公开(公告)号：US20250149133A1

公开(公告)日：2025-05-08

申请号：US18922837

申请日：2024-10-22

Applicant: NEC Laboratories America, Inc.

Inventor： LuAn Tang ,  Yuyang Ye ,  Haifeng Chen ,  Haoyu Wang ,  Zhengzhang Chen ,  Wenchao Yu

IPC: G16H10/60 ,  G06N3/0455

Abstract: Systems and methods for optimizing key performance indicators (KPIs) using adversarial imitation deep learning include processing sensor data received from sensors to remove irrelevant data based on correlation to a final KPI and generating, using a policy generator network with a transformer-based architecture, an optimal sequence of actions based on the processed sensor data. A discriminator network is employed to differentiate between the generated action sequences and real-world high performance sequences employing. Final KPI results are estimated based on the generated action sequences using a performance prediction network. The generated action sequences are applied to the process to optimize the KPI in real-time.

公开(公告)号：US20250148768A1

公开(公告)日：2025-05-08

申请号：US18937628

申请日：2024-11-05

Applicant: NEC Laboratories America, Inc.

Inventor： Kai Li ,  Deep Patel ,  Renqiang Min ,  Wentao Bao

IPC: G06V10/80 ,  G06V10/82 ,  G06V20/40 ,  G06V20/58 ,  G06V40/20

Abstract: Methods and systems for action detection include encoding a text feature of an input textual description of an action using a visual language model (VLM). A video feature of an input video is encoded using the VLM. The action in the video is recognized, based on the text feature and the video feature, to localize the action within the video. A person performing the action is located within the video using the VLM.

公开(公告)号：US20250148431A1

公开(公告)日：2025-05-08

申请号：US18938823

申请日：2024-11-06

Applicant: NEC Laboratories America, Inc.

Inventor： Haoyu Wang ,  Christopher A. White ,  Haifeng Chen ,  LuAn Tang ,  Zhengzhang Chen ,  Xujiang Zhao

IPC: G06Q10/30 ,  G06Q10/0637

Abstract: Systems and methods for an agent-based carbon emission reduction system. A carbon product of a supply chain system can be limited below a carbon product threshold by performing a corrective action to monitored entities based on a calculated carbon emission. The carbon emission can be calculated based on carbon-relevant data and a calculation route by utilizing an agent-based simulation model that simulates a learned relationship between a supply chain system and the carbon-relevant data. The calculation route can be determined based on the carbon-relevant data based on a relevance of a carbon product contribution of monitored entities to a goal of the monitored entities. Carbon-relevant data can be extracted from the monitored entities.

公开(公告)号：US20250148391A1

公开(公告)日：2025-05-08

申请号：US18935505

申请日：2024-11-02

Applicant: NEC Laboratories America, Inc.

Inventor： Yangmin DING ,  Ting WANG

IPC: G06Q10/0631

Abstract: Disclosed are integrated systems and methods that utilize a network of DFOS sensors installed on power lines, communication networks, and transportation systems, which continuously monitor infrastructures and provide real-time data. This data is collected, processed, and analyzed, and used to identify any affected areas of infrastructure and assess severity of any damage. Prioritization and resource allocation is performed and uses this analysis to prioritize restoration efforts and allocate resources such as repair crews, equipment, and materials to areas with a highest priority.

公开(公告)号：US20250146842A1

公开(公告)日：2025-05-08

申请号：US18932877

申请日：2024-10-31

Applicant: NEC Laboratories America, Inc.

Inventor： Yangmin Ding ,  Ting Wang ,  Yue Tian ,  Sarper Ozharar ,  Zhuocheng Jiang ,  Yanchao Wang

IPC: G01D5/353

Abstract: Methods and systems for anomaly detection include measuring time-series data about a system using an optical sensing system. The time-series data is adapted to natural language data. One or more anomaly detection models are selected based on the natural language data and a task. An anomaly is detected in the system using the selected one or more anomaly detection models. A corrective action is performed responsive to the anomaly.

公开(公告)号：US20250131064A1

公开(公告)日：2025-04-24

申请号：US18901647

申请日：2024-09-30

Applicant: NEC Laboratories America, Inc.

Inventor： Yangmin DING ,  Yanchao WANG ,  Ting WANG

IPC: G06F18/241 ,  G06Q10/0639

Abstract: Disclosed are systems, methods, and structures that enhance advanced metering infrastructure (AMI) event classification with graph neural networks (GNNs) in which AMI data is represented as a graph, where each meter is a node and connections between nodes represent the physical or functional relationship between meters. As a result, our systems and methods capture dependency information between different meters and use this information to predict events and anomalies.

公开(公告)号：US20250130307A1

公开(公告)日：2025-04-24

申请号：US18901760

申请日：2024-09-30

Applicant: NEC Laboratories America, Inc.

Inventor： Jian FANG ,  Wataru KOHNO ,  Yaowen LI ,  Ting WANG

IPC: G01S5/22

Abstract: Disclosed are systems and methods directed to a MIMO method that detects and localizes an object without requiring the object to emit a sound. Operationally, multiple speakers generate tone signals at different frequencies, while multiple acoustic sensors demodulate the complex amplitude of each frequency. By monitoring the feature variation of the relative phase (or intensity) vector from the complex amplitude, our method detects or localizes movement of the object. For large-scale applications, a fiber-optic system and method that employs distributed acoustic sensing (DAS) in which an optical fiber is used as one or more acoustic sensors located at points along the length of the optical fiber. A single DAS system provides numerous sensors using only a single optical fiber thereby enabling perfect synchronization and centralized signal processing. Notably, with such a DAS arrangement, cost and complexity is significantly reduced, while privacy is preserved.

公开(公告)号：US20250130074A1

公开(公告)日：2025-04-24

申请号：US18901783

申请日：2024-09-30

Applicant: NEC Laboratories America, Inc.

Inventor： Yangmin DING ,  Sarper OZHARAR ,  Zhuocheng JIANG ,  Yue TIAN ,  Ting WANG

IPC: G01D5/353

Abstract: Disclosed are systems, methods, and structures that employ distributed fiber sensing that utilizes existing fiber cables for detecting tree events. Our inventive systems and methods can detect when a tree or other types of vibration occur on the telecom cable or poles, creating a high-resolution spatial profile of the cable. Systems and methods according to aspects of the present disclosure distinguish between tree events and other vibrations, such as hammer strikes on a utility pole, by employing Information Noise Contrastive Estimation (InfoNCE) and contrastive learning. Our inventive approach accurately differentiates between different types of vibrations and identifies patterns specific to tree events.

公开(公告)号：US20250123127A1

公开(公告)日：2025-04-17

申请号：US18890304

申请日：2024-09-19

Applicant: NEC Laboratories America, Inc.

Inventor： Junqiang HU ,  Ting WANG ,  Yue-Kai HUANG

IPC: G01D5/353 ,  G01H9/00 ,  H04B10/071

Abstract: Disclosed are systems, methods, and structures that increase overall sensing reach of a DFOS system and reduces system cost without sacrificing sensed signal quality by employing a cascaded arrangement of DFOS interrogators and operating method providing backscattering DFOS, maintaining each span within a desired length which can advantageously be determined by signal quality, pulse rate, or other factors such as physical layout. The cascaded DFOS interrogators work independently while sharing the pulse light produced by the first interrogator in a cascaded series of interrogators. The light is amplified in successive fiber spans and a circulator may be employed to cut-off any backscattered signal.

公开(公告)号：US20250118063A1

公开(公告)日：2025-04-10

申请号：US18891625

申请日：2024-09-20

Applicant: NEC Laboratories America, Inc.

Inventor： Jong-Chyi Su ,  Samuel Schulter ,  Sparsh Garg ,  Manmohan Chandraker ,  Mingfu Liang

IPC: G06V10/82 ,  G06V10/75 ,  G06V20/70

Abstract: Systems and methods include detecting one or more objects in an image and generating one or more captions for the image. One or more predicted categories of the one or more objects detected in the image and the one or more captions are matched. From the one or more predicted categories, a category that is not successfully predicted in the image is identified. Data is curated to improve the category that is not successfully predicted in the image. A perception model is finetuned using data curated.