JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

AOI-OPEN: federated operation and control for DAO-based trustworthy and intelligent AOI ecology

Author(s): Yansong CAO ^’¹, Yutong WANG^’² , Jing YANG^’² , Yonglin TIAN^‡² , Jiangong WANG², Fei-Yue WANG^1, ²
Affiliation(s): ¹Faculty of Innovation Engineering, Macau University of Science and Technology, Macau 999078, China; more
Corresponding email(s): yscao@maverickvc.com, yutong.wang@ia.ac.cn, yangjing2020@ia.ac.cn
Key Words: Automated optical inspection; Decentralized autonomous organizations; Parallel data; Federated intelligence

Share this article to： More <<< Previous Paper \|Next Paper >>>

Yansong CAO ^’¹, Yutong WANG^’² , Jing YANG^’² , Yonglin TIAN^‡² , Jiangong WANG², Fei-Yue WANG^1,². AOI-OPEN: federated operation and control for DAO-based trustworthy and intelligent AOI ecology[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2400975

@article{title="AOI-OPEN: federated operation and control for DAO-based trustworthy and intelligent AOI ecology",
author="Yansong CAO ^’¹, Yutong WANG^’² , Jing YANG^’² , Yonglin TIAN^‡² , Jiangong WANG², Fei-Yue WANG^1,²",
journal="Frontiers of Information Technology & Electronic Engineering",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/FITEE.2400975"
}

%0 Journal Article
%T AOI-OPEN: federated operation and control for DAO-based trustworthy and intelligent AOI ecology
%A Yansong CAO ^’¹
%A Yutong WANG^’²
%A Jing YANG^’²
%A Yonglin TIAN^‡²
%A Jiangong WANG²
%A Fei-Yue WANG^1
%A²
%J Frontiers of Information Technology & Electronic Engineering
%P
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/FITEE.2400975"

TY - JOUR
T1 - AOI-OPEN: federated operation and control for DAO-based trustworthy and intelligent AOI ecology
A1 - Yansong CAO ^’¹
A1 - Yutong WANG^’²
A1 - Jing YANG^’²
A1 - Yonglin TIAN^‡²
A1 - Jiangong WANG²
A1 - Fei-Yue WANG^{1
A1 -}²
J0 - Frontiers of Information Technology & Electronic Engineering
SP -
EP -
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/FITEE.2400975"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Isolated data islands are prevalent in intelligent automated optical inspection (AOI) systems, limiting the full utilization of data resources and impeding the potential of AOI systems. Establishing a collaborative ecology involving software providers, hardware manufacturers, and factories offers an encouraging solution to build a closed-loop data flow and achieve optimal data resource utilization. However, concerns about privacy issues, rights infringement, and threats from other participants present challenges in establishing an efficient and effective community. In this paper, we propose a novel framework, AOI‐ OPEN, that first creates a trustworthy AOI ecology to gather related entities with decentralized autonomous organization (DAO) mechanisms. Then, a Parallel Data pipeline is proposed to generate large-scale virtual samples from small-scale real data for AOI systems. Finally, Federated Learning (FL) is adopted to utilize the distributed data resource among multiple entities and build large privacy-preserving models. Experiments on defect classification tasks show that, with privacy preserved, AOI‐ OPEN greatly strengthens the utilization of distributed data resources and improves the accuracy of inspection models.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference