Adaptive Convolutional Neural Knowledge Graph Learning System Leveraging Entity Descriptions

    公开(公告)号:US20190122111A1

    公开(公告)日:2019-04-25

    申请号:US16168244

    申请日:2018-10-23

    Abstract: Systems and methods for predicting new relationships in the knowledge graph, including embedding a partial triplet including a head entity description and a relationship or a tail entity description to produce a separate vector for each of the head, relationship, and tail. The vectors for the head entity, relationship, and tail entity can be combined into a first matrix, and adaptive kernels generated from the entity descriptions can be applied to the matrix through convolutions to produce a second matrix having a different dimension from the first matrix. An activation function can be applied to the second matrix to obtain non-negative feature maps, and max-pooling can be used over the feature maps to get subsamples. A fixed length vector, Z, flattens the subsampling feature maps into a feature vector, and a linear mapping method is used to map the feature vectors into a prediction score.

    Probabilistic Shaping for Arbitrary Modulation Formats

    公开(公告)号:US20190109752A1

    公开(公告)日:2019-04-11

    申请号:US16153029

    申请日:2018-10-05

    Abstract: Systems and methods for optical data transport, including controlling data transport across an optical transmission medium by generating two-dimensional (2D) distribution matchers (DMs) based on probabilistic fold shaping (PFS) and arbitrary probabilistic shaping (APS). The 2D PFS-based DM is can encode any N-fold rotationally symmetrical Quadrature Amplitude Modulation (QAM) format by applying the 2D PFS-based DM only to symbols in one quadrant based on a target entropy. A fold index yield uniform distribution is determined, and is utilized to carry generated uniform distributed parity check bits across the optical transmission medium. The 2D APS-based DM can encode any arbitrary modulation formats by encoding uniform binary data to generate non-uniform target symbols, and generating a probability distribution for the target symbols by indirectly applying the 2D APS-based DM based on a target probability distribution and a detected code rate of generated FEC code.

    NEURAL NETWORK TRANSFER LEARNING FOR QUALITY OF TRANSMISSION PREDICTION

    公开(公告)号:US20190108445A1

    公开(公告)日:2019-04-11

    申请号:US16153018

    申请日:2018-10-05

    Abstract: Systems and methods for predicting performance of a modulation system are provided. A neural network model is trained using performance information of a source system. The neural network model is modified with transferable knowledge about a target system to be evaluated. The neural network model is tuned using specific characteristics of the target system to create a source-based target model. The target system performance is evaluated using the source-based target model to predict system performance of the target system.

    HOST BEHAVIOR AND NETWORK ANALYTICS BASED AUTOMOTIVE SECURE GATEWAY

    公开(公告)号:US20190104108A1

    公开(公告)日:2019-04-04

    申请号:US16146166

    申请日:2018-09-28

    Abstract: Systems and methods for an automotive security gateway include an in-gateway security system that monitors local host behaviors in vehicle devices to identify anomalous local host behaviors using a blueprint model trained to recognize secure local host behaviors. An out-of-gateway security system monitors network traffic across remote hosts, local devices, hotspot network, and in-car network to identify anomalous behaviors using deep packet inspection to inspect packets of the network. A threat mitigation system issues threat mitigation instructions corresponding to the identified anomalous local host behaviors and the anomalous remote host behaviors to secure the vehicle devices by removing the identified anomalous local host behaviors and the anomalous remote host behaviors. Automotive security gateway services and vehicle electronic control units operate the vehicle devices according to the threat mitigation instructions.

    LONG-TAIL LARGE SCALE FACE RECOGNITION BY NON-LINEAR FEATURE LEVEL DOMAIN ADAPTION

    公开(公告)号:US20190095699A1

    公开(公告)日:2019-03-28

    申请号:US16145578

    申请日:2018-09-28

    Abstract: A computer-implemented method, system, and computer program product are provided for facial recognition. The method includes receiving, by a processor device, a plurality of images. The method also includes extracting, by the processor device with a feature extractor utilizing a convolutional neural network (CNN) with an enlarged intra-class variance of long-tail classes, feature vectors for each of the plurality of images. The method additionally includes generating, by the processor device with a feature generator, discriminative feature vectors for each of the feature vectors. The method further includes classifying, by the processor device utilizing a fully connected classifier, an identity from the discriminative feature vector. The method also includes control an operation of a processor-based machine to react in accordance with the identity.

    GENERATIVE ADVERSARIAL INVERSE TRAJECTORY OPTIMIZATION FOR PROBABILISTIC VEHICLE FORECASTING

    公开(公告)号:US20190094867A1

    公开(公告)日:2019-03-28

    申请号:US16145649

    申请日:2018-09-28

    Abstract: Systems and methods for predicting vehicle behavior includes capturing images of a vehicle in traffic using an imaging device. Future behavior of the vehicle is stochastically modeled using a processing device including an energy-based model stored in a memory of the processing device. The energy-based model includes generating a distribution of possible future trajectories of the vehicle using a generator, sampling the distribution of possible future trajectories according to an energy value of each trajectory in the distribution of possible future trajectories an energy model to determine probable future trajectories, and optimizing parameters of each of the generator and the energy model using an optimizer. A user is audibly alerted with a speaker upon an alert system recognizing hazardous trajectories of the probable future trajectories.

    Management of grid-scale energy storage systems

    公开(公告)号:US10234886B2

    公开(公告)日:2019-03-19

    申请号:US15228670

    申请日:2016-08-04

    Abstract: A system and method for management of one or more grid-scale Energy Storage Systems (GSSs), including generating an optimal GSS schedule in the presence of frequency regulation uncertainties. The GSS scheduling includes determining optimal capacity deployment factors to minimize penalties for failing to provide scheduled energy and frequency regulation up/down services subject to risk constraints; generating a schedule for a GSS unit by performing co-optimization using the optimal capacity deployment factors, the co-optimization including tracking upper and/or lower bounds on a state of charge (SoC) and including the bounds as a hard constraints; and calculating risk indices based on the optimal scheduling for the GSS unit, and outputting an optimal GSS schedule if risk constraints are satisfied. A controller charges and/or discharges energy from GSS units based on the generated optimal GSS schedule.

    Distance estimation between an RFID tag and an RFID reader

    公开(公告)号:US10234550B2

    公开(公告)日:2019-03-19

    申请号:US15891994

    申请日:2018-02-08

    Abstract: A system, method, and computer program product are provided for estimating a distance. The system includes a Radio Frequency Identifier (RFID) reader. The system further includes an RFID tag. The system also includes measurement equipment for measuring a plurality of phase differences at different frequencies between transmitted Radio Frequency (RF) signals from the RFID reader and corresponding received RF signals at the RFID tag. The system additionally includes a processor. The processor is configured to calculate normalized phases from the plurality of phase differences. The processor is further configured to calculate corrected phases by resolving one or more ambiguities from the normalized phases. The processor is also configured to obtain a characteristic curve using the corrected phases. The processor is additionally configured to provide an estimate of the distance based on the characteristic curve and the corrected phases.

    ELECTRONIC MESSAGE CLASSIFICATION AND DELIVERY USING A NEURAL NETWORK ARCHITECTURE

    公开(公告)号:US20190079999A1

    公开(公告)日:2019-03-14

    申请号:US16038858

    申请日:2018-07-18

    Abstract: A system for electronic message classification and delivery using a neural network architecture includes one or more computing devices associated with one or more users, and at least one computer processing system in communication with one or more computing devices over at least one network. The at least one computer processing system includes at least one processor operatively coupled to a memory device and configured to execute program code stored on the memory device to receive one or more inputs associated with one or more e-mails corresponding to the one or more users across the at least one network, classify the one or more e-mails by performing natural language processing based on one or more sets of filters conditioned on respective ones of the one or more inputs, and permit the one or more users access to the one or more classified e-mails via the one or more computing devices.

Patent Agency Ranking