AnoGAN-Based Anomaly Filtering for Intelligent Edge Device in Smart Factory

Maintenance of production equipment and controlling products quality through data analysis are the main issues of smart factory. During production, detected data for analysis is showing abnormal data more than normal data. Therefore, there is lots of energy consumption for analysis, cost, and saving...

Full description

Saved in:
Bibliographic Details
Published in2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM) pp. 1 - 6
Main Authors Kim, Donghyun, Cha, Jaegyeong, Oh, Seokju, Jeong, Jongpil
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.01.2021
Subjects
AnoGAN
Anomaly detection
Data analysis
Deep learning
Edge Intelligence Device
Filtering
IIoT
Image edge detection
Smart manufacturing
Virtual environments
Online AccessGet full text
DOI10.1109/IMCOM51814.2021.9377409

Cover

More Information
Summary:Maintenance of production equipment and controlling products quality through data analysis are the main issues of smart factory. During production, detected data for analysis is showing abnormal data more than normal data. Therefore, there is lots of energy consumption for analysis, cost, and saving of data. Edge Device which applied deep learning algorithm is able to solve this problem. In this paper, a framework for data filtering method before data analysis is proposed through Anomaly detection using single board computer (SBC). Using Nvidia Jetson nano and desktop computer to compare and analyze the two virtual environments to determine the framework of optimum anomaly data filtering. AnoGAN is a deep learning model utilized for anomaly detection.
DOI:10.1109/IMCOM51814.2021.9377409