公开(公告)号：US20230267305A1

公开(公告)日：2023-08-24

申请号：US18161428

申请日：2023-01-30

Applicant: NEC Laboratories America, Inc.

Inventor： Takehiko Mizoguchi ,  Liang Tong ,  Wei Cheng ,  Haifeng Chen

IPC: G06N3/044 ,  G06N3/08

CPC classification number: G06N3/044 ,  G06N3/08

Abstract: A computer implemented method is provided. The method includes jointly encoding, by a dual-channel feature extractor, a current time series segment with corresponding static statuses into a compact feature. The method further includes converting, by a binary code extractor, the compact feature into a binary code. The method also includes computing distances between the binary code and all binary codes stored in a binary code database. The method additionally includes retrieving the top relevant multivariate time series segments based on the distances.

公开(公告)号：US11710346B2

公开(公告)日：2023-07-25

申请号：US17330832

申请日：2021-05-26

Applicant: NEC Laboratories America, Inc.

Inventor： Manmohan Chandraker ,  Ting Wang ,  Xiang Xu ,  Francesco Pittaluga ,  Gaurav Sharma ,  Yi-Hsuan Tsai ,  Masoud Faraki ,  Yuheng Chen ,  Yue Tian ,  Ming-Fang Huang ,  Jian Fang

IPC: G06V40/16 ,  G06T3/00 ,  G06V10/774

CPC classification number: G06V40/172 ,  G06T3/0006 ,  G06V10/774 ,  G06V40/171

Abstract: Methods and systems for training a neural network include generate an image of a mask. A copy of an image is generated from an original set of training data. The copy is altered to add the image of a mask to a face detected within the copy. An augmented set of training data is generated that includes the original set of training data and the altered copy. A neural network model is trained to recognize masked faces using the augmented set of training data.

公开(公告)号：US20230228617A1

公开(公告)日：2023-07-20

申请号：US18126409

申请日：2023-03-25

Applicant: NEC Laboratories America, Inc.

Inventor： Junqiang HU ,  Ting WANG

IPC: G01H9/00 ,  G01K11/32 ,  G01L1/24

CPC classification number: G01H9/004 ,  G01K11/32 ,  G01L1/242

Abstract: Distributed fiber optic sensing systems (DFOS) methods, and structures that employ DVS / DAS point sensors and a two-stage processing methodology / structure that advantageously enable point sensors to send sensor data at any time - thereby providing significant processing advantages over the prior art.

公开(公告)号：US11698290B2

公开(公告)日：2023-07-11

申请号：US17714091

申请日：2022-04-05

Applicant: NEC Laboratories America, Inc.

Inventor： Shaobo Han ,  Yue Tian ,  Sarper Ozharar ,  Yangmin Ding ,  Ting Wang

IPC: G01H9/00

CPC classification number: G01H9/004

Abstract: Systems and methods for operating a distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) system include a length of optical sensing fiber suspended aerially by a plurality of utility poles and in optical communication with a DFOS interrogator/analyzer. The method includes operating the DFOS/DAS system while manually exciting more than one of the poles to obtain frequency response(s) of the excited poles; contrastively training a convolutional neural network (CNN) with the frequency responses obtained; classifying the utility poles using the contrastively trained CNN; and generating a profile map of the excited poles indicative of the classified utility poles.

公开(公告)号：US11686909B2

公开(公告)日：2023-06-27

申请号：US17228577

申请日：2021-04-12

Applicant: NEC Laboratories America, Inc.

Inventor： Yue Tian

IPC: G02B6/44 ,  G01S5/16 ,  H04B10/27 ,  G02B6/12

CPC classification number: G02B6/4401 ,  G01S5/16 ,  H04B10/27 ,  G02B2006/12138

Abstract: Aspects of the present disclosure describe distributed fiber optic sensing (DFOS) distributed acoustic sensing (DAS) systems, methods, and structures that advantageously provide the localization of utility poles along a route of fiber optic cable.

公开(公告)号：US20230196122A1

公开(公告)日：2023-06-22

申请号：US17899913

申请日：2022-08-31

Applicant: NEC Laboratories America, Inc.

Inventor： Yumin Suh ,  Samuel Schulter ,  Xiang Yu ,  Masoud Faraki ,  Manmohan Chandraker ,  Dripta Raychaudhuri

IPC: G06N3/0985

CPC classification number: G06N3/0985

Abstract: Systems and methods for generating a hypernetwork configured to be trained for a plurality of tasks; receiving a task preference vector identifying a hierarchical priority for the plurality of tasks, and a resource constraint as a tuple; finding tree sub-structures and the corresponding modulation of features for every tuple within an N-stream anchor network; optimizing a branching regularized loss function to train an edge hypernet; and training a weight hypernet, keeping the anchor net and the edge hypernet fixed.

公开(公告)号：US20230170971A1

公开(公告)日：2023-06-01

申请号：US17993341

申请日：2022-11-23

Applicant: NEC Laboratories America, Inc.

Inventor： Mohammad Khojastepour ,  Nairman Torkzaban

IPC: H04B7/06

CPC classification number: H04B7/0695 ,  H04B7/0617 ,  H04B7/0619

Abstract: A method for transmitting data is provided. The method includes sending a probing packet using a scanning beam selected from a set of probing beams. The method further includes receiving feedback about the probing packet. The method also includes determining a data transmission beam based on the set of probing beams and the received feedback. The method additionally includes transmitting data using a multi-element antenna that is configured according to the determined data transmission beam.

公开(公告)号：US20230169339A1

公开(公告)日：2023-06-01

申请号：US18072626

申请日：2022-11-30

Applicant: NEC Laboratories America, Inc.

Inventor： Thomas FERREIRA de LIMA ,  Hsuan-Tung PENG

IPC: G06N3/08 ,  G06N3/044

CPC classification number: G06N3/08 ,  G06N3/044

Abstract: A photonics-assisted platform for time series prediction and classification that performs signal processing directly after the signal acquisition before any analog-to-digital conversion by using a hardware neural network with recurrent connections, implemented in a silicon photonic chip. This neural network recurrency can be implemented in silicon photonics with a much lower latency than state-of-the-art electronic systems. The recurrent neural network can detect temporal correlations and extract features from the time series signal, and therefore reduce the latency constraints for the analog-to-digital conversion and further digital signal processing.

公开(公告)号：US11664893B2

公开(公告)日：2023-05-30

申请号：US17699148

申请日：2022-03-20

Applicant: NEC Laboratories America, Inc.

Inventor： Yue-Kai Huang ,  Junqiang Hu

IPC: H04B10/07 ,  H04B10/079 ,  H04B10/294 ,  H04B10/69 ,  G02B6/02 ,  G01M11/00 ,  H04B10/071 ,  H04J14/02

CPC classification number: H04B10/07957 ,  G02B6/022 ,  H04B10/294 ,  H04B10/6932 ,  G01M11/3109 ,  H04B10/07 ,  H04B10/071 ,  H04J14/02

Abstract: Aspects of the present disclosure describe distributed fiber optic sensing (DFOS) systems, methods, and structures that advantageously overcome problems encountered when operating DFOS systems over operational telecommunications facilities namely, cross-phase modulation, and uneven amplitude profiles through the use of a novel constant amplitude coded DFOS employing suppressed out-of-band signaling.

公开(公告)号：US20230154104A1

公开(公告)日：2023-05-18

申请号：US17963471

申请日：2022-10-11

Applicant: NEC Laboratories America, Inc.

Inventor： Bingbing Zhuang ,  Samuel Schulter ,  Yi-Hsuan Tsai ,  Buyu Liu ,  Nanbo Li

IPC: G06T15/20 ,  G06T17/00 ,  G06V10/774 ,  G06V20/40 ,  G06V10/82

CPC classification number: G06T15/20 ,  G06T17/00 ,  G06V10/774 ,  G06V20/41 ,  G06V10/82 ,  G06T2210/56 ,  G06T2200/08

Abstract: A method for achieving high-fidelity novel view synthesis and 3D reconstruction for large-scale scenes is presented. The method includes obtaining images from a video stream received from a plurality of video image capturing devices, grouping the images into different image clusters representing a large-scale 3D scene, training a neural radiance field (NeRF) and an uncertainty multilayer perceptron (MLP) for each of the image clusters to generate a plurality of NeRFs and a plurality of uncertainty MLPs for the large-scale 3D scene, applying a rendering loss and an entropy loss to the plurality of NeRFs, performing uncertainty-based fusion to the plurality of NeRFs to define a fused NeRF, and jointly fine-tuning the plurality of NeRFs and the plurality of uncertainty MLPs, and during inference, applying the fused NeRF for novel view synthesis of the large-scale 3D scene.