Nec Corporation

Shaobo Han

Ming-Fang Huang

Ting Wang

Yue Tian

Sarper Ozharar

Yangmin Ding

Yuheng Chen

Milad Salemi

Philip N Ji

Tingfeng Li

Eric Cosatto

Renqiang Min

Yuanda Xu

Zhuocheng Jiang

Yueheng Chen

Jiatong Li

Sheng Zhong

You Lu

A machine learning (ML)/artificial intelligence (AI) based distributed fiber optic sensing (DFOS) system and method providing detection and localization of gunshot events. In addition to the ML/AI DFOS, a signal processing pipeline that compresses an audible distributed acoustic sensing (DAS) waveform data into a small set of features that protects privacy of individuals while preserving the utility of acoustic events to detect the gunshot events and discriminate same from other events. A data-driven deep learning approach automatically predicts acoustic event types with higher accuracy that realized by prior art methods.

Gunshot detection via classification using deep learning and fiber sensing technologies

A distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) system and method employing a fiber optic sensor cable that collects vibrational data of individual utility poles suspending the fiber optic sensor cable and stores the vibrational data in a central office (CO). Machine learning (ML) models are developed, trained, and utilized to analyze vibrational features of the utility poles and determine their integrity. Additionally, DFOS/DAS systems and methods according to the present disclosure determine the location(s) of fiber coils that exist along a length of a fiber optic sensor cable.

System to measure coil locations and lengths on aerial fiber cables by distributed fiber sensing for decision making

A method for underground cable localization by fast time series template matching and distributed fiber optic sensing (DFOS) includes: providing the DFOS system including a length of optical sensor fiber; a DFOS interrogator in optical communication with the optical sensor fiber, said DFOS interrogator configured to generate optical pulses, introduce the generated pulses into the length of optical sensor fiber, and receive backscattered signals from the length of the optical sensor fiber; and an intelligent analyzer configured to analyze DFOS data received by the DFOS interrogator and determine from the backscattered signals, vibrational activity occurring at locations along the length of the optical sensor fiber; deploying a programmable vibration generator to a field location proximate to the length of optical sensor fiber; transmitting to the programmable vibration generator a unique vibration pattern to be generated by the vibration generator; and operating the programmable vibration generator to generate the unique vibration pattern transmitted; and operating the DFOS system and collecting/analyzing the determined vibrational activity to further determine vibrational activity indicative of the unique vibration pattern generated by the vibration generator.

Underground cable localization by fast time series template matching

Aspects of the present disclosure describe the localization of a utility pole by distributed fiber sensing of aerial fiber cable suspended from the utility pole.

Utility pole localization by distributed fiber sensing of aerial fiber cable

Systems, methods, and structures for efficiently identifying individual fibers located in a deployed cable that advantageously reduces laborious field efforts while reducing service outage time. The systems and methods locate a targeted fiber in a cable ('Cable ID') and then identify the targeted fiber (“Fiber ID”) by detecting DFOS signal attentions—without cutting the optical fiber. Two distinct determinations may be made namely, Cable ID and Fiber ID. DFOS operation detects vibration signals occurring along a sensor fiber. As implemented, Cable ID is an interactive-machine learning-based algorithm that automatically locates cable position along a sensor fiber route. Fiber ID detects a signal attenuation by bending a group of fibers with bifurcation to pinpoint a targeted individual fiber within a fiber cable.

Fiber identification without cut point using distributed fiber optic sensing

A reinforcement learning based approach to the problem of query object localization, where an agent is trained to localize objects of interest specified by a small exemplary set. We learn a transferable reward signal formulated using the exemplary set by ordinal metric learning. It enables test-time policy adaptation to new environments where the reward signals are not readily available, and thus outperforms fine-tuning approaches that are limited to annotated images. In addition, the transferable reward allows repurposing of the trained agent for new tasks, such as annotation refinement, or selective localization from multiple common objects across a set of images. Experiments on corrupted MNIST dataset and CU-Birds dataset demonstrate the effectiveness of our approach.

Learning ordinal representations for deep reinforcement learning based object localization

Aspects of the present disclosure describe distributed fiber optic sensing (DFOS) systems, methods, and structures that advantageously identify location(s) of construction—or other activities—taking place along fiber optic cable routes that can damage the fiber optic cables.

Object localization and threat classification for optical cable protection

Systems, and methods for automatically identifying an underground optical fiber cable length from DFOS systems in real time and pair it with GPS coordinates that advantageously eliminate the need for in-field inspection/work by service personnel to make such real-time distance/location determinations. As such, inefficient, error-prone and labor-intensive prior art methods are rendered obsolete. Operationally, our method disclosure involves driving vehicles including GPS to generate traffic patterns and automatically mapping traffic trajectory signals from a deployed buried fiber optic cable to locate geographic location(s) of the buried fiber optic cable. Traffic patterns are automatically recognized; slack in the fiber optic cable is accounted for; location of traffic lights and other traffic control devices/structures may be determined; and turns in the fiber optic cable may likewise be determined.

Fiber sensing using supervisory path of submarine cables

Aspects of the present disclosure describe DFOS systems, methods, and structures that advantageously extract road traffic from DFOS vibration patterns such that anomaly detection is possible. Sensed vibration data is represented accurately as a set of points, where each point is denoted as a tuple with elements indicating a time stamp, a location along a length of a DFOS optical sensing cable, and vibration strength detected at the location at the time. Traffic pattern detection is based on a progressive probabilistic Hough transform (PPHT) that exploits global information from an entire spatial-temporal data snapshot to assess a cause of detected vibrations.

Road traffic extraction for unknown anomaly detection using distributed fiber optic sensing

A fiber optic sensing technology for vehicle run-off-road incident automatic detection by an indicator of sonic alert pattern (SNAP) vibration patterns. A machine learning method is employed and trained and evaluated against a variety of heterogeneous factors using controlled experiments, demonstrating applicability for future field deployment. Extracted events resulting from operation of our system may be advantageously incorporated into existing management systems for intelligent transportation and smart city applications, facilitating real-time alleviation of traffic congestion and/or providing a quick response rescue and clearance operation.

Distributed intelligent SNAP informatics

Distributed fiber optic sensing (DFOS) systems, methods and structures for determining the proximity of vibration sources located perpendicular to a sensor fiber that is part of the DFOS system that may potentially threaten/damage or otherwise compromise the sensor fiber itself. Systems, methods, and structures according to aspects of the present disclosure employ Artificial Intelligence (AI) methodology(ies) that use as input a fundamental physical understanding of wave propagation and attenuation in the ground along with Bayesian inference and Maximum Likelihood Estimation (MLE) techniques for estimating/determining the proximity of potentially damaging vibration sources to the optical sensor fiber.

Perpendicular distance prediction of vibrations by distributed fiber optic sensing

A method of utility pole integrity assessment by distributed fiber optic sensing/distributed acoustic sensing (DFOS/DAS) employing existing telecommunications fiber optic cable as a sensor. The fiber optic cable is suspended aerially from a plurality of utility poles and a machine learning model is developed during training by mechanically exciting the utility poles. Once developed, and in sharp contrast to the prior art, the machine learning model—in conjunction with DFOS/DAS operation—determines an integrity assessment for a plurality of the utility poles aerially suspending the fiber optic cable from a mechanical impact of a single pole.

Utility pole integrity assessment by distributed acoustic sensing and machine learning

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 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.

Growing community of inventors

Princeton, NJ, United States of America

Shaobo Han