Multimodal Intelligent Perception, Semantic Communications, Data Analytics and Privacy Preservation for AIoT Systems

Dear Colleagues,

The rapid convergence of artificial intelligence, wireless communications, edge computing, and pervasive sensing is reshaping the evolution of the Artificial Intelligence of Things (AIoT). In emerging AIoT systems, massive heterogeneous data are continuously generated by cameras, sensors, mobile devices, vehicles, wearables, robots, and industrial terminals. These data are often multimodal, time-varying, privacy-sensitive, and resource-constrained, which poses significant challenges to conventional perception, communication, analytics, and security mechanisms. To address these challenges, this topical collection, "Multimodal Intelligent Perception, Semantic Communications, Data Analytics and Privacy Preservation for AIoT Systems" aims to provide a timely forum for researchers and practitioners to present recent advances, theoretical foundations, enabling technologies, and practical applications at the intersection of multimodal intelligence, semantic communications, data-driven analytics, and privacy-preserving AIoT systems.

The focus of this collection is to explore how AIoT systems can move beyond conventional data acquisition and bit-level transmission, toward intelligent, semantic-aware, and privacy-preserving perception and communication. It welcomes original research and review articles on multimodal sensing and fusion, intelligent perception under complex environments, task-oriented and semantic communications, edge-cloud collaborative intelligence, distributed and federated learning, trustworthy data analytics, privacy-preserving machine learning, secure multimodal representation, and resource-efficient AIoT deployment. The scope also covers application-driven studies in intelligent transportation, Internet of Vehicles, smart healthcare, industrial IoT, smart cities, autonomous systems, human–machine interaction, and connected sensing networks. Particular attention will be given to works that jointly consider perception accuracy, communication efficiency, semantic fidelity, data utility, privacy leakage, security robustness, and real-time deployment constraints.

The purpose of this topical collection is threefold. First, it seeks to clarify the emerging research landscape of AIoT by integrating several traditionally separated research directions, including multimodal data analysis, semantic communication, edge intelligence, and privacy protection. Second, it aims to stimulate new methodologies that enable AIoT devices and networks to understand, compress, transmit, and analyze task-relevant semantics rather than raw data alone. Third, it encourages the development of trustworthy and deployable AIoT solutions that can operate under limited bandwidth, constrained computation, dynamic wireless channels, heterogeneous modalities, and strict privacy requirements.

This collection will usefully supplement the existing literature in several aspects. Current studies on multimodal perception mainly emphasize representation learning and decision fusion, but often pay insufficient attention to communication constraints and privacy risks in networked AIoT environments. Research on semantic communications has demonstrated the potential of task-oriented transmission, yet many existing works remain focused on single-modality, single-task, or idealized communication settings. Meanwhile, privacy-preserving AI and secure data analytics have been widely investigated, but their integration with multimodal semantic representation and resource-constrained AIoT networking is still underexplored. By bringing these perspectives together, this topical collection will provide a coherent platform for advancing cross-layer, cross-modal, and privacy-aware intelligence in next-generation AIoT systems. It is expected to promote new theoretical insights, system architectures, algorithms, benchmarks, and real-world applications for building secure, efficient, and intelligent connected environments.

Prof. Dr. Puning Zhang
Dr. Zhigang Yang
Dr. Jianer Zhou
Dr. Xiaomin Jin
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• artificial intelligence of things (AIoT)
• multimodal intelligent perception
• semantic communications
• multimodal data analytics
• multimodal sentiment analysis
• multimodal emotion recognition
• privacy preservation
• edge intelligence
• federated learning
• trustworthy AI
• secure data fusion
• task-oriented communications
• semantic-aware networking
• internet of vehicles
• smart sensing systems
• privacy-preserving machine learning