IEEE Internet of Things (IoT) Journal publishes articles on the latest advances, as well as review articles, on the various aspects of IoT. Topics include IoT system architecture, IoT enabling technologies, IoT communication and networking protocols such as network coding, and IoT services and applications. Examples are IoT demands, impacts, and implications on sensors technologies, big data management, and future internet design for various IoT use cases, such as smart cities, smart environments, smart homes, etc. The fields of interest include: IoT architecture such as things-centric, data-centric, service-oriented IoT architecture; IoT enabling technologies and systematic integration such as sensor technologies, big sensor data management, and future Internet design for IoT; IoT services, applications, and test-beds such as IoT service middleware, IoT application programming interface (API), IoT application design, and IoT trials/experiments; IoT standardization activities and technology development in different standard development organizations (SDO) such as IEEE, IETF, ITU, 3GPP, ETSI, etc.

Special Issue on Advancing Intelligent IoT Systems through Transformer Architectures: New Paradigms, Applications, and Challenges
Submission Date: 2025-08-31

The evolution of Internet of Things (IoT) into the Intelligent Internet of Things (IIoT) marks a
significant shift from conventional connected devices to systems capable of real-time data
processing, decision-making, and autonomous operations. IIoT systems generate vast amounts
of real-time data from diverse sources, including sensors, video streams, logs, and human-
machine interfaces. Traditional deep learning approaches, including convolutional neural
networks and recurrent neural networks, have demonstrated efficacy in specific domains but
struggle with large-scale, multimodal IIoT data due to their inherent architectural limitations.
Transformers, initially introduced for natural language processing, have rapidly emerged as a
leading architecture in deep learning, significantly transforming the manner in which machines
process data. With their scalability, flexibility, and cutting-edge performance, Transformers are
increasingly seen as a promising solution to address the challenges unique to the IIoT
environment. Their ability to handle large data volumes, process heterogeneous inputs, and
uncover complex patterns positions them as a powerful tool for intelligent IIoT systems.
However, adapting Transformers to meet the demands of IIoT systems introduces several
technical and practical challenges, ranging from computational constraints and model efficiency
to issues related to data privacy and security. This special issue focuses on exploring the
transformative impact of Transformer architectures on the evolution of intelligent Internet of

Things (IIoT) systems. Key areas of interest include:
 Transformer-Based IIoT Data Processing
 Edge Computing with Transformers for IIoT
 Multimodal Data Fusion Using Transformers
 Self-Supervised Learning for IIoT with Transformers
 AI-Driven IIoT Security with Transformer Models
 Transformer-Enabled Predictive Maintenance in IIoT
 Transformer Models for IIoT in Smart Cities
 Scalable Transformer Architectures for IIoT Networks
 Federated Learning with Transformers for IIoT

Important Dates
 Submission Deadline: August 31st, 2025
 First Review Due: September 30th, 2025
 Revision Due: October 31st, 2025
 Second Reviews Due/Notification: December 31st 2025
 Final Manuscript Due: February 28th, 2026
 Publication Date: May 2026

Special Issue on Intent-based Networking for AI powered IoT Communications
Submission Date: 2025-09-15

In recent years, the demand for wireless communication has witnessed a tremendous growth which
has shifted the focus of research fraternities towards big data analytics (BDA). This technological
trend has put significant pressure on data center providers to create the next-generation wireless
communication infrastructures, which can provide more flexible services regarding end-to-end
latency and reliability. In this direction, Intent-based Networking (IBN) has been evolving as a
promising solution where a specialized software seamlessly plans, designs and implements the
changes in the network. Numerous high-computing networking paradigms like Software Defined
Networks and Network Function Virtualization have already gained much attention in the recent years,
but their device-to-device management strategy often falls short while dealing with the advanced
wireless communication technologies like 5G. Further, investigating new software interfaces between
ML and the IoT is crucial for enhancing the functionality and efficiency of interconnected devices.
The investigation of these interfaces not only enhances the operational efficiency of IoT devices but
will also contributes to creating more intelligent, interconnected, and energy-efficient ecosystems.
Thus, the objective of this special issue focuses on exploring the recent advances in wireless
communication networks while addressing the practical challenges and limitations associated with
current state-of-the-art architectures. This special issue aims to bring together leading researchers and
developers to present their experimental, conceptual, and theoretical contributions for amalgamating
IBN for AI powered IoT communications. Particular emphasis is placed on novel solutions which are
not just the evolution of 5G but also act as key drivers for the next generation communication
networks.

Suitable topics include, but are not limited to following areas:
• New framework, algorithms, and protocol designs for IBN-based big data communications
• Security, privacy and fault detection
• Emerging technologies on AI and Machine Learning (ML) for future IoT communications
• IBN in mobile data offloading
• IBN in emerging networks like flying ad-hoc networks, vehicular networks, smart grids, etc.
• Emerging IoT and cloud applications
• Mission-critical applications like smart grid, industry automation, health-care, etc.
• IBN inspired MAC and routing protocols
• Big data analytics frameworks
• Deep learning and federated learning for network control and communications
• AI and ML algorithms for network management
• Software interfaces for integrating AI/ML with IoT
• Protocol design and optimization
• Energy-efficient solutions and their integration to network architectures
• Results from experiments, testbeds, and simulations
• Other concepts and technologies

Important Dates
Submission Deadline: Extended to September 15, 2025
First Review Due: October 15, 2025
Revision Due: November 15, 2025
Sec. Reviews Due/Notification: December 15, 2025
Final Manuscript Due: January 15, 2026
Publication Date: March 2026

Special Issue on Effective, Efficient, and Trustworthy AI Agents for the Internet of Things
Submission Date: 2025-12-31

The Internet of Things (IoT) is evolving into a complex ecosystem of interconnected devices and
sensors that generate vast streams of real-time data. To manage this complexity, AI agents are
increasingly deployed for tasks such as perception, reasoning, and decision-making, enabling
intelligent services in domains like smart healthcare, industrial automation, and urban
infrastructure. These agents bring advantages in real-time processing, contextual awareness, and
autonomous adaptability, but also face challenges related to effectiveness, efficiency, and
trustworthiness—especially under resource constraints and in dynamic environments.
This special issue invites research on intelligent AI agents tailored for IoT systems. We welcome
contributions focused on lightweight models, scalable learning frameworks, privacy-preserving
mechanisms, and robust integration strategies. The goal is to advance the development of
effective, efficient, and trustworthy AI agents that can unlock the full potential of IoT across
diverse real-world applications.

Topics of interest include, but not limited to:
• Real-time analytics and autonomous decision-making in IoT using AI agents
• Memory-augmented and context-aware architectures for long-term learning
• Reinforcement learning for adaptive decision-making in dynamic environments
• Lightweight and low-latency perception models for AI agents in IoT
• Perceptual interaction for collaborative intelligence in AI agents
• Multimodal perception and sensor fusion for cognitive AI agents
• Robust Interaction of AI Agents for IoT
• Federated learning and differential privacy for AI agents for IoT
• Efficient architectures for AI agents in IoT applications
• Interpretable decision-making for AI agents for IoT
• Adversarial training and defense strategies for secure AI agents for IoT
• Dynamic cognitive architectures for AI agents for IoT
• Goal-directed planning and reasoning mechanisms for AI agents for IoT
• Internal mental state modeling (memory, emotions, rewards) in AI agents for IoT
• World model development for AI agents for IoT

Important Dates
• Submission Deadline: December 31st, 2025
• First Review Due: February 28th, 2026
• Revision Due: April 15th, 2026
• Second Reviews Due/Notification: June 15th, 2026
• Final Manuscript Due: June 30th, 2026
• Publication Date: September 2026