Particularly as environmental issues and data privacy become more important, the fast growth of supply chain systems calls for ever more complex demand forecasting methods. Often, conventional techniques find it difficult to compromise these conflicting needs, which results in poor performance in either data security, environmental effect, or prediction accuracy. Artificial intelligence Internet of Things-enabled federated demand forecasting for green supply chains with a privacy-preserving carbon reference effect mechanism (AFED-Green/PCREM) is presented in this study. This new framework combining artificial intelligence and the Internet of Things (AIoT) features with federated learning provides sustainable supply chain demand forecasting. Using a distributed network of AIoT sensors, our method allows merchants to train demand prediction models cooperatively while preserving data privacy and, including environmental consciousness. The system uses a carbon reference effect mechanism that tracks how past emission levels affect consumer behavior and demand trends. Simulation findings show better performance than state-of-the-art baselines, with a 27% increase in prediction accuracy, a 42% drop in carbon emissions, and information leakage below 0.05%.

The rapid evolution of transportation cyber-physical systems (T-CPS) has led to unprecedented advancements in mobility and efficiency. However, ensuring the safety and reliability of these complex systems remains a critical challenge, particularly in verifying and refining their temporal behaviors. This paper presents a novel compositional approach for temporal behavior analysis and synthesis in safety-critical T-CPS, the safety-critical temporal analysis, and refinement for the T-CPS (STAR-TCPS) framework, which combines iterative compositional verification with L*-based learning techniques to analyze and refine timing behaviors efficiently. The method leverages the clock constraint specification language for high-level timing specifications and introduces a systematic refinement process to transform abstract requirements into implementable task models. The framework incorporates innovative constraint handling mechanisms tailored for T-CPS, addressing unique challenges such as vehicle-to-infrastructure communication delays and adaptive traffic management timing. Experimental evaluations, including a case study on an intelligent vehicle system, demonstrate STAR-TCPS’s superiority over existing methods. Results show significant improvements in verification time (up to 63% reduction), memory usage (44% decrease), and task generation efficiency (18-25% fewer tasks) compared to state-of-the-art approaches. The STAR-TCPS framework enhances T-CPS’s safety and reliability by enabling more efficient verification and refinement of critical timing properties, paving the way for safer and more robust transportation systems.

Conventional security architectures and models are considered single-network architecture solutions, which assume that devices authenticated within the network are implicitly trusted. However, such an approach is unsuitable for next-generation networks (NGNs). Zero-trust security was introduced to overcome these challenges using context-aware, dynamic, and intelligent authentication schemes. This paper proposes a novel zero-trust blockchain-enabled framework for secure next-generation healthcare communication network (HCN). The proposed framework integrates zero-trust and blockchain to provide a decentralized, secure, and intelligent solution for healthcare communication in NGNs. The system model comprises three components: HCN user identity modeling, blockchain and risk assessment-based access control, and dynamic trust gateway. The user identity modeling component utilizes attribute-based user behavior trajectory features, while the access control component leverages smart contracts-based risk assessment. The dynamic trust gateway component employs a consensus mechanism to achieve dynamic gateway switching and enhance network resilience. Simulation results demonstrate that the proposed framework achieves 31% lower calculation delays, 3% higher trust values, and 3% better attack detection accuracy compared to best baseline methods. It also exhibits a 2% improvement in access control granularity and maintains 95% network throughput under various failure scenarios.