Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
TARGET MAP INFERENCE SYSTEM AND METHOD USING ARTIFICIAL INTELLIGENCE NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2024/038948
Kind Code:
A1
Abstract:
The present invention relates to a target map inference system and method using an artificial intelligence neural network. The target map inference system using an artificial intelligence neural network, according to an embodiment of the present invention, may comprise: an input unit that receives, as an input, input data including information regarding a sound source; a data transform unit that generates transform-input data by transforming the input data; and an artificial intelligence neural network that infers, from the transform-input data, a target map displaying a location and intensity of the sound source included in the transform-input data. According to the present invention, a sound source map having a high resolution can be generated even at a very low frequency, and thus, it is possible to solve a problem of a small spatial variation in a value on an input sound source map and a problem of processing all sound source maps at multiple frequencies.

Inventors:
CHANG JI HO (KR)
CHO WAN HO (KR)
HAN SANG MYEONG (KR)
Application Number:
PCT/KR2022/014408
Publication Date:
February 22, 2024
Filing Date:
September 27, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
KOREA RES INST STANDARDS & SCI (KR)
VIZWAVE INC (KR)
International Classes:
G01S5/18; G01S3/801; G06F17/15; G06N3/08
Foreign References:
KR20220032382A2022-03-15
KR20210140932A2021-11-23
JP2015164267A2015-09-10
KR20130065029A2013-06-19
KR20200020233A2020-02-26
Attorney, Agent or Firm:
PCR INTELLECTUAL PROPERTY LAW FIRM (KR)
Download PDF: