Trustworthy Artificial Intelligence in Cyber-Physical Systems

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

Deadline for manuscript submissions: closed (15 November 2024) | Viewed by 2268

Special Issue Editors


E-Mail Website
Guest Editor
Graduate School of Data Science, Chonnam National University, Gwangju 61186, Republic of Korea
Interests: metaverse; digital twin; AIoT; AI trust
Special Issues, Collections and Topics in MDPI journals
Department of Intelligent Electronic and Computer Engineering, Chonnam National University, Room 802, Building 7, 77 Yongbong-ro, Buk-gu, Gwangju 61186, Republic of Korea
Interests: computer network; 5G network; metaverse; MEC; artificial intelligence
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) is very important for autonomous systems and applications interating physical and cyber worlds with information and communication technology in our daily life. This Special Issue focuses on the adoption of AI in cyber-physical systems. Recently, digital twin technologies that model objects, people, and spaces in the physical world as Internet-based virtual objects and predict and prepare for future problems through AI-based simulation are developing. In addition, people and sensors in the physical world can also be linked to the cyber world of the Metaverse to perform social and economic activities, such as games and commerce. Although AI provides tremendous benefits to humans, there are a lot of negative effects due to the lack of trust in the proper use of AI. Therefore, buidling trust between cyber-physical systems and humans is essential in terms of explainablity, robustness, and bias. To address these trust related issues, this Special Issue on “Trustworthy Artificial Intelligence in Cyber-Physical Systems” aims to cover key concepts, archiectural approaches, methodology and technical solutions, including policy, regulatory, and ethics issues for trustworthy AI in intelligent and advanced cyber-physical systems, taking into account emerging technologies, such as digital twin, metaverse, and web 3.0.

Prof. Dr. Tai-Won Um
Dr. Jinsul Kim
Prof. Dr. Gyu Myoung Lee
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 100 words) can be sent to the Editorial Office for announcement on this website.

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

  • trustworthy AI in cyber-physical systems
  • trustworthy AI in metaverse
  • trustworthy AI in web 3.0
  • autonomous digital twins
  • autonomous internet of things (IoT)
  • autonomous system of systems
  • artificial intelligence of things (AIoT)

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 (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 3417 KiB  
Article
TransSMPL: Efficient Human Pose Estimation with Pruned and Quantized Transformer Networks
by Yeonggwang Kim, Hyeongjun Yoo, Je-Ho Ryu, Seungjoo Lee, Jong Hun Lee and Jinsul Kim
Electronics 2024, 13(24), 4980; https://doi.org/10.3390/electronics13244980 - 18 Dec 2024
Cited by 1 | Viewed by 1094
Abstract
Existing Transformers for 3D human pose and shape estimation models often struggle with computational complexity, particularly when handling high-resolution feature maps. These challenges limit their ability to efficiently utilize fine-grained features, leading to suboptimal performance in accurate body reconstruction. In this work, we [...] Read more.
Existing Transformers for 3D human pose and shape estimation models often struggle with computational complexity, particularly when handling high-resolution feature maps. These challenges limit their ability to efficiently utilize fine-grained features, leading to suboptimal performance in accurate body reconstruction. In this work, we propose TransSMPL, a novel Transformer framework built upon the SMPL model, specifically designed to address the challenges of computational complexity and inefficient utilization of high-resolution feature maps in 3D human pose and shape estimation. By replacing HRNet with MobileNetV3 for lightweight feature extraction, applying pruning and quantization techniques, and incorporating an early exit mechanism, TransSMPL significantly reduces both computational cost and memory usage. TransSMPL introduces two key innovations: (1) a multi-scale attention mechanism, reduced from four scales to two, allowing for more efficient global and local feature integration, and (2) a confidence-based early exit strategy, which enables the model to halt further computations when high-confidence predictions are achieved, further enhancing efficiency. Extensive pruning and dynamic quantization are also applied to reduce the model size while maintaining competitive performance. Quantitative and qualitative experiments on the Human3.6M dataset demonstrate the efficacy of TransSMPL. Our model achieves an MPJPE (Mean Per Joint Position Error) of 48.5 mm, reducing the model size by over 16% compared to existing methods while maintaining a similar level of accuracy. Full article
(This article belongs to the Special Issue Trustworthy Artificial Intelligence in Cyber-Physical Systems)
Show Figures

Figure 1

Back to TopTop