to feedback information received from the user.

Abstract: A method or system for dynamic network security control. The system discovers multiple external network addresses (ENAs) associated with multiple services in a trusted public cloud environment (TPCE), and records the discovered ENAs in a first storage. The system also accesses multiple network security policies stored in the TPCE. The system then maps the ENAs to the network security policies based on contextual relationships therebetween, and stores mappings between the ENAs and the network security policies in the TPCE. The system causes a network access control list to be update based in part on the mappings. The network access control list contains rules that specify which entities are granted or denied access to the ENAs associated with the services.

Abstract: An example apparatus disclosed includes interface circuitry, machine readable instructions, and programmable circuitry to at least one of execute or instantiate the machine readable instructions to send a global model to one or more collaborator models, the one or more collaborator models training on a local dataset associated with a collaborator model, receive one or more collaborator models trained on the local dataset, compute a similarity measurement between the global model and at least one collaborator model, determine aggregation for the global model based on the computed similarity measurement, aggregate one or more one or more collaborator models based on the determined aggregation, and update the global model based on the aggregation.

Abstract: A propulsion system for an aircraft having a two stage contra-rotating fan system to generate thrust. The contra-rotating fan system is surrounded by an aerodynamic duct, having the power train within the duct.

Abstract: Disclosed are various embodiments for self-healing data clusters. One or more candidates are determined from the candidate pool to be evaluated with the new record. A unique pair combination is generated for each one of the candidates of the candidate pool and the new record. Next, candidate data for the one or more candidates is identified from the existing record based at least in part on one or more matching rules. A weight is assigned to one or more matching rules. Then, the candidate data of the one or more candidates and the new record is evaluated for a data linkage. A distance is calculated between each of the unique pair combinations. Finally, the candidates of the existing record and the new record are clustered into groups.

Abstract: An apparatus and method for manufacturing glass include a heat extractor configured to extract heat from molten glass. The heat extractor includes a first conduit and at least one second conduit which may include a plurality of second conduits circumferentially surrounding the first conduit. The first conduit and the at least one second conduit are configured to flow a fluid therethrough.

Abstract: In implementations of systems for generating anti-aliased vector objects, a computing device implements an anti-aliasing system to receive input data describing a Bezier curve of a vector object. The anti-aliasing system generates an aliased curve by rasterizing the Bezier curve in a pixel space having pixels including intersected pixels that are intersected by the aliased curve and non-intersected pixels that are not intersected by the aliased curve. The anti-aliasing system segments the pixels into segments in a virtual space, and the segments have a higher density than the pixels. An intersected segment is identified that is intersected by a portion of the aliased curve in the virtual space. The anti-aliasing system determines a winding number for the intersected segment and generates a portion of an anti-aliased curve for display in a user interface by applying a color value to a coverage mask for an intersected pixel of the pixels.

Abstract: The present disclosure is directed to systems and techniques for processing frames of data. For example, a method can include obtaining a plurality of geospatial data inputs, each geospatial data input of the plurality of geospatial data inputs associated with a sample time and a surveyed area; generating a plurality of features corresponding to each geospatial data input of the plurality of geospatial data inputs; and generating, using a segmentation machine learning network, one or more segmentation masks for the plurality of geospatial data inputs.

Abstract: Embodiments of a method and system for facilitating improvement of a user condition through tailored communication with a user can include receiving a log of use dataset associated with a digital communication behavior at a mobile device, the log of use dataset further associated with a time period; receiving a mobility supplementary dataset corresponding to a mobility-related sensor of the mobile device, the mobility supplementary dataset associated with the time period; determining a tailored communication plan for the user based on at least one of the log of use dataset and the mobility supplementary dataset; transmitting, based on the tailored communication plan, a communication to the user at the mobile device; and promoting a therapeutic intervention to the user in association with transmitting the communication.

Abstract: A system performs automated network address synchronization in a multi-cloud environment. The system instantiates a trusted public cloud environment (TPCE) based on a specification in a first public cloud environment (PCE). The TPCE offers a set of services. The system discovers a set of external network addresses (ENAs) associated with the set of services, and records the set of ENAs in a storage in the TPCE. The system synchronizes the set of ENAs with another set of ENAs associated with a set of services in another TPCE, causing the services in the two TPCEs to have access to both ENAs associated with services in the two TPCEs.

Abstract: A robotic system, method, and device for controlling operation of a robot is disclosed. The robotic system includes (i) a robot configured to move one or more items within a workspace, (ii) a sensor configured to collect sensor data with respect to the workspace, and (iii) one or more processors. The one or more processors are configured to (a) determine to reset operation of the robot, (b) determine, based at least in part on the sensor data, that a human worker exited a safeguarded space within the workspace, and (c) in response to determining that the human worker exited the safeguarded space, resume operation of the robot.

Abstract: Respiratory rate can be calculated from an acoustic input signal using time domain and frequency domain techniques. Confidence in the calculated respiratory rate can also be calculated using time domain and frequency domain techniques. Overall respiratory rate and confidence values can be obtained from the time and frequency domain calculations. The overall respiratory rate and confidence values can be output for presentation to a clinician.