Deep and Transfer Learning Approaches for Complex Data Analysis in the Industry 4.0 Era
1Nantong University, Nantong, China
2Changshu Institute of Technology, Changshu, China
3University of Malaya, Kuala Lumpur, Malaysia
4Jiangnan University, Wuxi, China
Deep and Transfer Learning Approaches for Complex Data Analysis in the Industry 4.0 Era
Description
With the rapid development of information and communications technology, intelligent networking of machines, and processes for the industry has been created. Industry 4.0 is the current trend of data exchange, and automation in industry technologies. Technologies utilise existing data, and several other data sources. Collecting data from connected assets, transforming existing manufacturing processes, and gaining efficiency on multiple levels, make the industry 4.0 era possible. Finding the insights of complex data makes related industries more intelligent, more efficient and more customer-focused. It also helps create the smart industry, and detect new industry models.
Although deep learning can learn enough mapping patterns from input-output relationships, complex data analysis still comes with many challenges. The most important challenge is how to improve the generalization ability of a model when encountering different complex situations. Industry 4.0 era is full of scenarios that are not covered by an infinite number of datasets hence why we cannot train the model to predict well in all of them. Recently, rapid advancements in deep & transfer learning approaches have revolutionised a large number of areas of machine learning and data science. The main highlight of deep and transfer learning is it can learn enough knowledge representation from complex data, and it can also transfer the knowledge learned from the finite datasets in scenarios that are not covered.
The aim of this Special Issue is to collate original research articles, as well as review articles, discussing the ever-increasing challenges of complex data such as Internet of Things (IoT) network data, real-time data, industrial chain data, product data, etc. We also hope that this Special Issue inspires further exploitation and development of deep, and transfer learning approaches for complex data analysis in the industry 4.0 era. Submissions focusing on the recent advancements of complex data via deep, and transfer learning methods within the industry 4.0 era are particularly encouraged.
Potential topics include but are not limited to the following:
- Novel theories in deep and transfer learning
- Representation learning for complex data analysis in the industry 4.0 era
- Online deep and transfer learning frameworks for real-time data analysis in the industry 4.0 era
- Explainable deep and transfer learning models for complex data analysis in the industry 4.0 era
- Multi-view, and multi-task deep and transfer models for complex data analysis in the industry 4.0 era
- Manifold-based deep and transfer models for complex data analysis in the industry 4.0 era
- High-efficiency deep and transfer models for big data analysis in the industry 4.0 era