Title:
APPARATUS AND METHOD FOR DETECTING ABNORMAL SYMPTOMS OF VEHICLE BASED ON SELF-SUPERVISED LEARNING BY USING PSEUDO NORMAL DATA
Document Type and Number:
WIPO Patent Application WO/2022/075678
Kind Code:
A3
Abstract:
A method for detecting abnormal symptoms of a vehicle based on self-supervised learning by using pseudo normal data may comprise the steps of: obtaining normal data generated in a vehicle; preprocessing the obtained normal data; generating pseudo normal data by inputting the preprocessed normal data into a pre-trained first neural network model; training a second neural network model on the basis of the generated pseudo normal data; and detecting abnormal symptoms of the vehicle by inputting the data generated in the vehicle into the trained second neural network model.
Inventors:
KIM HUY KANG (KR)
SONG HYUN MIN (KR)
SONG HYUN MIN (KR)
Application Number:
PCT/KR2021/013572
Publication Date:
October 27, 2022
Filing Date:
October 05, 2021
Export Citation:
Assignee:
UNIV KOREA RES & BUS FOUND (KR)
International Classes:
H04L9/40; B60R25/30; H04L12/40
Foreign References:
| JP2020096286A | 2020-06-18 | |||
| KR20150037285A | 2015-04-08 | |||
| KR20180015791A | 2018-02-14 | |||
| KR102088428B1 | 2020-04-24 | |||
| KR101714520B1 | 2017-03-09 |
Attorney, Agent or Firm:
LEE, Dae Ho et al. (KR)
Download PDF: