公开(公告)号：US20220092430A1

公开(公告)日：2022-03-24

申请号：US17541298

申请日：2021-12-03

Applicant: ZHEJIANG LAB

Inventor： Jingsong LI ,  Tianshu ZHOU ,  Ziyue YANG ,  Shengqiang CHI

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/00 ,  G06K9/62

Abstract: Provided is a time series deep survival analysis system combined with active learning. The system includes: a data collection module, an active learning module, and a time series deep survival analysis module; the data collection module is used for obtaining survival data of objects to be analyzed; combined with an active learning method, the active learning module selects a part of right censored data to label a survival time; and the time series deep survival analysis module constructs a time series deep survival analysis neural network model, and takes uncensored data and right censored data as model inputs, so as to obtain survival time prediction results of the objects to be analyzed. The present application can make full use of the right censored data in the survival data and time series features.

公开(公告)号：US11255767B2

公开(公告)日：2022-02-22

申请号：US17372419

申请日：2021-07-10

Applicant: Zhejiang Lab ,  Zhejiang University

Inventor： Zhenhai Fu ,  Cheng Liu ,  Zhiming Chen ,  Xingfan Chen ,  Nan Li ,  Huizhu Hu

IPC: G01N15/02 ,  G01N15/06 ,  G03H1/00

Abstract: A method and a device for measuring light field distribution are provided; including steps of utilizing the optical trap to stably levitating particles, moving the optical trap to bring the particles close to the light field to be measured, and utilizing the photodetector to collect the scattered light signals of the particles at different positions in the three-dimensional space of the light field to be measured, and calculating the light field distribution of the light field to be measured according to the scattered light intensity which is proportional to the light intensity at that position. The device for measuring the optical field distribution includes a laser, an optical trapping path, particles, a photodetector, a control system and an upper computer; the laser emits a laser, passes through the optical trapping path, and emits highly focused captured light B to form an V optical trap to capture particles.

公开(公告)号：US20250165760A1

公开(公告)日：2025-05-22

申请号：US18288819

申请日：2023-07-31

Applicant: ZHEJIANG LAB ,  ZHEJIANG UNIVERSITY

Inventor： Yukun HE ,  De MA ,  Ying LI ,  Shichun SUN ,  Ming ZHANG ,  Xiaofei JIN ,  Guoquan ZHU ,  Fangchao YANG ,  Pan LV ,  Shuiguang DENG ,  Gang PAN

IPC: G06N3/063 ,  G06N3/049

Abstract: A neural network on-chip mapping method and apparatus based on a tabu search algorithm are provided. The method includes: constructing a tabu search table and using a heuristic-based iterative search process to select local computing cores of a network-on-chip as candidates, establishing an integer programming model and solving an optimal solution, continuously reducing an objective cost function of a mapping solution by loop iteration, and finally obtaining an approximately optimal deployment scheme.

公开(公告)号：US20250155321A1

公开(公告)日：2025-05-15

申请号：US18932720

申请日：2024-10-31

Applicant: ZHEJIANG UNIVERSITY ,  ZHEJIANG LAB

Inventor： Dazhuan WU ,  Yaochun HOU ,  Tian XIANG ,  Peng WU ,  Bin HUANG ,  Shuai YANG

IPC: G01M13/021 ,  G01M13/028

Abstract: A gear fault diagnosis method based on joint weighted envelope noise-resistant correlation of sub-signals, comprising: converting an original vibration signal sequence into an envelope signal through a signal sequence element-wise squaring-low-pass filtering-square root computation process, reconstructing the envelope signal according to different time intervals to obtain a series of sub-signals, calculating a fault information representation measure of each sub-signal based on an L-moment theoretical index, assigning a weight to each sub-signal with Sigmoid transformation, calculating a joint weighted envelope noise-resistant correlation function of the envelope signal sequence and the reconstructed sub-signals based on the envelope signal, the reconstructed sub-signals and the corresponding weights thereof, and determining a characteristic frequency according to a reciprocal of a time interval value corresponding to the characteristic peak in a plot of the joint weighted envelope noise-resistant correlation function with the time interval to eventually identifying a gear fault.

公开(公告)号：US12289157B2

公开(公告)日：2025-04-29

申请号：US18085495

申请日：2022-12-20

Applicant: ZHEJIANG LAB

Inventor： Bin Yang ,  Shanyun Liu ,  Xiangming Zhu ,  Yinan Qi ,  Xingming Zhang ,  Yongdong Zhu ,  Tao Xu ,  Peijun Chen ,  Kainan Zhu

IPC: H04B7/185 ,  H04W12/06

Abstract: Disclosed is a two-phase access authentication method integrating spatial-temporal features in space-air-ground integrated networks. In the method, an access authentication is divided into two phases: a primary authentication phase and a continued authentication phase. In the primary authentication phase, a user equipment and a satellite are respectively initialized and registered through a ground network control center. In the authentication phase, a fast and secure access is achieved by using a user ID, facial features, and other authentication factors. In the continued authentication phase, data of a user flow and behavior features are acquired, and feature comparison is performed by using historical user data; and a security level and an authentication decision are output. According to the disclosure, the spatial-temporal features are integrated to perform access authentication on a satellite-ground communication network, the authentication not only achieves a fast access, but also continuously ensures the system security in a service phase.

公开(公告)号：US20250124347A1

公开(公告)日：2025-04-17

申请号：US18804240

申请日：2024-08-14

Applicant: ZHEJIANG LAB

Inventor： Fei YANG ,  Shuang PENG ,  Ning SUN ,  Fangyu WANG ,  Aimin PAN

IPC: G06N20/00

Abstract: A training model allocation method, an apparatus, a computer device, and a storage medium are provided. The method includes: acquiring hierarchy information, calculating parameter information, and a training data set of a to-be-trained model; dividing the to-be-trained model into sub-models according to the hierarchy information, and allocating each of sub-models to machine nodes in a training cluster; dividing each of sub-models into sub-model slices according to the calculating parameter information, and allocating each of sub-model slices to computing processors of the machine nodes in the training cluster; dividing the training data set into training data subsets according to the calculating parameter information, and allocating each of training data subsets to the computing processors in the training cluster; and training the to-be-trained model according to all computing processors, sub-model slices, and training data subsets in the training cluster.

公开(公告)号：US12197330B2

公开(公告)日：2025-01-14

申请号：US18470346

申请日：2023-09-19

Applicant: ZHEJIANG LAB ,  Huazhong University of Science and Technology

Inventor： Zhan Zhang ,  Yu Zhang ,  Jin Zhao ,  Haifei Wu

IPC: G06F12/0804

Abstract: The present disclosure provides a data storage system, including data cache module, data processing module, and a persistent memory. The data cache module includes an on-chip mapping data cache and an on-chip counter cache, where the mapping data cache is configured to cache mapping data, and when the free space of the mapping data cache is less than a preset threshold, the least recently used mapping data cache line will be evicted from the cache and written back to the persistent memory. The data processing module encrypts/decrypts persistent memory data by using their counters, and accesses the persistent memory blocks indicated by their corresponding mapping data. The persistent memory comprises the first and second storage regions for the latest checkpoint data and modified working data in the current checkpoint interval respectively.

公开(公告)号：US20250014754A1

公开(公告)日：2025-01-09

申请号：US18635048

申请日：2024-04-15

Applicant: ZHEJIANG LAB

Inventor： Jingsong LI ,  Shengqiang CHI ,  Feng WANG ,  Tianshu ZHOU ,  Yu TIAN

IPC: G16H50/30 ,  G06F18/2413 ,  G16H50/20

Abstract: A clinical risk prediction system oriented to data distribution drift detection and self-adaptation, comprising a central server comprising a first drift detection module and a model aggregation module, and nodes comprising a data acquisition module configured to acquire patient clinical diagnosis and treatment data, a second drift detection module and a model updating module. The first and second drift detection module determine whether the patient clinical diagnosis and treatment data distribution has drifted according to whether the new/old patient clinical diagnosis and treatment data set comes from the same data distribution. When the data distribution has drifted, a local clinical risk prediction model is trained, and its parameters are uploaded to the central server and aggregated to obtain an updated model, which is issued to each node for deployment. The new patient clinical diagnosis and treatment data is input into the updated model to obtain a clinical risk prediction result.

公开(公告)号：US12177072B1

公开(公告)日：2024-12-24

申请号：US18555805

申请日：2023-07-13

Applicant: ZHEJIANG LAB

Inventor： Peilei Wang ,  Ruyun Zhang ,  Jun Zhu ,  Tao Zou ,  Shunbin Li ,  Qi Xu

IPC: H04L41/082 ,  H04L41/0894 ,  H04L67/1097

Abstract: A data storage system includes: a server, a client and a control end; the control end is configured to generate a configuration file, and send the configuration file to the client and the server; the client is configured to generate an encapsulation rule based on the configuration file, generate a storage request, perform encapsulation on the storage request to obtain a message packet, and send the message packet to the server; the server is configured to generate an extraction unit and an action unit based on the configuration file, analyze the message packet to obtain the target information, write the target information into each extraction unit, read action information and determine an action unit matching the action information as a target action unit, and execute the storage actions corresponding to the target action unit to store byte stream data of the target information.

公开(公告)号：US20240393417A1

公开(公告)日：2024-11-28

申请号：US18796233

申请日：2024-08-06

Applicant: ZHEJIANG LAB

Inventor： Yu ZHANG ,  Zhichao WANG ,  Chaoliang SUN ,  Huan ZHANG ,  Haotian QIAN ,  Junyang ZHANG ,  Tianzi JIANG

IPC: G01R33/561 ,  G01R33/56 ,  G01R33/565

Abstract: A method and a system for simulating magnetic resonance echo-planar imaging artifacts. Firstly, for K-space artifacts, K-space data are restored through normal magnetic resonance images, and the K-space data are modified pertinently, and then images with artifacts are reconstructed; for susceptibility artifacts, a susceptibility model is constructed through normal magnetic resonance images, and the magnetic field distribution is reconstructed, and then the images with distortion artifacts are reconstructed. According to the present disclosure, a large number of artifact data sets with different artifact types and artifact degrees can be quickly created through a small number of normal images, thus laying a foundation for the research of identifying artifacts, eliminating or weakening artifacts. A simulation algorithm is designed according to the principle of generation of EPI sequence artifacts, and the obtained images such as stripe artifacts, Moer artifacts, Nyquist artifacts, susceptibility artifacts and the like have good scientificity, accuracy and interpretability.