公开(公告)号：US20190079820A1

公开(公告)日：2019-03-14

申请号：US16033278

申请日：2018-07-12

Applicant: NEC Laboratories America, Inc.

Inventor： Pranay Anchuri ,  Jianwu Xu ,  Hui Zhang

IPC: G06F11/07

CPC classification number: G06F11/079 ,  G06F11/0751 ,  G06F11/0778 ,  G06F11/0787

Abstract: Systems and methods for automatically generating failure signatures in a computer system for performing computer system fault diagnosis are provided. The method includes receiving log data, converting each log in the log data into a collection of log pattern sequences including one or more log pattern sequences corresponding to one or more respective failure categories associated with the computer system, generating a collection of seed patterns by computing a global set of patterns from the collection of log pattern sequences, and extracting the collection of seed patterns from the global set of patterns, generating a log pattern grammar representation for each of the one or more log pattern sequences, generating a failure signature for each of the one or more failure categories based on the log pattern grammar representation and the collection of seed patterns, and employing the failure signatures to perform computer system fault diagnosis on new log data.

公开(公告)号：US20190056451A1

公开(公告)日：2019-02-21

申请号：US16103970

申请日：2018-08-16

Applicant: NEC Laboratories America, Inc.

Inventor： Babak Asghari ,  Ratnesh Sharma ,  Mohammad Ehsan Raoufat

IPC: G01R31/36 ,  H02S40/30 ,  H02S20/23 ,  H02J7/00

Abstract: Systems and methods for controlling Battery Energy Storage Systems (BESSs), including determining historical minimum state of charge (SOC) for peak shaving of a previous day based on historical photovoltaic (PV)/load profiles, historical demand charge thresholds (DCT), and battery capacity of the BESSs. A minimum SOC for successful peak shaving of a next day is estimated by generating a weighted average based on the historical minimum SOC, and optimal charging/discharging profiles for predetermined intervals are generated based on estimated PV/load profiles for a next selected time period and grid feed-in limitations. Continuous optimal charging/discharging functions are provided for the one or more BESSs using a real-time controller configured for overriding the optimal charging/discharging profiles when at least one of a high excess PV generation, a peak shaving event, or a feed-in limit violation is detected.

公开(公告)号：US10204299B2

公开(公告)日：2019-02-12

申请号：US15342766

申请日：2016-11-03

Applicant: NEC Laboratories America, Inc.

Inventor： Manmohan Chandraker ,  Angjoo Kim

IPC: G06K9/00 ,  G06N3/04 ,  G06F17/30 ,  G06T7/33 ,  G06T7/50

Abstract: A computer-implemented method for training a deep learning network is presented. The method includes receiving a first image and a second image, mining exemplar thin-plate spline (TPS) to determine transformations for generating point correspondences between the first and second images, using artificial point correspondences to train the deep neural network, learning and using the TPS transformation output through a spatial transformer, and applying heuristics for selecting an acceptable set of images to match for accurate reconstruction. The deep learning network learns to warp points in the first image to points in the second image.

公开(公告)号：US20190036602A1

公开(公告)日：2019-01-31

申请号：US16048155

申请日：2018-07-27

Applicant: NEC Laboratories America, Inc.

Inventor： Giovanni MILIONE

IPC: H04B10/11 ,  H04J14/04 ,  H04B10/516

CPC classification number: H04B10/11 ,  H04B10/112 ,  H04B10/516 ,  H04J14/04

Abstract: Aspects of the present disclosure describe systems, methods, and structures for free-space optical communications using Hermite-Gaussian modes resulting in advantageous performance over prior art systems particularly with respect to lateral misalignment.

公开(公告)号：US10169656B2

公开(公告)日：2019-01-01

申请号：US15688131

申请日：2017-08-28

Applicant: NEC Laboratories America, Inc.

Inventor： Dongjin Song ,  Haifeng Chen ,  Guofei Jiang ,  Yao Qin

IPC: G06K9/00 ,  G06N3/02 ,  G06F17/18 ,  G06F15/18 ,  G08B23/00 ,  G08B31/00 ,  G06F17/30 ,  G06N3/04 ,  G06Q10/06

Abstract: Systems and devices including an imaging sensor to capture video sequences in an environment having safety concerns therein. The systems and devices further including a processor to generate driving series based on observations from the video sequences, and generate predictions of future events based on the observations using a dual-stage attention-based recurrent neural network (DA-RNN). The DA-RNN includes an input attention mechanism to extract relevant driving series, an encoder to encode the extracted relevant driving series into hidden states, a temporal attention mechanism to extract relevant hidden states, and a decoder to decode the relevant hidden states. The processor further generates a signal for initiating an action to machines to mitigate harm to items.

公开(公告)号：US20180374207A1

公开(公告)日：2018-12-27

申请号：US15983342

申请日：2018-05-18

Applicant: NEC Laboratories America, Inc.

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

IPC: G06T7/00 ,  H04N19/17 ,  H04N19/132

Abstract: Systems and methods for detecting and correcting defective products include capturing at least one image of a product with at least one image sensor to generate an original image of the product. An encoder encodes portions of an image extracted from the original image to generate feature space vectors. A decoder decodes the feature space vectors to reconstruct the portions of the image into reconstructed portions by predicting defect-free structural features in each of the portions according to hidden layers trained to predict defect-free products. Each of the reconstructed portions are merged into a reconstructed image of a defect-free representation of the product. The reconstructed image is communicated to a contrastor to detect anomalies indicating defects in the product.

公开(公告)号：US20180365696A1

公开(公告)日：2018-12-20

申请号：US15982496

申请日：2018-05-17

Applicant: NEC Laboratories America, Inc.

Inventor： Tan Yan ,  Haifeng Chen ,  Ajiro Yasuhiro

IPC: G06Q20/40 ,  H04L29/06 ,  H04L12/58 ,  H04L29/08 ,  G06K9/62

Abstract: Systems and methods for mitigating fraud in transactions including clustering account holders into groups with a cluster generator by jointly considering account activities as features in a clustering algorithm such that account holders in each group have similar behavior according to analysis of the features in the clustering algorithm. In each group, a list of suspicious transactions is detected with a suspicious behavior detector by determining outlier transactions for a transaction type of interest relative to transactions of each account holder in a group. An alert is generated and sent to users with a fraud suspicion response system to mitigate the suspicious transactions.

公开(公告)号：US20180336468A1

公开(公告)日：2018-11-22

申请号：US15979500

申请日：2018-05-15

Applicant: NEC Laboratories America, Inc.

Inventor： Asim Kadav ,  Igor Durdanovic ,  Hans Peter Graf

IPC: G06N3/08 ,  G06N5/04 ,  G06K9/00

Abstract: Systems and methods for pruning a convolutional neural network (CNN) for surveillance with image recognition are described, including extracting convolutional layers from a trained CNN, each convolutional layer including a kernel matrix having at least one filter formed in a corresponding output channel of the kernel matrix, and a feature map set having a feature map corresponding to each filter. An absolute kernel weight is determined for each kernel and summed across each filter to determine a magnitude of each filter. The magnitude of each filter is compared with a threshold and removed if it is below the threshold. A feature map corresponding to each of the removed filters is removed to prune the CNN of filters. The CNN is retrained to generate a pruned CNN having fewer convolutional layers to efficiently recognize and predict conditions in an environment being surveilled.

公开(公告)号：US20180336256A1

公开(公告)日：2018-11-22

申请号：US15979512

申请日：2018-05-15

Applicant: NEC Laboratories America, Inc.

Inventor： Ding Li ,  Kangkook Jee ,  Zhichun Li ,  Mu Zhang ,  Zhenyu Wu

IPC: G06F17/30

CPC classification number: G06F16/1744 ,  G06F3/0643 ,  G06F16/2246 ,  G06F16/2272 ,  G06F16/24568 ,  G06F16/25 ,  G06F16/258 ,  G06F16/9027 ,  G06F21/552 ,  G06F21/6218 ,  G06F2216/03 ,  G06F2221/2143 ,  G06K9/6219

Abstract: Systems and methods for data reduction including organizing data of an event stream into a file access table concurrently with receiving the event stream, the data including independent features and dependent features. A frequent pattern tree (FP-Tree) is built including nodes corresponding to the dependent features according to a frequency of occurrence of the dependent features relative to the independent features. Each single path in the FP-Tree is merged into a special node corresponding to segments of dependent features to produce a reduced FP-Tree. All path combinations in the reduced FP-Tree are identified. A compressible file access template (CFAT) is generated corresponding to each of the path combinations. The data of the event stream is compressed with the CFATs to reduce the dependent features to special events representing the dependent features.

公开(公告)号：US10122547B2

公开(公告)日：2018-11-06

申请号：US15237485

申请日：2016-08-15

Applicant: NEC Laboratories America, Inc.

Inventor： Rajesh Mahindra ,  Karthikeyan Sundaresan ,  Junguk Cho ,  Sampath Rangarajan

IPC: H04W4/00 ,  H04L12/46 ,  H04L12/66 ,  H04L12/851 ,  H04L12/14 ,  H04L12/407 ,  H04W76/00 ,  H04L29/08

Abstract: Systems and methods for standards compatible Mobile Edge Computing (MEC), including splitting Serving gateways (SGWs) and Packet Data Network gateways (PDN-GWs) to provision sufficient resources to deploy data-plane entity instances locally at a Radio Access Network (RAN) edge with one or more cloudlets. One or more local controller nodes is deployed in one or more operator clouds, a dedicated bearer is leveraged to route traffic from the one or more cloudlets through the split SGWs and PDN-GWs, and the dedicated bearer is configured with a traffic flow template (TFT) including an Internet Protocol (IP) address of the one or more cloudlets. Efficient access to one or more MEC applications at the RAN edge is provided to one or more user devices using the dedicated bearer.