Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Towards Deep Transfer Learning in Industrial Internet of Things

Published

Author(s)

Xing Liu, Wei Yu, Fan Liang, David Griffith, Nada T. Golmie

Abstract

In this paper, we propose a general framework to adopt transfer learning in IIoT systems. Transfer learning is a machine learning technique that fully uses the knowledge from pre- trained models to reduce the computing requirements for the training process, leading to efficient learning. In our study, we categorize the application space of applying transfer learning to the IIoT system into four generic scenarios, namely centralized transfer learning with large datasets, distributed transfer learning with large datasets, centralized transfer learning with small datasets, and distributed transfer learning with small datasets. According to the characteristics of each scenario, we design workflows to apply the transfer learning technique. To demonstrate the efficacy of the approach, we apply our transfer learning technique to the task of IIoT component recognition. We use the well-known VGG-16 model and leverage T-Less industrial datasets to evaluate the performance of our approach in different scenarios. Via extensive performance evaluation, our experimental results confirm the efficacy of our approach, which can not only reduce training time, but also achieve higher accuracy, compared with the classical convolutional neural network (CNN) approach.
Citation
IEEE Internet of Things

Keywords

Industrial Internet of Things, Machine Learning, Transfer Learning

Citation

Liu, X. , Yu, W. , Liang, F. , Griffith, D. and , N. (2021), Towards Deep Transfer Learning in Industrial Internet of Things, IEEE Internet of Things, [online], https://dx.doi.org/10.1109/JIOT.2021.3062482, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=931407 (Accessed September 22, 2021)
Created February 26, 2021, Updated April 6, 2021