Xidian University

About: Xidian University is a education organization based out in Xi'an, China. It is known for research contribution in the topics: Antenna (radio) & Synthetic aperture radar. The organization has 32099 authors who have published 38961 publications receiving 431820 citations. The organization is also known as: University of Electronic Science and Technology at Xi'an & Xīān Diànzǐ Kējì Dàxué.

Toward a Flexible and Reconfigurable Broadband Satellite Network: Resource Management Architecture and Strategies

Abstract: Traditional satellite networks are generally locked down to a specific space mission, with isolated substrate infrastructure as well as network resources. This forbids dynamic resource sharing among different networks, and thus leads to resource under utilization, poor service provisioning and unacceptable expenditure. In this regard, it is crucial to embrace emerging technologies such as software-defined networking and network virtualization to construct a FRBSN. Both the resource management architecture and enabling strategies are explicitly investigated to realize FRBSN. Specifically, we propose a novel TERG to precisely describe the evolution of multi-dimensional resources in BSN, and reveal the continuity and correlation relationships among various resources. Based on TERG, we further propose an optimal resource allocation strategy to facilitate efficient cooperation among various resources. The achievable performance limits are demonstrated by simulations under a realistic BSN setting.

DCSR: Dilated Convolutions for Single Image Super-Resolution

Abstract: Dilated convolutions support expanding receptive field without parameter exploration or resolution loss, which turn out to be suitable for pixel-level prediction problems. In this paper, we propose multiscale single image super-resolution (SR) based on dilated convolutions. We adopt dilated convolutions to expand the receptive field size without incurring additional computational complexity. We mix standard convolutions and dilated convolutions in each layer, called mixed convolutions, i.e., in the mixed convolutional layer, and the feature extracted by dilated convolutions and standard convolutions are concatenated. We theoretically analyze the receptive field and intensity of mixed convolutions to discover their role in SR. Mixed convolutions remove blind spots and capture the correlation between low-resolution (LR) and high-resolution (HR) image pairs successfully, thus achieving good generalization ability. We verify those properties of mixed convolutions by training 5-layer and 10-layer networks. We also train a 20-layer deep network to compare the performance of the proposed method with those of the state-of-the-art ones. Moreover, we jointly learn maps with different scales from a LR image to its HR one in a single network. Experimental results demonstrate that the proposed method outperforms the state-of-the-art ones in terms of PSNR and SSIM, especially for a large-scale factor.

Semi-supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model

Abstract: Automated brain lesion segmentation provides valuable information for the analysis and intervention of patients. In particular, methods that are based on convolutional neural networks (CNNs) have achieved state-of-the-art segmentation performance. However, CNNs usually require a decent amount of annotated data, which may be costly and time-consuming to obtain. Since unannotated data is generally abundant, it is desirable to use unannotated data to improve the segmentation performance for CNNs when limited annotated data is available. In this work, we propose a semi-supervised learning (SSL) approach to brain lesion segmentation, where unannotated data is incorporated into the training of CNNs. We adapt the mean teacher model, which is originally developed for SSL-based image classification, for brain lesion segmentation. Assuming that the network should produce consistent outputs for similar inputs, a loss of segmentation consistency is designed and integrated into a self-ensembling framework. Self-ensembling exploits the information in the intermediate training steps, and the ensemble prediction based on the information can be closer to the correct result than the single latest model. To exploit such information, we build a student model and a teacher model, which share the same CNN architecture for segmentation. The student and teacher models are updated alternately. At each step, the student model learns from the teacher model by minimizing the weighted sum of the segmentation loss computed from annotated data and the segmentation consistency loss between the teacher and student models computed from unannotated data. Then, the teacher model is updated by combining the updated student model with the historical information of teacher models using an exponential moving average strategy. For demonstration, the proposed approach was evaluated on ischemic stroke lesion segmentation. Results indicate that the proposed method improves stroke lesion segmentation with the incorporation of unannotated data and outperforms competing SSL-based methods.

Outsourcing encryption of attribute-based encryption with mapreduce

Abstract: Attribute-based encryption (ABE) is a promising cryptographic tool for fine-grained access control. However, the computational cost in encryption commonly grows with the complexity of access policy in existing ABE schemes, which becomes a bottleneck limiting its application. In this paper, we formulize the novel paradigm of outsourcing encryption of ABE to cloud service provider to relieve local computation burden. We propose an optimized construction with MapReduce cloud which is secure under the assumption that the master node as well as at least one of the slave nodes is honest. After outsourcing, the computational cost at user side during encryption is reduced to approximate four exponentiations, which is constant. Another advantage of the proposed construction is that the user is able to delegate encryption for any policy.

A novel artificial bee colony algorithm with Powell's method

Abstract: Artificial bee colony (ABC) algorithm is a relatively new optimization technique which has been shown to be competitive to other population-based algorithms. However, there is still an insufficiency in ABC regarding its solution search equation, which is good at exploration but poor at exploitation. To address this concerning issue, we first propose a modified search equation which is applied to generate a candidate solution in the onlookers phase to improve the search ability of ABC. Further, we use the Powell's method as a local search tool to enhance the exploitation of the algorithm. The new algorithm is tested on 22 unconstrained benchmark functions and 13 constrained benchmark functions, and are compared with some other ABCs and several state-of-the-art algorithms. The comparisons show that the proposed algorithm offers the highest solution quality, fastest global convergence, and strongest robustness among all the contenders on almost all test functions.