Manufaqtury запустила цифровой двойник бизнес-центра в платформе «Призма»
В платформе для управления коммерческой недвижимостью «Призма» (Prysm) появился цифровой двойник здания. Он связывает...
The study addresses the challenge of training a global model in DT-VANET under data heterogeneity and sparsity. The proposed HFTL method clusters vehicles by type and applies transfer learning within clusters, improving prediction accuracy for different vehicle types.
This approach improves federated learning efficiency in distributed systems with heterogeneous agents, which is important for traffic management in smart cities.
Translation and summary are machine-generated from the source. The full article is not republished; its rights belong to the source.