-
公开(公告)号：WO2023086533A1
公开(公告)日：2023-05-19
申请号：PCT/US2022/049646
申请日：2022-11-11
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： TANG, LuAn , CHEN, Yuncong , CHENG, Wei , CHEN, Haifeng , CHEN, Zhengzhang , KOBAYASHI, Yuji
Abstract: Systems and methods for defect detection for vehicle operations, including collecting a multiple modality input data stream from a plurality of different types of vehicle sensors, extracting one or more features from the input data stream using a grid-based feature extractor, and retrieving spatial attributes of objects positioned in any of a plurality of cells of the grid-based feature extractor. One or more anomalies are detected based on residual scores generated by each of cross attention-based anomaly detection and time-series-based anomaly detection. One or more defects are identified based on a generated overall defect score determined by integrating the residual scores for the cross attention-based anomaly detection and the time-series based anomaly detection being above a predetermined defect score threshold. Operation of the vehicle is controlled based on the one or more defects identified.
-
公开(公告)号：WO2022225806A1
公开(公告)日：2022-10-27
申请号：PCT/US2022/024995
申请日：2022-04-15
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： LIU, Yanchi , CHEN, Haifeng , ZHANG, Xuchao
IPC: G06F16/35 , G06F40/279 , G06K9/62 , G06N3/08
Abstract: Systems and methods are provided for detail matching. The method includes training a feature classifier (200) to identify technical features, and training a neural network model for a trained importance calculator (300) to calculate an importance value for each identified technical feature. The method further includes receiving a specification sheet (110) including a plurality of technical features, and receiving a plurality of descriptive sheets (120) each including a plurality of technical features. The method further includes identifying the technical features (130) in the specification sheet and the plurality of descriptive sheets using the trained feature classifier (200), and calculating an importance (140) for each identified technical feature using the trained feature importance calculator (300). The method further includes calculating a matching score (150) between the identified technical features of the specification sheet and the identified technical features of the plurality of descriptive sheets based on the importance of each identified technical feature.
-
公开(公告)号：WO2022216618A1
公开(公告)日：2022-10-13
申请号：PCT/US2022/023327
申请日：2022-04-04
Applicant: NEC LABORATORIES AMERICA, INC. , NEC CORPORATION
Inventor： NI, Jingchao , CHENG, Wei , CHEN, Haifeng , ASAKURA, Takayoshi
Abstract: Systems and methods for predicting an occurrence of a medical event for a patient using a trained neural network. Historical patient data is preprocessed (902) to generate (904) normalized training samples, and the normalized training samples are sent to a personalized deep convolutional neural network for model pretraining and updating (906) of model parameters. The pretrained model is stored (908) in a remote server for utilization by a local machine for personalization during a preparation time period for a medical treatment. A normalized finetuning set is generated (906) as output, and the model parameters are iteratively finetuned (912). A personal prediction score for future medical events is generated (914), and an operation of a medical treatment device is controlled (916) responsive to the prediction score.
-
公开(公告)号：WO2022055783A1
公开(公告)日：2022-03-17
申请号：PCT/US2021/048817
申请日：2021-09-02
Applicant: NEC LABORATORIES AMERICA, INC. , NEC CORPORATION
Inventor： TANG, LuAn , CHENG, Wei , CHEN, Haifeng , KOBAYASHI, Yuji , CHEN, Zhengzhang
Abstract: A method for early warning is provided. The method clusters (810) normal historical data of normal cars into groups based on the car subsystem to which they belong. The method extracts (820) (i) features based on group membership and (ii) feature correlations based on correlation graphs formed from the groups. The method trains (830) an Auto-Encoder and Auto Decoder (AE&AD) model based on the features and the feature correlations to reconstruct the normal historical data with minimum reconstruction errors. The method reconstructs (840), using the trained AE&AD model, historical data of specific car fault types with reconstruction errors, normalizes the reconstruction errors, and selects features of the car faults with a top k large errors as fault signatures. The method reconstructs (850) streaming data of monitored cars using the trained AE&AD model to determine streaming reconstruction errors, comparing the streaming reconstruction errors with the fault signatures to predict and provide alerts for impending known faults.
-
公开(公告)号：WO2021225841A1
公开(公告)日：2021-11-11
申请号：PCT/US2021/029583
申请日：2021-04-28
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： TANG, LuAn , CHEN, Haifeng , CHENG, Wei , RHEE, Junghwan , KAMIMURA, Jumpei
Abstract: Methods and systems for training a neural network model include processing (302) a set of normal state training data and a set of fault state training data to generate respective normal state inputs and fault state inputs that each include data features and sensor correlation graph information. A neural network model is trained (304), using the normal state inputs and the fault state inputs, to generate a fault score that provides a similarity of an input to the fault state training data and an anomaly score that provides a dissimilarity of the input to the normal state training data.
-
Patent Agency Ranking
公开(公告)号：WO2021183382A1
公开(公告)日：2021-09-16
申请号：PCT/US2021/021063
申请日：2021-03-05
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： ZONG, Bo , CHEN, Haifeng , ZHANG, Xunchao
IPC: G06F11/36 , G06F16/36 , G06F16/901
Abstract: A computer-implemented method executed by at least one processor for software bug localization is presented. The method includes constructing (701) a bug localization graph to capture relationships between bug tickets and relevant source code files from historical change-sets and an underlying source code repository, leveraging (703) natural processing language tools to evaluate semantic similarity between a new bug ticket and a historical ticket, in response to the evaluated semantic similarity, for the new bug ticket, adding (705) links between the new bug ticket a set of similar historical tickets, incorporating (707) the new bug ticket in the bug localization graph, and developing (709) a mathematical graph expression to determine a closeness relationship between the relevant source code files and the new bug ticket.
-
公开(公告)号：WO2021055239A1
公开(公告)日：2021-03-25
申请号：PCT/US2020/050302
申请日：2020-09-11
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： XU, Jianwu , LI, Ding , CHENG, Wei , CHEN, Haifeng
Abstract: A method for automatically recommending a reviewer for submitted codes is presented. The method includes employing (801), in a learning phase, an artificial intelligence agent for learning an underlying and contextual structure of code regions, mapping (803) the code regions into a distributed representation to define code region representations, employing (805), in a recommendation phase, the artificial intelligence agent to produce a ranked list of recommended reviewers for any given submitted code review request, and outputting (807) the ranked list of recommended reviewers to a visualization device.
-
公开(公告)号：WO2020242553A1
公开(公告)日：2020-12-03
申请号：PCT/US2020/022531
申请日：2020-03-13
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： NATSUMEDA, Masanao , CHENG, Wei , CHEN, Haifeng , CHEN, Yuncong
Abstract: Methods and systems for predicting failure in a cyber-physical system include determining a prediction index based on a comparison of input time series, from respective sensors in a cyber-physical system, to failure precursors. A failure precursor is detected in the input time series, responsive to a comparison of the prediction index to a threshold. A subset of the sensors associated with the failure precursor is determined, based on a gradient of the prediction index. A corrective action is performed responsive to the determined subset of sensors.
-
公开(公告)号：WO2020172015A1
公开(公告)日：2020-08-27
申请号：PCT/US2020/017861
申请日：2020-02-12
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： CHENG, Wei , CHEN, Haifeng
IPC: G06Q30/02 , G06F16/2457 , G06N20/00
Abstract: A system is provided for interpretable viewing interest. A transformer with multi-head self-attention derives different hierarchical orders of input features. A plurality of hierarchical attention layers aggregate the different hierarchical orders to obtain aggregated single-order feature representations and derive aggregation attention weights for the different hierarchical orders based on an applied order of the plurality of hierarchical attention layers. A hierarchical interpretation layer determines a respective importance of each of the input features in various input feature combinations from which various CTR predictions are derived based on the aggregation attention weights and the significance of each order. A display device configured to display each of the various input feature combinations for the various CTR predictions along with the respective importance of each of the constituent one of the input features in the various input feature combinations.
-
公开(公告)号：WO2020086355A1
公开(公告)日：2020-04-30
申请号：PCT/US2019/056498
申请日：2019-10-16
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： YU, Wenchao , NI, Jingchao , ZONG, Bo , CHENG, Wei , CHEN, Haifeng , TANG, LuAn
Abstract: Systems and methods for predicting system device failure are provided. The method includes performing (740) graph-based predictive maintenance (GBPM) to determine a trained ensemble classification model for detecting maintenance ready components that includes extracted node features and graph features. The method includes constructing (750), based on testing data and the trained ensemble classification model, an attributed temporal graph and the extracted node features and graph features. The method further includes concatenating (760) the extracted node features and graph features. The method also includes determining (770), based on the trained ensemble classification model, a list of prediction results of components that are to be scheduled for component maintenance.
-
-
-
-
-
-
-
-
-
Search Results
98
records
(took 0.034 seconds)
