For deployment of active network technology, active network applications play an important role. They should show good performance to users even under the condition that a small number of routers are equipped with active network technology. From performance aspects, crossing point of performance of active network application and end-to-end approach is very important. An active network applicati...

In today's networks, the evolution of wide-area services is constrained by standardization and compatibility concerns. The result is that the introduction of a new service occurs much more slowly than the emergence of new applications and technologies that bene t from it. To ameliorate this problem, an active network exploits mobile code and programmable infrastructure to provide rapid and spec...

Deep neural networks (DNNs) have been widely applied to active learning. Despite of its effectiveness, the generalization ability discriminative classifier (the softmax classifier) is questionable when there a significant distribution bias between labeled set and unlabeled set. In this paper, we attempt replace in deep network with nearest neighbor classifier, considering progressive within unk...

This paper seeks to describe new and better ways to represent network health and thus attempts to explore concepts other than those based on network topology-based representations of network management. It examines the manner in which active network management can benefit from Algorithmic Information Theory. Due to the new paradigm and enhanced capabilities of active networks, this work proceed...