Search

Recent years witness the booming trend of applying generative adversarial nets (GAN) and its variants to image style transfer. Although many reported results strongly demonstrate the power of GAN on this task, there is still little known about neither the interpretations of several fundamental phenomenons of image style transfer by generative adversarial learning, nor its underlying mechanism. To bridge this gap, this paper presents a general framework for analyzing style transfer with adversarial learning through the lens of differential geometry. To demonstrate the utility of our proposed framework, we provide an in-depth analysis of Isola et al.’s pioneering style transfer model pix2pix and reach a comprehensive interpretation on their major experimental phenomena. Furthermore, we extend the notion of generalization to conditional GAN and derive a condition to control the generalization capability of the pix2pix model. From a higher viewpoint, we further prove a learning-free condition to guarantee the existence of infinitely many perfect style transfer mappings. Besides, we also provide a number of practical suggestions on model design and dataset construction based on these derived theoretical results to facilitate further researches. [ABSTRACT FROM AUTHOR]

In this paper, collaborative task offloading in edge computing is studied, where computation requesters can offload tasks to not only the edge server, but also nearby smartphone users. By considering the fact that smartphone users may not always be willing to provide such computation service because of the consumption of their own energy and resources, a truthful mechanism is designed to provide incentive to smartphone users. The design aims to maximize the net revenue of the service provider and addresses more practical, but more complicated, scenarios of unknown a prior distribution information on smartphone users’ private information. To tackle this high computational complexity, which makes the traditional mechanism design methods infeasible, a new approach, called truthful deep mechanism, is proposed by leveraging a multi-task machine learning model, where inherently inter-connected collaborator selection and pricing policy determination are decided by designing two deep neural networks. The numerical results show that the proposed deep truthful mechanism can ensure a convergence to a stable state and can satisfy all required economical properties, including individual rationality, incentive compatibility, and budget balance. [ABSTRACT FROM AUTHOR]

In an ultra-dense network (UDN), how to associate the mobile user equipments (UEs) with the appropriate low power nodes (LPNs) is a very essential and challenging problem, especially when the UEs are moving and may suffer from frequent handovers. In this paper, the UE association problem is investigated from a long-term perspective, where the UE's mobility pattern, i.e., the moving velocity and direction, is taken into consideration. To predict the UE's positions based on their previous activity data, a practical scheme, i.e., the classification and batch online learning method (CBOM), is proposed for achieving the UE's velocity and direction transition matrices. Then the UE association problem with the objective of maximizing the UEs’ expected achievable rate while minimizing the number of handovers is formulated. Since the proposed problem is a NP-hard mixed integer nonlinear programming problem, we reformulate it into a matching game, and propose a mobility-based long-term matching game algorithm to find the near-optimal solutions. We prove that our proposed algorithm is convergent and has low computational complexity. Simulation results show our two proposed schemes outperform the existing schemes in terms of the achieved data rate, the number of handovers, and the overall system utility. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles (UAVs) are emerging as important users of next-generation cellular networks. By operating in the sky, UAV users experience very different radio conditions than terrestrial users, due to factors such as strong Line-of-Sight (LoS) channels (and interference) and Base Station (BS) antenna misalignment. As a consequence, the UAVs may experience significant degradation to their received quality of service, particularly when they are moving and are subject to frequent handovers. The solution is to allow the UAV to be aware of its surrounding environment, and intelligently connect into the cellular network taking advantage of this awareness. In this paper we present REgression and deep Q-learning for Intelligent UAV cellular user to Base station Association (REQIBA), a solution that allows a UAV flying over an urban area to intelligently connect to underlying BSs, using information about the received signal powers, the BS locations, and the surrounding building topology. We demonstrate how REQIBA can as much as double the total UAV throughput, when compared to heuristic association schemes similar to those commonly used by terrestrial users. We also evaluate how environmental factors such as UAV height, building density, and throughput loss due to handovers impact the performance of our solution. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is playing an increasingly important role in processing large amounts of data generated by communication networks, since it can efficiently solve the problems of non-linearity and unstructured data. Recently, ML has been widely used in the processing of wireless channel data, as the noisy channel in real propagation environment is usually non-linear and unstructured. In this paper, a denoising method based on ML is presented. Two ML algorithms are used to classify and remove noise in channel impulse responses. Then, the results of the traditional noise threshold denoising are compared with ML denoising, and it is found that the denoising classifier using the bidirectional recurrent neural network has the better denoising performance. Finally, some channel parameters such as RMS delay spread are estimated based on measured channel data using different denoising methods. The results are evaluated and compared to explore the impact of denoising method on the extracted channel parameters. [ABSTRACT FROM AUTHOR]

In the era of ubiquitous computing, offloading certain computing tasks to the mobile ad hoc cloud (MAHC) could help mobile devices reduce execution time. However, if multiple resource demanders (RDs) offload tasks to the MAHC without a proper scheduling policy, it may cause unbalanced load distribution among resource providers (RPs), which will affect the overall quality of service (QoS). To this end, in this paper, we propose a multi-agent independent learning approach aiming to optimize the QoS of MAHC. Firstly, for the distributed MAHC, we formulate the QoS optimization model as a non-cooperative game, where each RD competes for maximizing its own utility. Secondly, based on the potential game theory, we prove the existence of Nash equilibrium. A multi-agent independent learning algorithm is then proposed to obtain the equilibrium points, and the convergence of this algorithm is analyzed. Simulation results confirm that the proposed approach helps balance the load distribution and enhances the QoS of MAHC. [ABSTRACT FROM AUTHOR]

Remote sensing scene classification (RSSC) is a hotspot and play very important role in the field of remote sensing image interpretation in recent years. With the recent development of the convolutional neural networks, a significant breakthrough has been made in the classification of remote sensing scenes. Many objects form complex and diverse scenes through spatial combination and association, which makes it difficult to classify remote sensing image scenes. The problem of insufficient differentiation of feature representations extracted by Convolutional Neural Networks (CNNs) still exists, which is mainly due to the characteristics of similarity for inter-class images and diversity for intra-class images. In this paper, we propose a remote sensing image scene classification method via Multi-Branch Local Attention Network (MBLANet), where Convolutional Local Attention Module (CLAM) is embedded into all down-sampling blocks and residual blocks of ResNet backbone. CLAM contains two submodules, Convolutional Channel Attention Module (CCAM) and Local Spatial Attention Module (LSAM). The two submodules are placed in parallel to obtain both channel and spatial attentions, which helps to emphasize the main target in the complex background and improve the ability of feature representation. Extensive experiments on three benchmark datasets show that our method is better than state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The low-rank matrix completion problem is fundamental in both machine learning and computer vision fields with many important applications, such as recommendation system, motion capture, face recognition, and image inpainting. In order to avoid solving the rank minimization problem which is NP-hard, several surrogate functions of the rank have been proposed in the literature. However, the matrix restored from the optimization problem based on the existing surrogate functions seriously deviates from the original one. In this paper, we first design a new non-convex Schatten capped $p$ p norm which generalizes several existing non-convex matrix norms and balances between the rank and the nuclear norm of the matrix. Then, a matrix completion method based on the Schatten capped $p$ p norm is proposed by exploiting the framework of the alternating direction method of multipliers. Meanwhile, the Schatten capped $p$ p norm regularized least squares subproblem is analyzed in detail and is solved explicitly. Finally, we evaluate the performance of the proposed matrix completion method based on extensive experiments in the field of image inpainting. All the experimental results demonstrate that the proposed method can indeed improve the accuracy of matrix completion compared with the existing methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose to extend the standard Convolutional Dictionary Learning problem to a tensor representation where the activations are constrained to be “low-rank” through a Canonical Polyadic decomposition. We show that this additional constraint increases the robustness of the CDL with respect to noise and improve the interpretability of the final results. In addition, we discuss in detail the advantages of this representation and introduce two algorithms, based on ADMM or FISTA, that efficiently solve this problem. We show that by exploiting the low rank property of activations, they achieve lower complexity than the main CDL algorithms. Finally, we evaluate our approach on a wide range of experiments, highlighting the modularity and the advantages of this tensorial low-rank formulation. [ABSTRACT FROM AUTHOR]

Voltage over-scaling (VOS) optimizes energy while causing timing errors due to an unsustainable clock frequency. Many algorithms, such as in multimedia and machine learning applications, are capable of tolerating such errors. VOS has never been investigated in hardware accelerators running closed-loop algorithms. As the errors impact most decisions and actions in the subsequent steps, closed-loops dynamically change the execution flow. Timing errors should be evaluated by an accurate gate-level simulation, but a large gap still remains: how these timing errors propagate from the underlying hardware all the way up to the entire algorithm run, where they just may degrade the performance and quality of service of the application at stake? This paper tackles this issue showing a framework for VOS investigation, embracing any kind of application. Our framework simulates the VOS-induced timing errors at gate-level, dynamically linking the hardware result with the algorithm and vice versa during the evolution of the runtime of the application. The state-of-the-art VOS literature for video encoding application fails to assess the ultimate impacts of VOS-induced timing errors, as current works open the encoding loops. Unlike those, our work investigates the ultimate impact of a hardware accelerator dynamically carrying through to the video encoder all VOS-induced timing errors and preserving the full compliance to the standard. We employ a parallel sum of absolute differences (SAD) hardware accelerator as a case study. We assess the performance of the overall encoder under varying timing guardbands. Next, it is demonstrated that, under VOS, the ultimate impact in compression efficiency is related to the video’s motion intensity. Additionally, the advantages of timing guardband controlled reduction are clearly quantified in our results by virtue of the framework. Reducing at maximum 9.5% the clock frequency, energy savings (up to 16.5% in energy/operation) are achieved in SAD for video compression. [ABSTRACT FROM AUTHOR]

Seizure prediction for drug-refractory epilepsy patients can improve their quality of life, reduce their anxiety, and help them take the necessary precautions. Nowadays, numerous deep learning algorithms have been proposed to predict seizure onset and obtain better performance than traditional machine learning methods. However, these methods require a large set of parameters and large hardware resources; they also have high energy consumption. Therefore, these methods cannot be implemented on compact, low-power wearable, or implantable medical devices. The devices should operate on a real-time basis to continually inform the epileptic patients. In this paper, we describe energy-efficient and hardware-friendly methods to predict the epileptic seizures. A model of only 45 kB was obtained by the neural architecture search and was evaluated across three datasets. The overall sensitivity, false prediction rate, and area under receiver operating characteristic curve were 99.81%, 0.005/h, 1 and 93.48%, 0.063/h, 0.977 and 85.19%, 0.116/h, 0.933, respectively, for three public datasets. This model was further reduced with several methods for model compression. The performances for the model sizes less than 50 kB for scalp EEG data and less than 10 kB for intracranial EEG data outperformed all the other models of similar model sizes. In particular, the energy consumption estimation was less than 10 mJ per inference for scalp EEG signal and less than 0.5 mJ per inference for intracranial EEG signal, which meet the requirements for low-power wearable and implantable devices, respectively. [ABSTRACT FROM AUTHOR]

Objective: Pain assessment in children continues to challenge clinicians and researchers, as subjective experiences of pain require inference through observable behaviors, both involuntary and deliberate. The presented approach supplements the subjective self-report-based method by fusing electrodermal activity (EDA) recordings with video facial expressions to develop an objective pain assessment metric. Such an approach is specifically important for assessing pain in children who are not capable of providing accurate self-pain reports, requiring nonverbal pain assessment. We demonstrate the performance of our approach using data recorded from children in post-operative recovery following laparoscopic appendectomy. We examined separately and combined the usefulness of EDA and video facial expression data as predictors of children's self-reports of pain following surgery through recovery. Findings indicate that EDA and facial expression data independently provide above chance sensitivities and specificities, but their fusion for classifying clinically significant pain vs. clinically nonsignificant pain achieved substantial improvement, yielding 90.91% accuracy, with 100% sensitivity and 81.82% specificity. The multimodal measures capitalize upon different features of the complex pain response. Thus, this paper presents both evidence for the utility of a weighted maximum likelihood algorithm as a novel feature selection method for EDA and video facial expression data and an accurate and objective automated classification algorithm capable ofdiscriminating clinically significant pain from clinically nonsignificant pain in children. [ABSTRACT FROM AUTHOR]

This paper proposes a semi-automatic Fontan surgery planning method for designing and manufacturing hemodynamically optimized patient-specific grafts. Fontan surgery is a palliative procedure for patients with a single ventricle heart defect by creating a new path using a vascular graft for the deoxygenated blood to be directed to the lungs, bypassing the heart. However, designing patient-specific grafts with optimized hemodynamic performance is a complex task due to the variety of patient-specific anatomies, confined surgical planning space, and the requirement of simultaneously considering multiple design criteria for vascular graft optimization. To address these challenges, we used parameterized Fontan pathways to explore patient-specific vascular graft design spaces and search for optimal solutions by formulating a nonlinear constrained optimization problem, which minimizes indexed power loss (iPL) of the Fontan model by constraining hepatic flow distribution (HFD), percentage of abnormal wall shear stress (%WSS) and geometric interference between Fontan pathways and the heart models (InDep) within clinically acceptable thresholds. Gaussian process regression was employed to build surrogate models of the hemodynamic parameters as well as InDep and $\text{N}_\text{v}$ (conduit model smoothness indicator) for optimization by pattern search. We tested the proposed method on two patient-specific models (n=2). The results showed the automatically optimized (AutoOpt) Fontan models hemodynamically outperformed or at least are comparable to manually optimized Fontan models with significantly reduced surgical planning time (15 hours versus over 2 weeks). We also demonstrated feasibility of manufacturing the AutoOpt Fontan conduits by using electrospun nanofibers. [ABSTRACT FROM AUTHOR]

This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view. Specifically, we study possible connections between several effective methods, including input-gradient regularization, Jacobian regularization, curvature regularization, and a cross-Lipschitz functional. We investigate them on DNNs with general rectified linear activations, which constitute one of the most prevalent families of models for image classification and a host of other machine learning applications. We shed light on essential ingredients of these regularizations and re-interpret their functionality. Through the lens of our study, more principled and efficient regularizations can possibly be invented in the near future. [ABSTRACT FROM AUTHOR]

Energy statistics was proposed by Székely in the 80’s inspired by Newton’s gravitational potential in classical mechanics and it provides a model-free hypothesis test for equality of distributions. In its original form, energy statistics was formulated in euclidean spaces. More recently, it was generalized to metric spaces of negative type. In this paper, we consider a formulation for the clustering problem using a weighted version of energy statistics in spaces of negative type. We show that this approach leads to a quadratically constrained quadratic program in the associated kernel space, establishing connections with graph partitioning problems and kernel methods in machine learning. To find local solutions of such an optimization problem, we propose kernel k-groups, which is an extension of Hartigan’s method to kernel spaces. Kernel k-groups is cheaper than spectral clustering and has the same computational cost as kernel k-means (which is based on Lloyd’s heuristic) but our numerical results show an improved performance, especially in higher dimensions. Moreover, we verify the efficiency of kernel k-groups in community detection in sparse stochastic block models which has fascinating applications in several areas of science. [ABSTRACT FROM AUTHOR]

Multi-view representation learning is a promising and challenging research topic, which aims to integrate multiple data information from different views to improve the learning performance. The recent deep Gaussian processes (DGPs) have the advantages of good uncertainty estimates, powerful non-linear mapping ability and great generalization capability, which can be used as an excellent data representation learning method. However, DGPs only focus on single view data and are rarely applied to the multi-view scenario. In this paper, we propose a multi-view representation learning algorithm with deep Gaussian processes (named MvDGPs), which inherits the advantages of deep Gaussian processes and multi-view representation learning, and can learn more effective representation of multi-view data. The MvDGPs consist of two stages. The first stage is multi-view data representation learning, which is mainly used to learn more comprehensive representations of multi-view data. The second stage is classifier design, which aims to select an appropriate classifier to better employ the representations obtained in the first stage. In contrast with DGPs, MvDGPs support asymmetrical modeling depths for different views of data, resulting in better characterizations of the discrepancies among different views. Experimental results on real-world multi-view data sets verify the effectiveness of the proposed algorithm, which indicates that MvDGPs can integrate the complementary information in multiple views to discover a good representation of the data. [ABSTRACT FROM AUTHOR]

The internet of satellites (IoS), containing multiple low earth orbit (LEO) satellite constellations, can support tremendous traffic, massive connectivity, and vast coverage. But it also puts forward higher demands for resource management due to the high dynamics of the IoS networks, especially in the malicious jamming environment, where the jammers launch jamming attacks to reduce the efficiency and reliability. Thus, this paper investigates the problem of resource management in malicious jamming environment for IoS, which is divided into three sub-problems: traffic prediction problem, anti-jamming decision problem and resource matching problem. To solve these problems, we proposed a distributed resource management framework (DRMF), which consists of three sub-algorithms. Firstly, the traffic prediction algorithm (TPA) is proposed to deeply mine and accurately predict the traffic rule. Meanwhile, the dynamic anti-jamming algorithm (DAA) is developed to make anti-jamming decision autonomously. Then, based on the outputs obtained by TPA and DAA, the distributed resource matching algorithm (DRMA) is proposed for IoS, and the satellites with insufficient resource can apply for assistance from neighboring satellites with excess resource, thereby improving the safety and efficiency of the entire IoS network. Finally, experiment results and algorithm analysis verify the proposed scheme has better performance than the existing algorithms. [ABSTRACT FROM AUTHOR]

The development of Autonomous Vehicles (AVs) envisions the promising technology of future Intelligent Transportation Systems (ITS). However, the complex road structures and increased vehicles cause traffic congestion and road safety, which eventually leads to horrible accidents. Cooperative driving of AVs, a groundbreaking initiative of vehicle platooning, epitomizes the next wave in vehicular technology through minimizing accident risks, transport times, costs, energy, and fuel consumption. However, the traditional machine learning-based platooning approaches fail to regulate the policy with the dynamic feature of AVs. This paper proposes a hybrid Deep Reinforcement learning and Genetic algorithm for Smart-Platooning (DRG-SP) the AVs. The leverage of the deep reinforcement learning mechanism addresses the computational complexity and accommodates the high dynamic platoon environments. Adopting the Genetic Algorithm in Deep Reinforcement learning overcomes the slow convergence problem and offers long-term performance. The simulation results reveal that the Smart-Platooning effectively forms and maintains the platoons by minimizing traffic congestion and fuel consumption. [ABSTRACT FROM AUTHOR]

Air ground integrated mobile cloud computing (MCC) provides unmanned aerial vehicles (UAVs) the capability to act as an aerial relay with more flexibility and resilience. In the cloud computing architecture, the data generated by ground users (GUs) can be offloaded to the remote server for fast processing. However, the heterogeneity of mobile tasks makes the data size distributed among GUs unbalanced. Besides, the energy efficiency of UAVs movement should be carefully considered for sustainable flight and obstacle avoidance. In general, such a joint trajectory issue can hardly be formulated as a convex optimization in unpredictable and dynamic environments. This paper proposes a potential game combined multi-agent deep deterministic policy gradient (MADDPG) approach to optimize multiple UAVs' trajectory with the consideration of GUs' offloading delay, energy efficiency as well as obstacle avoidance system. In specific, we first model the issue as a mixed integer non-linear problem (MINP), in which the service assignment between multi-user and multi-UAV is solved by potential game. The convergence to a Nash Equilibrium (NE) can be achieved by distributive service assignment update with infinite iteration. Then, we optimize the trajectory with obstacle avoidance at each UAV by MADDPG approach, which has a great advantage of centralized-training and decentralized-execution to reduce the global synchronized communication overhead. UAVs movement can be optimized in continuity rather than other deep reinforcement learning (DRL) approaches generating discrete simple actions. Experiments demonstrate the proposed game-combined learning algorithm can minimize the offloading delay, enhance UAVs’ energy efficiency and avoid the obstacles at the same time. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) as a promising technique is able to address the privacy issues in machine learning. However, due to the broadcast nature of wireless channel, one of the key challenges of FL is its vulnerability to wireless security threats. Thus, in this paper, we consider the model update security in FL. In particular, we propose to adopt a covert communication technique with which a friendly jammer transmits jamming signals to prevent a warden from detecting local model update transmissions of mobile devices in FL. The use of jamming signals reduces the transmission rate of the devices. Thus, we formulate an optimization problem that jointly determines the jamming power, local model transmission power, and local training accuracy to minimize the FL latency, given a security performance requirement. The problem is non-convex, and we propose an alternating descent algorithm to solve it. Extensive simulations are conducted and the results demonstrate the effectiveness and network performance improvement of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Battery energy storage systems (BESSs) rely on battery sensor data and communication. It is crucial to evaluate the trustworthiness of battery sensor and communication data in (BESS) since inaccurate battery data caused by sensor faults, communication failures, and even cyber-attacks can not only impose serious damages to BESSs, but also threaten the overall reliability of BESS-based applications (e.g., electric vehicles (EVs), power grids). This paper proposes a battery data trust framework that enables detect and classify false battery sensor data and communication data by using a deep learning algorithm. The proposed convolutional neural network (CNN)-based false battery data detection and classification (FBD2C) model could potentially improve safety and reliability of the BESSs. The proposed algorithm is validated by simulation and experimental results. [ABSTRACT FROM AUTHOR]

Recent advances in objective-based uncertaintyquantification (objective-UQ) have shown that such a goal-driven approach for quantifying model uncertainty is extremely usefulin real-world problems that aim at achieving specific objectives based on complex uncertain systems. Central to this objective-UQ is the concept of mean objective cost of uncertainty (MOCU), which provides effective means of quantifying the impact of uncertainty on the operational goals at hand. MOCU is especially useful for optimal experimental design (OED) as the potential efficacy of an experimental (or data acquisition) campaign can be quantified by estimating the MOCU that is expected to remain after the campaign. However, MOCU-based OED tends to be computationally expensive, which limits its practical applicability. In this paper, we propose a novel machine learning (ML) scheme that can significantly accelerate MOCU computation and expedite MOCU-based experimental design. The main idea is to use an ML model to efficiently search for the optimal robust operator under model uncertainty, a necessary step for computing MOCU. We apply the proposed ML-based OED acceleration scheme to design experiments aimed at optimally enhancing the control performance of uncertain Kuramoto oscillator models. Our results show that the proposed scheme results in up to ${154}$ -fold speed improvement without any degradation of the OED performance. [ABSTRACT FROM AUTHOR]

As a new member of convex universal learning machines (CULMs), an augmented space linear model (ASLM) demonstrates strong learning and tracking capabilities in the fields of signal process and machine learning. Unfortunately, the ASLM is only suitable for offline learning, and its estimated accuracy and noise immunity highly depend on the estimated error learned from a generated error table. To address these two issues and apply ASLM into adaptive filtering, online ASLM algorithms with a weighted $k$ nearest neighbor ($k$ -NN) method, based on an updated orthogonal error table, are therefore proposed in this paper. To further improve the robustness of ASLM to heavy-tail noises, a robust ASLM (RASLM) algorithm is proposed with the help of kernel function, and thus a novel robust adaptive filtering algorithm named maximum correntropy criterion RASLM (MCC-RASLM) is developed based the maximum correntropy criterion. However, the linear growth error table existing in MCC-RASLM incurs an ever-growing computational burden. Therefore, to reduce the computational complexity of MCC-RASLM, another novel online variable-centroid clustering is proposed to generate a maximum correntropy criterion cluster RASLM (MCC-C-RASLM) algorithm. Finally, the theoretical analyses regarding robustness and the error bound of RASLM with weighted $k$ -NN regression are performed to verify the effectiveness of MCC-RASLM. Simulation results based on synthetic and real-world data validate the superiorities of the proposed algorithms from aspects of filtering accuracy and robustness. [ABSTRACT FROM AUTHOR]

Accurate and reliable segmentation of colorectal tumors and surrounding colorectal tissues on 3D magnetic resonance images has critical importance in preoperative prediction, staging, and radiotherapy. Previous works simply combine multilevel features without aggregating representative semantic information and without compensating for the loss of spatial information caused by down-sampling. Therefore, they are vulnerable to noise from complex backgrounds and suffer from misclassification and target incompleteness-related failures. In this paper, we address these limitations with a novel adaptive lesion-aware attention network (ALA-Net) which explicitly integrates useful contextual information with spatial details and captures richer feature dependencies based on 3D attention mechanisms. The model comprises two parallel encoding paths. One of these is designed to explore global contextual features and enlarge the receptive field using a recurrent strategy. The other captures sharper object boundaries and the details of small objects that are lost in repeated down-sampling layers. Our lesion-aware attention module adaptively captures long-range semantic dependencies and highlights the most discriminative features, improving semantic consistency and completeness. Furthermore, we introduce a prediction aggregation module to combine multiscale feature maps and to further filter out irrelevant information for precise voxel-wise prediction. Experimental results show that ALA-Net outperforms state-of-the-art methods and inherently generalizes well to other 3D medical images segmentation tasks, providing multiple benefits in terms of target completeness, reduction of false positives, and accurate detection of ambiguous lesion regions. [ABSTRACT FROM AUTHOR]

The growing concern over catastrophic weather events, mostly as a direct result of climate changes, has underscored the need for expanding traditional power system contingency analyses to handle the associated risks of extreme power outages. To enable power system operators to make timely decisions when facing extreme events, we explore in this paper the viability of a classifier which uses the machine learning approach based on the Bayes decision theory as a means of predicting power system component outages. However, owing to an excessively imbalanced and largely sparse power component outage datasets, the corresponding classifier learning is a challenging problem in the data mining community. In the proposed approach, we apply a resampling method to overcome the class imbalance problem. The proposed classifier provides an effective framework that not only minimizes outage prediction errors for power system components, but also considers the cost of each preventive action according to its implication in extreme events. The outcome of the proposed model can be used for introducing operation-oriented preventive measures that allow the rescheduling of generation resources for maximizing the power system resilience. The performance of the proposed classifier is examined through numerical simulations by utilizing the confusion matrix. [ABSTRACT FROM AUTHOR]

Stochastic unit commitment is an efficient method for grid operation in the presence of significant uncertainties. An example is an operation during a predicted hurricane with uncertain line out-ages. However, the solution quality comes at the cost of substantial computational burden, which makes its adoption challenging. This paper evaluates some possible ways that machine learning can be used to reduce this computational burden. First, a set of feasibility studies is conducted. Results suggest that using machine learning as an assistant to the stochastic unit commitment solver is more advantageous than using it as a standalone solver. In particular, the machine learning model is trained to facilitate solving the problem by determining the unnecessary constraints that can be removed from the original problem without affecting the final accuracy. The variables that can be used as input features/predictors or outputs for the machine learning model are determined through feasibility studies. Then, an algorithm to train and utilize a machine learning model is proposed. The method is tested on a 500-bus synthetic South Carolina system. Various test cases show an average reduction in solution time by more than 90% by using the trained machine learning model to assist the stochastic unit commitment solver. [ABSTRACT FROM AUTHOR]

Deep multi-view clustering utilizes neural networks to extract the potential peculiarities of complementarity and consistency information among multi-view features. This can obtain a consistent representation that improves clustering performance. Although a multitude of deep multi-view clustering approaches have been proposed, most lack theoretic interpretability while maintaining the advantages of good performance. In this paper, we propose an effective differentiable network with alternating iterative optimization for multi-view co-clustering termed differentiable bi-sparse multi-view co-clustering (DBMC) and an extension named elevated DBMC (EDBMC). The proposed methods are transformed into equivalent deep networks based on the constructed objective loss functions. They have the advantages of strong interpretability of the classical machine learning methods and the superior performance of deep networks. Moreover, DBMC and EDBMC can learn a joint and consistent collaborative representation from multi-source features and guarantee sparsity between multi-view feature space and single-view sample space. Meanwhile, they can be converted into deep differentiable network frameworks with block-wise iterative training. Correspondingly, we design two three-step iterative differentiable networks to resolve resultant optimization problems with theoretically guaranteed convergence. Extensive experiments on six multi-view benchmark datasets demonstrate that the proposed frameworks outperform other state-of-the-art multi-view clustering methods. [ABSTRACT FROM AUTHOR]

This paper targets developing algorithms for solving distributed learning problems in a communication-efficient fashion, by generalizing the recent method of lazily aggregated gradient (LAG) to deal with stochastic gradient — justifying the name of the new method LASG. While LAG is effective at reducing communication without sacrificing the rate of convergence, we show it only works with deterministic gradients. We introduce new rules and analysis for LASG that are tailored for stochastic gradients, so it effectively saves downloads, uploads, or both for distributed stochastic gradient descent. LASG achieves impressive empirical performance — it typically saves total communication by an order of magnitude. LASG can be used together with gradient quantization to bring more savings. [ABSTRACT FROM AUTHOR]

We consider the problem of minimizing the $\ell _1$ norm of a linear map over the sphere, which arises in various machine learning applications such as orthogonal dictionary learning (ODL) and robust subspace recovery (RSR). The problem is numerically challenging due to its nonsmooth objective and nonconvex constraint, and its algorithmic aspects have not been well explored. In this paper, we show how the manifold structure of the sphere can be exploited to design fast algorithms with provable guarantees for tackling this problem. Specifically, our contribution is fourfold. First, we present a manifold proximal point algorithm (ManPPA) for the problem and show that it converges at a global sublinear rate. Furthermore, we show that ManPPA can achieve a local quadratic convergence rate when applied to sharp instances of the problem. Second, we develop a semismooth Newton-based inexact augmented Lagrangian method for computing the search direction in each iteration of ManPPA and show that it has an asymptotic superlinear convergence rate. Third, we propose a stochastic variant of ManPPA called StManPPA, which is well suited for large-scale computation, and establish its sublinear convergence rate. Both ManPPA and StManPPA have provably faster convergence rates than existing subgradient-type methods. Fourth, using ManPPA as a building block, we propose a new heuristic method for solving a matrix analog of the problem, in which the sphere is replaced by the Stiefel manifold. The results from our extensive numerical experiments on the ODL and RSR problems demonstrate the efficiency and efficacy of our proposed methods. [ABSTRACT FROM AUTHOR]

The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation. The early single-image deraining methods employ a cost function, where various priors are developed to represent the properties of rain and background layers. Since 2017, single-image deraining methods step into a deep-learning era, and exploit various types of networks, i.e., convolutional neural networks, recurrent neural networks, generative adversarial networks, etc., demonstrating impressive performance. Given the current rapid development, in this paper, we provide a comprehensive survey of deraining methods over the last decade. We summarize the rain appearance models, and discuss two categories of deraining approaches: model-based and data-driven approaches. For the former, we organize the literature based on their basic models and priors. For the latter, we discuss the developed ideas related to architectures, constraints, loss functions, and training datasets. We present milestones of single-image deraining methods, review a broad selection of previous works in different categories, and provide insights on the historical development route from the model-based to data-driven methods. We also summarize performance comparisons quantitatively and qualitatively. Beyond discussing the technicality of deraining methods, we also discuss the future possible directions. [ABSTRACT FROM AUTHOR]

Principal component analysis (PCA) and Kernel principal component analysis (KPCA) are fundamental methods in machine learning for dimensionality reduction. The former is a technique for finding this approximation in finite dimensions and the latter is often in an infinite dimensional reproducing Kernel Hilbert-space (RKHS). In this paper, we present a geometric framework for computing the principal linear subspaces in both (finite and infinite) situations as well as for the robust PCA case, that amounts to computing the intrinsic average on the space of all subspaces: the Grassmann manifold. Points on this manifold are defined as the subspaces spanned by $K$ K -tuples of observations. The intrinsic Grassmann average of these subspaces are shown to coincide with the principal components of the observations when they are drawn from a Gaussian distribution. We show similar results in the RKHS case and provide an efficient algorithm for computing the projection onto the this average subspace. The result is a method akin to KPCA which is substantially faster. Further, we present a novel online version of the KPCA using our geometric framework. Competitive performance of all our algorithms are demonstrated on a variety of real and synthetic data sets. [ABSTRACT FROM AUTHOR]

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the average-precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly. For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. We provide in-depth analyses on the good convergence property and computational complexity of the proposed algorithm, both theoretically and empirically. Experimental results demonstrate notable improvement in addressing the imbalance issue in object detection over existing AP-based optimization algorithms. An improved state-of-the-art performance is achieved in one-stage detectors based on AP-loss over detectors using classification-losses on various standard benchmarks. The proposed framework is also highly versatile in accommodating different network architectures. Code is available at https://github.com/cccorn/AP-loss. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel unified framework to protect multi-function wireless systems from jamming attacks. Examples of such multi-function system include joint radar and communication (JRC) systems and simultaneous wireless information and power transfer (SWIPT) systems. By abstracting the system functionalities as a joint optimization problem of multiple queues, we achieve effective resistance against jammers for the multi-functions simultaneously. We incorporate different anti-jamming techniques into one framework. Deception mechanism is adopted to lure the jammer to attack and make its actions more predictable, and ambient backscatter technology is used to leverage the jamming signals. Since conventional Markov decision process (MDP) has only one decision epoch at every time slot, it cannot be used to model the deception strategy which needs two decision epochs to leverage the jamming signals. We therefore formulate the problem using an advanced two-step MDP. After that, a deep reinforcement learning algorithm with a prioritized double deep Q-Learning architecture is proposed to learn optimal strategies in different system states. We show that by jointly considering the multi-functions of the system with potential jamming attacks during design phase, significant improvement can be achieved for both of the system functionalities. [ABSTRACT FROM AUTHOR]

Predicting the future trajectories of surrounding agents has become an crucial problem to be solved for the safety of autonomous vehicles. Recent studies based on Long Short Term Memory (LSTM) networks have shown powerful abilities to model social interactions. However, many of these approaches focus on spatial interactions of the neighborhood agents but ignore temporal interactions that accompany spatial interactions. In this paper, we propose a Hierarchical Spatio-Temporal Attention architecture (HSTA), which activates the utilization of spatial interactions with different weights, and jointly considers the temporal interactions across time steps of all agents. More specially, the graph attention mechanism (GAT) is presented to capture spatial interactions, the multi-head attention mechanism (MHA) is conducted to encode temporal correlations of interactions and a state gated fusion (SGF) layer is used to integrate spatial and temporal interactions. We evaluate our proposed method against baselines on both pedestrian and vehicle datasets. The results show that our model is effective and achieves state-of-the-art achievements. [ABSTRACT FROM AUTHOR]

Radar radio source (RRS) recognition plays an important role in the fields of military electronic support systems (ESM) and civilian autonomous driving. The rapid development of machine learning technology, especially deep learning, has effectively and efficiently improved RRS intelligent recognition performances when operating in the increasingly complex electromagnetic environment. However, the data sampling limitation and computation cost are still severe challenges in real RRS recognition scenarios. In this paper, we propose a novel network based on meta-transfer learning, called RRSARNet, to achieve effective adaptive RRS recognition in the context of low signal-to-noise ratio (SNR). First, by using the short-time Fourier transform, a six-type small samples RRS simulation dataset with different SNR levels is constructed. Then, a novel RRSARNet, based on metric learning, is proposed, which consists of a four-layer embedding module and a four-layer relational module. Finally, the RRS dataset is divided into training, supporting and testing subsets, which are used to train and test the RRSARNet in a meta-transfer learning method. Experiments on the RRS dataset show that the proposed RRSARNet can achieve an overall accuracy (OA) above 96% and 99% when the SNR is above −15 dB and −10 dB, respectively. Even when the SNR is -30 dB, OA can reach more than 70%. For 5-way 1-shot and 5-way 5-shot experiments, the inference time of an image is about 0.043 and 0.140 milliseconds, respectively. Besides, experiments on the RRS simulation dataset and the two benchmark datasets, the RRSARNet performs better or more competitive than many existing state-of-the-art technologies in terms of recognition accuracy. [ABSTRACT FROM AUTHOR]

Knowledge bases are critical to many applications. However, they are greatly incomplete. Enriching knowledge bases with new entities and new location attributes becomes increasingly important. Given a named entity with tweets and Web documents where the entity appears, we aim to predict the entity city-level location combining the geographical location knowledge embedded in both Twitter and Web. This task is helpful for knowledge base enrichment and tweet location prediction. In this paper we propose NELPTW, the first unsupervised framework for Named Entity Location Prediction by leveraging the knowledge from Twitter and Web. Based on each data source, NELPTW utilizes a linear function ranking model to generate several rankings to the candidate location set for each entity. To combine the knowledge from two sources which have different reliability and importance for the location prediction, an unsupervised rank aggregation algorithm is developed to aggregate multiple rankings for each entity to obtain a better ranking. A learning algorithm based on the EM method is proposed to automatically learn the parameters of the ranking model without requiring any training labels. The experimental results over a real world Twitter and Web data set show that our framework significantly outperforms the baselines in terms of accuracy. [ABSTRACT FROM AUTHOR]

In this paper, a novel Deep Multi-view Joint Clustering (DMJC) framework is proposed, where multiple deep embedded features, multi-view fusion mechanism, and clustering assignments can be learned simultaneously. Through the joint learning strategy, the clustering-friendly multi-view features and useful multi-view complementary information can be exploited effectively to improve the clustering performance. Under the proposed joint learning framework, we design two ingenious variants of deep multi-view joint clustering models, whose multi-view fusion is implemented by two kinds of simple yet effective schemes. The first model, called DMJC-S, performs multi-view fusion in an implicit way via a novel multi-view soft assignment distribution. The second model, termed DMJC-T, defines a novel multi-view auxiliary target distribution to conduct the multi-view fusion explicitly. Both DMJC-S and DMJC-T are optimized under a KL divergence objective. Experiments on eight challenging image datasets demonstrate the superiority of both DMJC-S and DMJC-T over single/multi-view baselines and the state-of-the-art multi-view clustering methods, which proves the effectiveness of the proposed DMJC framework. To the best of our knowledge, this is the first work to model the multi-view clustering in a deep joint framework, which will provide a meaningful thinking in unsupervised multi-view learning. [ABSTRACT FROM AUTHOR]

It is a very well-known fact, that the high complexity of the High Efficiency Video Coding standard (HEVC) is the main hurdle for its wide deployment and use. To tackle this problem, a number of recent research outcomes exploit heuristic algorithms and machine learning, including deep learning, to reduce the coding complexity. However, in most cases, each encoder module, i.e., encoding process, is first accelerated individually, and then different acceleration algorithms are manually combined. Without a holistic strategy, the acceleration potential of multi-module combination is not exploited and the Rate-Distortion (RD) loss is generally not well controlled. To tackle these shortcomings, this paper exploits the acceleration properties of different modules, i.e., the numerical representation of potential time saving and possible RD loss, from which a heuristic model is explored. Then a Heuristic Model Oriented Framework (HMOF) is proposed which adapts the properties of modules to underlying acceleration algorithms. In the framework, two advanced acceleration algorithms, including Border Considered CNN (BC-CNN)-based Coding Unit (CU) partition and Naive Bayes-based Prediction Unit (PU) partition, are proposed for the CU and PU modules, respectively. Further, by leveraging the heuristic model as the guidance to combine the proposed acceleration algorithms, HMOF is globally optimized, where different time saving budgets are wisely allocated to different modules and a theoretically minimal RD loss is achieved. According to the experimental results, through fusing a suitable deep learning technique and a Bayes-Based prediction, the proposed acceleration framework HMOF enable multiple acceleration choices. Here the proposed joint optimization strategy help to make a choice leading to the best cost-performance. Furthermore, within the proposed framework, intra coding time can be precisely controlled with negligible Bjøntegaard delta bit-rate (BDBR) loss. In this context, as a complexity control method, HMOF outperforms the state-of-the-art complexity reduction algorithms under a similar complexity reduction ratio. These results partially demonstrate the superiority of the proposed technique. [ABSTRACT FROM AUTHOR]

Few-shot learning has recently generated increasing popularity in machine learning, which addresses the fundamental yet challenging problem of learning to adapt to new tasks with the limited data. In this paper, we propose a new probabilistic framework that learns to fast adapt with external memory. We model the classifier parameters as distributions that are inferred from the support set and directly applied to the query set for prediction. The model is optimized by formulating as a variational inference problem. The probabilistic modeling enables better handling prediction uncertainty due to the limited data. We impose a discriminative constraint on the feature representations by exploring the class structure, which can improve the classification performance. We further introduce a memory unit to store task-specific information extracted from the support set and used for the query set to achieve explicit adaption to individual tasks. By episodic training, the model learns to acquire the capability of adapting to specific tasks, which guarantees its performance on new related tasks. We conduct extensive experiments on widely-used benchmarks for few-shot recognition. Our method achieves new state-of-the-art performance and largely surpassing previous methods by large margins. The ablation study further demonstrates the effectiveness of the proposed discriminative learning and memory unit. [ABSTRACT FROM AUTHOR]

As a follow-up to the first IEEE Transactions on Medical Imaging (TMI) special issue on the theme of deep tomographic reconstruction, the second special issue is assembled to reflect the status and momentum of this rapidly emerging field. In this editorial, we provide a brief background illustrating the motivation for the development of network-based, data-driven, and learning-oriented reconstruction methods, summarize the included papers, and report our verification of the shared deep learning codes. Finally, we discuss several important research topics to facilitate further investigation and collaboration. [ABSTRACT FROM AUTHOR]

In this paper, we propose a channel-wise interaction based binary convolutional neural networks (CI-BCNN) approach for efficient inference. Conventional binary convolutional neural networks usually apply the xnor and bitcount operations in the binary convolution with notable quantization errors, which obtain opposite signs of pixels in binary feature maps compared to their full-precision counterparts and lead to significant information loss. In our proposed CI-BCNN method, we exploit the channel-wise interactions with the prior knowledge which aims to alleviate inconsistency of signs in binary feature maps and preserves the information of input samples during inference. Specifically, we mine the channel-wise interactions by using a reinforcement learning model, and impose channel-wise priors on the intermediate feature maps to correct inconsistent signs through the interacted bitcount. Since CI-BCNN mines the channel-wise interactions in a large search space where each channel may correlate with others, the search deficiency caused by sparse interactions obstacles the agent to obtain the optimal policy. To address this, we further present a hierarchical channel-wise interaction based binary convolutional neural networks (HCI-BCNN) method to shrink the search space via hierarchical reinforcement learning. Moreover, we propose a denoising interacted bitcount operation in binary convolution by smoothing the channel-wise interactions, so that noise in channel-wise priors can be alleviated. Extensive experimental results on the CIFAR-10 and ImageNet datasets demonstrate the effectiveness of the proposed CI-BCNN and HCI-BCNN. [ABSTRACT FROM AUTHOR]

Partial multi-label learning (PML) deals with the problem where each training example is associated with an overcomplete set of candidate labels, among which only some candidate labels are valid. The task of PML naturally arises in learning scenarios with inaccurate supervision, and the goal is to induce a multi-label predictor which can assign a set of proper labels for unseen instance. The PML training procedure is prone to be misled by false positive labels concealed in the candidate label set, which serves as the major modeling difficulty for partial multi-label learning. In this paper, a novel two-stage PML approach is proposed which works by eliciting credible labels from the candidate label set for model induction. In the first stage, the labeling confidence of candidate label for each PML training example is estimated via iterative label propagation. In the second stage, by utilizing credible labels with high labeling confidence, multi-label predictor is induced via pairwise label ranking coupled with virtual label splitting or maximum a posteriori (MAP) reasoning. Experimental studies show that the proposed approach can achieve highly competitive generalization performance by excluding most false positive labels from the training procedure via credible label elicitation. [ABSTRACT FROM AUTHOR]

In this paper, we devise a highly efficient machine learning-based channel estimation for orthogonal frequency division multiplexing (OFDM) systems, in which the training of the estimator is performed online. A simple learning module is employed for the proposed learning-based estimator. The training process is thus much faster and the required training data is reduced significantly. Besides, a training data construction approach utilizing least square (LS) estimation results is proposed so that the training data can be collected during the data transmission. The feasibility of this novel construction approach is verified by theoretical analysis and simulations. Based on this construction approach, two alternative training data generation schemes are proposed. One scheme transmits additional block pilot symbols to create training data, while the other scheme adopts a decision-directed method and does not require extra pilot overhead. Simulation results show the robustness of the proposed channel estimation method. Furthermore, the proposed method shows better adaptation to practical imperfections compared with the conventional minimum mean-square error (MMSE) channel estimation. It outperforms the existing machine learning-based channel estimation techniques under varying channel conditions. [ABSTRACT FROM AUTHOR]

Millimeter wave (mmwave) communications, envisaged for the next generation wireless networks, rely on large antenna arrays and very narrow, high-gain beams. This poses significant challenges to beam alignment between transmitter and receiver, which has attracted considerable research attention. Even when alignment is achieved, the link is subject to beam drift (BD). BD, caused by non-ideal features inherent in practical beams and rapidly changing environments, is referred to as the phenomenon that the center of main-lobe of the used beam deviates from the real dominant channel direction, which further deteriorates the system’s performance. To mitigate the BD effect, in this paper we first theoretically analyze the BD effect on the performance of outage probability as well as effective achievable rate, which takes practical factors (e.g., the rate of change of the environment, beam width, transmit power) into account. Then, different from conventional practice, we propose a novel design philosophy where multi-resolution beams with varying beam widths are used for data transmission while narrow beams are employed for beam training. Finally, we design an efficient learning based algorithm which can adaptively choose an appropriate beam width according to the environment. Simulation results demonstrate the effectiveness and superiority of our proposals. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the detection problem for a massive machine-type communication (mMTC) system that has correlated user activities. Two deep learning assisted algorithms are proposed to exploit the user activity correlation to facilitate channel estimation and user identification. Due to the dependency among user activities, conventional element-wise minimum mean square error (MMSE) denoiser used in the orthogonal approximate message passing (OAMP) algorithm cannot achieve satisfying performance during the two-step iterative process. Therefore, we propose a deep learning modified OAMP (DL-mOAMP) algorithm, which iteratively modifies the user activity ratio via exploiting the user activity correlation in the MMSE denoiser based on the estimated sequence during each OAMP iteration. Moreover, given a specific false alarm probability, a constant threshold employed in the conventional user identification is not optimal in the presence of user activity correlation. Thus, we propose a neural network framework that is dedicated to the user identification (DL-mOAMP-UI algorithm), which minimizes the missed detection probability under a pre-determined false alarm probability. Numerical results show that the proposed DL-mOAMP algorithm provides a substantial mean squared error performance gain compared to the conventional OAMP algorithm and the DL-mOAMP-UI algorithm can further improve the user identification accuracy of an mMTC system. [ABSTRACT FROM AUTHOR]

In this paper, we first derive the channel capacity of the full-duplex spatial modulation (FD-SM) system and its upper and lower bounds. Furthermore, different from the traditional optimization-driven decision, we use the data-driven prediction method to solve the transmit antenna selection (TAS) problem in the FD-SM system. Specifically, two novel TAS methods based on the support vector machine (SVM) and deep neural network (DNN) are proposed for reducing the effect of residual self-interference (RSI) on the FD-SM system performance. In our design, we propose a novel feature extraction method based on the principal component analysis (PCA) to help the proposed classifiers improve training. Our simulation results show that our data-driven TAS schemes can approach the optimal performance achieved by exhaustive search while significantly reducing complexity. [ABSTRACT FROM AUTHOR]