Urban Internet-of-Things Intelligence

Recent years have witnessed the significant development of urban Internet-of-Things (IoT) for smart cities. Urban IoT is built on the top of complex Cyber-Physical Systems (CPSs) that consist of spatially distributed entities that interact with each other over time, leading to an inherently spatio-temporal and interconnected composition. In this setting, urban IoT generates ubiquitously available data for demonstrating real-time and fine-granular status of complicated urban systems. Mining such urban IoT data can reveal holistic human and system structures, dynamics, and semantics of the underlying urban systems, and further provides intelligent decision support for urban public administration in boosting commercial activities, enhancing public security, fostering social interaction, and thus yielding livable, sustainable, and viable environments.

This Research Topic, led by the organizers of the ICDM 2022 UNIT: 1st Workshop on Urban Internet-of-Things Intelligence workshop, aims to continue the discussion and research presented at the workshop and bring together academia researchers and industry practitioners to (1) discuss the principles, limitations and applications of urban IoT intelligence, and (2) foster research on innovative algorithms, novel techniques, and new applications of urban IoT intelligence in smart cities.

Researchers are welcome to submit their contributions to this Research Topic. Conference and workshop papers can be submitted in the form of extended papers: authors are requested to expand them by adding 30% of original content in the form of new raw material (experiments, data) or new treatment of old data sets which leads to original discussion and/or conclusions.

We encourage submissions on a broad range of data mining for urban IoT intelligence. Topics of interest include but are not limited to theories, algorithms, applications, systems, and tools, such as:

Building Sensing Infrastructures for Developing Urban or IoT Intelligence

• Mobile sensing
• Communication and networking for AI and machine learning
• Unmanned aerial vehicle (UAV)-based sensing/communications/networking
• Cellular communications and data networks, e.g. 5G, 6G, and beyond
• Cloud, Edge, and Fog computing for sensing and inference
• Sensing and Networking for Smart & Connected Communities
• Sensing and networking of social systems

Novel Machine Learning Models or Systems for Analytics and Prediction in Urban or IoTs Setting

• Deep learning, Representation Learning
• Transfer learning
• Meta-learning
• Multi-modality learning
• Multi-view learning
• Domain shift & generalization

Solving the Urban and IoT Data Challenges for Urban or IoT Analytics

• Data sparsity, noises, outliers, unbalanced, outlier non-IID issues
• Data spatial autocorrelation, temporal dependencies, heterogeneity
• Graph structure mining and learning issues
• Image, video, audio, multi-media data mining issues
• Data fusion and knowledge transferring

Computation

• Efficiency and scalability, e.g., model compression/pruning for IoT devices
• Trustworthiness, e.g., federated learning for IoT devices
• Robustness, e.g., attacks and defenses for IoT devices

Decision-Making & Operation & Management

• Decision and control, e.g., reinforcement learning for urban IoT
• Applications, e.g., intelligent transportation, public health/administration/policy, smart energy, power grids, smart homes, vehicle-to-vehicle networks, etc

Keywords: Internet of Things, Urban Intelligence, Machine Learning, Data Mining

Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.