Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
LAPLACIAN EIGENMAPS-BASED DIMENSION REDUCTION AND VISUALIZATION METHOD FOR HIGH-THROUGHPUT CALCIUM SIGNAL
Document Type and Number:
WIPO Patent Application WO/2023/173770
Kind Code:
A1
Abstract:
A Laplacian Eigenmaps-based dimension reduction and visualization method for a high-throughput calcium signal, comprising performing dimension reduction on a high-dimensional calcium signal recorded in neural optical imaging by means of Laplacian Eigenmaps; extracting effective information; and drawing a dynamic image in a low-dimensional space, so that the visual representation of a neural cluster activity mode recorded by a calcium imaging technique is achieved. Compared with a conventional method such as a generalized linear regression model, a high-throughput calcium signal having a larger scale and a lower signal-to-noise ratio can be processed in the present invention, so that the present invention has obvious advantages in the aspects of the processing of a calcium signal of a large-scale neuron cluster and the dynamic visualization of the signal. In the aspects of clustering accuracy and visual graph discrimination, a Laplacian Eigenmaps-based dimension reduction and visualization method for a high-throughput calcium signal is also superior to other dimension reduction methods, and Laplacian Eigenmaps has low calculation complexity, so that the present invention has remarkable advantages in the aspect of time consumption during operation, and can be used for real-time online dimension reduction and visualization processing.

More Like This:
JP2005524124Methods and equipment for identifying diagnostic components of the system
WO/2020/191435RADIATION DETECTION WITH NON-PARAMETRIC DECOMPOUNDING OF PULSE PILE-UP
JP2001356944METHOD AND DEVICE FOR UPDATING RECORD OF DATA BASE SYSTEM BASED ON MODEL IN WHICH TIME-DEPENDENT BEHAVIOR IS IMPROVED
Inventors:
ZHANG SHAOMIN (CN)
ZHANG YIWEI (CN)
LIU TENGJUN (CN)
CHEN WEIDONG (CN)
Application Number:
PCT/CN2022/131368
Publication Date:
September 21, 2023
Filing Date:
November 11, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UNIV ZHEJIANG (CN)
International Classes:
G06F17/18; G06F16/904
Foreign References:
CN115034253A2022-09-09
CN109033415A2018-12-18
CN112763225A2021-05-07
Other References:
SUN, GUANGHAO ET AL.: "Effective Dimensionality Reduction for Visualizing Neural Dynamics by Laplacian Eigenmaps", NEURAL COMPUTATION, vol. 31, no. 7, 1 July 2019 (2019-07-01), pages 1356 - 1379, XP009548787
Attorney, Agent or Firm:
HANGZHOU QIUSHI PATENT OFFICE CO., LTD. (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: ROTOR STRUCTURE AND FORMING METHOD THEREFOR, AND ELECTRIC MOTOR STRUCTURE

Next Patent: BATTERY WINDING METHOD AND APPARATUS