Search

The traditional method for transformer moisture diagnosis is to establish empirical equations between feature parameters extracted from frequency domain spectroscopy (FDS) and the transformer’s moisture content. However, the established empirical equation may not be applicable to a novel testing environment, resulting in an unreliable evaluation result. In this regard, it is acknowledged that FDS combined with machine learning is more suitable for estimating moisture content in a variety of test environments. Nonetheless, the accuracy of the estimation results obtained using the existing method is limited by the algorithm’s inability to generalize. To address this issue, we propose an AdaBoost algorithm-enhanced back-propagation neural network (BP_AdaBoost). This study creates a database by extracting feature parameters from the FDS that characterize the insulation states of the prepared samples. Then, using the BP_AdaBoost algorithm and the newly constructed database, the moisture estimation models are trained. Finally, the results of the estimation are discussed in terms of laboratory and field transformers. By comparing the proposed BP_AdaBoost algorithm to other intelligence algorithms, it is demonstrated that it not only performs better in generalization, but also maintains a high level of accuracy. [ABSTRACT FROM AUTHOR]

This paper presents a distributionally robust network-constrained unit commitment (DR-NCUC) model considering AC network modeling and uncertainties of demands and renewable productions. The proposed model characterizes uncertain parameters using a data-driven ambiguity set constructed by training samples. The non-convex AC power flow equations are approximated by convex quadratic and McCormick relaxations. Since the proposed min-max-min DR-NCUC problem cannot be solved directly by available solvers, a new decomposition algorithm with proof of convergence is reported in this paper. The master problem of this algorithm is solved using both primal and dual cuts, while the max-min sub-problem is solved using the primal-dual hybrid gradient method, obviating the need for using duality theory. Also, an active set strategy is proposed to enhance the tractability of the decomposition algorithm by ignoring the subset of inactive constraints. The proposed model is applied to a 6-bus test system and the IEEE 118-bus test system under different conditions. These case studies illustrate the performance of the proposed DR-NCUC model to characterize uncertainties and the superiority of the proposed decomposition algorithm over other decomposition approaches using either primal or dual cuts. [ABSTRACT FROM AUTHOR]

As an emulous alternative to deep neural networks, Deep Forest emerges with features like low complexity, fewer hyper-parameters, and good robustness, which are predominantly desired in distributed computing applications and ecosystems. Recently, an efficient distributed Deep Forest system, named ForestLayer, was proposed, designing a fine-grained sub-Forest-based task-parallel algorithm to improve the parallel computing efficiency of Deep Forest. However, the sub-Forest splitting of ForestLayer is static and one-off without adaptability to the computing environment, nevertheless, the size of splitting granularity has a significant impact on the system performance. To further improve the computing efficiency and scalability of the distributed Deep Forest, in this paper, we propose a novel distributed Deep Forest algorithm, named BLB-gcForest (Bag of Little Bootstraps-gcForest), which augments the gcForest (multi-Grained Cascade Forest) approach for constructing Deep Forest. BLB-gcForest carries out parallel computation for each tree in sub-Forests at a finer parallel granularity and integrates with the Bag of Little Bootstraps (BLB) mechanism to reduce massive transmitted feature instances for Cascade Forest Layers, utterly improving both computation efficiency and communication efficiency. Moreover, to solve the problem of the forest splitting granularity, we further design an adaptive sub-Forest splitting algorithm to ensure the maximum resource utilization for parallel computation of each sub-Forest. Experimental results on four well-known large-scale datasets, namely YEAST, LETTER, MNIST, CIFAR10, show that the training efficiency of BLB-gcForest achieves up to 20.3x and 1.64x speedups compared with the state-of-the-art gcForest and ForestLayer, respectively while guaranteeing higher accuracy and better robustness [ABSTRACT FROM AUTHOR]

For vehicle-to-network communications, handover (HO) management enables vehicles to maintain the connection with the network while transiting through coverage areas of different base stations (BSs). However, the high mobility of vehicles means shorter connection periods with each BS that leads to frequent HOs, hence raises the necessity for optimal HO decision making for high quality infotainment services. Machine learning is capable of capturing underlying pattern via data driven methods to find optimal solutions to complex problems, and much learning-based HO optimization research has been conducted focusing on specific network setups. However, attention still needs to be paid to the actual deployment aspect and standardized datasets or simulation environments for evaluation. This paper proposes a deep reinforcement learning-based HO algorithm using the input parameters that are configurable in the existing measurement report of cellular networks. The performance of the proposed algorithm is evaluated using the well-known network simulator ns-3 with its official LTE module. A realistic network setup in the city center of Glasgow (U.K.) is configured with vehicle trajectories generated by the routes mobility model using Google Maps Directions API. Evaluation results reveal that the proposed algorithm significantly outperforms the A3 RSRP baseline with an average of 25.72% packet loss reduction per HO, suggesting significant improvement in quality of service of phone call and video streaming, etc. The proposed algorithm also has a small implementation cost compared to some state-of-the-art and should be deployed by a software update to a local BS controller. [ABSTRACT FROM AUTHOR]

In this paper, we study the formalism of unsupervised multi-class domain adaptation (multi-class UDA), which underlies a few recent algorithms whose learning objectives are only motivated empirically. Multi-Class Scoring Disagreement (MCSD) divergence is presented by aggregating the absolute margin violations in multi-class classification, and this proposed MCSD is able to fully characterize the relations between any pair of multi-class scoring hypotheses. By using MCSD as a measure of domain distance, we develop a new domain adaptation bound for multi-class UDA; its data-dependent, probably approximately correct bound is also developed that naturally suggests adversarial learning objectives to align conditional feature distributions across source and target domains. Consequently, an algorithmic framework of Multi-class Domain-adversarial learning Networks (McDalNets) is developed, and its different instantiations via surrogate learning objectives either coincide with or resemble a few recently popular methods, thus (partially) underscoring their practical effectiveness. Based on our identical theory for multi-class UDA, we also introduce a new algorithm of Domain-Symmetric Networks (SymmNets), which is featured by a novel adversarial strategy of domain confusion and discrimination. SymmNets affords simple extensions that work equally well under the problem settings of either closed set, partial, or open set UDA. We conduct careful empirical studies to compare different algorithms of McDalNets and our newly introduced SymmNets. Experiments verify our theoretical analysis and show the efficacy of our proposed SymmNets. In addition, we have made our implementation code publicly available. [ABSTRACT FROM AUTHOR]

This paper proposes an online multi-camera multi-object tracker that only requires monocular detector training, independent of the multi-camera configurations, allowing seamless extension/deletion of cameras without retraining effort. The proposed algorithm has a linear complexity in the total number of detections across the cameras, and hence scales gracefully with the number of cameras. It operates in the 3D world frame, and provides 3D trajectory estimates of the objects. The key innovation is a high fidelity yet tractable 3D occlusion model, amenable to optimal Bayesian multi-view multi-object filtering, which seamlessly integrates, into a single Bayesian recursion, the sub-tasks of track management, state estimation, clutter rejection, and occlusion/misdetection handling. The proposed algorithm is evaluated on the latest WILDTRACKS dataset, and demonstrated to work in very crowded scenes on a new dataset. [ABSTRACT FROM AUTHOR]

Edge federated learning (FL) is an emerging paradigm that trains a global parametric model from distributed datasets based on wireless communications. This paper proposes a unit-modulus over-the-air computation (UMAirComp) framework to facilitate efficient edge federated learning, which simultaneously uploads local model parameters and updates global model parameters via analog beamforming. The proposed framework avoids sophisticated baseband signal processing, leading to low communication delays and implementation costs. Training loss bounds of UMAirComp FL systems are derived and two low-complexity large-scale optimization algorithms, termed penalty alternating minimization (PAM) and accelerated gradient projection (AGP), are proposed to minimize the nonconvex nonsmooth loss bound. Simulation results show that the proposed UMAirComp framework with PAM algorithm achieves a smaller mean square error of model parameters’ estimation, training loss, and test error compared with other benchmark schemes. Moreover, the proposed UMAirComp framework with AGP algorithm achieves satisfactory performance while reduces the computational complexity by orders of magnitude compared with existing optimization algorithms. Finally, we demonstrate the implementation of UMAirComp in a vehicle-to-everything autonomous driving simulation platform. It is found that autonomous driving tasks are more sensitive to model parameter errors than other tasks since the neural networks for autonomous driving contain sparser model parameters. [ABSTRACT FROM AUTHOR]

When imaging through a semi-reflective medium such as glass, the reflection of another scene can often be found in the captured images. It degrades the quality of the images and affects their subsequent analyses. In this paper, a novel deep neural network approach for solving the reflection problem in imaging is presented. Traditional reflection removal methods not only require long computation time for solving different optimization functions, their performance is also not guaranteed. As array cameras are readily available in nowadays imaging devices, we first suggest in this paper a multiple-image based depth estimation method using a convolutional neural network (CNN). The proposed network avoids the depth ambiguity problem due to the reflection in the image, and directly estimates the depths along the image edges. They are then used to classify the edges as belonging to the background or reflection. Since edges having similar depth values are error prone in the classification, they are removed from the reflection removal process. We suggest a generative adversarial network (GAN) to regenerate the removed background edges. Finally, the estimated background edge map is fed to another auto-encoder network to assist the extraction of the background from the original image. Experimental results show that the proposed reflection removal algorithm achieves superior performance both quantitatively and qualitatively as compared to the state-of-the-art methods. The proposed algorithm also shows much faster speed compared to the existing approaches using the traditional optimization methods. [ABSTRACT FROM AUTHOR]

Dictionary learning has achieved remarkable success on a wide range of machine learning-based applications. In this paper, a locality-adaptive structured dictionary learning (LASDL) algorithm for cross-domain recognition is proposed. In the LASDL, a projective structured double reconstruction strategy is developed to train class-oriented sub-dictionaries from the specific classes of cross-domain samples. The strategy benefits to make full advantage of the discriminative information of cross-domain data and bridge the distribution divergence between two different domains. Meanwhile, an adaptive geometrical structure preserving function is designed to not only preserve the local manifold structures spanned by the representation coefficient spaces of the source and target domains, but also impose a constraint that the coefficients should keep closer to their class centers, which is propitious to reduce the distribution divergence and make the representation more accurate. With the structured linear coding technique, the final cross-domain recognition can be efficiently performed by determining class-specific reconstruction error. The optimization of the proposed LASDL model can be efficiently solved by simple least square method and alternating direction method of multipliers (ADMM) algorithm. Extensive experimental results validate the superiority of the proposed algorithm in contrast to other state-of-the-art predecessors. [ABSTRACT FROM AUTHOR]

Craters are among the most abundant features on the surface of many planets with great importance for planetary scientists. They reveal chronology information about planets and may be used for autonomous spacecraft navigation and landing. Although numerous research efforts have been carried out in the field of crater detection, existing crater detection algorithms (CDAs) are only helpful in a limited number of applications. A promising crater detection approach involves two main steps: 1) hypothesis generation (HG) and 2) hypothesis verification (HV). During HG, potential crater locations are detected. The validity of the hypothesized crater locations is then tested in a HV step. In this context, we discuss some commonly used algorithms for HG such as highlight-shadow region detection and Hough transform as well as our novel and enhanced algorithms based on interest point detection and convex grouping. A key objective of this paper is to analyze their performance while paying special attention to how they affect the accuracy of the verification step. To deal with different size craters, we focus on multiscale HG. For HV, we have chosen convolutional neural networks which have recently achieved state-of-the-art performance in many computer vision applications. Due to the variation of test sets in the literature, it is often challenging to compare the performance of different CDAs in a fair way. In this paper, we present a comprehensive performance evaluation and comparison of CDAs. Each algorithm has been trained/tested using common data sets generated by a systematic approach. [ABSTRACT FROM AUTHOR]

In this paper, we propose three new compressive sensing-based algorithms for channel estimation in millimeter wave hybrid MIMO systems over doubly (time and frequency) selective channels. Utilizing the basis expansion model (BEM) for effectively representing doubly selective channels, we first propose a BEM-based block orthogonal matching pursuit (BBOMP) algorithm, which can work with any training sequence structure. Next, we present the second algorithm to reduce the complexity of the BBOMP method by employing a special training sequence which results in a computationally efficient block sparse sensing matrix. Finally, in order to further decrease the computational complexity, we propose the third algorithm, where the channel estimation is split into two separate steps of tap detection and gain estimation. The proposed algorithms exploit the entire available training sequence to estimate all channel parameters, and can capture channel variations across the entire training frames without requiring a feedback channel. The Cramer-Rao lower bound and the computational complexity of the proposed algorithms are also addressed. Intensive computer simulations are conducted to evaluate the accuracy of the proposed approaches, showing that they can significantly improve the mean squared error performance compared with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

A large-scale deployment of phasor measurement units (PMUs) that reveal the inherent physical laws of power systems from a data perspective enables an enhanced awareness of power system operation. However, the high-granularity and non-stationary nature of PMU data and imperfect data quality could bring great technical challenges for real-time system event identification. To address these challenges, this paper proposes a two-stage learning-based framework. In the first stage, a Markov transition field (MTF) algorithm is exploited to extract the latent data features by encoding temporal dependency and transition statistics of PMU data in graphs. Then, a spatial pyramid pooling (SPP)-aided convolutional neural network (CNN) is established to efficiently and accurately identify power events. The proposed method fully builds on and is also tested on a large real-world dataset from several tens of PMU sources (and the corresponding event logs), located across the U.S., with a time span of two consecutive years. The numerical results validate that our method has high identification accuracy while showing good robustness against poor data quality. [ABSTRACT FROM AUTHOR]

Existing power system resilience enhancement methods, such as proactive generation rescheduling, movable sources dispatch, and network topology reconfiguration, do not explore the capability and flexibility of shunts to maintain voltage stability during and after disrupting events. Besides, existing methods rely on accurate system models that are not easily scalable for large integrated power grids. In this paper, a data-driven multi-agent framework based on a deep-reinforcement-learning algorithm is proposed to overcome the computation and scalability concerns related to precise system models and to plan for the deployment of shunts for power system resilience enhancement. Specifically, voltage violations due to outages of multiple lines during windstorms are taken as an example of a power system resilience improvement problem. Then, a multi-agent based hybrid soft actor critic (HSAC) algorithm is developed for offline siting and sizing as well as online controlling of shunt reactive power compensators to enhance voltage resilience. The HSAC algorithm is derived from the fundamental SAC algorithms that contain both continuous and discrete action spaces. The proposed multi-agent framework learns from previous experiences and eventually gets trained to determine proper locations and sizes for shunts to avoid voltage violations during multiple line failures. The proposed approach is demonstrated on the IEEE 57-bus and IEEE 300-bus systems. The results show that the proposed multi-agent framework is effective for installation planning and controlling of shunts to enhance power system resilience. [ABSTRACT FROM AUTHOR]

In this paper, we investigate designs of linear precoders for vector Gaussian channels via stochastic optimizations and deep neural networks (DNNs). We assume that the channel inputs are drawn from practical finite alphabets, and we search for precoders maximizing the mutual information between channel inputs and outputs. Though the problem is generally non-convex, we prove that when the right singular matrix of precoder is fixed, any local optima of this problem is a global optima. Based on this fact, an efficient projected stochastic gradient descent (PSGD) algorithm is designed to search the optimal precoders. Moreover, to reduce the complexity of calculating a posterior means involved in gradients calculation, K-best algorithm is adopted to make approximations of a posterior means with negligible loss of accuracy. Furthermore, to avoid explicit calculation of mutual information and its gradients, DNN-based autoencoders (AEs) are constructed for this precoding task, and an efficient training algorithm is proposed. We also prove that the AEs, with ‘softmax’ activation function and ‘categorical cross entropy’ loss, maximize the mutual information under reasonable assumptions. Then, in order to extend the AE methods to large scale systems, ‘sigmoid’ activation function and ‘binary cross entropy’ loss are used such that the size of AEs will not grow prohibitively large. We prove that this maximizes a lower bound of the mutual information under reasonable assumptions. Finally, to make the precoders practical for high speed wireless scenarios, we propose an offline training paradigm which trains DNNs to infer optimal precoders given channel state information instead of training online for every different channel. Simulation results show that all the proposed methods work well in maximizing mutual information and improving bit error rate (BER) performance. [ABSTRACT FROM AUTHOR]

In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or classifier. A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training time, and unknown classes can be submitted to an algorithm during testing, requiring the classifiers to not only accurately classify the seen classes, but also effectively deal with unseen ones. This paper provides a comprehensive survey of existing open set recognition techniques covering various aspects ranging from related definitions, representations of models, datasets, evaluation criteria, and algorithm comparisons. Furthermore, we briefly analyze the relationships between OSR and its related tasks including zero-shot, one-shot (few-shot) recognition/learning techniques, classification with reject option, and so forth. Additionally, we also review the open world recognition which can be seen as a natural extension of OSR. Importantly, we highlight the limitations of existing approaches and point out some promising subsequent research directions in this field. [ABSTRACT FROM AUTHOR]

Recent workat the U.S. Army CCDC Ground Vehicle Systems Center has shown that machine learning classifiers can quickly construct high-fidelity mobility maps. Training these classifiers, on the other hand, is still a challenge, since each data instance is labeled by performing a computationally intensive, physics-based simulation. In this paper we introduce an active learning framework, based on the query-by-bagging algorithm, that substantially reduces the number of simulations needed to train a classifier. Experimental results suggest that our sampling algorithm can train a neural network, with higher accuracy, using less than half the number of simulations when compared to random sampling. [ABSTRACT FROM AUTHOR]

A deep learning assisted sum-product detection algorithm (DL-SPDA) for faster-than-Nyquist (FTN) signaling is proposed in this paper. The proposed detection algorithm works on a modified factor graph which concatenates a neural network function node to the variable nodes of the conventional FTN factor graph to approach the maximum a posterior probabilities (MAP) error performance. In specific, the neural network performs as a function node in the modified factor graph to deal with the residual intersymbol interference (ISI) that is not considered by the conventional detector with a limited complexity. We modify the updating rule in the conventional sum-product algorithm so that the neural network assisted detector can be complemented to a turbo equalization receiver. Furthermore, we propose a compatible training technique to improve the detection performance of the proposed DL-SPDA with turbo equalization. In particular, the neural network is optimized in terms of the mutual information between the transmitted sequence and the extrinsic information. We also investigate the maximum-likelihood bit error rate (BER) performance of a finite length coded FTN system. Simulation results show that the error performance of the proposed algorithm approaches the MAP performance, which is consistent with the analytical BER. [ABSTRACT FROM AUTHOR]

Multi-label classification is an important research topic in machine learning, for which exploiting label dependencies is an effective modeling principle. Recently, probabilistic models have shown great potential in discovering dependencies among labels. In this paper, motivated by the recent success of multi-view learning to improve the generalization performance, we propose a novel multi-view probabilistic model named latent conditional Bernoulli mixture (LCBM) for multi-label classification. LCBM is a generative model taking features from different views as inputs, and conditional on the latent subspace shared by the views a Bernoulli mixture model is adopted to build label dependencies. Inside each component of the mixture, the labels have a weak correlation which facilitates computational convenience. The mean field variational inference framework is used to carry out approximate posterior inference in the probabilistic model, where we propose a Gaussian mixture variational autoencoder (GMVAE) for effective posterior approximation. We further develop a scalable stochastic training algorithm for efficiently optimizing the model parameters and variational parameters, and derive an efficient prediction procedure based on greedy search. Experimental results on multiple benchmark datasets show that our approach outperforms other state-of-the-art methods under various metrics. [ABSTRACT FROM AUTHOR]

The measurement of received signal strength (RSS) and channel state information (CSI) has been widely used in the research of device-free localization (DFL). However, DFL systems based on these systems usually require labour-intensive training to understand the impact of the target on the surrounding wireless signals to build the target location-related model or image. In addition, the fact that the RSS is susceptible to multipath interference and is not directly accessible to CSI directly limits its actual deployment. In this paper, we explore the feasibility of DFL based on time-of-flight measurements of ultra-wideband signals, and propose a fusion method for simultaneous localization of multiple targets based on the evaluation results. Specifically, we mesh the feasible region of the target and utilize the geometric filtering method to re-evaluate the filtered wireless links in combination with the real-time adaptive relaxation target model. Consequently, we introduce the clustering method and combine the category matching strategy to ensure that the algorithm has robust real-time multi-target perception ability. Extensive experiments conducted in the lobby, laboratory and office scenarios demonstrate that the proposed method plays an active role in more than 82% and can control the mean error within 0.6 m. [ABSTRACT FROM AUTHOR]

This paper presents a novel methodology for the construction of a transient stability boundary (TSB) that overcomes the lack of TSB analytical description for multiple operating states and contingencies in power systems. The proposed approach models the TSB as a nonlinear mapping between the system parameters of interest and the corresponding critical clearing time (CCT). This compact mathematical expression is built based on an efficient discriminative network, broad learning system (BLS). While keeping a high accuracy and generalization ability, the newly introduced construction method provides an efficient update strategy that does not require an entire retraining cycle. These properties make this method suitable for online transient stability assessment (TSA). The prospects of the developed method are verified via case studies by employing the IEEE 9-bus, IEEE 39-bus (New England) test systems and a real system of China Southern Power Grid. In comparison with existing methods, the newly introduced algorithm has a higher prediction accuracy and improved robustness. The demonstrated characteristics indicate that the proposed method may serve as a valuable tool in the framework of online TSA. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have been widely applied for classification tasks in wireless communications such as link scheduling, user association and base station (BS) muting. When training a DNN using datasets with highly-skewed class distribution where most data belong to a few majority classes, learning performance for minority classes will degrade since the imbalanced data forces the training process to be biased towards the majority classes. In many wireless problems, multiple decisions for classification are made jointly, say deciding which BSs in a network should be muted to avoid interference. In this paper, we employ DNN to learn an optimal predictive interference coordination policy, and strive to avoid biased learning in such a multi-label multi-class classification problem. The major contribution is proposing a training method to encourage fairness among classes by minimizing the maximal cost of decisions among classes, which is converted into a problem to optimize the weighting factors on the training cost of each class. We provide a gradient descent algorithm to optimize the weighting factors and the model parameters of the DNN by alternative updates. Simulation results show that the training method can improve the learning performance for the minority class and can achieve higher network utility than existing training methods. [ABSTRACT FROM AUTHOR]

Face Super-Resolution (FSR) aims to infer High-Resolution (HR) face images from the captured Low-Resolution (LR) face image with the assistance of external information. Existing FSR methods are less effective for the LR face images captured with serious low-quality since the huge imaging/degradation gap caused by the different imaging scenarios (i.e., the complex practical imaging scenario that generates test LR images, the simple manual imaging degradation that generates the training LR images) is not considered in these algorithms. In this paper, we propose an image homogenization strategy via re-expression to solve this problem. In contrast to existing methods, we propose a homogenization projection in LR space and HR space as compensation for the classical LR/HR projection to formulate the FSR in a multi-stage framework. We then develop a re-expression process to bridge the gap between the complex degradation and the simple degradation, which can remove the heterogeneous factors such as serious noise and blur. To further improve the accuracy of the homogenization, we extract the image patch set that is invariant to degradation changes as Robust Neighbor Resources (RNR), with which these two homogenization projections re-express the input LR images and the initial inferred HR images successively. Both quantitative and qualitative results on the public datasets demonstrate the effectiveness of the proposed algorithm against the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Linear Regression (LR) is a popular and effective technique in pattern recognition area, which aims to find a transform matrix between source data and target data (usually label matrix). However, a binary zero-one label matrix may be too strict and inappropriate for regression. Besides, directly projecting source data to target data by one transform matrix may lose some intrinsic data information. To address these issues, this paper proposes a novel Pairwise Relations oriented Discriminative Regression (PRDR) method. In PRDR, the source data is regressed into a latent space instead of label space. To supervise the discriminative projection learning, the pairwise relations in source data space and label space are exploited in the latent space simultaneously. The pairwise label relations are transferred into the latent subspace by solving a distance-distance difference minimization problem, and the intraclass instance relations are also preserved in latent space. These two constraints ensure the pairwise similarity of data points after transformation which is beneficial for classification. By further enlarging the margins between true and false classes, PRDR is extended to a robust version, i.e., R-PRDR. An efficient algorithm is presented to solve the PRDR model. Extensive experiments on several popular image datasets demonstrate the effectiveness and efficiency of the proposed method compared with some state-of-the-art regression approaches. [ABSTRACT FROM AUTHOR]

As the training dataset size and the model size of machine learning increase rapidly, more computing resources are consumed to speedup the training process. However, the scalability and performance reproducibility of parallel machine learning training, which mainly uses stochastic optimization algorithms, are limited. In this paper, we demonstrate that the sample difference in the dataset plays a prominent role in the scalability of parallel machine learning algorithms. We propose to use statistical properties of dataset to measure sample differences. These properties include the variance of sample features, sample sparsity, sample diversity, and similarity in sampling sequences. We choose four types of parallel training algorithms as our research objects: (1) the asynchronous parallel SGD algorithm (Hogwild! algorithm), (2) the parallel model average SGD algorithm (minibatch SGD algorithm), (3) the decentralization optimization algorithm, and (4) the dual coordinate optimization (DADM algorithm). Our results show that the statistical properties of training datasets determine the scalability upper bound of these parallel training algorithms. [ABSTRACT FROM AUTHOR]

Intelligent reflecting surface (IRS) is a promising new paradigm to achieve high spectral and energy efficiency for future wireless networks by reconfiguring the wireless signal propagation via passive reflection. To reap the promising gains of IRS, channel state information (CSI) is essential, whereas channel estimation errors are inevitable in practice due to limited channel training resources. In this paper, in order to optimize the performance of IRS-aided multiuser communications with imperfect CSI, we propose to jointly design the active transmit precoding at the access point (AP) and passive reflection coefficients of the IRS, each consisting of not only the conventional phase shift and also the newly exploited amplitude variation. First, the achievable rate of each user is derived assuming a practical IRS channel estimation method, which shows that the interference due to CSI errors is intricately related to the AP transmit precoders, the channel training power and the IRS reflection coefficients during both channel training and data transmission. Next, for the single-user case, by combining the benefits of the penalty method, Dinkelbach method and block successive upper-bound minimization (BSUM) method, a new penalized Dinkelbach-BSUM algorithm is proposed to optimize the IRS reflection coefficients for maximizing the achievable data transmission rate subjected to CSI errors; while for the multiuser case, a new penalty dual decomposition (PDD)-based algorithm is proposed to maximize the users’ weighted sum-rate. Finally, simulation results are presented to validate the effectiveness of our proposed algorithms as compared to benchmark schemes. In particular, useful insights are drawn to characterize the effect of IRS reflection amplitude control (with/without the conventional phase-shift control) on the system performance under imperfect CSI. [ABSTRACT FROM AUTHOR]

In many practical engineering applications, the number of actions that have been finished should be known, particularly for an untrimmed video sequence that includes an event with a series of actions, it is important to know the number of actions that have been finished. In this paper, we termed this process as visual event progress estimation (EPE). However, the research related to this problem is few in the research community. To solve this problem, a visual human action analysis-based framework, namely one-shot simultaneously action detection and identification (SADI)-EPE, is presented in this paper. The visual EPE is modeled as an online one-shot learning-based problem; sliding window and attention-based bag of key poses formulate our framework. Unlike most of the action analysis methods relying on a number of training data of some predefined classes, our method can realize SADI for any event if one sample of the event is given, which makes it feasible for practical applications. At the same time, not only SADI but also the progress estimation of the event can be realized by our algorithm. In terms of methodology, the key pose is defined by an invariant pose descriptor from skeletal data and silhouette data. Moreover, in order to extract representative and discriminative poses from one training sample, we present a new bidirectional $k$ NN-based attention weighted key pose selection method, which can filter the unrelated actions and model different importance of various key poses. In addition, an attention-based multi-modal fusion scheme, which addresses the difficulty of high-dimensional features and few training samples, is proposed to augment the performance of our algorithm. Finally, we propose an evaluation criterion for the estimation problem. Extensive results demonstrated the efficacy of our proposed framework. [ABSTRACT FROM AUTHOR]

Hyperspectral imagery (HSI) has shown promising results in real-world applications. However, the technological evolution of optical sensors poses two main challenges in HSI classification: 1) the spectral band is usually redundant and noisy and 2) HSI with millions of pixels has become increasingly common in real-world applications. Motivated by the recent success of hybrid huberized support vector machines (HHSVMs), which inherit the benefits of both lasso and ridge regression, this paper first investigates the advantages of HHSVM for HSI applications. Unfortunately, the existing HHSVM solvers suffer from prohibitive computational costs on large-scale data sets. To solve this problem, this paper proposes simple and effective stochastic HHSVM algorithms for HSI classification. In the stochastic settings, we show that with a probability of at least $1-\varrho $ , our algorithms find an $\epsilon $ -accurate solution using $\tilde {O}({1}/{\lambda _{2}\epsilon })$ iterations. Since the convergence rate of our algorithms does not depend on the size of the training set, our algorithms are suitable for handling large-scale problems. We demonstrate the superiority of our algorithms by conducting experiments on large-scale binary and multiclass classification problems, comparing to the state-of-the-art HHSVM solvers. Finally, we apply our algorithms to real HSI classification and achieve promising results. [ABSTRACT FROM AUTHOR]

This paper addresses the position control of continuum manipulators. Their performances in terms of speed limitation and position accuracy are often mediocre compared with rigid body based robots. In regards to continuum manipulators control, nonadaptive kinematic schemes were shown poor performance in terms of tracking position accuracy, and existing adaptive schemes were time-consuming. This paper presents a novel adaptive control scheme, namely the adaptive support vector regressor controller. The proposed approach exploits the optimization learning methods which yield global solutions of the training problem while keeping small size regressors. These characteristics make it possible to accelerate the convergence of the closed-loop system, thus reducing the execution time. The experimental results obtained using the compact bionic handling assistant robot demonstrate that nonadaptive kinematic architectures even in the presence of accurate learning models are not robust enough to deal with these challenging platforms and that adaptive control schemes can significantly improve the performance. [ABSTRACT FROM AUTHOR]

High-dimensional and sparse (HiDS) matrices generated by recommender systems contain rich knowledge regarding various desired patterns like users’ potential preferences and community tendency. Latent factor (LF) analysis proves to be highly efficient in extracting such knowledge from an HiDS matrix efficiently. Stochastic gradient descent (SGD) is a highly efficient algorithm for building an LF model. However, current LF models mostly adopt a standard SGD algorithm. Can SGD be extended from various aspects in order to improve the resultant models’ convergence rate and prediction accuracy for missing data? Are such SGD extensions compatible with an LF model? To answer them, this paper carefully investigates eight extended SGD algorithms to propose eight novel LF models. Experimental results on two HiDS matrices generated by real recommender systems show that compared with an LF model with a standard SGD algorithm, an LF model with extended ones can achieve: 1) higher prediction accuracy for missing data; 2) faster convergence rate; and 3) model diversity. [ABSTRACT FROM AUTHOR]

In this paper we consider maximum-likelihood (ML) MIMO detection under one-bit quantized observations and binary symbol constellations. This problem is motivated by the recent interest in adopting coarse quantization in massive MIMO systems—as an effective way to scale down the hardware complexity and energy consumption. Classical MIMO detection techniques consider unquantized observations, and many of them are not applicable to the one-bit MIMO case. We develop a new non-convex optimization algorithm for the one-bit ML MIMO detection problem, using a strategy called homotopy optimization. The idea is to transform the ML problem into a sequence of approximate problems, from easy (convex) to hard (close to ML), and with each problem being a gradual modification of its previous. Then, our attempt is to iteratively trace the solution path of these approximate problems. This homotopy algorithm is well suited to the application of deep unfolding, a recently popular approach for turning certain model-based algorithms into data-driven, and performance enhanced, ones. While our initial focus is on one-bit MIMO detection, the proposed technique also applies naturally to the classical unquantized MIMO detection. We performed extensive simulations and show that the proposed homotopy algorithms, both non-deep and deep, have satisfactory bit-error probability performance compared to many state-of-the-art algorithms. Also, the deep homotopy algorithm has attractively low computational complexity. [ABSTRACT FROM AUTHOR]

Salient object detection has undergone a very rapid development with the blooming of Deep Neural Network (DNN), which is usually taken as an important preprocessing procedure in various computer vision tasks. However, the down-sampling operations, such as pooling and striding, always make the final predictions blurred at edges, which has seriously degenerated the performance of salient object detection. In this paper, we propose a simple yet effective approach, i.e., Hierarchical and Interactive Refinement Network (HIRN), to preserve the edge structures in detecting salient objects. In particular, a novel multi-stage and dual-path network structure is designed to estimate the salient edges and regions from the low-level and high-level feature maps, respectively. As a result, the predicted regions will become more accurate by enhancing the weak responses at edges, while the predicted edges will become more semantic by suppressing the false positives in background. Once the salient maps of edges and regions are obtained at the output layers, a novel edge-guided inference algorithm is introduced to further filter the resulting regions along the predicted edges. Extensive experiments on several benchmark datasets have been conducted, in which the results show that our method significantly outperforms a variety of state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Multi-view learning (MVL) is an active direction in machine learning that aims at exploiting the consensus and complementarity information among multiple distinct feature sets to boost the generalization performance of the counterpart algorithm. So far, two classical SVM-based MVL methods are SVM-2K and multi-view twin support vector machine (MvTSVM). They are designed only for two-view classification and cannot tackle the general multi-view classification problem. They also cannot effectively leverage the complementarity information among different feature views. In this paper, we propose two novel multi-view support vector machines with the consensus and complementarity information for MVL that not only can deal with the two-view classification problem but also the general multi-view classification problem by jointly learning multiple different views in a non-pairwise way. The disagreement among different views is regarded as a constraint or a regularization term in the objective function which plays an important role in exploring the consensus information. Combination weights for the reconstruction of each view in regularization terms are learned to explore complementarity information among different views. Finally, an efficient iteration algorithm with the classical convex quadratic programming is developed for optimization. Experimental results validate the effectiveness of our proposed methods. [ABSTRACT FROM AUTHOR]

In this paper, a new metric learning algorithm is proposed to improve face verification and person re-identification in RGB images by learning from RGB and Depth (RGB-D) training images. We address this problem by formulating it as a Learning Using Privileged Information problem, in which the additional depth images associated with the RGB training images are not available for the testing process. Based on the large margin nearest neighbor (LMNN) classification framework, we propose an effective metric learning method called large margin nearest neighbor classification with privileged information (LMNN+) by incorporating depth information to improve decision function learning in the training process. Specifically, two distance metrics based on visual features as well as depth features are jointly learned by minimizing the triplet loss in which the within-class difference is minimized, while the between-class difference is maximized. The distances in the depth feature space can be utilized to guide the training process in the visual feature space. In addition, we propose an efficient optimization method which can handle billions of constraints in the optimization problem of LMNN+. The comprehensive experiments on the EUROCOM data set, the CurtinFaces data set as well as the BIWI RGBD-ID data set demonstrate the effectiveness of our algorithm for face verification and person re-identification by leveraging privileged information. [ABSTRACT FROM AUTHOR]

Data for face analysis often exhibit highly-skewed class distribution, i.e., most data belong to a few majority classes, while the minority classes only contain a scarce amount of instances. To mitigate this issue, contemporary deep learning methods typically follow classic strategies such as class re-sampling or cost-sensitive training. In this paper, we conduct extensive and systematic experiments to validate the effectiveness of these classic schemes for representation learning on class-imbalanced data. We further demonstrate that more discriminative deep representation can be learned by enforcing a deep network to maintain inter-cluster margins both within and between classes. This tight constraint effectively reduces the class imbalance inherent in the local data neighborhood, thus carving much more balanced class boundaries locally. We show that it is easy to deploy angular margins between the cluster distributions on a hypersphere manifold. Such learned Cluster-based Large Margin Local Embedding (CLMLE), when combined with a simple k-nearest cluster algorithm, shows significant improvements in accuracy over existing methods on both face recognition and face attribute prediction tasks that exhibit imbalanced class distribution. [ABSTRACT FROM AUTHOR]

The implementation of artificial intelligence (AI) in wireless networks is becoming more and more popular because of the growing number of mobile devices and the availability of huge amount of data. However, directly transmitting data for centralized learning will cause long communication latency owing to the limited communication resource and may incur severe privacy issue as well. To address these issues, we consider the federated edge learning (FEEL) system in this paper and develop an importance-aware joint data selection and resource allocation algorithm to maximize the learning efficiency. Aiming at selecting important data for local training, we first analyze the relation between loss decay and gradient norm, which indicates that larger gradient norm generally leads to faster learning speed. Based on this, a learning efficiency maximization problem is formulated by jointly considering the communication resource allocation and data selection. The closed-form results for optimal communication resource allocation and data selection are both developed, where some insights are also highlighted. Furthermore, an optimal algorithm with low computational complexity is developed to obtain the optimal end-to-end latency in one training period. We show that the sample size should be set to its upper limit in order to maximize the learning performance. Finally, we conduct extensive experiments on three popular convolutional neural network (CNN) models. The results show that the proposed algorithm can effectively reduce the training latency and improve the learning accuracy as compared with some benchmark algorithms. [ABSTRACT FROM AUTHOR]

In recent years there has been a noticeable increase in the number of available Big Data infrastructures. This fact has promoted the adaptation of traditional machine learning techniques to be capable of addressing large scale problems in distributed environments. Kernel methods like support vector machines (SVMs) suffer from scalability problems due to their nonparametric nature and the complexity of their training procedures. In this paper, we propose a new and efficient distributed implementation of a training procedure for nonlinear semiparametric (budgeted) SVMs called distributed iterative reweighted least squares (IRWLS). This algorithm uses $ {k}$ -means to select the centroids of the semiparametric model and a new distributed algorithmic implementation of the IRWLS optimization procedure to find the weights of the model. We have implemented the proposed algorithm in Apache Spark and we have benchmarked it against other state-of-the-art methods, either full SVM ($ {p}$ -pack SVM) or budgeted (budgeted stochastic gradient descent). Experimental results show that the proposed algorithm achieves higher accuracy while controlling the size of the final model, and also offers high performance in terms of run time and efficiency, when processing very large datasets (the computation time grows linear with the number of training patterns). [ABSTRACT FROM AUTHOR]

Images acquired by outdoor vision systems easily suffer poor visibility and annoying interference due to the rainy weather, which brings great challenge for accurately understanding and describing the visual contents. Recent researches have devoted great efforts on the task of rain removal for improving the image visibility. However, there is very few exploration about the quality assessment of de-rained image, even it is crucial for accurately measuring the performance of various de-raining algorithms. In this paper, we first create a de-raining quality assessment (DQA) database that collects 206 authentic rain images and their de-rained versions produced by 6 representative single image rain removal algorithms. Then, a subjective study is conducted on our DQA database, which collects the subject-rated scores of all de-rained images. To quantitatively measure the quality of de-rained image with non-uniform artifacts, we propose a bi-directional feature embedding network (B-FEN) which integrates the features of global perception and local difference together. Experiments confirm that the proposed method significantly outperforms many existing universal blind image quality assessment models. To help the research towards perceptually preferred de-raining algorithm, we will publicly release our DQA database and B-FEN source code on https://github.com/wqb-uestc. [ABSTRACT FROM AUTHOR]

In this paper, we focus on large-scale environment monitoring by utilizing a fully decentralized team of mobile robots. The robots utilize the resource constrained-decentralized active sensing scheme to select the most informative (uncertain) locations to observe while conserving allocated resources (battery, travel distance, etc.). We utilize a distributed Gaussian process (GP) framework to split the computational load over our fleet of robots. Since each robot is individually generating a model of the environment, there may be conflicting predictions for test locations. Thus, in this paper, we propose an algorithm for aggregating individual prediction models into a single globally consistent model that can be used to infer the overall spatial dynamics of the environment. To make a prediction at a previously unobserved location, we propose a novel gating network for a mixture-of-experts model wherein the weight of an expert is determined by the responsibility of the expert over the unvisited location. The benefit of posing our problem as a centralized fusion with a distributed GP computation approach is that the robots never communicate with each other, individually optimize their own GP models based on their respective observations, and off-load all their learnt models on the base station only at the end of their respective mission times. We demonstrate the effectiveness of our approach using publicly available datasets. [ABSTRACT FROM AUTHOR]

Force estimation methods enable robots to interact with the environment or humans compliantly and safely without additional sensing device. In this paper, we present a novel method for estimating unknown contact forces exerted on a robot manipulator. The force estimation method is divided into two steps. The first step is to identify a robot dynamics model. A parametric model is derived first based on rigid-body dynamic (RBD) theory. To improve the model accuracy, a nonparametric compensator trained with multilayer perception (MLP) is added to compensate for errors of the RBD model. The result is a semiparametric model that provides better model accuracy than either the RBD model or the MLP model alone. The second step is to construct a force estimation observer. A novel estimation method called disturbance Kalman filter (DKF) is developed in this paper. The design of DKF based on a time-invariant composite system model is presented. DKF can take both manipulator's dynamics model and disturbance's dynamics model into account. As with Kalman filter, it can provide robust and accurate estimation against uncertainty. Simulation and experimental results, obtained using a six-degrees-of-freedom Kinova Jaco2 manipulator, demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This paper presents a method to improve the traditional mixture of deformable part models (MDPM) method from the learning perspective. First, an object part configuration learning algorithm based on group sparsity constraint is introduced to automatically discover the object part number, size, and location. The algorithm imposes two additional regularization terms in addition to the standard hinge loss function. The first term focuses on automatic part selection and the second term focuses on automatic part placement. Second, this paper introduces an improved MDPM training framework. The framework applies a learned transformation to normalize the prediction score from each individual deformable part model (DPM) into a pseudo probability such that the partition of the entire object appearance feature space becomes less sensitive to the prior distributions of different DPMs. Finally, the two proposed improvements are combined and formulated under the expectation-maximization framework. We evaluate our method mainly using the PASCAL VOC2007 and VOC2010 detection benchmarks and show that the proposed learning algorithms could increase the detection mean AP score by 2.4% and 0.9%, respectively, on these two data sets when using the proposed part selection method and the training algorithm. We also present further in-depth analysis of the proposed algorithm in the experiments. [ABSTRACT FROM PUBLISHER]

This paper presents a novel model-driven deep learning (DL) architecture, called TurboNet, for turbo decoding that integrates DL into the traditional max-log-maximum a posteriori (MAP) algorithm. The TurboNet inherits the superiority of the max-log-MAP algorithm and DL tools and thus presents excellent error-correction capability with low training cost. To design the TurboNet, the original iterative structure is unfolded as deep neural network (DNN) decoding units, where trainable weights are introduced to the max-log-MAP algorithm and optimized through supervised learning. To efficiently train the TurboNet, a loss function is carefully designed to prevent tricky gradient vanishing issue. To further reduce the computational complexity and training cost of the TurboNet, we can prune it into TurboNet+. Compared with the existing black-box DL approaches, the TurboNet+ has considerable advantage in computational complexity and is conducive to significantly reducing the decoding overhead. Furthermore, we also present a simple training strategy to address the overfitting issue, which enable efficient training of the proposed TurboNet+. Simulation results demonstrate TurboNet+’s superiority in error-correction ability, signal-to-noise ratio generalization, and computational overhead. In addition, an experimental system is established for an over-the-air (OTA) test with the help of a 5G rapid prototyping system and demonstrates TurboNet’s strong learning ability and great robustness to various scenarios. [ABSTRACT FROM AUTHOR]

In this paper, we propose an efficient beam training technique for millimeter-wave (mmWave) communications. Beam training should be performed frequently when some mobile users are under high mobility to ensure the accurate acquisition of the channel state information. To reduce the resource overhead caused by frequent beam training, we introduce a dedicated beam training strategy which sends the training beams separately to a specific high mobility user (called a target user) without changing the periodicity of the conventional beam training. The dedicated beam training requires a small amount of resources because the training beams can be optimized for the target user. To satisfy the performance requirement with a low training overhead, we propose the optimal training beam selection strategy which finds the best beamforming vectors yielding the lowest channel estimation error based on the target user’s probabilistic channel information. This dedicated beam training is combined with the greedy channel estimation algorithm that accounts for sparse characteristics and temporal dynamics of the target user’s channel. Our numerical evaluation demonstrates that the proposed scheme can maintain good channel estimation performance with significantly less training overhead compared to the conventional beam training protocols. [ABSTRACT FROM AUTHOR]

As urban traffic condition is diverse and complicated, applying reinforcement learning to reduce traffic congestion becomes one of the hot and promising topics. Especially, how to coordinate the traffic light controllers of multiple intersections is a key challenge for multi-agent reinforcement learning (MARL). Most existing MARL studies are based on traditional $Q$ -learning, but unstable environment leads to poor learning in the complicated and dynamic traffic scenarios. In this paper, we propose a novel multi-agent recurrent deep deterministic policy gradient (MARDDPG) algorithm based on deep deterministic policy gradient (DDPG) algorithm for traffic light control (TLC) in vehiclar networks. Specifically, the centralized learning in each critic network enables each agent to estimate the policies of other agents in the decision-making process and each agent can coordinate with each other, alleviating the problem of poor learning performance caused by environmental instability. The decentralized execution enables each agent to make decisions independently. We share parameters in actor networks to speed up the training process and reduce the memory footprint. The addition of LSTM is beneficial to alleviate the instability of the environment caused by partial observable state. We utilize surveillance cameras and vehicular networks to collect status information for each intersection. Unlike previous work, we have not only considered the vehicle but also considered the pedestrians waiting to pass through the intersection. Moreover, we also set different priorities for buses and ordinary vehicles. The experimental results in a vehicular network show that our method can run stably in various scenarios and coordinate multiple intersections, which significantly reduces vehicle congestion and pedestrian congestion. [ABSTRACT FROM AUTHOR]

Joint sparse representation (JSR) model has recently emerged as a powerful technique with wide variety of applications. In this paper, the JSR model is extended to error concealment (EC) application, being effective to recover the original image from its corrupted version. This model is based on jointly learning a dictionary pair and two mapping matrices that are trained offline from external training images. Given the trained dictionaries and mappings, the restoration is done by transferring the recovery problem into the sparse representation domain with respect to the trained dictionaries, which is further transformed into a common space using the respective mapping matrices. Then, the reconstructed image is obtained by back projection into the spatial domain. In order to improve the accuracy and stability of the proposed JSR-based EC algorithm and avoid unexpected artifacts, the local and non-local priors are seamlessly integrated into the JSR model. The non-local prior is based on the self-similarity within natural images and helps to find an accurate sparse representation by taking a weighted average of similar areas throughout the image. The local prior is based on learning the local structural regularity of the natural images and helps to regularize the sparse representation, exploiting the strong correlation in the small local areas within the image. Compared with the state-of-the-art EC algorithms, the results show that the proposed method has better reconstruction performance in terms of objective and subjective evaluations. [ABSTRACT FROM AUTHOR]

Most existing algorithms for depth estimation from single monocular images need large quantities of metric ground-truth depths for supervised learning. We show that relative depth can be an informative cue for metric depth estimation and can be easily obtained from vast stereo videos. Acquiring metric depths from stereo videos are sometimes impracticable due to the absence of camera parameters. In this paper, we propose to improve the performance of metric depth estimation with relative depths collected from stereo movie videos using existing stereo matching algorithm. We introduce a new “relative depth in stereo” (RDIS) dataset densely labeled with relative depths. We first pretrain a ResNet model on our RDIS dataset. Then, we finetune the model on RGB-D datasets with metric ground-truth depths. During our finetuning, we formulate depth estimation as a classification task. This re-formulation scheme enables us to obtain the confidence of a depth prediction in the form of probability distribution. With this confidence, we propose an information gain loss to make use of the predictions that are close to ground-truth. We evaluate our approach on both indoor and outdoor benchmark RGB-D datasets and achieve the state-of-the-art performance. [ABSTRACT FROM AUTHOR]