公开(公告)号：US20200097771A1

公开(公告)日：2020-03-26

申请号：US16580497

申请日：2019-09-24

Applicant: NEC Laboratories America, Inc.

Inventor： Renqiang Min ,  Kai Li ,  Bing Bai ,  Hans Peter Graf

IPC: G06K9/62 ,  G06T7/00 ,  G06N3/04 ,  G06N3/08

Abstract: A method is provided for visual inspection. The method includes learning, by a processor, group disentangled visual feature embedding vectors of input images. The input images include defective objects and defect-free objects. The method further includes generating, by the processor using a weight generation network, classification weights from visual features and semantic descriptions. Both the visual features and the semantic descriptions are for predicting defective and defect-free labels. The method also includes calculating, by the processor, a cosine similarity score between the classification weights and the group disentangled visual feature embedding vectors. The method additionally includes episodically training, by the processor, the weight generation network on the input images to update parameters of the weight generation network. The method further includes generating, by the processor using the trained weight generation network, a prediction of a test image as including any of defective objects and defect-free objects.

公开(公告)号：US10593033B2

公开(公告)日：2020-03-17

申请号：US15983392

申请日：2018-05-18

Applicant: NEC Laboratories America, Inc.

Inventor： Alexandru Niculescu-Mizil ,  Eric Cosatto ,  Felix Wu

IPC: G06K9/00 ,  G06T7/00 ,  H04N19/132 ,  H04N19/17 ,  G16H50/70 ,  G16H50/20 ,  G06T11/20 ,  G16H20/30 ,  G16H30/40 ,  G06T11/00

Abstract: Systems and methods for diagnosing a patient condition include a medical imaging device for generating an anatomical image. A reconstructor reconstructs the anatomical image by reconstructing portions of the anatomical image to be a healthy representation of the portions and merging the portions into the anatomical image to generate a reconstructed image. A contrastor contrasts the anatomical image with the reconstructed image to generate an anomaly map indicating locations of difference between the anatomical image and the reconstructed image. An anomaly tagging device tags the locations of difference as anomalies corresponding to anatomical abnormalities in the anatomical image, and a display displays the anatomical image with tags corresponding to the anatomical abnormalities.

公开(公告)号：US10582529B2

公开(公告)日：2020-03-03

申请号：US15915491

申请日：2018-03-08

Applicant: NEC Laboratories America, Inc.

Inventor： Karthikeyan Sundaresan ,  Eugene Chai ,  Mohammad Khojastepour ,  Sampath Rangarajan

IPC: H04J3/06 ,  H04W72/12 ,  H04W56/00 ,  H04W48/16 ,  H04W88/08 ,  H04W84/04

Abstract: A system is provided for speculative scheduling that includes a base station having a processor. The processor computes an overall schedule for a set of clients. The overall schedule is formed from a set of speculative schedules, is configured to maximize unlicensed spectrum usage, and is computed by (a) determining a speculative schedule for each resource block from a set of resource blocks in a given sub-frame based on statistics determined for the clients individually and jointly, and (b) selecting, for formation into the overall schedule, (i) a particular resource block and (ii) the speculative schedule for the particular resource block, that yield the maximum incremental utility relative to already determined speculative schedules for other resource blocks in the set, based on criteria including uplink access statistics. The processor executes the overall schedule responsive to a completion of the speculative schedule determination for each resource block in the given sub-frame.

公开(公告)号：US10574448B2

公开(公告)日：2020-02-25

申请号：US15897930

申请日：2018-02-15

Applicant: NEC Laboratories America, Inc.

Inventor： Ivan Djordjevic ,  Ting Wang ,  Shaoliang Zhang

IPC: H04L29/06 ,  H04L9/08 ,  H04B10/70 ,  H04J14/02 ,  H04B10/11 ,  H01Q3/26 ,  H01Q3/28 ,  H01Q3/38 ,  H04L27/34 ,  H04J14/04 ,  H04B10/516 ,  H01Q3/34 ,  H01Q21/00 ,  H04L27/36 ,  H04L27/38 ,  H04B7/0413 ,  H04B10/50

Abstract: Systems and methods for quantum key distribution using orbital angular momentum (OAM)-modes-enabled secure multidimensional coded modulation. The quantum key distribution including symbols of a raw key across subcarriers and multiplexing the subcarriers to form an electrical carrier. Then optically modulating the electrical carrier with an electro-optical modulator using an optical signal. The optically modulated electrical carrier is then imposed on a pre-determined OAM mode using an optical OAM multiplexer, attenuated, and transmitted across a quantum channel. A receiver then receives the transmitted signal and demultiplexes it with an optical OAM demultiplexer to extract projections. The projections then undergo optical-to-electrical conversion using a coherent optical detector with an optical signal from a local oscillator. A resulting estimated electrical carrier is then demultiplexed into subcarriers. The subcarrier undergo phase noise cancellation and subsequent demodulation to extract estimated symbol constellation points corresponding the symbols of the raw key.

公开(公告)号：US10572777B2

公开(公告)日：2020-02-25

申请号：US15436199

申请日：2017-02-17

Applicant: NEC Laboratories America, Inc.

Inventor： Xiang Yu ,  Feng Zhou ,  Manmohan Chandrakar

IPC: G06K9/62 ,  G06K9/00 ,  G06K9/46 ,  G06T7/73 ,  G06N3/04 ,  G06T7/60 ,  G06N3/08

Abstract: A system and method are provided. The system includes a processor. The processor is configured to generate a response map for an image, using a four stage convolutional structure. The processor is further configured to generate a plurality of landmark points for the image based on the response map, using a shape basis neural network. The processor is additionally configured to generate an optimal shape for the image based on the plurality of landmark points for the image and the response map, using a point deformation neural network. A recognition system configured to identify the image based on the generated optimal shape to generate a recognition result of the image. The processor is also configured to operate a hardware-based machine based on the recognition result.

公开(公告)号：US20200050899A1

公开(公告)日：2020-02-13

申请号：US16522711

申请日：2019-07-26

Applicant: NEC Laboratories America, Inc.

Inventor： Biplob Debnath ,  Debayan Deb ,  Srimat Chakradhar

IPC: G06K9/62 ,  G06T7/00 ,  G06N20/10

Abstract: A method is provided for classifying objects. The method detects objects in one or more images. The method tags each object with multiple features. Each feature describes a specific object attribute and has a range of values to assist with a determination of an overall quality of the one or more images. The method specifies a set of training examples by classifying the overall quality of at least some of the objects as being of an acceptable quality or an unacceptable quality, based on a user's domain knowledge about an application program that takes the objects as inputs. The method constructs a plurality of first-level classifiers using the set of training examples. The method constructs a second-level classifier from outputs of the first-level automatic classifiers. The second-level classifier is for providing a classification for at least some of the objects of either the acceptable quality or the unacceptable quality.

公开(公告)号：US20200050807A1

公开(公告)日：2020-02-13

申请号：US16517941

申请日：2019-07-22

Applicant: NEC Laboratories America, Inc.

Inventor： Mohammad Khojastepour ,  Mustafa Arslan ,  Sampath Rangarajan

IPC: G06K7/10

Abstract: Systems and methods for sequential detection-based classifications of radio-frequency identification (RFID) tags in three-dimensional space are provided. The methods include modeling a response from RFID tags as a probabilistic macro-channel and interrogating an RFID tag by transmitting a series of packets. Each packet is a transmit symbol and a first series of packet is a transmitted codeword. The method includes receiving, from the RFID tag, a second series of packets that is a received codeword in response to the transmitted codeword and finding a jointly typical transmit and receive codeword across all classes of macro-channels. The method also includes declaring a class of the RFID tag based on a largest likelihood between the transmitted codeword and the received codeword.

公开(公告)号：US20200042700A1

公开(公告)日：2020-02-06

申请号：US16507353

申请日：2019-07-10

Applicant: NEC Laboratories America, Inc.

Inventor： Ding Li ,  Kangkook Jee ,  Zhengzhang Chen ,  Zhichun Li ,  Wajih Ul Hassan

IPC: G06F21/55

Abstract: A method for implementing automated threat alert triage via data provenance includes receiving a set of alerts and security provenance data, separating true alert events within the set of alert events corresponding to malicious activity from false alert events within the set of alert events corresponding to benign activity based on an alert anomaly score assigned to the at least one alert event, and automatically generating a set of triaged alert events based on the separation.

公开(公告)号：US20190393965A1

公开(公告)日：2019-12-26

申请号：US16449319

申请日：2019-06-21

Applicant: NEC Laboratories America, Inc.

Inventor： Shaoliang ZHANG ,  Fatih YAMAN ,  Eduardo RODRIGUEZ ,  Yoshihisa INADA ,  Kohei NAKAMURA ,  Takanori INOUE

IPC: H04B10/61 ,  H04B10/2543 ,  G06K9/62 ,  H04L27/20 ,  G06N3/08 ,  H04B10/2531 ,  H04L27/26

Abstract: Aspects of the present disclosure describe systems, methods and structures for optical fiber nonlinearity compensation using neural networks that advantageously employ machine learning (ML) algorithms for nonlinearity compensation (NLC) that advantageously provide a system-agnostic model independent of link parameters, and yet still achieve a similar or better performance at a lower complexity as compared with prior-art methods. Systems, methods, and structures according to aspects of the present disclosure include a data-driven model using the neural network (NN) to predict received signal nonlinearity without prior knowledge of the link parameters. Operationally, the NN is provided with intra-channel cross-phase modulation (IXPM) and intra-channel four-wave mixing (IFWM) triplets that advantageously provide a more direct pathway to underlying nonlinear interactions.

公开(公告)号：US10511613B2

公开(公告)日：2019-12-17

申请号：US16055675

申请日：2018-08-06

Applicant: NEC Laboratories America, Inc.

Inventor： Zhengzhang Chen ,  LuAn Tang ,  Zhichun Li ,  Chen Luo

IPC: H04L29/06 ,  H04L12/24

Abstract: A computer-implemented method for implementing a knowledge transfer based model for accelerating invariant network learning is presented. The computer-implemented method includes generating an invariant network from data streams, the invariant network representing an enterprise information network including a plurality of nodes representing entities, employing a multi-relational based entity estimation model for transferring the entities from a source domain graph to a target domain graph by filtering irrelevant entities from the source domain graph, employing a reference construction model for determining differences between the source and target domain graphs, and constructing unbiased dependencies between the entities to generate a target invariant network, and outputting the generated target invariant network on a user interface of a computing device.