In recent years,Digital Twin(DT)has emerged as a transformative paradigm for enabling the future of the Internet of Things.By mapping the real-time status of physical entities to their digital counterparts,DTs facilit...In recent years,Digital Twin(DT)has emerged as a transformative paradigm for enabling the future of the Internet of Things.By mapping the real-time status of physical entities to their digital counterparts,DTs facilitate the creation of high-fidelity,interactive environments suitable for advanced simulation and deeper insight.One of the key challenges lies in achieving a sufficient level of convergence between Physical Twins(PTs)and their corresponding DTs.To tackle this challenge,we introduce a mobile edge computing environment that enables the coordination between PTs and DTs in Digital Twin Networks(DTNs)by offloading data transmission and processing tasks to the edge.A Hierarchical Deep Reinforcement Learning(HDRL)framework is proposed to improve DT-PT synchronization and enhance coordination effectiveness in optimizing information freshness across multiple action policies within the Digital Twin Communication Infrastructure(DTCI).Our approach is validated through a DTCI simulator,where comprehensive evaluations of age of information performance are conducted.Experimental results show that our HDRL-based solution significantly enhances the information freshness under constrained DTCI resources and across diverse environmental conditions.展开更多
We propose to address the open set domain adaptation problem by aligning images at both the pixel space and the feature space.Our approach,called Open Set Translation and Adaptation Network(OSTAN),consists of two main...We propose to address the open set domain adaptation problem by aligning images at both the pixel space and the feature space.Our approach,called Open Set Translation and Adaptation Network(OSTAN),consists of two main components:translation and adaptation.The translation is a cycle-consistent generative adversarial network,which translates any source image to the“style”of a target domain to eliminate domain discrepancy in the pixel space.The adaptation is an instance-weighted adversarial network,which projects both(labeled)translated source images and(unlabeled)target images into a domain-invariant feature space to learn a prior probability for each target image.The learned probability is applied as a weight to the unknown classifier to facilitate the identification of the unknown class.The proposed OSTAN model significantly outperforms the state-of-the-art open set domain adaptation methods on multiple public datasets.Our experiments also demonstrate that both the image-to-image translation and the instance-weighting framework can further improve the decision boundaries for both known and unknown classes.展开更多
基金supported by the U.S.National Science Foundation(Nos.2416872,2244219,2315596,and 2146497).
文摘In recent years,Digital Twin(DT)has emerged as a transformative paradigm for enabling the future of the Internet of Things.By mapping the real-time status of physical entities to their digital counterparts,DTs facilitate the creation of high-fidelity,interactive environments suitable for advanced simulation and deeper insight.One of the key challenges lies in achieving a sufficient level of convergence between Physical Twins(PTs)and their corresponding DTs.To tackle this challenge,we introduce a mobile edge computing environment that enables the coordination between PTs and DTs in Digital Twin Networks(DTNs)by offloading data transmission and processing tasks to the edge.A Hierarchical Deep Reinforcement Learning(HDRL)framework is proposed to improve DT-PT synchronization and enhance coordination effectiveness in optimizing information freshness across multiple action policies within the Digital Twin Communication Infrastructure(DTCI).Our approach is validated through a DTCI simulator,where comprehensive evaluations of age of information performance are conducted.Experimental results show that our HDRL-based solution significantly enhances the information freshness under constrained DTCI resources and across diverse environmental conditions.
基金supported by the National Natural Science Foundation of China under Grant Nos.62032011 and 61772257.
文摘We propose to address the open set domain adaptation problem by aligning images at both the pixel space and the feature space.Our approach,called Open Set Translation and Adaptation Network(OSTAN),consists of two main components:translation and adaptation.The translation is a cycle-consistent generative adversarial network,which translates any source image to the“style”of a target domain to eliminate domain discrepancy in the pixel space.The adaptation is an instance-weighted adversarial network,which projects both(labeled)translated source images and(unlabeled)target images into a domain-invariant feature space to learn a prior probability for each target image.The learned probability is applied as a weight to the unknown classifier to facilitate the identification of the unknown class.The proposed OSTAN model significantly outperforms the state-of-the-art open set domain adaptation methods on multiple public datasets.Our experiments also demonstrate that both the image-to-image translation and the instance-weighting framework can further improve the decision boundaries for both known and unknown classes.
