Abstract: Systems and methods for optimizing delivery vehicle resources (e.g. a plurality of vehicles) are described herein. Available time slots for the plurality of vehicles are determined and presented to a user. In response to receiving a delivery order indicating a selected time slot, the delivery order is assigned to a vehicle from the plurality of vehicles based on a time slot indicated in the delivery order and a set of delivery parameters. A delivery route is calculated for each vehicle having a delivery order based on the set of delivery parameters. An optimized delivery route is calculated for each vehicle having a delivery order based on the set of delivery parameters.

Abstract: Systems, methods, and computer-readable media for hierarchichal sharding of flows from sensors to collectors. A first collector can receive a first portion of a network flow from a first capturing agent and determine that a second portion of the network flow was not received from the first capturing agent. The first collector can then send the first portion of the network flow to a second collector. A third collector can receive the second portion of the network flow from a second capturing agent and determine that the third collector did not receive the first portion of the network flow. The third collector can then send the second portion of the network flow to the second collector. The second collector can then aggregate the first portion and second portion of the network flow to yield the entire portion of the network flow.

Abstract: A method for nanoscale tomographic infrared absorption imaging is provided, the method including: generating a first plurality of sets of probe measurements for a plurality of sample locations located across a surface of a sample, and measuring a magnitude and phase of a variation in displacement of the surface of the sample at the particular sample location at the second frequency, wherein the first frequency and the second frequency differ; and generating, based on the first plurality of sets of probe measurements, a three-dimensional tomographic map of absorption of infrared light at the first wavelength by the sample. Generating measurements for a particular location includes generating a first probe measurement by illuminating the sample with infrared light that varies at a first frequency and measuring a variation in displacement of the surface of the sample at the particular sample location at the first frequency.

Abstract: Provided is a compound according to Formula 1 wherein X, R, R1, R2, R3, and R4 are as defined herein. The compound of Formula 1 can be useful in a composition and in a method for inducing ferroptosis in a cell.

Abstract: A CDN system and method to provide access and a better user experience based on a novel CDN architecture wherein each edge server may be outside of an Internet data center, may be stationary or mobile, may be intermittently connected to the multi-tiered content delivery network, may be connected to a last mile over Wi-Fi and may be physically located in a place of interest.

Abstract: An online system uses a model to determine affinities of users for geographical locations. Using the affinities, which may indicate travel-related preferences of the users, the online system may customize content items to include content captured by client devices of other users of the online system. For example, the online system presents to a particular user a content item including a photo or video of a geographical location captured by a camera of a client device of another user who is connected to the particular user. The model may implement, for example, collaborative filtering or other machine learning techniques to determine commonalities between users' travel affinities. Additionally, the model may determine latent properties or temporal trends of user preferences based on training data including historical actions performed on the online system or social data. The model may also classify different types of geographical locations.

Abstract: Features are disclosed for accurately authenticating a delivery agent for unattended delivery of an item. The systems and methods described confirm the location of the delivery agent and proximity to the delivery location using short range wireless communications between a monitoring device at the delivery location and a communication device associated with the delivery agent. Access may also be conditioned on user specified “do not disturb” rules indicating when remote access is authorized. The authentication may be dynamically assessed such as based on a type of item being delivered.

Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform controlling a delivery of a video conference call to a viewport, setting an event-based threshold with respect to the video conference call, determining whether the event-based threshold has been triggered based on an event and whether an amount of time having elapsed from another event is less than a predetermined amount of time, and further controlling the delivery of the video conference call to the viewport based on determining whether the event-based threshold has been triggered and whether the amount of time having elapsed from the other event is less than the predetermined amount of time.

Abstract: A sensor management system includes a historical data repository, a building management system (BMS) controller, and a sensor diagnostics system. The historical data repository may store historical data by a plurality of sensors. The BMS controller may control one or more components of a building subsystem based on data provided by one or more sensors. The sensor diagnostic system may receive, from a sensor, sensor data. The sensor diagnostic system may determine at least one fault in the sensor data. The sensor diagnostic system may select, from the historical data repository, substitute sensor data for the sensor based on a comparison of one or more attributes of the sensor data and one or more attributes of the historical data in the data repository. The sensor diagnostic system may provide, in replacement of the sensor data from the sensor, the supplemental sensor data to the BMS controller.

Abstract: In various examples, a two-dimensional (2D) and three-dimensional (3D) deep neural network (DNN) is implemented to fuse 2D and 3D object detection results for classifying objects. For example, regions of interest (ROIs) and/or bounding shapes corresponding thereto may be determined using one or more region proposal networks (RPNs)—such as an image-based RPN and/or a depth-based RPN. Each ROI may be extended into a frustum in 3D world-space, and a point cloud may be filtered to include only points from within the frustum. The remaining points may be voxelated to generate a volume in 3D world space, and the volume may be applied to a 3D DNN to generate one or more vectors. The one or more vectors, in addition to one or more additional vectors generated using a 2D DNN processing image data, may be applied to a classifier network to generate a classification for an object.

Abstract: Disclosed herein are systems, devices, and methods for providing auto-scaling in a cluster of device instances. In one embodiment, a method is disclosed comprising updating, using a distributed counter, a metric associated with one or more instances executing a network application; identifying that the metric has exceeded a threshold defined in a scaling policy based on comparing the distributed counter to the scaling policy; identifying a command to execute in response to the metric exceeding the threshold; and executing the command to modify the one or more instances.

Abstract: A system and a method for facilitating a processing of a service request is provided. The method includes: accessing a plurality of previously received service requests; receiving a first new service request; determining a handling protocol for the first new service request; adding the received first new service request to the plurality of previously received service requests to generate an updated list of open service requests; and displaying a listing of a least a subset of the updated list of open service requests. The handling protocol includes a priority ranking of the first new service request and an identification of a proposed technician for resolving the corresponding problem. The determination of the handling protocol is performed by assigning weights to each of a set of predefined parameters and algorithmically combining the assigned weights to obtain an overall priority score.

Abstract: Apparatuses, systems, and methods for a user equipment device (UE) to perform methods for triggering a change in beam configuration based on UL beam conditions. The UE may detect an unsafe UL beam condition for an UL beam based, at least in part, on an MPE level being exceeded by the UL beam. In response to the detection, remedial actions that to alleviate the unsafe UL beam condition may be performed. The remedial actions may prioritize UL beam quality over DL beam quality and may include reducing a transmit power of the UL beam based on an MPR, triggering an intra-panel antenna switch to a candidate UL beam that satisfies one or more conditions for intra-panel beam switching, triggering an inter-panel antenna switch to a candidate UL beam that satisfies one or more conditions for intra-panel beam switching, and/or signaling a beam failure to a network serving the UE.

Abstract: A method for rideshare personalization may include identifying one or more unmet needs among a set of needs of a user during a ride of a vehicle based on data from a sensor of the vehicle, updating a user profile of the user to include the one or more unmet needs in association with a set of contextual data related to the ride, and providing services associated with the one or more unmet needs to the user during another ride based on the updated user profile and the set of contextual data related to the another ride.

Abstract: A method of producing a model capable of reducing an influence of spectral variation of reflected light from a workpiece, such as a wafer, and capable of determining an accurate film thickness is disclosed. The method includes: determining sample features representing features of sample spectra of reflected lights from a sample having a film; obtaining similarities by calculating a similarity between each of the sample spectra and a representative spectrum; and producing a film-thickness estimation model by performing machine leaning using training data including the sample features, the similarities, and film thicknesses corresponding to the sample spectra.

Abstract: The need for extracting information trapped in unstructured document images is becoming more acute. A major hurdle to this objective is that these images often contain information in the form of tables and extracting data from tabular sub-images presents a unique set of challenges. Embodiments of the present disclosure provide systems and methods that implement a deep learning network for both table detection and structure recognition, wherein interdependence between table detection and table structure recognition are exploited to segment out the table and column regions. This is followed by semantic rule-based row extraction from the identified tabular sub-regions.

Abstract: This disclosure relates to high-performance computing, and more particularly to techniques for kernel-assisted device polling of user-space devices. A common kernel-based polling mechanism is provided for concurrently handling both kernel-based polling for kernel-space devices such as network interfaces (e.g., network NICs) and kernel-based polling for user-space devices such as remote direct memory access devices (e.g., RDMA NICs). Embodiments perform kernel-based polling on a first device that has a corresponding device driver in an operating system kernel. Using the same polling mechanism, the kernel-based polling is performed on a second device, the second device being a user-space device wherein the kernel-based polling on the second device is configured by creating a second device file descriptor that is not associated with a corresponding device driver in the operating system kernel.

Abstract: Presented herein are systems and methods for dynamically updating and rendering graphical user interfaces at a surgical hub device that is configured to simultaneously coordinate the operation of multiple medical devices connected to the hub. According to an aspect, when a device is connected to the hub, the device can send identifying information to the hub so that the hub can ascertain the identity of the device. Based on the identification data, the hub can access an internal graphical user interface (GUI) database to determine if there are any entries in the database that correspond to the device that is now connected to the hub. If it is determined that the internal GUI database of the hub contains one or more GUIs associated with the device, then the GUI database can transmit the corresponding to GUIs to the electronic display for rendering at the appropriate times.

Abstract: Methods, apparatus, and processor-readable storage media for implementing a message management framework using machine learning techniques are provided herein. An example computer-implemented method includes processing a message comprising identifying at least one message type of the message; determining, based at least in part on the at least one identified message type, one or more message failures by applying one or more machine learning-based rules to at least a portion of the message; determining one or more remedial actions by processing, using one or more machine learning techniques, the at least one identified message type, the one or more determined message failures, and multiple attributes of the message; and performing one or more automated actions based at least in part on the one or more determined remedial actions.

Abstract: Systems and methods described herein perform computer vision (CV) model training in a distributed edge network. Regional Multi-access Edge Compute (MEC) clusters are provided with a local copy of a CV model and a local synthetic training data generator. A MEC cluster receives client data requiring computer vision and applies the local copy of the CV model to the client data. The MEC cluster detects an exception to the local copy of the CV model and generates local synthetic training data for the exception. The MEC cluster updates, based on the local synthetic training data, the local copy of the CV model to form an updated local CV model. The MEC cluster sends the local synthetic training data and the updated local CV model to a central network. The central network uses the local synthetic training data to update a master CV model and any other interconnected CV models.