Semantic communication improves task effectiveness by transmitting task-relevant information. However, most existing schemes remain organized as task-specific, end-to-end pipelines, which are difficult to reuse across models, applications, and deployment environments. Against this background, we propose the Semantic Internet of Everything (SIoE), a composable service architecture that represents heterogeneous communication and artificial intelligence (AI) functions as capability-profiled services and coordinates them according to application objectives. SIoE comprises three planes: a task and service plane, an agentic orchestration plane, and a semantic capability plane. In this framework, task requirements are captured via a semantic service-level agreement (SLA), while an agentic planner discovers and composes candidate capabilities under deterministic compatibility, resource, privacy, and policy validation. Feedback from the communication, semantic, and task levels enables continuous adaptation and replanning. A lightweight vehicle-to-everything case study illustrates profile-grounded capability planning under explicit service constraints. The results demonstrate the feasibility of decoupling service objectives from fixed communication implementations and also highlight key open challenges, including semantic SLA design, capability interoperability, scalable planning, and trustworthy execution.
Da-Yu Fan, Rui Meng, Yun-Fei Liu et al.· IEEE Internet of Things Maga...· 0 citations
End-edge collaborative inference has emerged as an important trend for deploying deep learning applications on resource-constrained end devices. However, the continuous data interaction between end devices and edge server inevitably raises privacy concerns. Fully homomorphic encryption (FHE) provides a privacy-preserving solution by enabling inference directly on encrypted data, but deploying full FHE inference on the edge suffers from high latency. To address these issues, we propose FHE-EESI, an FHE-based end-edge collaborative split inference framework. In FHE-EESI, the end device executes the initial layers on plaintext, encrypts intermediate features using the residue number system Cheon-Kim-Kim-Song (RNS-CKKS) scheme, and transmits them to the edge server for the remaining FHE inference. To construct an FHE-compatible inference network and enable flexible partitionability, we adopt a stage-wise key management strategy and the Chebyshev polynomial approximation. Furthermore, considering dynamic channel conditions and heterogeneous computational capabilities, we design a dueling double deep Q-network (D3QN)-based dynamic split mechanism to adaptively determine the optimal split point. Experimental results on the CIFAR-10 dataset show that FHE-EESI achieves 83.3% inference accuracy and 183.1 s total latency, effectively providing privacy-preserving inference while maintaining inference efficiency.
Haiyue Zhang, Yiming Liu, Jing Jin et al.· IEEE Transactions on Cogniti...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
