Abstract: A material handling system sorts mixed materials utilizing a combination of x-ray fluorescence and/or a vision system that implements an artificial intelligence system in order to identify or classify each of the materials, which are then sorted into separate groups based on such an identification or classification. The system is capable of sorting between materials typically found within Zorba, Zebra, and Twitch.

Abstract: Systems/techniques that facilitate interpretable task-specific dimensionality-reduction are provided. In various embodiments, a system can access a three-dimensional medical image. In various aspects, the system can generate, via execution of a first deep learning neural network, a voxel-wise weight map corresponding to the three-dimensional medical image and a set of projection vectors corresponding to the three-dimensional medical image. In various instances, the system can generate a set of two-dimensional projection images of the three-dimensional medical image, based on the voxel-wise weight map and the set of projection vectors. In various cases, the first deep learning neural network can be trained in a serial pipeline with a second deep learning neural network that is configured to perform an inferencing task on two-dimensional inputs. This can cause the set of two-dimensional projection images to be tailored to the inferencing task.

Abstract: Embodiments include methods, performed by a user equipment (UE), for hybrid ARQ (HARQ) feedback in relation to multicast transmissions from a network node in a radio access network (RAN). Such methods include receiving, from the network node, first downlink control information (DCI) scheduling a first multicast transmission associated with the UE and determining a HARQ feedback mode for the first multicast transmission. Such methods also include, based on the first DCI, attempting to decode the first multicast transmission; and selectively transmitting HARQ feedback related to the first multicast transmission to the network node based on the determined HARQ feedback mode and on whether the attempt to decode is successful or unsuccessful. Embodiments also include complementary methods for a network node, as well as UEs and network nodes configured to perform such methods.

Abstract: The disclosure relates to a communication method and system for converging a fifth-generation (5G) communication system for supporting higher data rates beyond a fourth-generation (4G) system with a technology for Internet of Things (IoT). The disclosure may be applied to intelligent services based on the 5G communication technology and the IoT-related technology, such as a smart home, a smart building, a smart city, a smart car, a connected car, health care, digital education, smart retail, security and safety services. A method for predicting channel quality status (CQS) in a wireless network by a base station (BS) is provided.

Abstract: A method, system, and computer program product for generating lineage events of machine learning models. The method may include identifying a machine learning model with missing lineage. The method may also include generating a creation event and deployment event for the machine learning model. The method may also include generating a version change event for the machine learning model. Generating the version change event may include identifying one or more predicted data points with a low model confidence; rescoring the one or more predicted data points based on the machine learning model at a second time period; determining that the updated one or more predicted data points are significantly different than the one or more predicted data points; and determining that there is a new version of the machine learning model. The method may also include creating a lineage path for the machine learning model.

Abstract: Certain aspects of the present disclosure provide techniques for beam management between two or more user equipment (UEs). In some aspects, the disclosure is directed to methods and techniques for performing various beam management procedures (e.g., P1, P2, and P3 procedures) on a sidelink communication between two or more UEs.

Abstract: Nocturia has been defined as the need for an individual to wake up one or more times during the night to void. Further, Nocturia detection also requires analysis of sleeping pattern of the person. In such cases a lot of assumptions are made when the person is not in bedroom during nights. A method and system for detection and validation of Nocturia in the person has been provided. The system is utilizing a statistical based analysis, a rule based analysis, a machine learning based analysis and analysis of sleeping pattern of the person to detect and validate Nocturia. The system ensures that the person is not disturbed in his/her daily activities. Further, the processes deployed in the system are completely un-supervisory in nature meaning it does not have the dependency of needing to have trained machine learning dataset.

Abstract: Aspect 19 is the apparatus of any of aspects 14-18, further includes that the value of the response time and a value of the first time slot are based on an actual slot of the transmission of the first SL-PRS.

Abstract: Identifying an indistinct entity within an image can include generating by an image filter multiple gradients, each of which corresponds to one of a plurality of pixels of an image captured by an imager. The image can be searched for a likely repeating pattern. Responsive to detecting, based on the multiple gradients, a likely repeating pattern within the image, data structures can be generated, the data structures comprising a set of probabilistically weighted feature vectors corresponding to the likely repeating pattern. A machine learning model can classify each of the set of probabilistically weighted feature vectors. An identity of the likely repeating pattern can be output, the identity based on the machine learning model classifications of the probabilistically weighted feature vectors.

Abstract: In an example implementation consistent with the features disclosed herein, high availability of a stateful application is achieved by orchestrating multiple computing clusters. A stateful application is deployed at a first application operator and a second application operator of a first computing cluster and a second computing cluster, respectively. The first application operator includes a first control loop that changes the first computing cluster based on first resources of the first computing cluster. The second application operator includes a second control loop that changes the second computing cluster based on second resources of the second computing cluster. Synchronization of the first resources with the second resources is configured, such as via an object storage service. The first application operator and the second application operator are scaled to, respectively, nonzero and zero. A load balancer is configured to route requests to the first computing cluster.

Abstract: An apparatus including an air conditioner device including a condenser, an expansion valve, an evaporator, and a compressor, a cooling fan configured to cool the condenser, wherein the cooling fan includes a fan motor and a blade, a sensing unit, and a controller configured to determine whether an operating condition of the cooling fan and a flooding condition of a vehicle are satisfied based on driving information of the vehicle detected by the sensing unit and to control an operation of the fan motor of the cooling fan according to whether the vehicle is flooded.

Abstract: A module of a processing system for flipping a substrate in vacuum includes a clamp assembly for securing the substrate, a first motor assembly coupled to the clamp assembly for rotating the clamp assembly, and a second motor assembly coupled to the first motor assembly for raising and lowering the first motor assembly and the clamp assembly.

Abstract: A method of controlling a plurality of Internet of Things (IoT) devices included in an IoT ecosystem is provided. A change of a value of a resource of an IoT device from among the plurality of IoT devices is detected, an intent associated with the resource of which the value is changed is identified, a resource associated with the identified intent from among resources of the plurality of IoT devices is determined, and a value of the determined resource is controlled based on a context corresponding to the identified intent.

Abstract: Aspects of the disclosure provide for congestion control mechanisms to reduce data transmission queues and to increase link utilization through precise congestion signals and reduction of control loop delay. A congestion control system (CC) system can utilize Back-To-Sender (BTS) packets over (round trip time) RTT control loop delay to react to congestion faster. The CC system can apply Proactive Ramp-up (PRU) to identify flow completions to occupy released bandwidth right on time, e.g., as bandwidth is made available. The CC system can perform supply matching (SM) through network calculus concepts to increase link utilization. The CC system can apply some or all of the use of BTS packets, PRU, and/or SM to reduce network latency and improve data flow completion time as compared with other approaches.

Abstract: Disclosed are various embodiments for rate proportional scheduling to reduce packet loss in virtualized network function chains. A congestion monitor executed by a first virtual machine executed by a host computing device can detect congestion in a receive queue associated with a first virtualized network function implemented by a first virtual machine. The congestion monitor can send a pause signal to a rate controller executed by a second virtual machine executed by the host computing device. The rate controller can receive the pause signal. In response, the rate controller can pause the processing of packets by a second virtualized network function implemented by the second virtual machine to reduce congestion in the receive queue of the first virtualized network function.

Abstract: Methods, apparatuses and systems related to maintaining stored data are described. The apparatus may be configured to refresh the stored data according to schedule that includes different delays between successive refresh operations.

Abstract: A health signature of each switching device in a control system is estimated using system parameters such as a DC-link voltage, three-phase voltages, three-phase currents, and temperature. The switching devices can be implemented as transistors, and a health signature for each transistor may be an on-state resistance or an on-state voltage of the transistors. For example, the on-state resistance for a metal-oxide-semiconductor field-effect transistor (MOSFET) functions as a health signature. Alternatively, the on-state voltage is used as a health signature for an insulated-gate bipolar transistor (IGBT). Additionally, a junction temperature is estimated for each transistor. Using the estimated health signatures and the junction temperatures, the remaining useful life of each transistor is estimated.

Abstract: An electronic device comprising a lower deck and an upper deck adjacent to a source. Each of the lower deck and the upper deck comprise tiers of alternating conductive materials and dielectric materials. Each of the lower deck and the upper deck also comprise an array region and one or more non-array regions. Memory pillars are in the lower deck and the upper deck of the array region and the memory pillars are configured to be operably coupled to the source. Dummy pillars are in the upper deck of the one or more non-array regions and the dummy pillars are configured to be electrically isolated from the source. Another conductive material is in the upper deck and the lower deck of the one or more non-array regions. Additional electronic devices and related systems and methods of forming an electronic device are also disclosed.

Abstract: In one embodiment, a method comprises: obtaining, by a process, path trace data collected by a plurality of performance monitoring agents across a computer network; obtaining, by the process, one or more catalogs having application-based correlation information for the path trace data; generating, by the process, network mapping directed graphs by correlating the path trace data using the one or more catalogs, the network mapping directed graphs logically comprising nodes categorized at a plurality of levels of aggregation and edges connecting the nodes; associating, by the process, test-based performance data with the edges of the network mapping directed graphs; and providing, by the process, at least one Sankey diagram based on the network mapping directed graphs and test-based performance data associated with their edges for selectable display by a user interface.

Abstract: Methods, systems, and devices for wireless communications are described. In some examples, a user equipment (UE) may support dual connectivity. That is, the UE may establish communications with a master node and a secondary node of a wireless communications network. The master node may correspond to a master cell group (MCG) and the secondary node may correspond to a secondary cell group (SCG). In some examples, as described herein, the UE operating in dual connectivity may collect data for optimization of the wireless communications network or upon detecting a failure associated with the master cell group or the SCG and transmit the collected data to a network entity (e.g., one of the master node or the secondary node), where the collected data is based on the SCG being in a deactivated state. In some examples, upon receiving the collected data, the network entity may attempt to recover from the failure.