公开(公告)号：WO2019133316A1

公开(公告)日：2019-07-04

申请号：PCT/US2018/065900

申请日：2018-12-17

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： NICULESCU-MIZIL, Alexandru ,  COSATTO, Eric ,  FONTAINE, Xavier

IPC: G05B23/02 ,  G06N3/08 ,  G06N5/04

Abstract: Methods and systems for detecting and correcting anomalies include predicting normal behavior of a monitored system based on training data that includes only sensor data collected during normal behavior of the monitored system. The predicted normal behavior is compared to recent sensor data to determine that the monitored system is behaving abnormally. A corrective action is performed responsive to the abnormal behavior to correct the abnormal behavior.

公开(公告)号：WO2022066388A1

公开(公告)日：2022-03-31

申请号：PCT/US2021/048832

申请日：2021-09-02

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： KADAV, Asim ,  LAI, Farley ,  GRAF, Hans, Peter ,  NICULESCU-MIZIL, Alexandru ,  MIN, Renqiang ,  ZHOU, Honglu

IPC: G06N3/08 ,  G06N3/04 ,  G06N5/04

Abstract: A method for using a multi-hop reasoning framework to perform multi-step compositional long-term reasoning is presented. The method includes extracting (1001) feature maps and frame-level representations from a video stream by using a convolutional neural network (CNN), performing (1003) object representation learning and detection, linking (1005) objects through time via tracking to generate object tracks and image feature tracks, feeding (1007) the object tracks and the image feature tracks to a multi-hop transformer that hops over frames in the video stream while concurrently attending to one or more of the objects in the video stream until the multi-hop transformer arrives at a correct answer, and employing (1009) video representation learning and recognition from the objects and image context to locate a target object within the video stream.

公开(公告)号：WO2021071911A1

公开(公告)日：2021-04-15

申请号：PCT/US2020/054529

申请日：2020-10-07

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： NICULESCU-MIZIL, Alexandru ,  HAN, Shuchu

IPC: G05B23/02 ,  G05B19/418 ,  H04L29/08 ,  H04W84/18 ,  G06Q50/10

Abstract: Methods and systems for detecting and correcting anomalies include detecting (202) an anomaly in a cyber-physical system, based on a classification of time series information from sensors that monitor the cyber-physical system as being anomalous. A similarity graph is determined (302) for each of the sensors, based on the time series information. A subset of the sensors that are related to the classification is selected (308), based on a spectral embedding of the similarity graphs. A corrective action is performed (206) responsive to the detected anomaly, prioritized according to the selected subset.

公开(公告)号：WO2019005457A1

公开(公告)日：2019-01-03

申请号：PCT/US2018/036809

申请日：2018-06-11

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： NICULESCU-MIZIL, Alexandru ,  COSATTO, Eric ,  WU, Felix

IPC: G01N21/88 ,  A61B5/00 ,  A61B6/00 ,  G16H30/00 ,  G06T7/00

Abstract: Systems and methods for detecting and correcting defective products include capturing (221) at least one image of a product with at least one image sensor to generate an original image of the product. An encoder (223a) encodes portions of an image extracted from the original image to generate feature space vectors. A decoder (223b) 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 (224) into a reconstructed image of a defect-free representation of the product. The reconstructed image (225) is communicated to a contrastor (230) to detect anomalies indicating defects in the product.