Nec Corporation

Jian Fang

Ting Wang

Yaowen Li

Ming-Fang Huang

Manmohan Chandraker

Philip N Ji

Junqiang Nochur Hu

Yue Tian

Yi-Hsuan Tsai

Sarper Ozharar

Shaobo Han

Yuheng Chen

Gaurav Sharma

Masoud Faraki

Francesco Pittaluga

Qiang Wang

Christopher White

Shuj Murakami

Xiang Xu

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

Systems, methods, and structures for colorless distributed fiber optic sensing/distributed vibration sensing (DOFS/DVS) over dense wavelength division multiplexing (DWDM) telecommunications facilities that operate over a C-band wavelength range spanning from 1525 nm to 1565 nm wherein the DOFS/DVS systems exhibit suitable reconfigurability of its wavelength to match a wavelength of a desired testing channel providing DOFS/DVS capabilities to existing DWDM communications infrastructure as a retrofit. The DFOS/DVS systems include an optical sensor fiber; a colorless DFOS/DVS interrogator in optical communication with the optical sensor fiber and configured to generate optical pulses, introduce the generated pulses into the optical sensor fiber, and receive backscattered signals from the optical sensor fiber; and an intelligent analyzer configured to analyze colorless DFOS/DVS data received by the DFOS/DVS interrogator and determine from the backscattered signals, vibrational activity occurring at locations along the optical sensor fiber.

Colorless distributed fiber optic sensing / distributed vibration sensing

Aspects of the present disclosure describe Rayleigh-based DTSS that utilizes few-mode fiber (FMF), which supports multiple spatial modes. For each spatial mode, a wavelength-scanning configuration gives the relative wavelength (or frequency) shift between two consecutive measurements. The temperature and strain changes can therefore be separated through different temperature/strain sensitivities of various mode-pairs. Advantageously, Rayleigh-based DTSS according to aspects of the present disclosure removes temperature-strain ambiguity, enhances measurement accuracy, reduces errors. and enables new features for multi-parameter sensing.

Few-mode Rayleigh-based distributed fiber sensor for simultaneous temperature and strain sensing

A method for time synchronization using distributed fiber optic sensing (DFOS) that employs several trusted time beacons that are attached to the DFOS sensing fiber which in turn is connected to the DFOS interrogator. The beacons transmit their signal via two different mediums, (1) wirelessly to sensor nodes in the coverage area, and (2) through vibrations on fiber to the DFOS/DAS system located at a trusted area such as the central office. Wireless broadcast to nearby sensors includes a timestamp and beacon ID. All the sensors in the field use one of the beacons in their vicinity (the one with the strongest signal) as their time reference and send the data back with the corresponding beacon index.

Time synchronization method with trusted beacons and distributed fiber sensing

Physimetric-based data security for coded distributed temperature sensing (DTS) in which physimetric information is extracted from a coded-DTS interrogator which is unique for each interrogator at each operating run time—and used to reconstruct a final temperature determination from DTS data. The physimetric information includes coded-DTS pulse code and coded-DTS pulse profile information as a key to permit secure sharing with authorized users. The pulse code and pulse profile information are encrypted and made available to an authorized user. The authorized user can then decrypt the pulse code and pulse profile information and subsequently use this key information (pulse profile and pulse code files) to retrieve temperature information from for example, a remote computer providing a continuous raw data feed—without being susceptible to eavesdropping. The pulse profile and pulse code files permit reconstruction of temperature from DTS continuous raw data feed which have no meaningful informational value to an eavesdropper who has no access to the unencrypted pulse profile and pulse code information.

Physimetric-based data security for coded distributed temperature sensing

Aspects of the present disclosure describe systems, methods, and structures for distributed temperature sensing that employ joint wavelet denoising to achieve desirable signal-to-noise ratio(s) over extended sensor fiber distances.

Joint wavelet denoising for distributed temperature sensing

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.

Facial recognition for masked individuals

Aspects of the present disclosure describe a multilayer coding method for physical value measurements in which a multi-pulse pattern is generated through several layers, each of which is encoded with a different cyclic codeword. The total coding gain is the product of the gains of each layer advantageously allowing a long cyclic codeword to be replaced by combining several short cyclic codewords. Of particular advantage, methods according to the present disclosure provide better signal-to-noise characteristics, longer sensing distances and lower computational complexity particularly suitable for high-performance and cost-effective distributed optical fiber sensing (DOFS).

Growing community of inventors

West Windsor, NJ, United States of America

Jian Fang