December 5th, 2023 
Daniela Lopez de Luise The Industry 4.0/5.0 movement seeks to elevate efficiency, productivity, and flexibility, with Deep Learning pivotal in this context. However, while supervised learning dominates research, real-world industrial applications demand alternative approaches due to dynamic environments and labeling challenges.
We encourage researchers to submit innovative work on various learning paradigms applicable to industrial tasks. This includes, but is not limited to, the following paradigms:
– Continual Learning
– Meta Learning
– Multi-Task Learning
– Lifelong Learning
– Online Learning
– AutoML
– Few-Shot Learning
– Domain Adaptation
– Active Learning
– Transfer Learning
– OpenWorld Learning
– Out-Of-Distribution Learning
Moreover, we invite submissions focusing on industrial challenges such as (but not limited to):
– Anomaly Detection
– Fault Detection
– Predictive Maintenance
– Process Optimization
– Production Scheduling
– Quality Control
– Soft Sensing
– Sensor Fusion
Authors should submit manuscripts through the IEEE Transactions on Automation Science and Engineering's online system (https://mc.manuscriptcentral.com/t-ase), adhering to the journal's guidelines available at https://www.ieee-ras.org/publications/t-ase/information-for-authors-t-ase
Important Dates:
– Paper submission deadline: April 1, 2024
– Completion of the first round review: August 1, 2024
– Completion of the second round review: December 1, 2024
– Final submission due: February 1, 2025
– Tentative publication date: July 2025
Best regards from the Guest Editors,
Gian Antonio Susto, Olga Fink, Seokho Kang, Lars Moench, Davide Dalle Pezze
Posted in