The Internet of Things (IoT) is an ecosystem of connected physical objects that are accessible through the Internet. This involves the creation of smart communications and computational environments, such as smart homes, smart transportation, and smart fintech, with the help of several devices in a network that enable the transmission of data within these devices such as wireless sensor networks (WSN), radio frequency identification (RFID), cloud services, near field communication (NFC), gateways, data storage and analytics, and visualization elements. Computation, control, system latency, robustness, reliability, performance, and energy efficiency at different layers in IoT ecosystems are dictated by computational intelligence techniques, which are responsible for data collection, interconnection between devices and the internet, data processing, and decision-making, without human interaction. Therefore, super-fast computing with ultra-low latency has always been crucial in the rapid development of IoT applications.

Various learning and optimization methods are the backbone of computational intelligence. Therefore, the integration of new learning methods, such as opposition-based learning or federated learning, and optimization methods, for example, quantum artificial butterfly optimization, with a focus on performance-quality of service (QoS) trade-off, is an emerging trend of great significance in the next generation IoT applications. These advancements in computational intelligence approaches can significantly enhance sustainability regarding latency and computing resources, without compromising the quality of service. However, the exponentially increasing use of sensors and actuators for next generation IoT applications generates massive amounts of data and throughout cloud computation, which can significantly deteriorate computing efficiency. Hence, ameliorating the performance of ultra-fast computing in IoT through computational intelligence techniques is a key challenge facing researchers in academia and industry. Due to the growing use of advanced learning and optimization, several computational intelligence techniques are entering a more mature phase, which could potentially play an important role in improving not only computing efficiency but also the performance of the entire IoT ecosystem. However, it is essential to investigate the trade-off between the performance of emerging computational intelligence techniques and the requirements of next generation IoT applications.

With this motivation, this Special Issue aims to collect high-quality articles that address the open technical problems and challenges concerning emerging computational intelligence approaches, considering the constraints of computing efficiency, intelligence, and QoS. In particular, we seek submissions which efficiently integrate novel learning and optimization methodologies into computational intelligence techniques for several verticals of the IoT, focusing on system performance evaluation and comparison with existing smart computational intelligence algorithms.

Potential topics include but are not limited to the following:

• Novel computational intelligence techniques for resource orchestration in next generation IoT
• Federated learning-based computational intelligence modeling and analysis for next generation IoT
• ML/DL combined computational intelligence approaches for energy efficiency in IoT
• Advanced computational intelligence algorithm design and deployments for IoT
• New learning methods in computational intelligence approaches for quality of service in IoT
• Advanced evolutionary algorithms and computational intelligence approaches for IoT applications
• Emerging computational intelligence models for security, privacy, and trust in IoT
• Perception-based computational intelligence algorithms for anomaly detection in IoT
• Big data analytics using novel computational intelligence for IoT applications
• Experimental test-beds and results for novel computational intelligence in IoT applications
• Framework designs for novel computational intelligence algorithms for IoT
• Advanced computational intelligence-based protocols for future IoT applications and services
• Novel computational intelligence protocols for coordinating devices in IoT
• Interoperability and dynamic adaptation of advanced computational intelligence algorithms for IoT
• Advanced computational intelligence for blockchain-empowered IoT
• Advanced computational intelligence approaches for industrial automation and services and for Industry 4.0