Showing papers by "Xidian University published in 2019"

A Survey of Deep Learning-Based Object Detection

Abstract: Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in people's life, such as monitoring security, autonomous driving and so on, with the purpose of locating instances of semantic objects of a certain class. With the rapid development of deep learning algorithms for detection tasks, the performance of object detectors has been greatly improved. In order to understand the main development status of object detection pipeline thoroughly and deeply, in this survey, we analyze the methods of existing typical detection models and describe the benchmark datasets at first. Afterwards and primarily, we provide a comprehensive overview of a variety of object detection methods in a systematic manner, covering the one-stage and two-stage detectors. Moreover, we list the traditional and new applications. Some representative branches of object detection are analyzed as well. Finally, we discuss the architecture of exploiting these object detection methods to build an effective and efficient system and point out a set of development trends to better follow the state-of-the-art algorithms and further research.

Space/Aerial-Assisted Computing Offloading for IoT Applications: A Learning-Based Approach

Abstract: Internet of Things (IoT) computing offloading is a challenging issue, especially in remote areas where common edge/cloud infrastructure is unavailable. In this paper, we present a space-air-ground integrated network (SAGIN) edge/cloud computing architecture for offloading the computation-intensive applications considering remote energy and computation constraints, where flying unmanned aerial vehicles (UAVs) provide near-user edge computing and satellites provide access to the cloud computing. First, for UAV edge servers, we propose a joint resource allocation and task scheduling approach to efficiently allocate the computing resources to virtual machines (VMs) and schedule the offloaded tasks. Second, we investigate the computing offloading problem in SAGIN and propose a learning-based approach to learn the optimal offloading policy from the dynamic SAGIN environments. Specifically, we formulate the offloading decision making as a Markov decision process where the system state considers the network dynamics. To cope with the system dynamics and complexity, we propose a deep reinforcement learning-based computing offloading approach to learn the optimal offloading policy on-the-fly, where we adopt the policy gradient method to handle the large action space and actor-critic method to accelerate the learning process. Simulation results show that the proposed edge VM allocation and task scheduling approach can achieve near-optimal performance with very low complexity and the proposed learning-based computing offloading algorithm not only converges fast but also achieves a lower total cost compared with other offloading approaches.

Smart Contract-Based Access Control for the Internet of Things

Abstract: This paper investigates a critical access control issue in the Internet of Things (IoT). In particular, we propose a smart contract-based framework, which consists of multiple access control contracts (ACCs), one judge contract (JC), and one register contract (RC), to achieve distributed and trustworthy access control for IoT systems. Each ACC provides one access control method for a subject-object pair, and implements both static access right validation based on predefined policies and dynamic access right validation by checking the behavior of the subject. The JC implements a misbehavior-judging method to facilitate the dynamic validation of the ACCs by receiving misbehavior reports from the ACCs, judging the misbehavior and returning the corresponding penalty. The RC registers the information of the access control and misbehavior-judging methods as well as their smart contracts, and also provides functions (e.g., register, update, and delete) to manage these methods. To demonstrate the application of the framework, we provide a case study in an IoT system with one desktop computer, one laptop and two Raspberry Pi single-board computers, where the ACCs, JC, and RC are implemented based on the Ethereum smart contract platform to achieve the access control.

The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges.

Abstract: Medical imaging can assess the tumor and its environment in their entirety, which makes it suitable for monitoring the temporal and spatial characteristics of the tumor. Progress in computational methods, especially in artificial intelligence for medical image process and analysis, has converted these images into quantitative and minable data associated with clinical events in oncology management. This concept was first described as radiomics in 2012. Since then, computer scientists, radiologists, and oncologists have gravitated towards this new tool and exploited advanced methodologies to mine the information behind medical images. On the basis of a great quantity of radiographic images and novel computational technologies, researchers developed and validated radiomic models that may improve the accuracy of diagnoses and therapy response assessments. Here, we review the recent methodological developments in radiomics, including data acquisition, tumor segmentation, feature extraction, and modelling, as well as the rapidly developing deep learning technology. Moreover, we outline the main applications of radiomics in diagnosis, treatment planning and evaluations in the field of oncology with the aim of developing quantitative and personalized medicine. Finally, we discuss the challenges in the field of radiomics and the scope and clinical applicability of these methods.

UAV-Assisted Emergency Networks in Disasters

Abstract: Reliable and flexible emergency communication is a key challenge for search and rescue in the event of disasters, especially for the case when base stations are no longer functioning. Unmanned aerial vehicle (UAV)-assisted networking is emerging as a promising method to establish emergency networks. In this article, a unified framework for a UAV-assisted emergency network is established in disasters. First, the trajectory and scheduling of UAVs are jointly optimized to provide wireless service to ground devices with surviving BSs. Then the transceiver design of UAV and establishment of multihop ground device-to-device communication are studied to extend the wireless coverage of UAV. In addition, multihop UAV relaying is added to realize information exchange between the disaster areas and outside through optimizing the hovering positions of UAVs. Simulation results are presented to show the effectiveness of these three schemes. Finally, open research issues and challenges are discussed.

The Seventh Visual Object Tracking VOT2019 Challenge Results

Abstract: The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis as well as the standard VOT methodology for long-term tracking analysis. The VOT2019 challenge was composed of five challenges focusing on different tracking domains: (i) VOTST2019 challenge focused on short-term tracking in RGB, (ii) VOT-RT2019 challenge focused on "real-time" shortterm tracking in RGB, (iii) VOT-LT2019 focused on longterm tracking namely coping with target disappearance and reappearance. Two new challenges have been introduced: (iv) VOT-RGBT2019 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2019 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2019, VOT-RT2019 and VOT-LT2019 datasets were refreshed while new datasets were introduced for VOT-RGBT2019 and VOT-RGBD2019. The VOT toolkit has been updated to support both standard shortterm, long-term tracking and tracking with multi-channel imagery. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website.

Lightweight Image Super-Resolution with Information Multi-distillation Network

Abstract: In recent years, single image super-resolution (SISR) methods using deep convolution neural network (CNN) have achieved impressive results. Thanks to the powerful representation capabilities of the deep networks, numerous previous ways can learn the complex non-linear mapping between low-resolution (LR) image patches and their high-resolution (HR) versions. However, excessive convolutions will limit the application of super-resolution technology in low computing power devices. Besides, super-resolution of any arbitrary scale factor is a critical issue in practical applications, which has not been well solved in the previous approaches. To address these issues, we propose a lightweight information multi-distillation network (IMDN) by constructing the cascaded information multi-distillation blocks (IMDB), which contains distillation and selective fusion parts. Specifically, the distillation module extracts hierarchical features step-by-step, and fusion module aggregates them according to the importance of candidate features, which is evaluated by the proposed contrast-aware channel attention mechanism. To process real images with any sizes, we develop an adaptive cropping strategy (ACS) to super-resolve block-wise image patches using the same well-trained model. Extensive experiments suggest that the proposed method performs favorably against the state-of-the-art SR algorithms in term of visual quality, memory footprint, and inference time. Code is available at \urlhttps://github.com/Zheng222/IMDN.

HyperDense-Net: A Hyper-Densely Connected CNN for Multi-Modal Image Segmentation

Abstract: Recently, dense connections have attracted substantial attention in computer vision because they facilitate gradient flow and implicit deep supervision during training. Particularly, DenseNet that connects each layer to every other layer in a feed-forward fashion and has shown impressive performances in natural image classification tasks. We propose HyperDenseNet , a 3-D fully convolutional neural network that extends the definition of dense connectivity to multi-modal segmentation problems. Each imaging modality has a path, and dense connections occur not only between the pairs of layers within the same path but also between those across different paths. This contrasts with the existing multi-modal CNN approaches, in which modeling several modalities relies entirely on a single joint layer (or level of abstraction) for fusion, typically either at the input or at the output of the network. Therefore, the proposed network has total freedom to learn more complex combinations between the modalities, within and in-between all the levels of abstraction , which increases significantly the learning representation. We report extensive evaluations over two different and highly competitive multi-modal brain tissue segmentation challenges, iSEG 2017 and MRBrainS 2013, with the former focusing on six month infant data and the latter on adult images. HyperDenseNet yielded significant improvements over many state-of-the-art segmentation networks, ranking at the top on both benchmarks. We further provide a comprehensive experimental analysis of features re-use, which confirms the importance of hyper-dense connections in multi-modal representation learning. Our code is publicly available.

Denoising Prior Driven Deep Neural Network for Image Restoration

Abstract: Deep neural networks (DNNs) have shown very promising results for various image restoration (IR) tasks. However, the design of network architectures remains a major challenging for achieving further improvements. While most existing DNN-based methods solve the IR problems by directly mapping low quality images to desirable high-quality images, the observation models characterizing the image degradation processes have been largely ignored. In this paper, we first propose a denoising-based IR algorithm, whose iterative steps can be computed efficiently. Then, the iterative process is unfolded into a deep neural network, which is composed of multiple denoisers modules interleaved with back-projection (BP) modules that ensure the observation consistencies. A convolutional neural network (CNN) based denoiser that can exploit the multi-scale redundancies of natural images is proposed. As such, the proposed network not only exploits the powerful denoising ability of DNNs, but also leverages the prior of the observation model. Through end-to-end training, both the denoisers and the BP modules can be jointly optimized. Experimental results on several IR tasks, e.g., image denoisig, super-resolution and deblurring show that the proposed method can lead to very competitive and often state-of-the-art results on several IR tasks, including image denoising, deblurring, and super-resolution.

Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning

Abstract: Predicting urban traffic is of great importance to intelligent transportation systems and public safety, yet is very challenging because of two aspects: 1) complex spatio-temporal correlations of urban traffic, including spatial correlations between locations along with temporal correlations among timestamps; 2) diversity of such spatio-temporal correlations, which vary from location to location and depend on the surrounding geographical information, e.g., points of interests and road networks. To tackle these challenges, we proposed a deep-meta-learning based model, entitled ST-MetaNet, to collectively predict traffic in all location at once. ST-MetaNet employs a sequence-to-sequence architecture, consisting of an encoder to learn historical information and a decoder to make predictions step by step. In specific, the encoder and decoder have the same network structure, consisting of a recurrent neural network to encode the traffic, a meta graph attention network to capture diverse spatial correlations, and a meta recurrent neural network to consider diverse temporal correlations. Extensive experiments were conducted based on two real-world datasets to illustrate the effectiveness of ST-MetaNet beyond several state-of-the-art methods.

Networking and Communications in Autonomous Driving: A Survey

Abstract: The development of light detection and ranging, Radar, camera, and other advanced sensor technologies inaugurated a new era in autonomous driving. However, due to the intrinsic limitations of these sensors, autonomous vehicles are prone to making erroneous decisions and causing serious disasters. At this point, networking and communication technologies can greatly make up for sensor deficiencies, and are more reliable, feasible and efficient to promote the information interaction, thereby improving autonomous vehicle’s perception and planning capabilities as well as realizing better vehicle control. This paper surveys the networking and communication technologies in autonomous driving from two aspects: intra- and inter-vehicle. The intra-vehicle network as the basis of realizing autonomous driving connects the on-board electronic parts. The inter-vehicle network is the medium for interaction between vehicles and outside information. In addition, we present the new trends of communication technologies in autonomous driving, as well as investigate the current mainstream verification methods and emphasize the challenges and open issues of networking and communications in autonomous driving.

ECG Arrhythmia Classification Using STFT-Based Spectrogram and Convolutional Neural Network

Abstract: The classification of electrocardiogram (ECG) signals is very important for the automatic diagnosis of heart disease. Traditionally, it is divided into two steps, including the step of feature extraction and the step of pattern classification. Owing to recent advances in artificial intelligence, it has been demonstrated that deep neural network, which trained on a huge amount of data, can carry out the task of feature extraction directly from the data and recognize cardiac arrhythmias better than professional cardiologists. This paper proposes an ECG arrhythmia classification method using two-dimensional (2D) deep convolutional neural network (CNN). The time domain signals of ECG, belonging to five heart beat types including normal beat (NOR), left bundle branch block beat (LBB), right bundle branch block beat (RBB), premature ventricular contraction beat (PVC), and atrial premature contraction beat (APC), were first transformed into time-frequency spectrograms by short-time Fourier transform. Subsequently, the spectrograms of the five arrhythmia types were utilized as input to the 2D-CNN such that the ECG arrhythmia types were identified and classified finally. Using ECG recordings from the MIT-BIH arrhythmia database as the training and testing data, the classification results show that the proposed 2D-CNN model can reach an averaged accuracy of 99.00%. On the other hand, in order to achieve optimal classification performances, the model parameter optimization was investigated. It was found when the learning rate is 0.001 and the batch size parameter is 2500, the classifier achieved the highest accuracy and the lowest loss. We also compared the proposed 2D-CNN model with a conventional one-dimensional CNN model. Comparison results show that the 1D-CNN classifier can achieve an averaged accuracy of 90.93%. Therefore, it is validated that the proposed CNN classifier using ECG spectrograms as input can achieve improved classification accuracy without additional manual pre-processing of the ECG signals.

Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training

Abstract: Most existing Re-IDentification (Re-ID) methods are highly dependent on precise bounding boxes that enable images to be aligned with each other. However, due to the challenging practical scenarios, current detection models often produce inaccurate bounding boxes, which inevitably degenerate the performance of existing Re-ID algorithms. In this paper, we propose a novel coarse-to-fine pyramid model to relax the need of bounding boxes, which not only incorporates local and global information, but also integrates the gradual cues between them. The pyramid model is able to match at different scales and then search for the correct image of the same identity, even when the image pairs are not aligned. In addition, in order to learn discriminative identity representation, we explore a dynamic training scheme to seamlessly unify two losses and extract appropriate shared information between them. Experimental results clearly demonstrate that the proposed method achieves the state-of-the-art results on three datasets. Especially, our approach exceeds the current best method by 9.5% on the most challenging CUHK03 dataset.

Achieving Both High Voltage and High Capacity in Aqueous Zinc‐Ion Battery for Record High Energy Density

Abstract: © 2019 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim 1906142 (1 of 10) (1.5–1.7),[11,12] they always deliver a low capacity (<120 mAh g−1 for Zn/PBA batteries; 150 mAh g−1 Zn/MxV3(PO4)2 (M = Li, Na) batteries; and <280 mAh g−1 for Zn/manganese-based oxides batteries). The widely used vanadium-based oxides possess multiple oxidations and could deliver a high capacity >300 mAh g−1 as a cathode for the aqueous zinc-ion battery.[13–15] The V2O5·nH2O with a platelike structure, Zn0.25V2O5·nH2O nanobelts, Ca0.24V2O5·0.83H2O nanobelts, Ag0.4V2O5 nanoblelts,[19] LixV2O5·nH2O blocks,[20] H2V3O8 nanobelts,[21] NaV3O8·1.5H2O nanobelts,[22] and lamellar zinc orthovanadate[23] were intensively studied, which deliver a feasible capacity (>300 mAh g−1). However, their cycling stability is not satisfactory; typically, the Zn/vanadium-based oxide batteries can only run 1000–2000 cycles. What is even more frustrating, is that they all operate at low voltages. Typically, their capacity at above 1.0 V is less than 70 mAh g−1; thus, usually over 80% of the capacity is delivered below 1.0 V, leading to a low energy density (<250 Wh kg−1) in sharp contrast to their large capacity. A high-voltage Zn/vanadium-based oxide battery that maintains a large capacity is highly anticipated, as it may potentially renew the energy density performance of Zn-ion batteries. Herein, for the first time, we report a Zn/ Co0.247V2O5 ⋅ 0.944H2O battery with most of its capacity delivered at a voltage above 1.0 V. Structural characterization and first-principles calculations show that the interlayer cobalt ions Achieving Both High Voltage and High Capacity in Aqueous Zinc-Ion Battery for Record High Energy Density

A Novel Attribute-Based Access Control Scheme Using Blockchain for IoT

Abstract: With the sharp increase in the number of intelligent devices, the Internet of Things (IoT) has gained more and more attention and rapid development in recent years. It effectively integrates the physical world with the Internet over existing network infrastructure to facilitate sharing data among intelligent devices. However, its complex and large-scale network structure brings new security risks and challenges to IoT systems. To ensure the security of data, traditional access control technologies are not suitable to be directly used for implementing access control in IoT systems because of their complicated access management and the lack of credibility due to centralization. In this paper, we proposed a novel attribute-based access control scheme for IoT systems, which simplifies greatly the access management. We use blockchain technology to record the distribution of attributes in order to avoid single point failure and data tampering. The access control process has also been optimized to meet the need for high efficiency and lightweight calculation for IoT devices. The security and performance analysis show that our scheme could effectively resist multiple attacks and be efficiently implemented in IoT systems.

Radiomics of Multiparametric MRI for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer: A Multicenter Study.

Abstract: Purpose: We evaluated the performance of the newly proposed radiomics of multiparametric MRI (RMM), developed and validated based on a multicenter dataset adopting a radiomic strategy, for pretreatment prediction of pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer. Experimental Design: A total of 586 potentially eligible patients were retrospectively enrolled from four hospitals (primary cohort and external validation cohort 1–3). Quantitative imaging features were extracted from T2-weighted imaging, diffusion-weighted imaging, and contrast-enhanced T1-weighted imaging before NAC for each patient. With features selected using a coarse to fine feature selection strategy, four radiomic signatures were constructed based on each of the three MRI sequences and their combination. RMM was developed based on the best radiomic signature incorporating with independent clinicopathologic risk factors. The performance of RMM was assessed with respect to its discrimination and clinical usefulness, and compared with that of clinical information–based prediction model. Results: Radiomic signature combining multiparametric MRI achieved an AUC of 0.79 (the highest among the four radiomic signatures). The signature further achieved good performances in hormone receptor–positive and HER2-negative group and triple-negative group. RMM yielded an AUC of 0.86, which was significantly higher than that of clinical model in two of the three external validation cohorts. Conclusions: The study suggested a possibility that RMM provided a potential tool to develop a model for predicting pCR to NAC in breast cancer.

Computation Offloading and Resource Allocation in Vehicular Networks Based on Dual-Side Cost Minimization

Abstract: The proliferation of smart vehicular terminals (VTs) and their resource hungry applications impose serious challenges to the processing capabilities of VTs and the delivery of vehicular services. Mobile Edge Computing (MEC) offers a promising paradigm to solve this problem by offloading VT applications to proximal MEC servers, while TV white space (TVWS) bands can be used to supplement the bandwidth for computation offloading. In this paper, we consider a cognitive vehicular network that uses the TVWS band, and formulate a dual-side optimization problem, to minimize the cost of VTs and that of the MEC server at the same time. Specifically, the dual-side cost minimization is achieved by jointly optimizing the offloading decision and local CPU frequency on the VT side, and the radio resource allocation and server provisioning on the server side, while guaranteeing network stability. Based on Lyapunov optimization, we design an algorithm called DDORV to tackle the joint optimization problem, where only current system states, such as channel states and traffic arrivals, are needed. The closed-form solution to the VT-side problem is obtained easily by derivation and comparing two values. For MEC server side optimization, we first obtain server provisioning independently, and then devise a continuous relaxation and Lagrangian dual decomposition based iterative algorithm for joint radio resource and power allocation. Simulation results demonstrate that DDORV converges fast, can balance the cost-delay tradeoff flexibly, and can obtain more performance gains in cost reduction as compared with existing schemes.

Disease Detection with Molecular Biomarkers: From Chemistry of Body Fluids to Nature-Inspired Chemical Sensors.

Abstract: This article aims to review nature-inspired chemical sensors for enabling fast, relatively inexpensive, and minimally (or non-) invasive diagnostics and follow-up of the health conditions. It can be achieved via monitoring of biomarkers and volatile biomarkers, that are excreted from one or combination of body fluids (breath, sweat, saliva, urine, seminal fluid, nipple aspirate fluid, tears, stool, blood, interstitial fluid, and cerebrospinal fluid). The first part of the review gives an updated compilation of the biomarkers linked with specific sickness and/or sampling origin. The other part of the review provides a didactic examination of the concepts and approaches related to the emerging chemistries, sensing materials, and transduction techniques used for biomarker-based medical evaluations. The strengths and pitfalls of each approach are discussed and criticized. Future perspective with relation to the information and communication era is presented and discussed.

The Effect of IoT New Features on Security and Privacy: New Threats, Existing Solutions, and Challenges Yet to Be Solved

Abstract: Internet of Things (IoT) is an increasingly popular technology that enables physical devices, vehicles, home appliances, etc., to communicate and even inter operate with one another. It has been widely used in industrial production and social applications including smart home, healthcare, and industrial automation. While bringing unprecedented convenience, accessibility, and efficiency, IoT has caused acute security and privacy threats in recent years. There are increasing research works to ease these threats, but many problems remain open. To better understand the essential reasons of new IoT threats and the challenges in current research, this survey first proposes the concept of “IoT features.” Then, we discuss the security and privacy effects of eight IoT features including the threats they cause, existing solutions to threats and research challenges yet to be solved. To help researchers follow the up-to-date works in this field, this paper finally illustrates the developing trend of IoT security research and reveals how IoT features affect existing security research by investigating most existing research works related to IoT security from 2013 to 2017.

Optimizing Space-Air-Ground Integrated Networks by Artificial Intelligence

Abstract: It is widely acknowledged that the development of traditional terrestrial communication technologies cannot provide all users with fair and high quality services due to scarce network resources and limited coverage areas. To complement the terrestrial connection, especially for users in rural, disaster-stricken, or other difficult-to-serve areas, satellites, UAVs, and balloons have been utilized to relay communication signals. On this basis, SAGINs have been proposed to improve the users' QoE. However, compared with existing networks such as ad hoc networks and cellular networks, SAGINs are much more complex due to the various characteristics of three network segments. To improve the performance of SAGINs, researchers are facing many unprecedented challenges. In this article, we propose the AI technique to optimize SAGINs, as the AI technique has shown its predominant advantages in many applications. We first analyze several main challenges of SAGINs and explain how these problems can be solved by AI. Then, we consider the satellite traffic balance as an example and propose a deep learning based method to improve traffic control performance. Simulation results evaluate that the deep learning technique can be an efficient tool to improve the performance of SAGINs.

Deep Spectral Clustering Using Dual Autoencoder Network

Abstract: The clustering methods have recently absorbed even-increasing attention in learning and vision. Deep clustering combines embedding and clustering together to obtain optimal embedding subspace for clustering, which can be more effective compared with conventional clustering methods. In this paper, we propose a joint learning framework for discriminative embedding and spectral clustering. We first devise a dual autoencoder network, which enforces the reconstruction constraint for the latent representations and their noisy versions, to embed the inputs into a latent space for clustering. As such the learned latent representations can be more robust to noise. Then the mutual information estimation is utilized to provide more discriminative information from the inputs. Furthermore, a deep spectral clustering method is applied to embed the latent representations into the eigenspace and subsequently clusters them, which can fully exploit the relationship between inputs to achieve optimal clustering results. Experimental results on benchmark datasets show that our method can significantly outperform state-of-the-art clustering approaches.

HSI-DeNet: Hyperspectral Image Restoration via Convolutional Neural Network

Abstract: The spectral and the spatial information in hyperspectral images (HSIs) are the two sides of the same coin. How to jointly model them is the key issue for HSIs’ noise removal, including random noise, structural stripe noise, and dead pixels/lines. In this paper, we introduce the deep convolutional neural network (CNN) to achieve this goal. The learned filters can well extract the spatial information within their local receptive filed. Meanwhile, the spectral correlation can be depicted by the multiple channels of the learned 2-D filters, namely, the number of filters in each layer. The consequent advantages of our CNN-based HSI denoising method (HSI-DeNet) over previous methods are threefold. First, the proposed HSI-DeNet can be regarded as a tensor-based method by directly learning the filters in each layer without damaging the spectral-spatial structures. Second, the HSI-DeNet can simultaneously accommodate various kinds of noise in HSIs. Moreover, our method is flexible for both single image and multiple images by slightly modifying the channels of the filters in the first and last layers. Last but not least, our method is extremely fast in the testing phase, which makes it more practical for real application. The proposed HSI-DeNet is extensively evaluated on several HSIs, and outperforms the state-of-the-art HSI-DeNets in terms of both speed and performance.

HSME: Hypersphere Manifold Embedding for Visible Thermal Person Re-Identification

Abstract: Person Re-identification(re-ID) has great potential to contribute to video surveillance that automatically searches and identifies people across different cameras. Heterogeneous person re-identification between thermal(infrared) and visible images is essentially a cross-modality problem and important for night-time surveillance application. Current methods usually train a model by combining classification and metric learning algorithms to obtain discriminative and robust feature representations. However, the combined loss function ignored the correlation between classification subspace and feature embedding subspace. In this paper, we use Sphere Softmax to learn a hypersphere manifold embedding and constrain the intra-modality variations and cross-modality variations on this hypersphere. We propose an end-to-end dualstream hypersphere manifold embedding network(HSMEnet) with both classification and identification constraint. Meanwhile, we design a two-stage training scheme to acquire decorrelated features, we refer the HSME with decorrelation as D-HSME. We conduct experiments on two crossmodality person re-identification datasets. Experimental results demonstrate that our method outperforms the state-of-the-art methods on two datasets. On RegDB dataset, rank-1 accuracy is improved from 33.47% to 50.85%, and mAP is improved from 31.83% to 47.00%.

Deep Learning-Based Channel Estimation for Doubly Selective Fading Channels

Abstract: In this paper, online deep learning (DL)-based channel estimation algorithm for doubly selective fading channels is proposed by employing the deep neural network (DNN). With properly selected inputs, the DNN can not only exploit the features of channel variation from previous channel estimates but also extract additional features from pilots and received signals. Moreover, the DNN can take the advantages of the least squares estimation to further improve the performance of channel estimation. The DNN is first trained with simulated data in an off-line manner and then it could track the dynamic channel in an online manner. To reduce the performance degradation from random initialization, a pre-training approach is designed to refine the initial parameters of the DNN with several epochs of training. The proposed algorithm benefits from the excellent learning and generalization capability of DL and requires no prior knowledge about the channel statistics. Hence, it is more suitable for communication systems with modeling errors or non-stationary channels, such as high-mobility vehicular systems, underwater acoustic systems, and molecular communication systems. The numerical results show that the proposed DL-based algorithm outperforms the existing estimator in terms of both efficiency and robustness, especially when the channel statistics are time-varying.

A MIMO Dielectric Resonator Antenna With Improved Isolation for 5G mm-Wave Applications

Abstract: A multiple-input–multiple-output dielectric resonator antenna with enhanced isolation is proposed in this letter for the future 5G millimeter (mm)-wave applications. Two rectangular dielectric resonators (DRs) are mounted on a substrate excited by rectangular microstrip-fed slots underneath DRs. Each DR has a metal strip printed on its upper surface moving the strongest part of the coupling field away from the exciting slot to improve the isolation between two antenna elements. The proposed antenna obtains a simulated impedance bandwidth ( S 11 ≤ –10 dB) from 27.25 to 28.59 GHz, which covers the 28 GHz band (27.5–28.35 GHz) allocated by the Federal Communications Commission for the 5G applications. A maximum improvement of 12 dB on the isolation over 27.5–28.35 GHz is achieved. The mechanism of the isolation improvement and the design procedure are given in this letter. A prototype is manufactured and measured as a validation of the proposed decoupling method.

Abstractive text summarization using LSTM-CNN based deep learning

Abstract: ive Text Summarization (ATS), which is the task of constructing summary sentences by merging facts from different source sentences and condensing them into a shorter representation while preserving information content and overall meaning. It is very difficult and time consuming for human beings to manually summarize large documents of text. In this paper, we propose an LSTM-CNN based ATS framework (ATSDL) that can construct new sentences by exploring more fine-grained fragments than sentences, namely, semantic phrases. Different from existing abstraction based approaches, ATSDL is composed of two main stages, the first of which extracts phrases from source sentences and the second generates text summaries using deep learning. Experimental results on the datasets CNN and DailyMail show that our ATSDL framework outperforms the state-of-the-art models in terms of both semantics and syntactic structure, and achieves competitive results on manual linguistic quality evaluation.

Prognostic Value of Deep Learning PET/CT-Based Radiomics: Potential Role for Future Individual Induction Chemotherapy in Advanced Nasopharyngeal Carcinoma

Abstract: Purpose: We aimed to evaluate the value of deep learning on positron emission tomography with computed tomography (PET/CT)–based radiomics for individual induction chemotherapy (IC) in advanced nasopharyngeal carcinoma (NPC). Experimental Design: We constructed radiomics signatures and nomogram for predicting disease-free survival (DFS) based on the extracted features from PET and CT images in a training set (n = 470), and then validated it on a test set (n = 237). Harrell9s concordance indices (C-index) and time-independent receiver operating characteristic (ROC) analysis were applied to evaluate the discriminatory ability of radiomics nomogram, and compare radiomics signatures with plasma Epstein–Barr virus (EBV) DNA. Results: A total of 18 features were selected to construct CT-based and PET-based signatures, which were significantly associated with DFS (P Conclusions: Deep learning PET/CT-based radiomics could serve as a reliable and powerful tool for prognosis prediction and may act as a potential indicator for individual IC in advanced NPC.

Multiobjective Cloud Workflow Scheduling: A Multiple Populations Ant Colony System Approach

Abstract: Cloud workflow scheduling is significantly challenging due to not only the large scale of workflow but also the elasticity and heterogeneity of cloud resources. Moreover, the pricing model of clouds makes the execution time and execution cost two critical issues in the scheduling. This paper models the cloud workflow scheduling as a multiobjective optimization problem that optimizes both execution time and execution cost. A novel multiobjective ant colony system based on a co-evolutionary multiple populations for multiple objectives framework is proposed, which adopts two colonies to deal with these two objectives, respectively. Moreover, the proposed approach incorporates with the following three novel designs to efficiently deal with the multiobjective challenges: 1) a new pheromone update rule based on a set of nondominated solutions from a global archive to guide each colony to search its optimization objective sufficiently; 2) a complementary heuristic strategy to avoid a colony only focusing on its corresponding single optimization objective, cooperating with the pheromone update rule to balance the search of both objectives; and 3) an elite study strategy to improve the solution quality of the global archive to help further approach the global Pareto front. Experimental simulations are conducted on five types of real-world scientific workflows and consider the properties of Amazon EC2 cloud platform. The experimental results show that the proposed algorithm performs better than both some state-of-the-art multiobjective optimization approaches and the constrained optimization approaches.

Vehicular Edge Computing and Networking: A Survey.

Abstract: As one key enabler of Intelligent Transportation System (ITS), Vehicular Ad Hoc Network (VANET) has received remarkable interest from academia and industry. The emerging vehicular applications and the exponential growing data have naturally led to the increased needs of communication, computation and storage resources, and also to strict performance requirements on response time and network bandwidth. In order to deal with these challenges, Mobile Edge Computing (MEC) is regarded as a promising solution. MEC pushes powerful computational and storage capacities from the remote cloud to the edge of networks in close proximity of vehicular users, which enables low latency and reduced bandwidth consumption. Driven by the benefits of MEC, many efforts have been devoted to integrating vehicular networks into MEC, thereby forming a novel paradigm named as Vehicular Edge Computing (VEC). In this paper, we provide a comprehensive survey of state-of-art research on VEC. First of all, we provide an overview of VEC, including the introduction, architecture, key enablers, advantages, challenges as well as several attractive application scenarios. Then, we describe several typical research topics where VEC is applied. After that, we present a careful literature review on existing research work in VEC by classification. Finally, we identify open research issues and discuss future research directions.