Showing papers by "Xidian University published in 2021"
TL;DR: An AI system that automatically analyzes CT images and provides the probability of infection to rapidly detect COVID-19 pneumonia and is able to overcome a series of challenges in this particular situation and deploy the system in four weeks.
266 citations
TL;DR: A smart, Deep Reinforcement Learning based Resource Allocation (DRLRA) scheme, which can allocate computing and network resources adaptively, reduce the average service time and balance the use of resources under varying MEC environment is proposed.
Abstract: The development of mobile devices with improving communication and perceptual capabilities has brought about a proliferation of numerous complex and computation-intensive mobile applications. Mobile devices with limited resources face more severe capacity constraints than ever before. As a new concept of network architecture and an extension of cloud computing, Mobile Edge Computing (MEC) seems to be a promising solution to meet this emerging challenge. However, MEC also has some limitations, such as the high cost of infrastructure deployment and maintenance, as well as the severe pressure that the complex and mutative edge computing environment brings to MEC servers. At this point, how to allocate computing resources and network resources rationally to satisfy the requirements of mobile devices under the changeable MEC conditions has become a great aporia. To combat this issue, we propose a smart, Deep Reinforcement Learning based Resource Allocation (DRLRA) scheme, which can allocate computing and network resources adaptively, reduce the average service time and balance the use of resources under varying MEC environment. Experimental results show that the proposed DRLRA performs better than the traditional OSPF algorithm in the mutative MEC conditions.
261 citations
TL;DR: In this article, a lead halide-templated crystallization strategy is developed for printing formamidinium (FA)-cesium (Cs) lead triiodide perovskite films.
Abstract: Upscaling efficient and stable perovskite layers is one of the most challenging issues in the commercialization of perovskite solar cells. Here, a lead halide-templated crystallization strategy is developed for printing formamidinium (FA)-cesium (Cs) lead triiodide perovskite films. High-quality large-area films are achieved through controlled nucleation and growth of a lead halide•N-methyl-2-pyrrolidone adduct that can react in situ with embedded FAI/CsI to directly form α-phase perovskite, sidestepping the phase transformation from δ-phase. A nonencapsulated device with 23% efficiency and excellent long-term thermal stability (at 85°C) in ambient air (~80% efficiency retention after 500 hours) is achieved with further addition of potassium hexafluorophosphate. The slot die-printed minimodules achieve champion efficiencies of 20.42% (certified efficiency 19.3%) and 19.54% with an active area of 17.1 and 65.0 square centimeters, respectively.
241 citations
TL;DR: Zhang et al. as discussed by the authors proposed an end-to-end residual spectral-spatial attention network (RSSAN) for hyperspectral image classification, which takes raw 3D cubes as input data without additional feature engineering.
Abstract: In the last five years, deep learning has been introduced to tackle the hyperspectral image (HSI) classification and demonstrated good performance. In particular, the convolutional neural network (CNN)-based methods for HSI classification have made great progress. However, due to the high dimensionality of HSI and equal treatment of all bands, the performance of these methods is hampered by learning features from useless bands for classification. Moreover, for patchwise-based CNN models, equal treatment of spatial information from the pixel-centered neighborhood also hinders the performance of these methods. In this article, we propose an end-to-end residual spectral–spatial attention network (RSSAN) for HSI classification. The RSSAN takes raw 3-D cubes as input data without additional feature engineering. First, a spectral attention module is designed for spectral band selection from raw input data by emphasizing useful bands for classification and suppressing useless bands. Then, a spatial attention module is designed for the adaptive selection of spatial information by emphasizing pixels from the same class as the center pixel or those are useful for classification in the pixel-centered neighborhood and suppressing those from a different class or useless. Second, two attention modules are also used in the following CNN for adaptive feature refinement in spectral–spatial feature learning. Third, a sequential spectral–spatial attention module is embedded into a residual block to avoid overfitting and accelerate the training of the proposed model. Experimental studies demonstrate that the RSSAN achieved superior classification accuracy compared with the state of the art on three HSI data sets: Indian Pines (IN), University of Pavia (UP), and Kennedy Space Center (KSC).
239 citations
TL;DR: Federated learning as discussed by the authors is a set-up in which multiple clients collaborate to solve machine learning problems, which is under the coordination of a central aggregator, where the original data of the client is stored locally and cannot be exchanged or migrated.
Abstract: Federated learning is a set-up in which multiple clients collaborate to solve machine learning problems, which is under the coordination of a central aggregator. This setting also allows the training data decentralized to ensure the data privacy of each device. Federated learning adheres to two major ideas: local computing and model transmission, which reduces some systematic privacy risks and costs brought by traditional centralized machine learning methods. The original data of the client is stored locally and cannot be exchanged or migrated. With the application of federated learning, each device uses local data for local training, then uploads the model to the server for aggregation, and finally the server sends the model update to the participants to achieve the learning goal. To provide a comprehensive survey and facilitate the potential research of this area, we systematically introduce the existing works of federated learning from five aspects: data partitioning, privacy mechanism, machine learning model, communication architecture and systems heterogeneity. Then, we sort out the current challenges and future research directions of federated learning. Finally, we summarize the characteristics of existing federated learning, and analyze the current practical application of federated learning.
207 citations
TL;DR: A comprehensive survey of state-of-the-art research on VEC can be found in this paper, where the authors provide an overview of VEC, including the introduction, architecture, key enablers, advantages, challenges as well as several attractive application scenarios.
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.
205 citations
TL;DR: An attention steered interweave fusion network (ASIF-Net) is proposed to detect salient objects, which progressively integrates cross-modal and cross-level complementarity from the RGB image and corresponding depth map via steering of an attention mechanism.
Abstract: Salient object detection from RGB-D images is an important yet challenging vision task, which aims at detecting the most distinctive objects in a scene by combining color information and depth constraints. Unlike prior fusion manners, we propose an attention steered interweave fusion network (ASIF-Net) to detect salient objects, which progressively integrates cross-modal and cross-level complementarity from the RGB image and corresponding depth map via steering of an attention mechanism. Specifically, the complementary features from RGB-D images are jointly extracted and hierarchically fused in a dense and interweaved manner. Such a manner breaks down the barriers of inconsistency existing in the cross-modal data and also sufficiently captures the complementarity. Meanwhile, an attention mechanism is introduced to locate the potential salient regions in an attention-weighted fashion, which advances in highlighting the salient objects and suppressing the cluttered background regions. Instead of focusing only on pixelwise saliency, we also ensure that the detected salient objects have the objectness characteristics (e.g., complete structure and sharp boundary) by incorporating the adversarial learning that provides a global semantic constraint for RGB-D salient object detection. Quantitative and qualitative experiments demonstrate that the proposed method performs favorably against 17 state-of-the-art saliency detectors on four publicly available RGB-D salient object detection datasets. The code and results of our method are available at https://github.com/Li-Chongyi/ASIF-Net .
188 citations
TL;DR: Findings indicate that the developed framework successfully distinguishes individuals who walk too near and breaches/violates social distances; also, the transfer learning approach boosts the overall efficiency of the model.
182 citations
TL;DR: A real-time vehicle tracking counter for vehicles that combines the vehicle detection and vehicle tracking algorithms to realize the detection of traffic flow is proposed.
Abstract: An intelligent transportation system (ITS) plays an important role in public transport management, security and other issues. Traffic flow detection is an important part of the ITS. Based on the real-time acquisition of urban road traffic flow information, an ITS provides intelligent guidance for relieving traffic jams and reducing environmental pollution. The traffic flow detection in an ITS usually adopts the cloud computing mode. The edge of the network will transmit all the captured video to the cloud computing center. However, the increasing traffic monitoring has brought great challenges to the storage, communication and processing of traditional transportation systems based on cloud computing. To address this issue, a traffic flow detection scheme based on deep learning on the edge node is proposed in this article. First, we propose a vehicle detection algorithm based on the YOLOv3 (You Only Look Once) model trained with a great volume of traffic data. We pruned the model to ensure its efficiency on the edge equipment. After that, the DeepSORT (Deep Simple Online and Realtime Tracking) algorithm is optimized by retraining the feature extractor for multiobject vehicle tracking. Then, we propose a real-time vehicle tracking counter for vehicles that combines the vehicle detection and vehicle tracking algorithms to realize the detection of traffic flow. Finally, the vehicle detection network and multiple-object tracking network are migrated and deployed on the edge device Jetson TX2 platform, and we verify the correctness and efficiency of our framework. The test results indicate that our model can efficiently detect the traffic flow with an average processing speed of 37.9 FPS (frames per second) and an average accuracy of 92.0% on the edge device.
173 citations
TL;DR: In this article, an intelligent reflecting surface (IRS) is employed to enhance the performance of UAV-aided air-ground networks, where the UAV trajectory, the transmit beamforming and the RIS passive beamforming are jointly optimized.
Abstract: Thanks to their flexibility and mobility, unmanned aerial vehicles (UAVs) have been widely applied in wireless networks. However, UAV communications may suffer from blockage and eavesdropping in practical scenarios due to the complex environment. Taking the recent advances in intelligent reflecting surface (IRS) to reconfigure the propagation environments, in this article, we employ IRS to enhance the performance of UAV-aided air-ground networks. First, we overview the combination of UAV and IRS, by introducing the diverse applications of IRS and the appealing advantages of UAV, and highlighting the benefits of combining them. Then, we investigate two case studies where the UAV trajectory, the transmit beamforming and the IRS passive beamforming are jointly optimized. In the first case study, by equipping the IRS on a UAV, the average achievable rate of the relaying network is maximized. In the second one, the IRS is deployed to assist the UAV-ground communication while combating the adversarial eavesdropper. Simulation results are provided to demonstrate the performance enhancement resulting from combining UAV and IRS in air-ground networks. Finally, we shed light on some challenging issues to be resolved for practical implementations in this direction.
161 citations
TL;DR: This article studies the bipartite containment control problem for nonlinear multiagent systems (MASs) with input quantization over a signed digraph with an event-triggered control scheme developed via backstepping technique.
Abstract: This article studies the bipartite containment control problem for nonlinear multiagent systems (MASs) with input quantization over a signed digraph. The design objective is to provide an appropriate distributed protocol such that the followers converge to a convex hull containing each leader's trajectory as well as its opposite trajectory different in sign. Based on a nonlinear decomposition approach of input quantization, an event-triggered control scheme is developed via backstepping technique. A fuzzy observer is constructed to estimate unmeasurable states. Moreover, the bipartite containment control scheme for nonlinear MASs is designed. It is demonstrated that all signals in the closed-loop system are semiglobally uniformly ultimately bounded and Zeno behavior is excluded. Finally, a simulation example is given to verify the validity of the designed method.
TL;DR: The proposed cross-modality deep feature learning framework can effectively improve the brain tumor segmentation performance when compared with the baseline methods and state-of-the-art methods.
TL;DR: A comprehensive survey of weakly supervised object localization and detection methods can be found in this paper, where the authors review classic models, approaches with feature representations from off-the-shelf deep networks, approaches solely based on deep learning, and publicly available datasets and standard evaluation metrics that are widely used in this field.
Abstract: As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received significant attention in the past decade. As methods have been proposed, a comprehensive survey of these topics is of great importance. In this work, we review (1) classic models, (2) approaches with feature representations from off-the-shelf deep networks, (3) approaches solely based on deep learning, and (4) publicly available datasets and standard evaluation metrics that are widely used in this field. We also discuss the key challenges in this field, development history of this field, advantages/disadvantages of the methods in each category, the relationships between methods in different categories, applications of the weakly supervised object localization and detection methods, and potential future directions to further promote the development of this research field.
TL;DR: In this article, a secure data sharing scheme in the blockchain-enabled mobile edge computing system using an asynchronous learning approach is presented, and an adaptive privacy-preserving mechanism according to available system resources and privacy demands of users is presented.
Abstract: Mobile-edge computing (MEC) plays a significant role in enabling diverse service applications by implementing efficient data sharing. However, the unique characteristics of MEC also bring data privacy and security problem, which impedes the development of MEC. Blockchain is viewed as a promising technology to guarantee the security and traceability of data sharing. Nonetheless, how to integrate blockchain into MEC system is quite challenging because of dynamic characteristics of channel conditions and network loads. To this end, we propose a secure data sharing scheme in the blockchain-enabled MEC system using an asynchronous learning approach in this article. First, a blockchain-enabled secure data sharing framework in the MEC system is presented. Then, we present an adaptive privacy-preserving mechanism according to available system resources and privacy demands of users. Next, an optimization problem of secure data sharing is formulated in the blockchain-enabled MEC system with the aim to maximize the system performance with respect to the decreased energy consumption of MEC system and the increased throughput of blockchain system. Especially, an asynchronous learning approach is employed to solve the formulated problem. The numerical results demonstrate the superiority of our proposed secure data sharing scheme when compared with some popular benchmark algorithms in terms of average throughput, average energy consumption, and reward.
TL;DR: This article considers a new architecture of digital twin (DT) empowered Industrial IoT, where DTs capture the characteristics of industrial devices to assist federated learning, and adaptively adjusts the aggregation frequency of federatedlearning based on Lyapunov dynamic deficit queue and deep reinforcement learning.
Abstract: Industrial Internet of Things (IoT) enables distributed intelligent services varying with the dynamic and realtime industrial environment to achieve Industry 4.0 benefits. In this article, we consider a new architecture of digital twin (DT) empowered Industrial IoT, where DTs capture the characteristics of industrial devices to assist federated learning. Noticing that DTs may bring estimation deviations from the actual value of device state, a trusted-based aggregation is proposed in federated learning to alleviate the effects of such deviation. We adaptively adjust the aggregation frequency of federated learning based on Lyapunov dynamic deficit queue and deep reinforcement learning (DRL), to improve the learning performance under the resource constraints. To further adapt to the heterogeneity of industrial IoT, a clustering-based asynchronous federated learning framework is proposed. Numerical results show that the proposed framework is superior to the benchmark in terms of learning accuracy, convergence, and energy saving.
TL;DR: In this article, a two-layer federated learning model is proposed to take advantage of the distributed end-edge-cloud architecture typical in 6G environment, and to achieve a more efficient and more accurate learning while ensuring data privacy protection and reducing communication overheads.
Abstract: The vision of the upcoming 6G technologies that have fast data rate, low latency, and ultra-dense network, draws great attentions to the Internet of Vehicles (IoV) and Vehicle-to-Everything (V2X) communication for intelligent transportation systems. There is an urgent need for distributed machine learning techniques that can take advantages of massive interconnected networks with explosive amount of heterogeneous data generated at the network edge. In this study, a two-layer federated learning model is proposed to take advantages of the distributed end-edge-cloud architecture typical in 6G environment, and to achieve a more efficient and more accurate learning while ensuring data privacy protection and reducing communication overheads. A novel multi-layer heterogeneous model selection and aggregation scheme is designed as a part of the federated learning process to better utilize the local and global contexts of individual vehicles and road side units (RSUs) in 6G supported vehicular networks. This context-aware distributed learning mechanism is then developed and applied to address intelligent object detection, which is one of the most critical challenges in modern intelligent transportation systems with autonomous vehicles. Evaluation results showed that the proposed method, which demonstrates a higher learning accuracy with better precision, recall and F1 score, outperforms other state-of-the-art methods under 6G network configuration by achieving faster convergence, and scales better with larger numbers of RSUs involved in the learning process.
TL;DR: In this paper, the authors propose a federated edge intelligence based architecture for supporting resource-efficient semantic-aware networking, where each user can offload computationally intensive semantic encoding and decoding tasks to edge servers and protect its proprietary model-related information by coordinating via intermediate results.
Abstract: Existing communication systems are mainly built based on Shannon's information theory, which deliberately ignores the semantic aspects of communication. The recent iteration of wireless technology, 5G and beyond, promises to support a plethora of services enabled by carefully tailored network capabilities based on contents, requirements, as well as semantics. This has sparked significant interest in semantic communication, a novel paradigm that involves the meaning of messages in communication. In this article, we first review classic semantic communication frameworks and then summarize key challenges that hinder its popularity. We observe that some semantic communication processes such as semantic detection, knowledge modeling, and coordination can be resource-consuming and inefficient, especially for communication between a single source and a destination. We therefore propose a novel architecture based on federated edge intelligence for supporting resource-efficient semantic-aware networking. Our architecture allows each user to offload computationally intensive semantic encoding and decoding tasks to edge servers and protect its proprietary model-re-lated information by coordinating via intermediate results. Our simulation result shows that the proposed architecture can reduce resource consumption and significantly improve communication efficiency.
TL;DR: A newly designed deep neural network model called A-YONet, which is constructed by combining the advantages of YOLO and MTCNN is proposed to be deployed in an end–edge–cloud surveillance system, in order to realize the lightweight training and feature learning with limited computing sources.
Abstract: Along with the rapid development of cloud computing, IoT, and AI technologies, cloud video surveillance (CVS) has become a hotly discussed topic, especially when facing the requirement of real-time analysis in smart applications Object detection usually plays an important role for environment monitoring and activity tracking in surveillance system The emerging edge-cloud computing paradigm provides us an opportunity to deal with the continuously generated huge amount of surveillance data in an on-site manner across IoT systems However, the detection performance is still far away from satisfactions due to the complex surveilling environment In this study, we focus on the multitarget detection for real-time surveillance in smart IoT systems A newly designed deep neural network model called A-YONet, which is constructed by combining the advantages of YOLO and MTCNN, is proposed to be deployed in an end–edge–cloud surveillance system, in order to realize the lightweight training and feature learning with limited computing sources An intelligent detection algorithm is then developed based on a preadjusting scheme of anchor box and a multilevel feature fusion mechanism Experiments and evaluations using two data sets, including one public data set and one homemade data set obtained in a real surveillance system, demonstrate the effectiveness of our proposed method in enhancing training efficiency and detection precision, especially for multitarget detection in smart IoT application developments
TL;DR: In JKT, it is not only possible to establish connections between exercises under cross-concepts, but also to help capture high-level semantic information and increase the model’s interpretability.
TL;DR: In this article, a hierarchical flower-like Ni-doped Co3O4 was synthesized via a facile one-step coprecipitation method, and a series of solvent-dependent experiments were carried out to investigate the effect of ethanol/water ratio (R-E/W) on samples.
Abstract: In this work, hierarchical flower-like Ni-doped Co3O4 was synthesized via a facile one-step coprecipitation method. In the synthesis process, a series of solvent-dependent experiments were carried out to investigate the effect of ethanol/water ratio (R-E/W) on samples. With the increasing ethanol/water ratio, the doping concentration of Ni2+ increased and the microstructure evolved from micro-leaves to micro-flowers. Additionally, gas sensors based on prepared materials were fabricated to evaluate their gas sensing properties. The comparative analysis illustrated that the sensor based on 5.3 mol% Ni-doped Co3O4 microflowers (R-E/W = 3/30) presented the highest response (8.34) to 100 ppm n-butanol at low optimum temperature (165 °C), with a response/recovery time of 59/63 s, and it also exhibited excellent anti-humidity properties and long-term stability. The unique hierarchical flower-like microstructure and the optimized parameters (catalytic sites, carrier concentration, ratio of Co2+, oxygen component) caused by the doping of Ni were responsible for the improved gas sensing performance. Therefore, this work presented a simple solvent-dependent route to controllably synthesize Ni-doped Co3O4 sensing material, and the excellent gas sensing properties of the sensor based on 5.3 mol% Ni-doped Co3O4 microflowers revealed a great application prospect in detecting n-butanol.
TL;DR: This article proposes a graph theory based algorithm to efficiently solve the data sharing problem, which is formulated as a maximum weighted independent set problem on the constructed conflict graph, and proposes a balanced greedy algorithm, which can make the content distribution more balanced.
Abstract: It is widely recognized that connected vehicles have the potential to further improve the road safety, transportation intelligence and enhance the in-vehicle entertainment. By leveraging the 5G enabled Vehicular Ad hoc NETworks (VANET) technology, which is referred to as 5G-VANET, a flexible software-defined communication can be achieved with ultra-high reliability, low latency, and high capacity. Many enabling applications in 5G-VANET rely on sharing mobile data among vehicles, which is still a challenging issue due to the extremely large data volume and the prohibitive cost of transmitting such data using 5G cellular networks. This article focuses on efficient cooperative data sharing in edge computing assisted 5G-VANET. First, to enable efficient cooperation between cellular communication and Dedicated Short-Range Communication (DSRC), we first propose a software-defined cooperative data sharing architecture in 5G-VANET. The cellular link allows the communications between OpenFlow enabled vehicles and the Controller to collect contextual information, while the DSRC serves as the data plane, enabling cooperative data sharing among adjacent vehicles. Second, we propose a graph theory based algorithm to efficiently solve the data sharing problem, which is formulated as a maximum weighted independent set problem on the constructed conflict graph. Specifically, considering the continuous data sharing, we propose a balanced greedy algorithm, which can make the content distribution more balanced. Furthermore, due to the fixed amount of computing resources allocated to this software-defined cooperative data sharing service, we propose an integer linear programming based decomposition algorithm to make full use of the computing resources. Extensive simulations in NS3 and SUMO demonstrate the superiority and scalability of the proposed software-defined architecture and cooperative data sharing algorithms.
TL;DR: The specific characteristics of permissionless blockchain are analyzed, the potential privacy threats are summarized, the existing privacy preservation technologies are carefully surveyed and evaluated based on the proposed evaluation criteria.
TL;DR: An unsupervised anomaly detection method is presented, which combines Sub-Space Clustering (SSC) and One Class Support Vector Machine (OCSVM) to detect attacks without any prior knowledge.
TL;DR: It is proved that the proposed ABKS-SM systems achieve selective security and resist off-line keyword-guessing attack in the generic bilinear group model, and their performance is evaluated using real-world datasets.
Abstract: Ciphertext-Policy Attribute-Based Keyword Search (CP-ABKS) facilitates search queries and supports fine-grained access control over encrypted data in the cloud. However, prior CP-ABKS schemes were designed to support unshared multi-owner setting, and cannot be directly applied in the shared multi-owner setting (where each record is accredited by a fixed number of data owners), without incurring high computational and storage costs. In addition, due to privacy concerns on access policies, most existing schemes are vulnerable to off-line keyword-guessing attacks if the keyword space is of polynomial size. Furthermore, it is difficult to identify malicious users who leak the secret keys when more than one data user has the same subset of attributes. In this paper, we present a privacy-preserving CP-ABKS system with hidden access policy in Shared Multi-owner setting (basic ABKS-SM system), and demonstrate how it is improved to support malicious user tracing (modified ABKS-SM system). We then prove that the proposed ABKS-SM systems achieve selective security and resist off-line keyword-guessing attack in the generic bilinear group model. We also evaluate their performance using real-world datasets.
TL;DR: A 3-D octave convolution with the spatial-spectral attention network (3DOC-SSAN) to capture discriminative spatial–spectral features for the classification of HSIs and designs an information complement model to transmit important information between spatial and spectral attention features.
Abstract: In recent years, with the development of deep learning (DL), the hyperspectral image (HSI) classification methods based on DL have shown superior performance. Although these DL-based methods have great successes, there is still room to improve their ability to explore spatial–spectral information. In this article, we propose a 3-D octave convolution with the spatial–spectral attention network (3DOC-SSAN) to capture discriminative spatial–spectral features for the classification of HSIs. Especially, we first extend the octave convolution model using 3-D convolution, namely, a 3-D octave convolution model (3D-OCM), in which four 3-D octave convolution blocks are combined to capture spatial–spectral features from HSIs. Not only the spatial information can be mined deeply from the high- and low-frequency aspects but also the spectral information can be taken into account by our 3D-OCM. Second, we introduce two attention models from spatial and spectral dimensions to highlight the important spatial areas and specific spectral bands that consist of significant information for the classification tasks. Finally, in order to integrate spatial and spectral information, we design an information complement model to transmit important information between spatial and spectral attention features. Through the information complement model, the beneficial parts of spatial and spectral attention features for the classification tasks can be fully utilized. Comparing with several existing popular classifiers, our proposed method can achieve competitive performance on four benchmark data sets.
TL;DR: In the proposed method, a convolutional neural network is employed to extract the degradation features and multiple-kernel maximum mean discrepancies are integrated into optimization objective to reduce distribution discrepancy.
TL;DR: This paper explores the cache deployment in a large-scale WiFi system, which contains 8,000 APs and serves more than 40,000 active users, to maximize the long-term caching gain, and proposes a cache deployment strategy, named LeaD, which is able to achieve the near-optimal caching performance and can outperform other benchmark strategies significantly.
Abstract: Widespread and large-scale WiFi systems have been deployed in many corporate locations, while the backhual capacity becomes the bottleneck in providing high-rate data services to a tremendous number of WiFi users. Mobile edge caching is a promising solution to relieve backhaul pressure and deliver quality services by proactively pushing contents to access points (APs). However, how to deploy cache in large-scale WiFi system is not well studied yet quite challenging since numerous APs can have heterogeneous traffic characteristics, and future traffic conditions are unknown ahead. In this paper, given the cache storage budget, we explore the cache deployment in a large-scale WiFi system, which contains 8,000 APs and serves more than 40,000 active users, to maximize the long-term caching gain. Specifically, we first collect two-month user association records and conduct intensive spatio-temporal analytics on WiFi traffic consumption, gaining two major observations. First, per AP traffic consumption varies in a rather wide range and the proportion of AP distributes evenly within the range, indicating that the cache size should be heterogeneously allocated in accordance to the underlying traffic demands. Second, compared to a single AP, the traffic consumption of a group of APs (clustered by physical locations) is more stable, which means that the short-term traffic statistics can be used to infer the future long-term traffic conditions. We then propose our cache deployment strategy, named LeaD (i.e., L arge-scale WiFi E dge c A che D eployment), in which we first cluster large-scale APs into well-sized edge nodes, then conduct the stationary testing on edge level traffic consumption and sample sufficient traffic statistics in order to precisely characterize long-term traffic conditions, and finally devise the TEG ( T raffic-w E ighted G reedy) algorithm to solve the long-term caching gain maximization problem. Extensive trace-driven experiments are carried out, and the results demonstrate that LeaD is able to achieve the near-optimal caching performance and can outperform other benchmark strategies significantly.
TL;DR: In this article, the authors studied the decentralized event-triggered control problem for a class of constrained nonlinear interconnected systems, where the original control problem is equivalently transformed into finding a series of optimal control policies updating in an aperiodic manner.
Abstract: This article studies the decentralized event-triggered control problem for a class of constrained nonlinear interconnected systems. By assigning a specific cost function for each constrained auxiliary subsystem, the original control problem is equivalently transformed into finding a series of optimal control policies updating in an aperiodic manner, and these optimal event-triggered control laws together constitute the desired decentralized controller. It is strictly proven that the system under consideration is stable in the sense of uniformly ultimate boundedness provided by the solutions of event-triggered Hamilton-Jacobi-Bellman equations. Different from the traditional adaptive critic design methods, we present an identifier-critic network architecture to relax the restrictions posed on the system dynamics, and the actor network commonly used to approximate the optimal control law is circumvented. The weights in the critic network are tuned on the basis of the gradient descent approach as well as the historical data, such that the persistence of excitation condition is no longer needed. The validity of our control scheme is demonstrated through a simulation example.
TL;DR: The proposed CenterNet++ method achieves a remarkable accuracy improvement with negligible increase in time cost, and to alleviate the impact of complex background, head enhancement module is proposed for a balance between foreground and background.
TL;DR: A novel CoEG-Net is proposed that augments the authors' prior model EGNet with a co-attention projection strategy to enable fast common information learning and fully leverages previous large-scale SOD datasets and significantly improves the model scalability and stability.
Abstract: Existing CoSOD datasets often have a serious data bias, assuming that each group of images contains salient objects of similar visual appearances. This bias can lead to the ideal settings and effectiveness of models trained on existing datasets, being impaired in real-life situations, where similarities are usually semantic or conceptual. To tackle this issue, we first introduce a new benchmark, called CoSOD3k in the wild, which requires a large amount of semantic context, making it more challenging than existing CoSOD datasets. Our CoSOD3k consists of 3,316 high-quality, elaborately selected images divided into 160 groups with hierarchical annotations. The images span a wide range of categories, shapes, object sizes, and backgrounds. Second, we integrate the existing SOD techniques to build a unified, trainable CoSOD framework, which is long overdue in this field. Specifically, we propose a novel CoEG-Net that augments our prior model EGNet with a co-attention projection strategy to enable fast common information learning. CoEG-Net fully leverages previous large-scale SOD datasets and significantly improves the model scalability and stability. Third, we comprehensively summarize 34 cutting-edge algorithms, benchmarking 16 of them over three challenging CoSOD datasets, and reporting group-level performance analysis. Finally, we discuss the challenges and future works of CoSOD.