| 1. |
- Yang, Wei, et al.
(författare)
-
Adaptive optimization federated learning enabled digital twins in industrial IoT
- 2024
-
Ingår i: Journal of Industrial Information Integration. - : Elsevier BV. - 2467-964X .- 2452-414X. ; 41
-
Tidskriftsartikel (refereegranskat)abstract
- The Industrial Internet of Things (IIoT) plays a pivotal role in steering enterprises towards comprehensive digital transformation and fostering intelligent production, which serves as a critical pillar of Industry 4.0. Digital twin (DT) emerges as a highly promising technology, enabling the digital transformation of the IIoT by seamlessly bridging physical systems with digital spaces. However, the overall service quality of the IIoT is severely impacted by the resource-limited devices and the massive, heterogeneous and sensitive data in the IIoT. As an innovative distributed machine learning paradigm, federated learning (FL) inherently possesses advantages in handling private and heterogeneous data. In this paper, we propose a novel framework integrating F L with D T-enabled e nabled I IoT, termed FDEI, which combines the merits of both to improve service quality while maintaining trustworthiness. To enhance the modeling efficiency, we develop FedOA, an a daptive o ptimization F L method that dynamically adjusts the local update coefficient and model compression rate in resource-limited IIoT scenarios, to construct the FDEI model. Specifically, leveraging the interdependence between the two variables, we conduct a theoretical analysis of the model convergence rate and derive the associated convergence bounds. Building upon the theoretical analysis, we further propose a joint adaptive adjustment strategy by optimizing the two variables across various clients to minimize runtime differences and accelerate the convergence rate. Numerical results demonstrate that our proposed approach achieves an approximate 68% improvement in convergence speed and a reduction of approximately 66% in traffic consumption compared to the benchmarks (e.g., FedAvg, AFL, and CSFL).
|
|
| 2. |
- Ding, Yuemin, et al.
(författare)
-
Guest Editorial of the Special section on Emerging Technologies and Applications of Consumer Electronics for Healthy and Sustainable Life
- 2024
-
Ingår i: IEEE transactions on consumer electronics. - : Institute of Electrical and Electronics Engineers Inc.. - 0098-3063 .- 1558-4127. ; 70:1, s. 2378-2381
-
Tidskriftsartikel (refereegranskat)abstract
- Ensuring a healthy and sustainable life and promoting the wellness of human beings at all ages are essential to sustainable development. For this purpose, consumer electronics play important roles, such as body-centric healthcare, health-related ambient monitoring, sustainable health management, etc. Undoubtedly, in modern health and sustainable applications, Consumer Electronics (CE) is at the forefront of bridging physical and digital worlds, offering innovative solutions to improve health outcomes and enhance sustainable practices.
|
|
| 3. |
- Hu, Dongxiao, et al.
(författare)
-
Embodied AI Through Cloud-Fog Computing: A Framework for Everywhere Intelligence
- 2024
-
Ingår i: 2024 33rd International Symposium on Industrial Electronics, ISIE 2024 - Proceedings. - : Institute of Electrical and Electronics Engineers (IEEE).
-
Konferensbidrag (refereegranskat)abstract
- Embodied AI represents a crucial step towards achieving Artificial General Intelligence (AGI). The next paradigm of Embodied AI involves physical embodiment, enhanced perception capabilities, and adaptive automation. This advances the field significantly, paving the way for broader expansion. Despite the significant progress, existing computing frameworks, like local computation or cloud computing, struggle to meet the substantial demands of Embodied AI. The Cloud-Fog Embodied framework, namely based on CFA (cloud-fog automation) offers a promising solution to address these challenges. Our goal is to drive integration across multiple domains, including AI, robotics and industrial production, to tackle multifaceted challenges and seize opportunities to achieve AGI in the future.
|
|
| 4. |
- Wang, Qi, et al.
(författare)
-
Improving Transferability and Immunity of Physical Layer Authentication by the Channel Time-Varying Pattern
- 2024
-
Ingår i: IEEE Wireless Communications Letters. - : Institute of Electrical and Electronics Engineers (IEEE). - 2162-2337 .- 2162-2345. ; 13:3, s. 751-755
-
Tidskriftsartikel (refereegranskat)abstract
- Channel State Information (CSI)-based Physical Layer Authentication (PLA) is typically a promising strategy for wireless security. However, existing algorithms fail to transfer across various scenarios and immunize against attacks forging CSI. To improve the transferability and immunity of PLA, we propose a PLA enhancement framework to analyze, enhance, and assess authentication. Firstly, we provide a theoretical analysis method to discover the factors affecting the transferability and immunity of PLA. Secondly, inspired by the above discovery, an enhanced PLA algorithm is developed based on the channel time-varying pattern. Finally, we theoretically assess the scenario transferability and provide a closed-form expression for the bypassing condition of authentication. Furthermore, experimental results validate the practical applicability of our theoretical insights.
|
|
| 5. |
- Yang, Geng, et al.
(författare)
-
A digital twin-based large-area robot skin system for safer human-centered healthcare robots toward healthcare 4.0
- 2024
-
Ingår i: IEEE Transactions on Medical Robotics and Bionics. - : Institute of Electrical and Electronics Engineers (IEEE). - 2576-3202. ; 6:3, s. 1104-1115
-
Tidskriftsartikel (refereegranskat)abstract
- The fourth revolution of healthcare technologies, i.e., Healthcare 4.0, is putting robotics into human-dominated environments. In such a context, one of the main challenges is to develop human-centered robotics technologies that enable safe and reliable human-robot interaction toward human-robot symbiosis. Herein, robot skin is developed to endow healthcare robots with on-body proximity perception so as to fulfill the promise of safe and reliable robotic systems alongside humans. The sensing performance of the robot skin is evaluated by extensive experiments, providing important guidance on its effective implementation into a specific robot platform. Results show that the developed robot skin has a detection range of 0-50 mm, a maximum sensitivity of 0.7 pF/mm, a minimum resolution of 0.05 mm, a repeatability error of 6.6%, a hysteresis error of 7.1%, and bending durability of 2000 cycles. The robot skin is further customized and scaled up to form a large-area sensing system on the exterior of robot arms to support functional safety, which is experimentally validated by approaching distance monitoring and reactive collision avoidance. During the validation, the sensing feedback of the robot skin and the motion of the host robot are visualized remotely in the robot digital twin in a real-time manner via a cloud server. The cloud-based monitoring interface bridges the gap between local healthcare robots and remote professionals, illustrating promising applications where professionals monitor the robot state and intervene in challenging situations to provide instant support for emergent safety issues in human-robot interaction.
|
|
