Machine Learning in the Industrial Internet of Things

Dear Colleagues, 

The Internet of Things (IoT), according to the European Parliament, is a global, distributed network (or networks) of physical objects that are capable of sensing or acting on their environment, and able to communicate with each other, other machines, or computers. Leveraging the IoT for the Fourth Industrial Revolution, or “Industry 4.0”, gave rise to the Industrial Internet of Things (IIoT). Originally a German initiative, Industry 4.0 has now gained international recognition for its potential to innovate product design, enhance manufacturing flexibility and efficiency, improve productivity, and reduce costs. According to the Boston Consulting Group, IIoT is only one of the nine pillars of Industry 4.0. A common enabler of IIoT and the other pillars of Industry 4.0—including autonomous robots, big data analytics, cybersecurity, and simulation—is machine learning, and in particular, deep learning. Deep learning refers to the application of neural networks consisting of many layers of activity vectors as representations to a learning task that can be supervised, unsupervised, semi-supervised, or self-supervised.

For the past few years, many deep learning architectures and approaches (e.g., convolutional neural networks, generative adversarial networks, deep reinforcement learning, transformers) have been proposed for different applications targeted at the IIoT. Many of these applications have made a major impact. For example, major advances in automating robots to handle challenging tasks using deep reinforcement learning have been frequenting media headlines. Applying big data analytics to predictive maintenance has become the core business model for many companies. Deep learning can be applied to intrusion detection in the IIoT. Graph networks have seen successes when used to accelerate mesh-based simulations (i.e., simulations of physical phenomena that can be described by partial differential equations, such as fluid dynamics and electromagnetics), paving the way for real-time digital twins. Deep-learning-enabled sensing, communication, and (edge/cloud) computing platforms are entering the IIoT market at a rapid pace. The availability of this ever-expanding portfolio of technologies further accelerates the applications of deep learning.

This Electronics Special Issue serves as a spiritual successor to the 2019 MDPI Electronics Special Issue “Towards an Industrial Internet of Things” and invites your original contributions related to the applications of machine learning, especially deep learning, to the IIoT. These applications include but are not limited to the aforementioned examples. Both theory-oriented and practice-oriented submissions are welcome.

Prof. Dr. Marimuthu Palaniswami
Prof. Dr. Jeng-Shyang Pan
Dr. Yee Wei Law
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• Industrial Internet of Things
• Industry 4.0
• Cyberphysical systems
• Wireless sensor networks
• Cloud computing, edge computing
• Deep learning, machine learning, artificial intelligence
• Autonomous robots, collaborative robots (cobots)
• Big data analytics
• Predictive maintenance