Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.1
2.6
Journals
Electronics
Special Issues
AI-Driven IoT: Beyond Connectivity, Toward Intelligence
share announcement

AI-Driven IoT: Beyond Connectivity, Toward Intelligence

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 15 September 2026 | Viewed by 8703

Special Issue Editors

Dr. Gaoya Dong

E-Mail Website
Guest Editor
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
Interests: deep reinforcement learning; internet of things; microwave sensor
Dr. Haoqiang Liu

E-Mail Website
Guest Editor
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
Interests: large-scale wireless network optimization; deep reinforcement learning; multi-agent reinforcement learning; microwave sensor
Dr. Meijun Qu

E-Mail Website
Guest Editor
School of Information and Communication Engineering, Communication University of China, Beijing 100024, China
Interests: reinforcement learning; internet of things; microwave sensor

Special Issue Information

Dear Colleagues,

The integration of Artificial Intelligence (AI) and the Internet of Things (IoT) has revolutionized how devices perceive, analyze, and interact with the physical world, enabling unprecedented levels of automation, efficiency, and intelligence in diverse domains such as smart cities, industrial automation, healthcare, and environmental monitoring. As this Special Issue, we aim to capture the rapid advancements in this interdisciplinary field, where AI techniques—including machine learning, deep learning, computer vision, and natural language processing—are increasingly empowering IoT systems to handle massive data streams, adapt to dynamic environments, and make autonomous, context-aware decisions. However, critical challenges persist, such as optimizing AI model deployment on resource-constrained IoT devices, ensuring real-time responsiveness, addressing privacy and security risks in interconnected systems, and enhancing scalability for large-scale IoT networks.

This Special Issue seeks to provide a comprehensive platform for researchers and practitioners to showcase cutting-edge innovations at the intersection of AI and IoT. We particularly encourage contributions that explore novel methodologies, system architectures, and practical applications that overcome the key limitations in current AI-enabled IoT solutions. Emphasis is placed on emerging trends such as edge AI for IoT, federated learning in distributed IoT networks, AI-driven predictive maintenance for industrial IoT, and ethical AI frameworks for privacy-preserving IoT systems. Interdisciplinary works integrating AI and IoT with fields like 5G/6G communications, digital twins, blockchain, and renewable energy systems are also highly welcome.

Topics of interest include, but are not limited to, the following:

  • AI-driven data analytics and decision-making in IoT systems;
  • Edge and fog computing for AI-enabled IoT applications;
  • Machine learning and deep learning algorithms for sensor design and optimization;
  • Privacy, security, and trust in AI-empowered IoT networks;
  • AI-based predictive maintenance and anomaly detection in industrial IoT;
  • Smart city and smart home applications leveraging AI and IoT integration;
  • 5G/6G-enabled AI-IoT systems for real-time communication and control.

Dr. Gaoya Dong
Dr. Haoqiang Liu
Dr. Meijun Qu
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.

Keywords

  • artificial intelligence
  • Internet of Things (IoT)
  • sensor design and optimization
  • industrial IoT
  • smart cities
  • AI-driven data analytics
  • IoT security and privacy

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

17 pages, 998 KB  
Article
A GeoSOT-Based Position-Linked Identifier Framework for Individual Tree Management in Digital Twin Forests
by Guang Deng and Xuan Ouyang
Electronics 2026, 15(9), 1928; https://doi.org/10.3390/electronics15091928 - 2 May 2026
Viewed by 90
Abstract
High-resolution LiDAR and individual-tree modeling are generating increasing volumes of tree-level spatial data, including coordinates, tree height, and diameter at breast height (DBH). However, the lack of scalable and spatially explicit identifiers still limits the organization and integration of tree records in digital [...] Read more.
High-resolution LiDAR and individual-tree modeling are generating increasing volumes of tree-level spatial data, including coordinates, tree height, and diameter at breast height (DBH). However, the lack of scalable and spatially explicit identifiers still limits the organization and integration of tree records in digital twin forest systems. This paper presents a GeoSOT-based framework for assigning position-linked identifiers to standardized tree observation records. The proposed code is used as a spatial anchor for record organization, candidate retrieval, and lifecycle-oriented management, rather than as a direct label of biological tree identity. The framework is implemented through a Yukon-based workflow for spatial storage and GeoSOT-code attachment, with a Bigtable-style schema described for time-stamped record organization. In a Mengjiagang forest farm case study, 604 treetop observations were extracted from airborne-LiDAR-derived canopy height models. Perturbation tests, boundary stress testing, controlled candidate matching, and a prototype retrieval benchmark show that fine-level GeoSOT codes are sensitive to positional uncertainty, whereas coarser levels combined with target-cell and adjacent-cell retrieval provide more stable candidate filtering with compact candidate sets under controlled experimental conditions. These results suggest that GeoSOT-based coding can support tree-observation record organization and candidate matching in digital twin forest systems. Independent cross-source identity validation and deployed database-level benchmarking should be addressed using real multi-source datasets and operational database environments. Full article
(This article belongs to the Special Issue AI-Driven IoT: Beyond Connectivity, Toward Intelligence)
11 pages, 3993 KB  
Article
A Mechanically Reconfigurable Phased Array Antenna with Switchable Radiation and Ultra-Wideband RCS Reduction
by Yang Li, Shen Meng, Lan Lu, Meijun Qu, Weibin Sun and Jianxun Su
Electronics 2026, 15(2), 308; https://doi.org/10.3390/electronics15020308 - 10 Jan 2026
Viewed by 695
Abstract
A mechanically reconfigurable phased array antenna (MRPA) with switchable radiation and scattering characteristics is presented. By adjusting the height of each array element, a continuous aperture phase response is achieved, enabling mechanical beam steering without electronic phase shifters. In the radiation mode, a [...] Read more.
A mechanically reconfigurable phased array antenna (MRPA) with switchable radiation and scattering characteristics is presented. By adjusting the height of each array element, a continuous aperture phase response is achieved, enabling mechanical beam steering without electronic phase shifters. In the radiation mode, a height-induced phase gradient is used to steer the beam, while in the scattering mode, the same height–phase mapping mechanism produces multi-element phase cancellation for radar cross-section (RCS) reduction. An 8 × 8 prototype operating at 7.9 GHz is designed and validated. The array achieves beam steering up to ±45° with a peak realized gain of 21.5 dBi and an aperture efficiency of 87.6%. Moreover, more than 10 dB monostatic RCS reduction is obtained over a wide frequency range from 3 to 38 GHz. The proposed design provides a unified mechanical approach for radiation enhancement and scattering suppression in multifunctional phased arrays. Full article
(This article belongs to the Special Issue AI-Driven IoT: Beyond Connectivity, Toward Intelligence)
►▼ Show Figures

Figure 1

8 pages, 2424 KB  
Article
Dual-Band Dual-Mode Antenna Without Extra Feeding Network Based on Characteristic Mode Analysis for Vehicular Applications
by Qi Du, Chensi Wang, Hui Zhang, Jianxun Su and Zhentao Zhao
Electronics 2025, 14(24), 4927; https://doi.org/10.3390/electronics14244927 - 16 Dec 2025
Viewed by 416
Abstract
In this study, a dual-band dual-mode antenna without any complex feeding network is proposed. The proposed antenna is a type of cascaded cavity antenna, which introduces periodically arranged shorting vias. Using characteristic mode analysis (CMA), the modal behaviors of the proposed antenna without [...] Read more.
In this study, a dual-band dual-mode antenna without any complex feeding network is proposed. The proposed antenna is a type of cascaded cavity antenna, which introduces periodically arranged shorting vias. Using characteristic mode analysis (CMA), the modal behaviors of the proposed antenna without external sources, including modal significance, modal radiation patterns, and modal currents, are analyzed in detail. By setting two properly placed coaxial ports based on CMA, a dual-band antenna with different radiation patterns is realized by exciting different modes at low- and high-frequency bands, allowing the proposed antenna to have a pattern diversity characteristic. Meanwhile, when port 1 is excited, the radiation patterns at 3 and 5 GHz are symmetrical to the radiation patterns when port 2 is excited and vice versa. The prototype is fabricated and investigated experimentally. A good agreement between the simulated and measured results proves the effectiveness and practicality of the proposed antenna. Full article
(This article belongs to the Special Issue AI-Driven IoT: Beyond Connectivity, Toward Intelligence)
►▼ Show Figures

Figure 1

17 pages, 18084 KB  
Article
A Multipurpose and Efficient Evaluation Method of Phase Characteristics in a Quiet Zone for a Defocused Feed in a Compact Antenna Test Range
by Yongquan Jiang, Meijun Qu, Hongcheng Yin, Chongjiang Mo and Ziwei Liu
Electronics 2025, 14(22), 4389; https://doi.org/10.3390/electronics14224389 - 10 Nov 2025
Viewed by 570
Abstract
A compact antenna test range (CATR) is an important testing facility for assessing electromagnetic characteristics of various wireless devices, in which the degradation of phase performance in a quiet zone due to feed defocusing severely affects the assessment results, especially for a higher [...] Read more.
A compact antenna test range (CATR) is an important testing facility for assessing electromagnetic characteristics of various wireless devices, in which the degradation of phase performance in a quiet zone due to feed defocusing severely affects the assessment results, especially for a higher frequency and longer defocusing distance. Based on the theory of geometric optics (GO), this paper precisely derives analytical formulas of phase characteristics in a quiet zone for a defocused feed in a commonly used CATR, such as that underpinned by single paraboloid and dual parabolic cylinders. The proposed evaluation method is of high accuracy and efficiency for higher frequencies and can be used in various scenarios with excellent results. The discrepancy between the formula calculation results and software simulation results of the machining accuracy tolerance for feeds and their turntable remains below 1°, demonstrating much better performance than the state of the art. Meanwhile, the deviation of the formula calculation results from the preset position of the feed stays within 1 mm, effectively supporting the confirmation of the feed position for equivalent pitch tests. Full article
(This article belongs to the Special Issue AI-Driven IoT: Beyond Connectivity, Toward Intelligence)
►▼ Show Figures

Figure 1

44 pages, 8751 KB  
Article
DataSense: A Real-Time Sensor-Based Benchmark Dataset for Attack Analysis in IIoT with Multi-Objective Feature Selection
by Amir Firouzi, Sajjad Dadkhah, Sebin Abraham Maret and Ali A. Ghorbani
Electronics 2025, 14(20), 4095; https://doi.org/10.3390/electronics14204095 - 19 Oct 2025
Cited by 5 | Viewed by 6267
Abstract
The widespread integration of Internet-connected devices into industrial environments has enhanced connectivity and automation but has also increased the exposure of industrial cyber–physical systems to security threats. Detecting anomalies is essential for ensuring operational continuity and safeguarding critical assets, yet the dynamic, real-time [...] Read more.
The widespread integration of Internet-connected devices into industrial environments has enhanced connectivity and automation but has also increased the exposure of industrial cyber–physical systems to security threats. Detecting anomalies is essential for ensuring operational continuity and safeguarding critical assets, yet the dynamic, real-time nature of such data poses challenges for developing effective defenses. This paper introduces DataSense, a comprehensive dataset designed to advance security research in industrial networked environments. DataSense contains synchronized sensor and network stream data, capturing interactions among diverse industrial sensors, commonly used connected devices, and network equipment, enabling vulnerability studies across heterogeneous industrial setups. The dataset was generated through the controlled execution of 50 realistic attacks spanning seven major categories: reconnaissance, denial of service, distributed denial of service, web exploitation, man-in-the-middle, brute force, and malware. This process produced a balanced mix of benign and malicious traffic that reflects real-world conditions. To enhance its utility, we introduce an original feature selection approach that identifies features most relevant to improving detection rates while minimizing resource usage. Comprehensive experiments with a broad spectrum of machine learning and deep learning models validate the dataset’s applicability, making DataSense a valuable resource for developing robust systems for detecting anomalies and preventing intrusions in real time within industrial environments. Full article
(This article belongs to the Special Issue AI-Driven IoT: Beyond Connectivity, Toward Intelligence)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop