Universal feature representation learning for face recognition

    公开(公告)号:US11580780B2

    公开(公告)日:2023-02-14

    申请号:US17091011

    申请日:2020-11-06

    Abstract: A computer-implemented method for implementing face recognition includes receiving training data including a plurality of augmented images each corresponding to a respective one of a plurality of input images augmented by one of a plurality of variations, splitting a feature embedding generated from the training data into a plurality of sub-embeddings each associated with one of the plurality of variations, associating each of the plurality of sub-embeddings with respective ones of a plurality of confidence values, and applying a plurality of losses including a confidence-aware identification loss and a variation-decorrelation loss to the plurality of sub-embeddings and the plurality of confidence values to improve face recognition performance by learning the plurality of sub-embeddings.

    Root cause analysis for space weather events

    公开(公告)号:US11543561B2

    公开(公告)日:2023-01-03

    申请号:US16665307

    申请日:2019-10-28

    Abstract: Methods and systems for preventing spacecraft damage include identifying a space weather event that corresponds to a spacecraft system failure. A spacecraft system is determined that causes the spacecraft system failure, triggered by the space weather event. A corrective action is performed on the determined spacecraft system to prevent spacecraft system failures from being triggered by future space weather events.

    Complex system anomaly detection based on discrete event sequences

    公开(公告)号:US11520981B2

    公开(公告)日:2022-12-06

    申请号:US16787774

    申请日:2020-02-11

    Abstract: A method detects anomalies in a system having sensors for collecting multivariate sensor data including discrete event sequences. The method determines, using a NMT model, pairwise relationships among the sensors based on the data. The method forms sequences of characters into sentences on a per sensor basis, by treating each discrete variable in the sequences as a character in natural language. The method translates, using the NMT, the sentences of source sensors to sentences of target sensors to obtain a translation score that quantifies a pairwise relationship strength therebetween. The method aggregates the pairwise relationships into a multivariate relationship graph having nodes representing sensors and edges denoted by the translation score for a sensor pair connected thereto to represent the pairwise relationship strength therebetween. The method performs a corrective action to correct an anomaly responsive to a detection of the anomaly relating to the sensor pair.

    INFORMATION-AWARE GRAPH CONTRASTIVE LEARNING

    公开(公告)号:US20220383108A1

    公开(公告)日:2022-12-01

    申请号:US17728071

    申请日:2022-04-25

    Abstract: A method for performing contrastive learning for graph tasks and datasets by employing an information-aware graph contrastive learning framework is presented. The method includes obtaining two semantically similar views of a graph coupled with a label for training by employing a view augmentation component, feeding the two semantically similar views into respective encoder networks to extract latent representations preserving both structure and attribute information in the two views, optimizing a contrastive loss based on a contrastive mode by maximizing feature consistency between the latent representations, training a neural network with the optimized contrastive loss, and predicting a new graph label or a new node label in the graph.

    APPLICATION-CENTRIC DESIGN FOR 5G AND EDGE COMPUTING APPLICATIONS

    公开(公告)号:US20220374259A1

    公开(公告)日:2022-11-24

    申请号:US17730499

    申请日:2022-04-27

    Abstract: A method for specifying and executing an application including multiple microservices on 5G slices within a multi-tiered 5G infrastructure is presented. The method includes managing compute requirements and network requirements of the application simultaneously by determining end-to-end application characteristics by employing an application slice specification including an application ID component, an application name component, an application metadata component, a function dependencies component, a function instances component, and an instance connections component, specifying a function slice specification including a function network slice specification and a function compute slice specification, and employing a runtime component including a resource manager, an application slice controller, and an application slice monitor, wherein the resource manager maintains a database and manages starting, stopping, updating, and deleting application instances.

    MAPPING USING OPTICAL FIBER SENSING

    公开(公告)号:US20220333956A1

    公开(公告)日:2022-10-20

    申请号:US17720245

    申请日:2022-04-13

    Abstract: Distributed fiber optic sensing (DFOS) systems and methods that automatically detect vibration signal patterns from waterfall data recorded by DFOS system operations in real- time and associate the detected vibration signal patterns to GPS location coordinates without human intervention or interpretation. When embodied as a computer vision-based operation according to aspects of the present disclosure, our inventive systems and method provide accurate, cost-efficient, and objective determination without relying on humans and their resulting bias' and inconsistencies.

    Utility Pole Hazardous Event Localization

    公开(公告)号:US20220329068A1

    公开(公告)日:2022-10-13

    申请号:US17717112

    申请日:2022-04-10

    Abstract: Distributed fiber optic sensing (DFOS) and artificial intelligence (AI) systems and methods for performing utility pole hazardous event localization that advantageously identify a utility pole that has undergone a hazardous event such as being struck by an automobile or other detectable impact. Systems and methods according to aspects of the present disclosure employ machine learning methodologies to uniquely identify an affected utility pole from a plurality of poles. Our systems and methods collect data using DFOS techniques in telecommunication fiber optic cable and use an AI engine to analyze the data collected for the event identification. The AI engine recognizes different vibration patterns when an event happens and advantageously localizes the event to a specific pole and location on the pole with high accuracy. The AI engine enables analyses of events in real-time with greater than 90% accuracy.

    DYNAMIC ANOMALY LOCALIZATION OF UTILITY POLE WIRES

    公开(公告)号:US20220329052A1

    公开(公告)日:2022-10-13

    申请号:US17717088

    申请日:2022-04-10

    Abstract: Systems and methods for performing the dynamic anomaly localization of utility pole aerial/suspended/supported wires/cables by distributed fiber optic sensing. In sharp contrast to the prior art, our inventive systems and methods according to aspects of the present disclosure advantageously identify a “location region” on a utility pole supporting an affected wire/cable, thereby permitting the identification and reporting of service personnel that are uniquely responsible for responding to such anomalous condition(s).

Patent Agency Ranking