Abstract: Aspects of the present disclosure describe systems, methods and structures providing non-destructive localization of underground optical fiber cables utilizing distributed fiber optic sensing (DFOS) and time difference of arrival techniques.
Abstract: Aspects of the present disclosure describe systems, methods and structures providing bipolar cyclic coding for Brillouin optical time domain analysis that may be employed—for example—to determine high accuracy temperature and/or strain measurements along an optical fiber. Systems, methods, and structures according to the present disclosure employ the bipolar cyclic coding technique that advantageously overcomes the problems that plague the prior art and provides extended sensing range resulting from superior signal-to-noise characteristics.
Abstract: 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.
Type:
Application
Filed:
October 27, 2020
Publication date:
May 6, 2021
Applicant:
NEC LABORATORIES AMERICA, INC
Inventors:
Giovanni MILIONE, Philip JI, Eric COSATTO
Abstract: Aspects of the present disclosure describe a computer implemented method for the transfer of sensor data on dynamic software defined network (SDN) controlled optical network.
Abstract: Aspects of the present disclosure describe systems, methods. and structures in which a hybrid neural network combining a CNN and several ANNs are shown useful for predicting G-ONSR for Ps-256QAM raw data in deployed SSMF metro networks with 0.27 dB RMSE. As demonstrated, the CNN classifier is trained with 80.96% testing accuracy to identify channel shaping factor. Several ANN regression models are trained to estimate G-OSNR with 0.2 dB for channels with various constellation shaping. Further aspects include the tuning of existing optical networks and the characterization of retrofit/upgraded optical networks to estimate capacity—both aspects employing our inventive hybrid neural network methodology.
Abstract: Aspects of the present disclosure describe improving neural network robustness through neighborhood preserving layers and learning weighted-average neighbor embeddings.
Type:
Application
Filed:
September 23, 2020
Publication date:
March 25, 2021
Applicant:
NEC LABORATORIES AMERICA, INC
Inventors:
Erik KRUUS, Christopher MALON, Bingyuan LIU
Abstract: Aspects of the present disclosure describe systems, methods and structures that perform linear-grammetry and calibration by simultaneous multilateration using only edge distance estimates via two-way ranging.
Type:
Application
Filed:
September 18, 2020
Publication date:
March 25, 2021
Applicant:
NEC LABORATORIES AMERICA, INC
Inventors:
Mohammad KHOJASTEPOUR, Sampath RANGARAJAN
Abstract: Aspects of the present disclosure describe systems, methods and structures including a network that recognizes action(s) from learned relationship(s) between various objects in video(s). Interaction(s) of objects over space and time is learned from a series of frames of the video. Object-like representations are learned directly from various 2D CNN layers by capturing the 2D CNN channels, resizing them to an appropriate dimension and then providing them to a transformer network that learns higher-order relationship(s) between them. To effectively learn object-like representations, we 1) combine channels from a first and last convolutional layer in the 2D CNN, and 2) optionally cluster the channel (feature map) representations so that channels representing the same object type are grouped together.
Abstract: Aspects of the present disclosure describe systems, methods and structures providing contextual grounding—a higher-order interaction technique to capture corresponding context between text entities and visual objects.
Abstract: Aspects of the present disclosure describe systems, methods, and structures that provide action recognition with high-order interaction with spatio-temporal object tracking. Image and object features are organized into into tracks, which advantageously facilitates many possible learnable embeddings and intra/inter-track interaction(s). Operationally, our systems, method, and structures according to the present disclosure employ an efficient high-order interaction model to learn embeddings and intra/inter object track interaction across the space and time for AR. Each frame is detected by an object detector to locate visual objects. Those objects are linked through time to form object tracks. The object tracks are then organized and combined with the embeddings as the input to our model. The model is trained to generate representative embeddings and discriminative video features through high-order interaction which is formulated as an efficient matrix operation without iterative processing delay.
Abstract: Aspects of the present disclosure describe systems, methods and structures for an efficient multi-person posetracking method that advantageously achieves state-of-the-art performance on PoseTrack datasets by only using keypoint information in a tracking step without optical flow or convolution routines. As a consequence, our method has fewer parameters and FLOPs and achieves faster FPS. Our method benefits from our parameter-free tracking method that outperforms commonly used bounding box propagation in top-down methods. Finally, we disclose tokenization and embedding multi-person pose keypoint information in the transformer architecture that can be re-used for other pose tasks such as pose-based action recognition.
Type:
Application
Filed:
September 9, 2020
Publication date:
March 18, 2021
Applicant:
NEC LABORATORIES AMERICA, INC
Inventors:
Asim KADAV, Farley LAI, Hans Peter GRAF, Michael SNOWER
Abstract: Aspects of the present disclosure describe systems, methods and structures providing bidirectional optical fiber communication and sensing using the same fiber transmission band and bidirectional WDM fiber sharing such that communications channels and optical fiber sensing channel(s) coexist on the same fiber. As a result, nonlinear interaction between communications channels and interrogating pulse(s) of sensing are much reduced or eliminated.
Type:
Application
Filed:
May 27, 2020
Publication date:
December 31, 2020
Applicant:
NEC LABORATORIES AMERICA, INC
Inventors:
Yue-Kai HUANG, Ezra IP, Philip Nan JI, Ming-Fang HUANG
Abstract: Aspects of the present disclosure describe systems, methods and structures for providing semiconductor amplifiers exhibiting a low polarization-dependent gain.
Abstract: Aspects of the present disclosure describe systems, methods and structures providing wide-area traffic monitoring based on distributed fiber-optic sensing (DFOS) that employs deep neural network(s) for denoising noisy waterfall traces measured by the DFOS. Such systems, methods, and structures according to aspects of the present disclosure may advantageously monitor multiple highways/roadways using a single interrogator and optical fiber switch(es) which provides traffic information along every sensing point of existing, deployed, in-service optical telecommunications facilities.
Abstract: Aspects of the present disclosure describe monitoring of optical fiber by distributed temperature sensing (DTS) and determining optical fiber degradation and/or abnormal environmental events including landslides, fires, etc., from DTS data.
Abstract: Aspects of the present disclosure describe systems, methods and apparatus for improving the performance of Rayleigh-based phase-OTDR with correlation-based diversity combining and bias removal.
Abstract: Aspects of the present disclosure describe Rayleigh fading mitigation via short pulse coherent distributed acoustic sensing with multi-location beating-term combination. In illustrative configurations, systems, methods, and structures according to the present disclosure employ a two stage modulation arrangement providing short interrogator pulses resulting in a greater number of sensing data points and reduced effective sectional length. The increased number of data points are used to mitigate Rayleigh fading via a spatial combining process, multi-location-beating combining (MLBC) which uses weighted complex-valued DAS beating results from neighboring locations and aligns phase signals of each of the locations, before combining them to produce a final DAS phase measurement. Since Rayleigh scattering is a random statistic, the MLBC process allows capture of different statics from neighboring locations with correlated vibration/acoustic signal.
Abstract: Aspects of the present disclosure describe amplifier dynamics compensation through feedback control for distributed fiber sensing systems, methods, and structures employing Brillouin optical time-domain reflectometry.
Abstract: Aspects of the present disclosure describe multi-frequency coherent distributed acoustic sensing with a single transmitter/receiver pair using an offset Tx/Rx framing scheme and an additional optical IQ modulator to generate the multiple frequency channels for DAS interrogation.
Abstract: Aspects of the present disclosure describe aerial fiber optical cable localization using distributed acoustic sensing (DAS) that advantageously may determine the locality of electrical transformers affixed to utility poles along with the aerial fiber optical cable as well as any length(s) of fiber optical cable between the poles. Further aspects employ survey manned or unmanned, aerial or terrestrial survey vehicles that acoustically excite locations along the fiber optical cable and associate those DAS excitations with global positioning location (GPS).