Intelligent computing has been widely distributed across various computing platforms, including the Internet of Things (IoT), Internet of Medical Things (IoMT), and Industrial Internet of Things (IIoT). The scale and volume of data generated from IoT intelligent computing platforms increases rapidly due to the increasing number of cheap information sensing embedded devices and sensors, such as flexible sensors, mobile devices, smartphones, smart cameras and microphones, interconnected smart devices, wireless sensor network equipment, and ubiquitous communication devices. Compared with conventional IoT intelligent computing platforms, future-generation IoT intelligent computing platforms should have sufficient capability for intelligent inference along with data processing and fusion on local devices, driven by machine learning methods, artificial intelligence models, fuzzy logic, genetic algorithms, and intelligent agents to expand their response range.

In recent intelligent computing platforms developed for numerous IoT scenarios, there are two unavoidable shortcomings in data processing and fusion. Most IoT data captured from discrete smart embedded systems or individual wearable sensors does not have global attributes and can only represent local features, which can draw into abnormal noise in the modeling and training of intelligence computing models. However, being equipped with specific computing performance is a necessary capability for IoT intelligent computing platforms. These computing performances are real-time, lightweight, and robust, and can adapt to resource-constrained embedded systems. Therefore, it is necessary to discuss, in depth, future generations of IoT intelligent computing platforms that meet the requirements of data processing and fusion for complex IoT applications. Intelligent computing algorithms or models for IoT platforms that run on edge systems or local servers can eliminate noise data in time, resulting in improved operating speed and decreased memory consumption for IoT intelligent computing platforms.

This Special Issue will focus on data processing and fusion in IoT data collection, modeling and simulation based on intelligent computing platforms, and further research and development of novel detection in various applications of smart embedded systems.

Potential topics include but are not limited to the following:

• Novel architectures, protocols, methodologies, and applications supporting future-generation IoT intelligent computing platforms
• Cognitive modeling and context-aware computing for IoT data processing and fusion
• Data processing and fusion in edge, mist, fog, and cloud computing
• Data warehousing and management in future-generation IoT intelligent computing platforms
• Data analysis and mining for future-generation IoT intelligent computing platforms
• Intrusion detection and security monitoring for future-generation IoT intelligent computing platforms
• Data processing and fusion based on machine learning in future-generation IoT intelligent computing platforms
• Machine learning-based multimodal data fusion for future-generation IoT intelligent computing platforms
• Machine learning-based IoT intelligent computing algorithms
• Data enhancing and privacy protection for future-generation IoT intelligent computing platforms
• Intelligent computing for smart IoT applications, such as smart buildings, smart healthcare, and Industry 4.0
• Data fusion strategies in the IoT intelligent computing platforms, such IoT, IoMT, or IIoT