This study investigates logistics path planning cost control through an optimized Ant Colony Algorithm (ACA) driven by highway enterprise operational data. Real-time transportation information, including traffic flow, vehicle speed, and road condition data, is integrated into pheromone update mechanisms and heuristic factor adjustments to enhance the adaptability of the algorithm in dynamic logistics environments. A data-driven optimization framework is developed to support intelligent route selection under continuously changing traffic conditions. Case-study results demonstrate that the proposed method significantly improves route planning efficiency and logistics cost control performance. Compared with traditional experience-based planning methods and the standard ACA, the optimized approach reduces total logistics distribution costs by 26.45%, transportation costs by 31.2%, and average travel distance by 12.12%. The framework exhibits strong robustness, adaptability, and operational efficiency in large-scale logistics networks. The proposed methodology is particularly applicable to intelligent transportation systems supported by wireless communication infrastructures and antenna-enabled sensing networks, where reliable real-time data acquisition and low-latency information transmission are essential for dynamic route optimization and operational decision-making. This research provides an effective engineering solution for intelligent logistics management, transportation optimization, and data-driven supply chain operations.
J. Zhang, X. C. Li, S. Zhang et al.· Advanced Electromagnetics· 0 citations
To address the conflict between model generalization and personalized recommendation in distributed educational environments, this paper constructs a personalized learning path recommendation model based on federated learning. Such privacy-preserving collaborative learning frameworks are also valuable for intelligent information processing and distributed decision-making in modern electromagnetic communication and edge computing systems, where data sharing is often restricted. The proposed model employs a Graph Neural Network (GNN)-Transformer hybrid encoder that combines knowledge graphs with learning behavior sequences to accurately capture knowledge transfer relationships. A dynamic knowledge distillation aggregation strategy is introduced to generate soft labels from the global model for guiding local optimization, thereby preserving personalized characteristics while improving semantic consistency. Furthermore, an adaptive aggregation mechanism based on Kullback-Leibler (KL) divergence dynamically adjusts client weights to enhance robustness under heterogeneous data distributions. Experimental results demonstrate that the proposed method achieves excellent recommendation accuracy (average Hit@5 of 0.676 ± 0.009), sequence consistency (average NDCG@10 of 0.712 ± 0.008), and personalized responsiveness (average personalized score difference rate of 0. 38). The framework effectively balances global generalization and local adaptation while maintaining privacy protection, providing a feasible solution for secure and intelligent recommendation in distributed learning environments and offering technical insights for collaborative intelligence in privacy-sensitive electromagnetic information systems.