Abstract: An arithmetic processing apparatus, includes a memory; and a processor coupled to the memory and the processor configured to: estimate an optical flow between consecutive frames of a moving image, and generate a sound wave corresponding to a target moving image, based on an optical flow estimated for the target moving image, and a deep neural network that generates a sound wave corresponding to an input optical flow and that has performed learning, by associating with time, an optical flow estimated for a moving image with sound wave and a sound wave of the moving image with sound wave.

Abstract: It is disclosed a method for managing a PDU session in a wireless communication system and an apparatus for supporting the same. Particularly, a method for performing handover of a User Equipment (UE) performed by a source Radio Access Network (RAN) that includes a processor, a memory and a communication module in a wireless communication system may include determining to initiate handover to a target RAN; and transmitting a Handover Required message to a source Access and Mobility Management Function (AMF), and the handover is a handover in a case that there is no interface between the RANs or AMF change is required, and the Handover Required message includes a PDU session Identifier (ID) of an activated Protocol Data Unit (PDU) session.

Abstract: A method of updating a PDU session and a network-side device are provided. The method includes: after a User Equipment UE moves across PLMNs or across systems, determining that the UE has a first PDU session of which an anchor SMF is not in a current PLMN; determining a Session Management Function V-SMF in a Visited Public Land Mobile Network VPLMN for the first PDU session, and updating the first PDN session by using the V-SMF.

Abstract: Provided is a machine learning-based semiconductor manufacturing yield prediction system and method. A result prediction method according to an embodiment of the present invention comprises: learning different neural network models by classifying different types of data according to their types and respectively inputting the classified different types of data to the different neural network models; and predicting result values by classifying input data according to their types and respectively inputting the classified input data to different neural network models. Therefore, it is possible to apply different neural network models to respective data according to their types, thereby ensuring a neural network model having a structure appropriate for the characteristics of each type of data and thus accurately predicting a result value.

Abstract: Interacting between users of mobile devices is provided by initiating a desired interaction at a first user device using a gesture sensed by the first user device, determining a gesture area, submitting a desired interaction request for interaction with associated users within the gesture area, and sending a notification to user devices indicating the desired interaction of the first user with one or more users of a local subset, wherein the notification identifies the first user with an identifier independent of identifiers used by the first user outside of interactions with a remote server.

Abstract: Certain aspects of the present disclosure relate to techniques for secondary cell (SCell) configuration signaling and activation procedures. For example, certain aspects provide a method for activating at a user equipment one or more secondary cells of a target base station. The method includes transmitting a measurement report for the one or more secondary cells. The method includes receiving secondary cell activation information for the user equipment from the target base station prior to completion of connection of the user equipment to the target base station, wherein the secondary cell activation information indicates the one or more secondary cells. The method includes activating the one or more secondary cells at the user equipment after completion of connection to the target base station.

Abstract: A system for acquiring three-dimensional (3-D) models of objects includes a first camera group including: a first plurality of depth cameras having overlapping fields of view; a first processor; and a first memory storing instructions that, when executed by the first processor, cause the first processor to: control the first depth cameras to simultaneously capture a first group of images of a first portion of a first object; compute a partial 3-D model representing the first portion of the first object; and detect defects in the first object based on the partial 3-D model representing the first portion of the first object.

Abstract: A user equipment (UE) configured to establish a multimedia data stream with a further UE, identify a predetermined condition, wherein the predetermined condition indicates a decrease in quality of the multimedia data stream at the further UE and implement a mechanism to mitigate the degradation of the decrease in quality of the multimedia data stream at the further UE.

Abstract: Disclosed are methods, systems, devices, servers, apparatus, computer-/processor-readable media, and other implementations, including a method that includes: establishing an emergency call session between a wireless device and a public safety answering point (PSAP) server, via a first communication link, in response to an emergency indication provided by the wireless device; and sending location information indicating a location of the wireless device to the PSAP server via a second communication link, the location information indicating the location of the wireless device and being associated with the emergency call session; where the first communication link is different from the second communication link.

Abstract: In a geographic area with limited satellite coverage, multiple signal sources are statically disposed along a path through the geographic area. To automatically determine geographic positions of the signal sources, signal data collected by a receiver moving along the path is received, where the signal data indicates changes, over a period of time, in strength of respective signals emitted by the signal sources. Indications of a first position of the receiver at a first time prior to entering the geographic area and a second position of the receiver at a second time subsequent to leaving the geographic area are received, and positions for the signal sources are determined using the received signal data and the received indications of the positions and the times. The determined positions for the signal sources are used to geoposition a device moving along the path.

Abstract: Some embodiments of the present disclosure provide a neural network location classifier that is designed and trained in accordance with a hierarchical architecture, thereby producing a hierarchical neural network location classifier. Further embodiments relate to obtaining, through use of the hierarchical neural network location classifier, an inferred hierarchical label for a user equipment location. The inferred hierarchical label may then be decoded to obtain a location.

Abstract: An allocation method of communication resources is use with at least a user mobile device, at least first and second wireless network access point devices, and a base station device for mobile communication. In the allocation method, the base station device receives a registration request from the user mobile device; and the base station device determines an order of the first and second wireless network access point devices for the user mobile device to register in according to intensities of signals of the first and second wireless network access point devices, which are measured by the user mobile device, and counts of user mobile devices having registered in the first and second wireless network access point devices, respectively.

Abstract: A system comprises an integrated small cell and WiFi (ISW) gateway (GW). The ISW GW is integrated with a mobility management entity (MME) and serving gateway (SGW) and has interfaces with both a 3GPP access network and a TWAN. The ISW GW operates as a common control gateway and a common user gateway for both LTE networks and TWANs. User equipment (UE) by means of the ISW GW is able to access the capabilities of a packet data network (PDN) through either the LTE network or TWAN. Further, the ISW GW provides for an existing communication connection between a UE and a PDN to be handed over from one of the LTE network or TWAN to the other. Still further, the ISW GW supports simultaneously maintaining two communication paths, one via the LTE network and one via the TWAN, between a UE and a packet network.

Abstract: A system and a method for multimedia data analysis. The system includes a computing device. The computer device includes a processor and a storage device storing computer executable code. The computer executable code, when executed at the processor, is configured to: encode task description and task meta info into concatenated task vectors; encode context text and context meta info into concatenated context text vectors; encode context image and the context meta info into concatenated context image vectors; perform dual coattention on the concatenated task vectors and the concatenated context text and image vectors to obtain attended task vectors and attended context vectors; perform BiLSTM on the attended task vectors and the attended context vectors to obtain task encoding and context encoding; and decode the task encoding and the context encoding to obtain an answer to the task.

Abstract: A core provider predicts that a device will enter an area of poor coverage by a wireless network provider. Based on the prediction, one or more rules are applied to prioritize data traffic to be received prior to entering the area of poor coverage. The prediction that the device will enter the area of poor coverage may be based on cell coverage data received from the wireless network provider, connection quality data received from other devices, a location of the device, a speed of the device, a direction of the device, or any suitable combination thereof. A route of the device may be changed to avoid or minimize an amount of time in the area of poor coverage. As another alternative, the device may be switched from the wireless network provider to another wireless network with better coverage.

Abstract: Systems, methods and computer software are disclosed for providing a bubble network are described. In one embodiment, a method is disclosed including providing an isolated base station having a coverage area, providing a local HetNet Gateway (HNG) disposed within the coverage area and in communication with the isolated base station, providing a local Evolved Packet Core (EPC) in communication with the local HNG and disposed within the coverage area, and wherein the bubble network is disconnected from a mobile operator core network.

Abstract: The present disclosure is directed toward systems and methods for managing a digital survey over voice-capable devices. In particular, the systems and methods described herein create a digital survey question from a verbal input. Additionally, the systems and methods described herein provide the digital survey question to respondents by way of voice-capable devices. The systems and methods also receive verbal survey responses, generate survey results from the verbal responses, and provide the survey results to a survey administrator.

Abstract: A device may receive site data identifying a site associated with a telecommunications network. The device may receive RF drive test data identifying signal strengths of the site at different location points. The device may receive network KPI data and throughput data associated with the site. The device may assign unique identifiers to the different location points. The device may determine, based on the site data, the RF drive test data, the network KPI data, and the unique identifiers, at least one of reference signal strength data for each of the different location points or downlink channel data for each of the different location points. The device may determine degraded signal strength data identifying a degraded signal strength of each of the different location points, if the site is decommissioned and based on the at least one of the reference signal strength data or the downlink channel data.

Abstract: The present invention discloses a terminal configuration method, including: obtaining, by a network device, cell access information and/or beam access information; determining configuration information based on the cell access information and/or the beam access information; and sending the configuration information to a terminal. The present invention further discloses a network device and a terminal that can implement the foregoing terminal configuration method. In the present invention, mobility of the terminal can be accurately determined, so that cell reselection performance, cell handover performance, or beam change performance of the terminal can be improved.

Abstract: Adversarial input detection and purification (AIDAP) preprocessor and deep learning computer model mechanisms are provided. The deep learning computer model receives input data and processes it to generate a first pass output that is output to the AIDAP preprocessor. The AIDAP preprocessor determines a discriminative region of the input data based on the first pass output and transforms a subset of elements in the discriminative region to modify a characteristic of the elements and generate a transformed input data. The deep learning computer model processes the transformed input data to generate a second pass output that is output to the AIDAP preprocessor which detects an adversarial input or not based on a comparison of the first pass and second pass outputs. If an adversarial input is detected, a responsive action that mitigates effects of the adversarial input is performed.