Content Delivery Network (CDN) can be applied to improve effectiveness and robustness of Internet in an economical manner. In this work we present an optimization problem of replica server location of a CDN. Most of previous papers on CDNs focus on connectionless techniques. In this paper we assume that CDN is located in MPLS network and traffic is modeled as connection-oriented flow. Another n...

A domain adaptation method for urban scene segmentation is proposed in this work. We develop a fully convolutional tri-branch network, where two branches assign pseudo labels to images in the unlabeled target domain while the third branch is trained with supervision based on images in the pseudo-labeled target domain. The re-labeling and re-training processes alternate. With this design, the tr...

Recently, advances in person re-identification (Re-ID) has benefitted from use of the popular multi-branch network. However, performing feature learning a single branch with uniform partitioning is likely to separate meaningful local regions, and correlation among different branches not well established. In this article, we propose novel harmonious network (HMBN) relieve these intra-branch inte...

We introduce a new functional element (synchronizer for marked pairs) meant to join results of parallel processing in two-branch fork-join queueing network. Approximations for distribution of sojourn time at the synchronizer are derived along with a validity domain. Calculations are performed assuming that: arrivals to the network form a Poisson process, each branch operates like an M/M/N queue...

Historically, Markovian predictors have been very successful in predicting branch outcomes. In this work we propose a hybrid scheme that employs two Prediction by Partial Matching (PPM) Markovian predictors, one that predicts based on local branch histories and one based on global branch histories. The two independent predictions are combined using a neural network. On the CBP-2 traces the prop...

This paper considers the task of thorax disease classification on chest X-ray images. Existing methods generally use the global image as input for network learning. Such a strategy is limited in two aspects. 1) A thorax disease usually happens in (small) localized areas which are disease specific. Training CNNs using global image may be affected by the (excessive) irrelevant noisy areas. 2) Due...

Phylogenetic networks are increasingly used in evolutionary biology to represent the history of species that have undergone reticulate events such as horizontal gene transfer, hybrid speciation and recombination. One of the most fundamental questions that arise in this context is whether the evolution of a gene with one copy in all species can be explained by a given network. In mathematical te...

Historically, Markovian predictors have been very successful in predicting branch outcomes. In this work we propose a hybrid scheme that employs two Prediction by Partial Matching (PPM) Markovian predictors, one that predicts based on local branch histories and one based on global branch histories. The two independent predictions are combined using a neural network. On the CBP-2 traces the prop...