Showing papers by "Xidian University published in 2018"

Space-Air-Ground Integrated Network: A Survey

Abstract: Space-air-ground integrated network (SAGIN), as an integration of satellite systems, aerial networks, and terrestrial communications, has been becoming an emerging architecture and attracted intensive research interest during the past years. Besides bringing significant benefits for various practical services and applications, SAGIN is also facing many unprecedented challenges due to its specific characteristics, such as heterogeneity, self-organization, and time-variability. Compared to traditional ground or satellite networks, SAGIN is affected by the limited and unbalanced network resources in all three network segments, so that it is difficult to obtain the best performances for traffic delivery. Therefore, the system integration, protocol optimization, resource management, and allocation in SAGIN is of great significance. To the best of our knowledge, we are the first to present the state-of-the-art of the SAGIN since existing survey papers focused on either only one single network segment in space or air, or the integration of space-ground, neglecting the integration of all the three network segments. In light of this, we present in this paper a comprehensive review of recent research works concerning SAGIN from network design and resource allocation to performance analysis and optimization. After discussing several existing network architectures, we also point out some technology challenges and future directions.

Fast and Accurate Single Image Super-Resolution via Information Distillation Network

Abstract: Recently, deep convolutional neural networks (CNNs) have been demonstrated remarkable progress on single image super-resolution. However, as the depth and width of the networks increase, CNN-based super-resolution methods have been faced with the challenges of computational complexity and memory consumption in practice. In order to solve the above questions, we propose a deep but compact convolutional network to directly reconstruct the high resolution image from the original low resolution image. In general, the proposed model consists of three parts, which are feature extraction block, stacked information distillation blocks and reconstruction block respectively. By combining an enhancement unit with a compression unit into a distillation block, the local long and short-path features can be effectively extracted. Specifically, the proposed enhancement unit mixes together two different types of features and the compression unit distills more useful information for the sequential blocks. In addition, the proposed network has the advantage of fast execution due to the comparatively few numbers of filters per layer and the use of group convolution. Experimental results demonstrate that the proposed method is superior to the state-of-the-art methods, especially in terms of time performance. Code is available at https://github.com/Zheng222/IDN-Caffe.

Computation Offloading and Resource Allocation in Mixed Fog/Cloud Computing Systems With Min-Max Fairness Guarantee

Abstract: Cooperation between the fog and the cloud in mobile cloud computing environments could offer improved offloading services to smart mobile user equipment (UE) with computation intensive tasks. In this paper, we tackle the computation offloading problem in a mixed fog/cloud system by jointly optimizing the offloading decisions and the allocation of computation resource, transmit power, and radio bandwidth while guaranteeing user fairness and maximum tolerable delay. This optimization problem is formulated to minimize the maximal weighted cost of delay and energy consumption (EC) among all UEs, which is a mixed-integer non-linear programming problem. Due to the NP-hardness of the problem, we propose a low-complexity suboptimal algorithm to solve it, where the offloading decisions are obtained via semidefinite relaxation and randomization, and the resource allocation is obtained using fractional programming theory and Lagrangian dual decomposition. Simulation results are presented to verify the convergence performance of our proposed algorithms and their achieved fairness among UEs, and the performance gains in terms of delay, EC, and the number of beneficial UEs over existing algorithms.

GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction

Abstract: Numerous sensors have been deployed in different geospatial locations to continuously and cooperatively monitor the surrounding environment, such as the air quality. These sensors generate multiple geo-sensory time series, with spatial correlations between their readings. Forecasting geo-sensory time series is of great importance yet very challenging as it is affected by many complex factors, i.e., dynamic spatio-temporal correlations and external factors. In this paper, we predict the readings of a geo-sensor over several future hours by using a multi-level attention-based recurrent neural network that considers multiple sensors' readings, meteorological data, and spatial data. More specifically, our model consists of two major parts: 1) a multi-level attention mechanism to model the dynamic spatio-temporal dependencies. 2) a general fusion module to incorporate the external factors from different domains. Experiments on two types of real-world datasets, viz., air quality data and water quality data, demonstrate that our method outperforms nine baseline methods.

MedBlock: Efficient and Secure Medical Data Sharing Via Blockchain

Abstract: With the development of electronic information technology, electronic medical records (EMRs) have been a common way to store the patients' data in hospitals. They are stored in different hospitals' databases, even for the same patient. Therefore, it is difficult to construct a summarized EMR for one patient from multiple hospital databases due to the security and privacy concerns. Meanwhile, current EMRs systems lack a standard data management and sharing policy, making it difficult for pharmaceutical scientists to develop precise medicines based on data obtained under different policies. To solve the above problems, we proposed a blockchain-based information management system, MedBlock, to handle patients' information. In this scheme, the distributed ledger of MedBlock allows the efficient EMRs access and EMRs retrieval. The improved consensus mechanism achieves consensus of EMRs without large energy consumption and network congestion. In addition, MedBlock also exhibits high information security combining the customized access control protocols and symmetric cryptography. MedBlock can play an important role in the sensitive medical information sharing.

A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar Images

Abstract: We propose an unsupervised deep convolutional coupling network for change detection based on two heterogeneous images acquired by optical sensors and radars on different dates. Most existing change detection methods are based on homogeneous images. Due to the complementary properties of optical and radar sensors, there is an increasing interest in change detection based on heterogeneous images. The proposed network is symmetric with each side consisting of one convolutional layer and several coupling layers. The two input images connected with the two sides of the network, respectively, are transformed into a feature space where their feature representations become more consistent. In this feature space, the different map is calculated, which then leads to the ultimate detection map by applying a thresholding algorithm. The network parameters are learned by optimizing a coupling function. The learning process is unsupervised, which is different from most existing change detection methods based on heterogeneous images. Experimental results on both homogenous and heterogeneous images demonstrate the promising performance of the proposed network compared with several existing approaches.

A Janus MoSSe monolayer: a potential wide solar-spectrum water-splitting photocatalyst with a low carrier recombination rate

Abstract: For realizing efficient solar to hydrogen energy conversion based on photocatalytic technology, it is important to explore a photocatalyst with wide-range solar absorption and high electron–hole separation efficiency. With a built-in electric field, the recently synthesized Janus MoSSe is intrinsically beneficial for promoting the separation of photo-generated electrons and holes. Thus in this work, we examine the possibility of MoSSe as an efficient water-splitting photocatalyst and the effects of isotropic and uniaxial strains by the first-principles calculations. It is interesting to find that MoSSe exhibits pronounced visible-light absorption efficiency, proper valence and conduction band positions for initializing the redox reactions of H2O, and high carrier mobilities. Moreover, the band gap of MoSSe is decreased and the direct–indirect band gap transition occurs upon tensile strain, which can not only extend the light absorption range, but also reduce the recombination of photo-generated carriers. Furthermore, H2O molecules adsorb more strongly on the MoSSe monolayer surface than on the MoS2 surface, which is also beneficial for the surface water-splitting reactions. These insights provide eloquent evidence that the Janus MoSSe monolayer is potentially an efficient and wide solar-spectrum water-splitting photocatalyst.

Triplet-Based Deep Hashing Network for Cross-Modal Retrieval

Abstract: Given the benefits of its low storage requirements and high retrieval efficiency, hashing has recently received increasing attention. In particular, cross-modal hashing has been widely and successfully used in multimedia similarity search applications. However, almost all existing methods employing cross-modal hashing cannot obtain powerful hash codes due to their ignoring the relative similarity between heterogeneous data that contains richer semantic information, leading to unsatisfactory retrieval performance. In this paper, we propose a triplet-based deep hashing (TDH) network for cross-modal retrieval. First, we utilize the triplet labels, which describe the relative relationships among three instances as supervision in order to capture more general semantic correlations between cross-modal instances. We then establish a loss function from the inter-modal view and the intra-modal view to boost the discriminative abilities of the hash codes. Finally, graph regularization is introduced into our proposed TDH method to preserve the original semantic similarity between hash codes in Hamming space. Experimental results show that our proposed method outperforms several state-of-the-art approaches on two popular cross-modal data sets.

Collaborative Computation Offloading for Multiaccess Edge Computing Over Fiber–Wireless Networks

Abstract: By offloading the computation tasks of the mobile devices (MDs) to the edge server, mobile-edge computing (MEC) provides a new paradigm to meet the increasing computation demands from mobile applications. However, existing mobile-edge computation offloading (MECO) research only took the resource allocation between the MDs and the MEC servers into consideration, and ignored the huge computation resources in the centralized cloud computing center. Moreover, current MEC hosted networks mostly adopt the networking technology integrating cellular and backbone networks, which have the shortcomings of single access mode, high congestion, high latency, and high energy consumption. Toward this end, we introduce hybrid fiber–wireless (FiWi) networks to provide supports for the coexistence of centralized cloud and multiaccess edge computing, and present an architecture by adopting the FiWi access networks. The problem of cloud-MEC collaborative computation offloading is studied, and two schemes are proposed as our solutions, i.e., an approximation collaborative computation offloading scheme, and a game-theoretic collaborative computation offloading scheme. Numerical results corroborate that our solutions not only achieve better offloading performance than the available MECO schemes but also scale well with the increasing number of computation tasks.

UAV Trajectory Optimization for Data Offloading at the Edge of Multiple Cells

Abstract: In future mobile networks, it is difficult for static base stations (BSs) to support the rapidly increasing data services, especially for cell-edge users. Unmanned aerial vehicle (UAV) is a promising method that can assist BSs to offload the data traffic, due to its high mobility and flexibility. In this correspondence, we focus on the UAV trajectory at the edges of three adjacent cells to offload traffic for BSs. In the proposed scheme, the sum rate of UAV-served edge users is maximized subject to the rate requirements for all the users, by optimizing the UAV trajectory in each flying cycle. The optimization is a mixed-integer nonconvex problem, which is difficult to solve. Thus, it is transformed into two convex problems, and an iterative algorithm is proposed to solve it by optimizing the UAV trajectory and edge user scheduling alternately. Simulation results are presented to show the effectiveness of the proposed scheme.

Toxic Reactive Oxygen Species Enhanced Synergistic Combination Therapy by Self-Assembled Metal-Phenolic Network Nanoparticles.

Abstract: Engineering functional nanomaterials with high therapeutic efficacy and minimum side effects has increasingly become a promising strategy for cancer treatment. Herein, a reactive oxygen species (ROS) enhanced combination chemotherapy platform is designed via a biocompatible metal-polyphenol networks self-assembly process by encapsulating doxorubicin (DOX) and platinum prodrugs in nanoparticles. Both DOX and platinum drugs can activate nicotinamide adenine dinucleotide phosphate oxidases, generating superoxide radicals (O2•- ). The superoxide dismutase-like activity of polyphenols can catalyze H2 O2 generation from O2•- . Finally, the highly toxic HO• free radicals are generated by a Fenton reaction. The ROS HO• can synergize the chemotherapy by a cascade of bioreactions. Positron emission tomography imaging of 89 Zr-labeled as-prepared DOX@Pt prodrug Fe3+ nanoparticles (DPPF NPs) shows prolonged blood circulation and high tumor accumulation. Furthermore, the DPPF NPs can effectively inhibit tumor growth and reduce the side effects of anticancer drugs. This study establishes a novel ROS promoted synergistic nanomedicine platform for cancer therapy.

Consensus of Hybrid Multi-Agent Systems

Abstract: In this brief, we consider the consensus problem of hybrid multiagent systems. First, the hybrid multiagent system is proposed, which is composed of continuous-time and discrete-time dynamic agents. Then, three kinds of consensus protocols are presented for the hybrid multiagent system. The analysis tool developed in this brief is based on the matrix theory and graph theory. With different restrictions of the sampling period, some necessary and sufficient conditions are established for solving the consensus of the hybrid multiagent system. The consensus states are also obtained under different protocols. Finally, simulation examples are provided to demonstrate the effectiveness of our theoretical results.

Mobile-Edge Computation Offloading for Ultradense IoT Networks

Abstract: The emergence of massive Internet of Things (IoT) mobile devices (MDs) and the deployment of ultradense 5G cells have promoted the evolution of IoT toward ultradense IoT networks. In order to meet the diverse quality-of-service and quality of experience demands from the ever-increasing IoT applications, the ultradense IoT networks face unprecedented challenges. Among them, a fundamental one is how to address the conflict between the resource-hungry IoT mobile applications and the resource-constrained IoT MDs. By offloading the IoT MDs’ computation tasks to the edge servers deployed at the radio access infrastructures, including macro base station (MBS) and small cells, mobile-edge computation offloading (MECO) provides us a promising solution. However, note that available MECO research mostly focused on single-tier base station scenario and computation offloading between the MDs and the edge server connected to the MBS. Little works can be found on performing MECO in ultradense IoT networks, i.e., a multiuser ultradense edge server scenario. Toward this end, we provide this paper to study the MECO problem in ultradense IoT networks, and propose a two-tier game-theoretic greedy offloading scheme as our solution. Extensive numerical results corroborate the superior performance of conducting computation offloading among multiple edge servers in ultradense IoT networks.

Hyperspectral Image Classification With Markov Random Fields and a Convolutional Neural Network

Abstract: This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework. First, we formulate the HSI classification problem from a Bayesian perspective. Then, we adopt a convolutional neural network (CNN) to learn the posterior class distributions using a patch-wise training strategy to better use the spatial information. Next, spatial information is further considered by placing a spatial smoothness prior on the labels. Finally, we iteratively update the CNN parameters using stochastic gradient decent and update the class labels of all pixel vectors using $\alpha $ -expansion min-cut-based algorithm. Compared with the other state-of-the-art methods, the classification method achieves better performance on one synthetic data set and two benchmark HSI data sets in a number of experimental settings.

Flexible, Stretchable Sensors for Wearable Health Monitoring: Sensing Mechanisms, Materials, Fabrication Strategies and Features

Abstract: Wearable health monitoring systems have gained considerable interest in recent years owing to their tremendous promise for personal portable health watching and remote medical practices. The sensors with excellent flexibility and stretchability are crucial components that can provide health monitoring systems with the capability of continuously tracking physiological signals of human body without conspicuous uncomfortableness and invasiveness. The signals acquired by these sensors, such as body motion, heart rate, breath, skin temperature and metabolism parameter, are closely associated with personal health conditions. This review attempts to summarize the recent progress in flexible and stretchable sensors, concerning the detected health indicators, sensing mechanisms, functional materials, fabrication strategies, basic and desired features. The potential challenges and future perspectives of wearable health monitoring system are also briefly discussed.

Fast and Accurate Single Image Super-Resolution via Information Distillation Network.

Abstract: Recently, deep convolutional neural networks (CNNs) have been demonstrated remarkable progress on single image super-resolution. However, as the depth and width of the networks increase, CNN-based super-resolution methods have been faced with the challenges of computational complexity and memory consumption in practice. In order to solve the above questions, we propose a deep but compact convolutional network to directly reconstruct the high resolution image from the original low resolution image. In general, the proposed model consists of three parts, which are feature extraction block, stacked information distillation blocks and reconstruction block respectively. By combining an enhancement unit with a compression unit into a distillation block, the local long and short-path features can be effectively extracted. Specifically, the proposed enhancement unit mixes together two different types of features and the compression unit distills more useful information for the sequential blocks. In addition, the proposed network has the advantage of fast execution due to the comparatively few numbers of filters per layer and the use of group convolution. Experimental results demonstrate that the proposed method is superior to the state-of-the-art methods, especially in terms of time performance.

From IoT to 5G I-IoT: The Next Generation IoT-Based Intelligent Algorithms and 5G Technologies

Abstract: The Internet of Things is a novel paradigm with access to wireless communication systems and artificial intelligence technologies, which is considered to be applicable to a variety of promising fields and applications. Meanwhile, the development of the fifth-generation cellular network technologies creates the possibility to deploy enormous sensors in the framework of the IoT and to process massive data, challenging the technologies of communications and data mining. In this article, we propose a novel paradigm, 5G Intelligent Internet of Things (5G I-IoT), to process big data intelligently and optimize communication channels. First, we articulate the concept of the 5G I-IoT and introduce three major components of the 5G I-IoT. Then we expound the interaction among these components and introduce the key methods and techniques based on our proposed paradigm, including big data mining, deep learning, and reinforcement learning. In addition, an experimental result evaluates the performance of 5G I-IoT, and the effective utilization of channels and QoS have been greatly improved. Finally, several application fields and open issues are discussed.

Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval

Abstract: Thanks to the success of deep learning, cross-modal retrieval has made significant progress recently. However, there still remains a crucial bottleneck: how to bridge the modality gap to further enhance the retrieval accuracy. In this paper, we propose a self-supervised adversarial hashing (SSAH) approach, which lies among the early attempts to incorporate adversarial learning into cross-modal hashing in a self-supervised fashion. The primary contribution of this work is that two adversarial networks are leveraged to maximize the semantic correlation and consistency of the representations between different modalities. In addition, we harness a self-supervised semantic network to discover high-level semantic information in the form of multi-label annotations. Such information guides the feature learning process and preserves the modality relationships in both the common semantic space and the Hamming space. Extensive experiments carried out on three benchmark datasets validate that the proposed SSAH surpasses the state-of-the-art methods.

Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval

Abstract: Thanks to the success of deep learning, cross-modal retrieval has made significant progress recently. However, there still remains a crucial bottleneck: how to bridge the modality gap to further enhance the retrieval accuracy. In this paper, we propose a self-supervised adversarial hashing (\textbf{SSAH}) approach, which lies among the early attempts to incorporate adversarial learning into cross-modal hashing in a self-supervised fashion. The primary contribution of this work is that two adversarial networks are leveraged to maximize the semantic correlation and consistency of the representations between different modalities. In addition, we harness a self-supervised semantic network to discover high-level semantic information in the form of multi-label annotations. Such information guides the feature learning process and preserves the modality relationships in both the common semantic space and the Hamming space. Extensive experiments carried out on three benchmark datasets validate that the proposed SSAH surpasses the state-of-the-art methods.

Cognitive Non-Orthogonal Multiple Access with Cooperative Relaying: A New Wireless Frontier for 5G Spectrum Sharing

Abstract: Two emerging technologies toward 5G wireless networks, namely non-orthogonal multiple access (NOMA) and cognitive radio (CR), will provide more efficient utilization of wireless spectrum in the future. In this article, we investigate the integration of NOMA with CR into a holistic system, namely a cognitive NOMA network, for more intelligent spectrum sharing. Design principles of cognitive NOMA networks are perfectly aligned to functionality requirements of 5G wireless networks, such as high spectrum efficiency, massive connectivity, low latency, and better fairness. Three different cognitive NOMA architectures are presented, including underlay NOMA networks, overlay NOMA networks, and CR-inspired NOMA networks. To address inter-network and intra-network interference, which largely degrade the performance of cognitive NOMA networks, cooperative relaying strategies are proposed. For each cognitive NOMA architecture, our proposed cooperative relaying strategy shows its potential to significantly lower outage probabilities. We discuss open challenges and future research directions on implementation of cognitive NOMA networks.

Anonymous and Traceable Group Data Sharing in Cloud Computing

Abstract: Group data sharing in cloud environments has become a hot topic in recent decades. With the popularity of cloud computing, how to achieve secure and efficient data sharing in cloud environments is an urgent problem to be solved. In addition, how to achieve both anonymity and traceability is also a challenge in the cloud for data sharing. This paper focuses on enabling data sharing and storage for the same group in the cloud with high security and efficiency in an anonymous manner. By leveraging the key agreement and the group signature, a novel traceable group data sharing scheme is proposed to support anonymous multiple users in public clouds. On the one hand, group members can communicate anonymously with respect to the group signature, and the real identities of members can be traced if necessary. On the other hand, a common conference key is derived based on the key agreement to enable group members to share and store their data securely. Note that a symmetric balanced incomplete block design is utilized for key generation, which substantially reduces the burden on members to derive a common conference key. Both theoretical and experimental analyses demonstrate that the proposed scheme is secure and efficient for group data sharing in cloud computing.

A deep learning framework for remote sensing image registration

Abstract: We propose an effective deep neural network aiming at remote sensing image registration problem. Unlike conventional methods doing feature extraction and feature matching separately, we pair patches from sensed and reference images, and then learn the mapping directly between these patch-pairs and their matching labels for later registration. This end-to-end architecture allows us to optimize the whole processing (learning mapping function) through information feedback when training the network, which is lacking in conventional methods. In addition, to alleviate the small data issue of remote sensing images for training, our proposal introduces a self-learning by learning the mapping function using images and their transformed copies. Moreover, we apply a transfer learning to reduce the huge computation cost in the training stage. It does not only speed up our framework, but also get extra performance gains. The comprehensive experiments conducted on seven sets of remote sensing images, acquired by Radarsat, SPOT and Landsat, show that our proposal improves the registration accuracy up to 2.4–53.7%.

On-Demand Deep Model Compression for Mobile Devices: A Usage-Driven Model Selection Framework

Abstract: Recent research has demonstrated the potential of deploying deep neural networks (DNNs) on resource-constrained mobile platforms by trimming down the network complexity using different compression techniques. The current practice only investigate stand-alone compression schemes even though each compression technique may be well suited only for certain types of DNN layers. Also, these compression techniques are optimized merely for the inference accuracy of DNNs, without explicitly considering other application-driven system performance (e.g. latency and energy cost) and the varying resource availabilities across platforms (e.g. storage and processing capability). In this paper, we explore the desirable tradeoff between performance and resource constraints by user-specified needs, from a holistic system-level viewpoint. Specifically, we develop a usage-driven selection framework, referred to as AdaDeep, to automatically select a combination of compression techniques for a given DNN, that will lead to an optimal balance between user-specified performance goals and resource constraints. With an extensive evaluation on five public datasets and across twelve mobile devices, experimental results show that AdaDeep enables up to 9.8x latency reduction, 4.3x energy efficiency improvement, and 38x storage reduction in DNNs while incurring negligible accuracy loss. AdaDeep also uncovers multiple effective combinations of compression techniques unexplored in existing literature.