Nec Corporation

At+t Corp.

At&t Intellectual Property I, LP

Nec Laboratories America, Inc.

Lucent Technologies Inc.

Nec C Orporation

Eric Cosatto

Hans Peter Graf

Andrea Basso

Joern Ostermann

Juergen Schroeter

Christopher Malon

Shan Liu

David Crawford Gibbon

Thomas M Isaacson

Renqiang Min

Alexandru Niculescu-Mizil

Iain Melvin

Volker Franz Strom

Mehmet Reha Civanlar

Yann Andre LeCun

Igor Durdanovic

Fu Jie Huang

Philip N Ji

Matthew Lynn Miller

Farley Lai

Gerasimos Potamianos

Felix Wu

Xavier Fontaine

Hans-Peter Graf

Steven Lloyd Greenspan

Dongjin Song

Giovanni Milione

David M Weimer

Barbara Buda

Vladimir Vapnik

Pierre-Francois Laquerre

Ting Wang

Srimat T Chakradhar

Ming-Fang Huang

Masayuki Ariyoshi

Srihari Cadambi

Kazumine Ogura

Shaobo Han

Atsushi Marugame

Christopher John Burges

Venkata S Jakkula

Murugan Sankaradass

Leon Bottou

Nagma Samreen Khan

Yang Gao

Harold Christopher Burger

Volker Franz Storm

Peter Graf Hans

Franz Storm Volker

Kyle Gerard

A peak label object detection system (PLODS) includes an object size database configured to store information related to object size for a plurality of objects. The PLODS further includes a three-dimensional (3D) sensor database configured to store information related to parameters of a 3D sensor. The PLODS further includes an annotation database configured to store ground truth annotation information for images. The PLODS further includes a peak shape parameter calculator configured to determine a peak label size based on object size from the object size database and the parameters of the 3D sensor. The PLODS further includes a label generator configured to generate a peak labels map based on label size and the ground truth annotation information.

Peak label object detection system and method of using

Methods and systems for processing a scanned tissue section include locating cells within a scanned tissue. Cells in the scanned tissue are classified using a classifier model. A tumor-cell ratio (TCR) map is generated based on classified normal cells and tumor cells. A TCR isoline is generated for a target TCR value using the TCR map, marking areas of the tissue section where a TCR is at or above the target TCR value. Dissection is performed on the tissue sample to isolate an area identified by the isoline.

Tumor cell isolines

Methods and systems for training a machine learning model include generating pairs of training pixel patches from a dataset of training images, each pair including a first patch representing a part of a respective training image, and a second patch, centered at the same location as the first, representing a larger part of the training image, being resized to a same size of as the first patch. A detection model is trained using the first pixel patches, to detect and locate cells in the images. A classification model is trained using the first pixel patches, to classify cells according to whether the detected cells are cancerous, based on cell location information generated by the detection model. A segmentation model is trained using the second pixel patches, to locate and classify cancerous arrangements of cells in the images.

Multi-scale tumor cell detection and classification

Methods and systems for training a neural network model include augmenting an original training dataset to generate an augmented training dataset, by applying an image artifact to a portion of an original image of the original dataset to generate an artifact image. A target image is generated corresponding to the artifact image by deleting labels from the target image at the position of the artifact. A neural network model is trained using the augmented training dataset and the corresponding target image, the neural network model including a first output that identifies artifact regions and other outputs identifying objects.

Cell nuclei classification with artifact area avoidance

Aspects of the present disclosure describe systems, methods, and structures for the machine learning based regression of complex coefficients of a linear combination of spatial modes from a multimode optical fiber.

Machine learning based regression of complex coefficients of a linear combination of spatial modes from multimode optical fiber

Aspects of the present disclosure describe distributed fiber optic sensing (DFOS) systems, methods, and structures that advantageously provide traffic monitoring, and traffic management which improves the safety and efficiency of a roadway.

Traffic monitoring using distributed fiber optic sensing

Aspects of the present disclosure describe an unsupervised context encoder-based fiber sensing method that detects anomalous vibrations proximate to a sensor fiber that is part of a distributed fiber optic sensing system (DFOS) such that damage to the sensor fiber by activities producing and anomalous vibrations are preventable. Advantageously, our method requires only normal data streams and a machine learning based operation is utilized to analyze the sensing data and report abnormal events related to construction or other fiber-threatening activities in real-time. Our machine learning algorithm is based on waterfall image inpainting by context encoder and is self-trained in an end-to-end manner and extended every time the DFOS sensor fiber is optically connected to a new route. Accordingly, our inventive method and system it is much easier to deploy as compared to supervised methods of the prior art.

Context encoder-based fiber sensing anomaly detection

Systems and methods for solving queries on image data are provided. The system includes a processor device coupled to a memory device. The system includes a detector manager with a detector application programming interface (API) to allow external detectors to be inserted into the system by exposing capabilities of the external detectors and providing a predetermined way to execute the external detectors. An ontology manager exposes knowledge bases regarding ontologies to a reasoning engine. A query parser transforms a natural query into query directed acyclic graph (DAG). The system includes a reasoning engine that uses the query DAG, the ontology manager and the detector API to plan an execution list of detectors. The reasoning engine uses the query DAG, a scene representation DAG produced by the external detectors and the ontology manager to answer the natural query.

Multi-detector probabilistic reasoning for natural language queries

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.

Reconstruction-based anomaly detection

A false alarm reduction system and method are provided for reducing false alarms in an automatic defect detection system. The false alarm reduction system includes a defect detection system, generating a list of image boxes marking detected potential defects in an input image. The false alarm reduction system further includes a feature extractor, transforming each of the image boxes in the list into a respective set of numerical features. The false alarm reduction system also includes a classifier, computing as a classification outcome for the each of the image boxes whether the detected potential defect is a true defect or a false alarm responsive to the respective set of numerical features for each of the image boxes.

False alarm reduction system for automatic manufacturing quality control

A computer-implemented method executed by a processor for training a neural network to recognize driving scenes from sensor data received from vehicle radar is presented. The computer-implemented method includes extracting substructures from the sensor data received from the vehicle radar to define a graph having a plurality of nodes and a plurality of edges, constructing a neural network for each extracted substructure, combining the outputs of each of the constructed neural networks for each of the plurality of edges into a single vector describing a driving scene of a vehicle, and classifying the single vector into a set of one or more dangerous situations involving the vehicle.

Detecting dangerous driving situations by parsing a scene graph of radar detections

A method is provided for model training to detect defective products. The method includes sampling training images of a product to (i) extract image portions therefrom made of a center patch and its context and (ii) black-out the center patch. The method further includes performing unsupervised back-propagation training of a Contextual Auto-Encoder (CAE) model using (i) the image portions with the blacked-out center patch as an input and, (ii) the center patch as a target output and, (iii) an image-based loss function, to obtain a trained CAE model. The method also includes sampling positive and negative center-patch-sized portions from the training images. The method additionally includes normalizing, using the trained CAE model, the positive and negative center-patch-sized portions. The method further includes performing supervised training of a classifier model using the normalized positive and negative center-patch-sized portions to obtain a trained supervised classifier model for detecting the defective products.

Anomaly detection with predictive normalization

Methods and systems for detecting and correcting anomalous inputs include training a neural network to embed high-dimensional input data into a low-dimensional space with an embedding that preserves neighbor relationships. Input data items are embedded into the low-dimensional space to form respective low-dimensional codes. An anomaly is determined among the high-dimensional input data based on the low-dimensional codes. The anomaly is corrected.

Unsupervised neighbor-preserving embedding for image stream visualization and anomaly detection

A false alarm reduction system is provided that includes a processor cropping each input image at randomly chosen positions to form cropped images of a same size at different scales in different contexts. The system further includes a CONDA-GMM, having a first and a second conditional deep autoencoder for respectively (i) taking each cropped image without a respective center block as input for measuring a discrepancy between a reconstructed and a target center block, and (ii) taking an entirety of cropped images with the target center block. The CONDA-GMM constructs density estimates based on reconstruction error features and low-dimensional embedding representations derived from image encodings. The processor determines an anomaly existence based on a prediction of a likelihood of the anomaly existing in a framework of a CGMM, given the context being a representation of the cropped image with the center block removed and having a discrepancy above a threshold.

Unsupervised image-based anomaly detection using multi-scale context-dependent deep autoencoding gaussian mixture model

Aspects of the present disclosure describe systems, methods and structures for classification of higher-order spatial modes using machine learning systems and methods in which the classification of high-order spatial modes emitted from a multimode optical fiber does not require indirect measurement of the complex amplitude of a light beam's electric field using interferometry or, holographic techniques via unconventional optical devices/elements, which have prohibitive cost and efficacy; classification of high-order spatial modes emitted from a multimode optical fiber is not dependent on a light beam's alignment, size, wave front (e.g. curvature, etc.), polarization, or wavelength, which has prohibitive cost and efficacy; classification of higher-order spatial modes from a multimode optical fiber does not require a prohibitive amount of experimentally generated training examples, which, in turn, has prohibitive efficacy; and the light beam from a multimode optical fiber can be advantageously separated into two orthogonal polarization components, such that, the different linear combination of higher order spatial modes comprising each polarization component can be classified.

Machine learning based classification of higher-order spatial modes

Growing community of inventors

Red Bank, NJ, United States of America

Eric Cosatto