公开(公告)号：US20220012274A1

公开(公告)日：2022-01-13

申请号：US17370498

申请日：2021-07-08

Applicant: NEC Laboratories America, Inc.

Inventor： Yuncong Chen ,  Dongjin Song ,  Cristian Lumezanu ,  Haifeng Chen ,  Takehiko Mizoguchi ,  Xuchao Zhang

IPC: G06F16/35 ,  G06K9/62 ,  G06N3/08 ,  G06F40/169

Abstract: Methods and systems of training and using a neural network model include training a time series embedding model and a text embedding model with unsupervised clustering to translate time series and text, respectively, to a shared latent space. The time series embedding model and the text embedding model are further trained using semi-supervised clustering that samples training data pairs of time series information and associated text for annotation.

公开(公告)号：US10999323B2

公开(公告)日：2021-05-04

申请号：US16101834

申请日：2018-08-13

Applicant: NEC Laboratories America, Inc.

Inventor： Cristian Lumezanu ,  Nipun Arora ,  Haifeng Chen ,  Bo Zong ,  Daeki Cho ,  Mingda Li

IPC: G06F21/00 ,  H04L29/06 ,  H04L12/733 ,  H04L12/26 ,  H04L12/741 ,  G06N20/00 ,  H04L12/751 ,  H04L12/893 ,  G06K9/62 ,  G06N3/08

Abstract: Endpoint security systems and methods include a distance estimation module configured to calculate a travel distance between a source Internet Protocol (IP) address and an IP address for a target network endpoint system from a received packet received by a network gateway system based on time-to-live (TTL) information from the received packet. A machine learning model is configured to estimate an expected travel distance between the source IP address and the target network endpoint system IP address based on a sparse set of known source/target distances. A spoof detection module is configured to determine that the received packet has a spoofed source IP address based on a comparison between the calculated travel distance and the expected travel distance. A security module is configured to perform a security action at the network gateway system responsive to the determination that the received packet has a spoofed source IP address.

公开(公告)号：US20210065735A1

公开(公告)日：2021-03-04

申请号：US16997314

申请日：2020-08-19

Applicant: NEC Laboratories America, Inc.

Inventor： Cristian Lumezanu ,  Yuncong Chen ,  Dongjin Song ,  Takehiko Mizuguchi ,  Haifeng Chen ,  Bo Dong

IPC: G10L25/51 ,  G10L25/24

Abstract: A method is provided. Intermediate audio features are generated from an input acoustic sequence. Using a nearest neighbor search, segments of the input acoustic sequence are classified based on the intermediate audio features to generate a final intermediate feature as a classification for the input acoustic sequence. Each segment corresponds to a respective different acoustic window. The generating step includes learning the intermediate audio features from Multi-Frequency Cepstral Component (MFCC) features extracted from the input acoustic sequence. The generating step includes dividing the same scene into the different acoustic windows having varying MFCC features. The generating step includes feeding the MFCC features of each of the different acoustic windows into respective LSTM units such that a hidden state of each respective LSTM unit is passed through an attention layer to identify feature correlations between hidden states at different time steps corresponding to different ones of the different acoustic windows.

公开(公告)号：US20210065059A1

公开(公告)日：2021-03-04

申请号：US17002960

申请日：2020-08-26

Applicant: NEC Laboratories America, Inc.

Inventor： Dongjin Song ,  Yuncong Chen ,  Cristian Lumezanu ,  Takehiko Mizoguchi ,  Haifeng Chen ,  Dixian Zhu

IPC: G06N20/00 ,  G06F11/30 ,  G06F11/34

Abstract: A computer-implemented method for monitoring computing system status by implementing a deep unsupervised binary coding network includes receiving multivariate time series data from one or more sensors associated with a system, implementing a long short-term memory (LSTM) encoder-decoder framework to capture temporal information of different time steps within the multivariate time series data and perform binary coding, the LSTM encoder-decoder framework including a temporal encoding mechanism, a clustering loss and an adversarial loss, computing a minimal distance from the binary code to historical data, and obtaining a status determination of the system based on a similar pattern analysis using the minimal distance.

公开(公告)号：US10930301B1

公开(公告)日：2021-02-23

申请号：US16997314

申请日：2020-08-19

Applicant: NEC Laboratories America, Inc.

Inventor： Cristian Lumezanu ,  Yuncong Chen ,  Dongjin Song ,  Takehiko Mizuguchi ,  Haifeng Chen ,  Bo Dong

IPC: G10L25/51 ,  G10L25/24 ,  G10L25/18 ,  G10L25/21

Abstract: A method is provided. Intermediate audio features are generated from an input acoustic sequence. Using a nearest neighbor search, segments of the input acoustic sequence are classified based on the intermediate audio features to generate a final intermediate feature as a classification for the input acoustic sequence. Each segment corresponds to a respective different acoustic window. The generating step includes learning the intermediate audio features from Multi-Frequency Cepstral Component (MFCC) features extracted from the input acoustic sequence. The generating step includes dividing the same scene into the different acoustic windows having varying MFCC features. The generating step includes feeding the MFCC features of each of the different acoustic windows into respective LSTM units such that a hidden state of each respective LSTM unit is passed through an attention layer to identify feature correlations between hidden states at different time steps corresponding to different ones of the different acoustic windows.

公开(公告)号：US10915535B2

公开(公告)日：2021-02-09

申请号：US15983404

申请日：2018-05-18

Applicant: NEC Laboratories America, Inc.

Inventor： Haifeng Chen ,  Youfu Li ,  Daeki Cho ,  Bo Zong ,  Nipun Arora ,  Cristian Lumezanu

IPC: G06F16/2455 ,  G06N20/00 ,  G06F16/22 ,  G06F16/2453 ,  G06N5/04

Abstract: Systems and methods for optimizing query execution to improve query processing by a computer are provided. A query is analyzed and translated into a logical plan. A runtime query optimizer is applied to the logical plan to identify a physical plan including operators for execution. The logical plan is translated into the physical plan. Execution of the query is scheduled according to the physical plan.

公开(公告)号：US20210027019A1

公开(公告)日：2021-01-28

申请号：US16918353

申请日：2020-07-01

Applicant: NEC Laboratories America, Inc. ,  NEC Corporation

Inventor： Yuncong Chen ,  Hao Yuan ,  Dongjin Song ,  Cristian Lumezanu ,  Haifeng Chen ,  Takehiko Mizoguchi

IPC: G06F40/30 ,  G06N3/08 ,  G06K9/62 ,  G06F17/16

Abstract: A system for cross-modal data retrieval is provided that includes a neural network having a time series encoder and text encoder which are jointly trained using an unsupervised training method which is based on a loss function. The loss function jointly evaluates a similarity of feature vectors of training sets of two different modalities of time series and free-form text comments and a compatibility of the time series and the free-form text comments with a word-overlap-based spectral clustering method configured to compute pseudo labels for the unsupervised training method. The computer processing system further includes a database for storing the training sets with feature vectors extracted from encodings of the training sets. The encodings are obtained by encoding a training set of the time series using the time series encoder and encoding a training set of the free-form text comments using the text encoder.

公开(公告)号：US09813301B2

公开(公告)日：2017-11-07

申请号：US14830303

申请日：2015-08-19

Applicant: NEC Laboratories America, Inc.

Inventor： Qiang Xu ,  Cristian Lumezanu ,  Zhuotao Liu ,  Nipun Arora ,  Abhishek Sharma ,  Hui Zhang ,  Guofei Jiang

IPC: H04L12/28 ,  H04L12/24 ,  H04L12/727 ,  H04L12/721 ,  H04L12/751 ,  H04L12/26 ,  G06F9/455

CPC classification number: H04L41/12 ,  G06F9/45533 ,  H04L41/083 ,  H04L43/087 ,  H04L45/02 ,  H04L45/121 ,  H04L45/123 ,  H04L45/124

Abstract: Systems and methods for decoupled searching and optimization for one or more data centers, including determining a network topology for one or more networks of interconnected computer systems embedded in the one or more data center, searching for routing candidates based on a network topology determined, and updating and applying one or more objective functions to the routing candidates to determine an optimal routing candidate to satisfy embedding goals based on tenant requests, and to embed the optimal routing candidate in the one or more data centers.

公开(公告)号：US09736053B2

公开(公告)日：2017-08-15

申请号：US14665069

申请日：2015-03-23

Applicant: NEC Laboratories America, Inc.

Inventor： Hui Zhang ,  Cristian Lumezanu ,  Junghwan Rhee ,  Nipun Arora ,  Qiang Xu ,  Guofei Jiang

IPC: H04L12/751 ,  H04L12/715 ,  H04L12/721

CPC classification number: H04L45/02 ,  H04L43/12 ,  H04L45/64 ,  H04L45/70

Abstract: A computer implemented method for network monitoring includes providing network packet event characterization and analysis for network monitoring that includes supporting summarization and characterization of network packet traces collected across multiple processing elements of different types in a virtual network, including a trace slicing to organize individual packet events into path-based trace slices, a trace characterization to extract at least 2 types of feature matrix describing those trace slices, and a trace analysis to cluster, rank and query packet traces based on metrics of the feature matrix.

公开(公告)号：US09736041B2

公开(公告)日：2017-08-15

申请号：US14456094

申请日：2014-08-11

Applicant: NEC Laboratories America, Inc.

Inventor： Cristian Lumezanu ,  Kyriakos Zanfis ,  Guofei Jiang

IPC: G06F15/173 ,  H04L12/26 ,  H04L12/24

CPC classification number: H04L43/04 ,  H04L41/046 ,  H04L41/147 ,  H04L43/026

Abstract: Systems and methods for network management, including adaptively installing one or more monitoring rules in one or more network devices on a network using an intelligent network middleware, detecting application traffic on the network transparently using an application demand monitor, and predicting future network demands of the network by analyzing historical and current demands. The one or more monitoring rules are updated once counters are collected; and network paths are determined and optimized to meet network demands and maximize utilization and application performance with minimal congestion on the network.