-
公开(公告)号：US20240303149A1
公开(公告)日：2024-09-12
申请号：US18599322
申请日：2024-03-08
Applicant: NEC Laboratories America, Inc.
Inventor： Yuncong Chen , Haifeng Chen , LuAn Tang , Zhengzhang Chen
CPC classification number: G06F11/079 , G06F11/0721 , G16H50/30
Abstract: Methods and systems for anomaly detection include encoding a time series with a time series encoder and encoding an event sequence with an event sequence encoder. A latent code is generated from outputs of the time series encoder and the event sequence encoder. The time series is reconstructed from the latent code using a time series decoder. The event sequence is reconstructed from the latent code using an event sequence decoder. An anomaly score is determined based on a reconstruction loss of the reconstructed time series and a reconstruction loss of the reconstructed event sequence. An action is performed responsive to the anomaly score.
-
公开(公告)号：US20240302225A1
公开(公告)日：2024-09-12
申请号：US18598386
申请日：2024-03-07
Applicant: NEC Laboratories America, Inc.
Inventor： Philip JI , Ting WANG , Yaowen LI , Junqiang HU , Shuji MURAKAMI , Jian FANG
CPC classification number: G01K15/005 , G01K11/32
Abstract: Disclosed are vehicle-infrastructure interaction systems and methods employing a distributed fiber optic sensing (DFOS) system operating with pre-deployed fiber-optic telecommunication cables buried alongside/proximate to highways/roadways which provide 24/7 continuous information stream of vehicle traffic at multiple sites; only require a single optical sensor cable that senses/monitors multiple locations of interest and multiple lanes of traffic; the single optical sensor cable measures multiple related information (multi-parameters) about a vehicle, including driving speed, wheelbase, number of axles, tire pressure, and others, that can be used to derive secondary information such as weight-in-motion; and overall information about a fleet of vehicles, such as traffic congestion or traffic-cargo volume. Different from merely traffic counts, our approach can provide the count grouped by vehicle-types and cargo weights. Precise measurements are facilitated by high temporal sampling rates of the distributed acoustic sensing and a dedicated peak finding algorithm for extracting the timing information reliably.
-
公开(公告)号：US20240274251A1
公开(公告)日：2024-08-15
申请号：US18439274
申请日：2024-02-12
Applicant: NEC Laboratories America, Inc.
Inventor： Christopher Malon
IPC: G16H20/00 , G06F40/205 , G06F40/40
CPC classification number: G16H20/00 , G06F40/205 , G06F40/40
Abstract: Methods and systems for document summarization include splitting documents into sentences and sorting the sentences by a metric that promotes review opinion prevalence from the documents to generate a ranked list of sentences. Groups of sentences with similar embeddings are formed and a trained generalization encoder-decoder model is applied to output a common generalization of the sentences in each group. Sentences are added to a summary from the generalizations corresponding to the sentences in the ranked list, in rank-order, until a target summary length has been reached. An action is performed responsive to the summary.
-
公开(公告)号：US12050664B2
公开(公告)日：2024-07-30
申请号：US17494979
申请日：2021-10-06
Applicant: NEC Laboratories America, Inc.
Inventor： Murugan Sankaradas , Kunal Rao , Yi Yang , Biplob Debnath , Utsav Drolia , Srimat Chakradhar , Amit Redkar , Ravi Kailasam Rajendran
CPC classification number: G06F18/253 , G06F18/2148 , G06N3/045 , G06T7/50 , G06T11/00 , G06V10/40 , G06V20/00 , G06T2207/20081 , G06T2207/20084 , G06T2207/20221 , G06T2210/12
Abstract: A method for real-time cross-spectral object association and depth estimation is presented. The method includes synthesizing, by a cross-spectral generative adversarial network (CS-GAN), visual images from different data streams obtained from a plurality of different types of sensors, applying a feature-preserving loss function resulting in real-time pairing of corresponding cross-spectral objects, and applying dual bottleneck residual layers with skip connections to accelerate real-time inference and to accelerate convergence during model training.
-
公开(公告)号：US12047242B2
公开(公告)日：2024-07-23
申请号：US18481988
申请日：2023-10-05
Applicant: NEC Laboratories America, Inc.
IPC: H04L41/0896 , H04L41/122
CPC classification number: H04L41/0896 , H04L41/122
Abstract: Described is a novel framework, we call intent-based computing jobs assignment framework, for efficiently accommodating a clients' computing job requests in a mobile edge computing infrastructure. We define the intent-based computing job assignment problem, which jointly optimizes the virtual topology design and virtual topology mapping with the objective of minimizing the total bandwidth consumption. We use the Integer Linear Programming (ILP) technique to formulate this problem, and to facilitate the optimal solution. In addition, we employ a novel and efficient heuristic algorithm, called modified Steiner tree-based (MST-based) heuristic, which coordinately determines the virtual topology design and the virtual topology mapping. Comprehensive simulations to evaluate the performance of our solutions show that the MST-based heuristic can achieve an efficient performance that is close to the optimal performance obtained by the ILP solution.
-
Patent Agency Ranking
公开(公告)号：US12045727B2
公开(公告)日：2024-07-23
申请号：US17115464
申请日：2020-12-08
Applicant: NEC Laboratories America, Inc.
Inventor： Renqiang Min , Christopher Malon , Pengyu Cheng
IPC: G06N3/088 , G06F40/20 , G06N3/02 , G06N3/0442 , G06N3/08 , G06N3/082 , G06N3/086 , G10L15/06 , G10L15/16 , G10L15/22
CPC classification number: G06N3/088 , G06F40/20 , G06N3/0442 , G06N3/08 , G06N3/086 , G10L15/063 , G10L15/16 , G10L15/22 , G06N3/02 , G06N3/082
Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing, by a bidirectional Long Short-Term Memory (LSTM) with a multi-head attention mechanism, a dataset including a plurality of pairs each formed from a given one of a plurality of input text structures and given one of a plurality of style labels for the plurality of input text structures. The method further includes training the bidirectional LSTM as an encoder to disentangle a sequential text input into disentangled representations comprising a content embedding and a style embedding based on a subset of the dataset. The method also includes training a unidirectional LSTM as a decoder to generate a next text structure prediction for the sequential text input based on previously generated text structure information and a current word, from a disentangled representation with the content embedding and the style embedding.
-
公开(公告)号：US12045569B2
公开(公告)日：2024-07-23
申请号：US17582706
申请日：2022-01-24
Applicant: NEC Laboratories America, Inc.
Inventor： Xuchao Zhang , Bo Zong , Yanchi Liu , Haifeng Chen
IPC: G06F40/284 , G06F40/205 , G06N3/044 , G06N3/08
CPC classification number: G06F40/284 , G06F40/205 , G06N3/044 , G06N3/08
Abstract: Methods and systems for natural language processing include generating an encoder that includes a global part and a local part, where the global part encodes multi-hop relations between words in an input and where the local part encodes one-hop relations between words in the input. The encoder is trained to form a graph that represents tokens of an input text as nodes and that represents relations between the tokens as edges between the nodes.
-
28.发明公开公开(公告)号：US20240241275A1
公开(公告)日：2024-07-18
申请号：US18414419
申请日：2024-01-16
Applicant: NEC Laboratories America, Inc.
Inventor： Shaobo HAN , Yuheng CHEN , Ming-Fang HUANG , Tingfeng LI
CPC classification number: G01V1/288 , G01V1/001 , G01V1/226 , G08G1/0104
Abstract: Disclosed are machine learning (ML) based Distributed Fiber Optic Sensing (DFOS) systems, methods, and structures for Sonic Alert Pattern (SNAP) event detection performed in real time including an intelligent SNAP informatic system in conjunction with DFOS/Distributed Acoustic Sensing (DAS) and machine learning technologies that utilize SNAP vibration signals as an indicator. Without installation of additional sensors, vibration signals indicative of SNAP events are detected along a length of an existing optical fiber through DAS. Raw DFOS data is utilized—and not DFOS waterfall data—resulting in faster and more accurate information derivation as rich, time-frequency information in the raw DFOS/DAS waveform data is preserved. A deep learning module Temporal Relation Network (TRN) that accurately detects SNAP events from among chaotic signals of normal traffic is employed, making it reliable when applied to busy roads with dense traffic and vehicles of different speed.
-
公开(公告)号：US20240235668A1
公开(公告)日：2024-07-11
申请号：US18485198
申请日：2023-10-11
Applicant: NEC Laboratories America, Inc.
Inventor： Junqiang HU , Yue-Kai HUANG , Ting Wang
IPC: H04B10/073 , G01H9/00
CPC classification number: H04B10/073 , G01H9/004
Abstract: A fast optical fiber identification system and method employing an acoustic pen that is connected to a portable device (such as a laptop, a smartphone, an iPad). The pen generates acoustic signals under the control of the portable device. The portable device interacts with a DFOS (Distributed Fiber Optic Sensor, e.g., a DAS or DVS) interrogator to notify the interrogator about the generated signals and receives a detection result from the interrogator. The result is either illustrated using a graph on the portable device, or as a tone of different volume, to indicate the strength of the pen's signal detected by the interrogator. As the pen touches/excites vibrationally/acoustically each of the fibers, the portable device notifies the user about the detected signal's strength or presence/no-presence, which allows a technician to quickly identify the fiber of interest.
-
公开(公告)号：US12028110B2
公开(公告)日：2024-07-02
申请号：US17713171
申请日：2022-04-04
Applicant: NEC Laboratories America, Inc.
CPC classification number: H04B10/27 , H04Q11/0062 , H04Q2011/009
Abstract: A procedure to solve the DFOS placement problem that uses a genetic algorithm to achieve a global optimization of sensor placement. First, our procedure according to aspects of the present disclosure defines a fitness function that counts the number of DFOS sensors used. Second, the procedure uses a valid DFOS placement assignment to model an individual in the genetic algorithm. Each individual consists of N genes, where N is the number of nodes in the given network infrastructure, e.g., N=|V|. Each gene has two genomes: (1) a list of 0s and/or 1s, in which is represent the network nodes that are equipped with DFOS sensors, and 0s represent the nodes that are not equipped with DFOS sensors; (2) a list of sensing fiber routes. An individual that has smallest number of is in their genes will be considered as the strongest individual. Thirdly, the procedure randomly generates a population of individuals. After a certain number of generations of population, the strongest individual in the last generation will be the global optima for the DFOS placement assignment.
-
-
-
-
-
-
-
-
-
Search Results
2291
records
(took 0.023 seconds)
