Call for Articles

The digitalization of business applications, including the critical infrastructure, promises transformative opportunities to Society. IoT devices are one of the most technological advancements that have significantly changed the landscape of critical infrastructure applications. However, it presents an array of challenges in defining implementation standards and best practices to secure operational control systems associated with critical infrastructures. Further, critical infrastructures such as electric grids, railways, pipelines, and healthcare are susceptible to numerous threats. Effectively managing these infrastructures with conventional IoT devices is extremely time-consuming and expensive. Here, security becomes the primary concern as the IoT devices are resource-constrained in nature, and they need cloud or edge computing infrastructures to process the data and respond to infrastructure problems. In many cases, when dealing with the long-distance surveillance of the critical infrastructures, IoT devices face the problem of low channel capacity, and it causes larger resource consumption in the delivery of images and videos. In this time gap, any significant deformation to the data sources may result in disastrous consequences. This creates the need for disruptive technologies to mitigate, adapt, and positively respond to various cyber threats across the critical infrastructure.

Visual IoT increases the sustainability, visibility, and efficiency of critical infrastructure applications, which can be challenging with conventional IoT techniques. They are equipped with visual sensors, and they rely on computer vision processing techniques for sensing and processing visual data. Hence, the use of disruptive technologies such as deep learning will enhance its applications. It provides real-time monitoring, alerts, and recommendations to the critical infrastructures. It improves communication and helps identify potential threats in vital infrastructures accurately and quickly, thus improving the resilience among the critical infrastructures. This indicates lesser downtime and reduced catastrophic system failure, enabling the IoT devices to efficiently use the resources and provide better services. The primary objective of using deep learning assisted visual IoT is to solve the research gaps between existing IoT systems in complex multimedia processing, where computer science, networks, and statistics are collectively integrated together to protect a critical environment. In addition, deep learning assisted visual IoT technologies authenticate resources across the networks, perform compliance checks, and notify network vulnerabilities with advanced protection measures. This Special Issue aims to reduce the risk of cyber-attacks by increasing visibility across critical infrastructures. It can be achieved using deep learning assisted visual IoT for the development of the secure architecture for critical infrastructures, implementing network segmentation capabilities, shaping up the IoT device security, developing enforceable security and information policies and the overall resilience measures. Researchers and practitioners working in this field are invited to submit their novel and innovative research contributions.

Topics of interest for the Special Issue include, but are not limited to, the following:

• The role of deep learning assisted visual IoT in monitoring and assessing the critical infrastructures
• Deep learning assisted visual IoT model for assessing and integrating threat, vulnerability, and risk across critical infrastructures
• Novel deep learning based visual IoT assisted architectures for critical infrastructure applications
• Deep learning based visual IoT for visual information processing across the critical infrastructures
• Mitigating unforeseen cyber risks across critical infrastructures with deep learning assisted visual IoT techniques
• Secure edge data storage and processing with deep learning assisted visual IoT
• Crowd sensing, crowdsourcing, and crowd intelligence with deep learning assisted visual IoT
• Effective ways of optimizing massive visual IoT communications across critical infrastructures
• Large scale multi-sensorial data processing in IoT assisted critical infrastructures with deep learning assisted visual IoT
• Efficient sensing, fusion, and caching across critical infrastructures with deep learning assisted visual IoT
• Anomaly detection and visualization aids

Submission Guidelines

Manuscripts should conform to the standard format as indicated in the Information for Authors section of the Article Submission Guidelines.  All manuscripts to be considered for publication must be submitted by the deadline through Manuscript Central. Select “June 2022/Deep Learning Assisted Visual IoT Technologies for Critical Infrastructure Protection” from the drop-down menu of Topic/Series titles.

Important Dates

Manuscript Submission Deadline Date: 25 October 2021 15 February 2022 (Extended Deadline)
Authors Notification Date: 29 December 2021
Revised Papers Due Date: 15 March 2022
Final Notification Date: 30 April 2022
Publication Date: June 2022

Guest Editors

Tu N. Nguyen (Lead Guest Editor)
Kennesaw State University, USA

Linh Le
Kennesaw State University, USA

Vincenzo Piuri
University of Milan, Italy

B. B. Gupta
National Institute of Technology, Kurukshetra, India

Lianyong Qi
School of Computer Science, Qufu Normal University, China

Shahid Mumtaz
Instituto de Telecomunicações, Portugal

Warren Huang-Chen Lee
National Chung Cheng University, Taiwan