Microgrids can be isolated from large-scale power transmission/distribution systems (macrogrids) to deliver energy to their local communities using local energy resources and distribution systems when power outages occur in the macrogrids. In such situations, microgrids could be considered the last available resource to provide energy to critical infrastructure.

Industrial agents (IAs) [1] are multiagentbased systems (MASs) [2] that, for many years, have been advocated as a promising and realistic solution for an emerging set of industrial challenges. In the past, MASs fell into the scope of enterprise agility [3]-[8], and now, more than ever, pertain to the industrial digital transformation and sustainability spheres. MAS technology is being applied to several

Currently, the necessity of efficient and reliable power systems is also increasing because of the strict requirements that standards and regulations impose, but still costs have to remain low. The monitoring and control of the components' lifetime can lead to reduce maintenance costs.However, overcoming the related challenges is not a straightforward task, as it involves knowledge of power device

Lithium (Li)-ion batteries have become the mainstream energy storage solution for many applications, such as electric vehicles (EVs) and smart grids. However, various faults in a Li-ion battery system (LIBS) can potentially cause performance degradation and severe safety issues. Developing advanced fault diagnosis technologies is becoming increasingly critical for the safe operation of LIBS. This article

This historical column follows the article on Mario Tchou's ELEA 9003, which was published in the June 2020 issue of IEEE Industrial Electronics Magazine, and recounts events that also took place at the Olivetti Company. We know that much of the early progress in personal computers took place in the United States, and particularly on the West Coast, in the early 1970s. Nevertheless, trailblazers were

Worldwide, the current year has been quite challenging due to the COVID-19 pandemic and its dramatic effects. All of us have had to suddenly change our lives and habits to face such an unexpected global emergency for which we were not prepared. From one day to the next, the luckiest ones, that is, those of us who have not lost our jobs, have had to switch from working on site to smart working. In many

Disturbance, which is generally unknown to the controller, is unavoidable in real-world systems and it may affect the expected system state and output. Existing control methods, like robust model predictive control, can produce robust solutions to maintain the system stability. However, these robust methods trade the solution optimality for stability. In this article, a method called generative adversarial

An enormous and ever-growing volume of data is nowadays becoming available in a sequential fashion in various real-world applications. Learning in nonstationary environments constitutes a major challenge, and this problem becomes orders of magnitude more complex in the presence of class imbalance. We provide new insights into learning from nonstationary and imbalanced data in online learning, a largely

In sparse empirical risk minimization (ERM) models, when sensitive personal data are used, e.g., genetic, healthcare, and financial data, it is crucial to preserve the differential privacy (DP) in training. In many applications, the information (i.e., features) of an individual is held by different organizations, which give rise to the prevalent yet challenging setting of the featurewise distributed

We introduce a gated value network (GVN) for general multilabel classification (MLC) tasks. GVN was motivated by deep value network (DVN) that directly exploits the ``compatibility'' metric as the learning pursuit for MLC. Meanwhile, it further improves traditional DVN on twofold. First, GVN relaxes the complex variable optimization steps in DVN inference by incorporating a feedforward predictor for

In this article, a novel learning methodology is introduced for the problem of classification in the context of high-dimensional data. In particular, the challenges introduced by high-dimensional data sets are addressed by formulating a L₁ regularized zero-sum game where optimal sparsity is estimated through a two-player game between the penalty coefficients/sparsity parameters and the deep neural

We aim at the optimization of the tracking control of a robot to improve the robustness, under the effect of unknown nonlinear perturbations. First, an auxiliary system is introduced, and optimal control of the auxiliary system can be seen as an approximate optimal control of the robot. Then, neural networks (NNs) are employed to approximate the solution of the Hamilton-Jacobi-Isaacs equation under

Optimal control of nonlinear impulsive systems with free impulse instants and the number of impulses is investigated in this study. A scheme based on adaptive dynamic programming is developed, which leads to a feedback (approximate) solution to the defined optimal impulsive control problem. This is done by proposing a learning algorithm for tuning parameters of a function approximator, which, once

This article proposes a neural terminal sliding mode controller (TSMC) with finite-time (FT) convergence for the uncertain MEMS gyroscope dynamics. To address the uncertainty, considering the periodic tracking property of MEMS gyroscopes, a composite learning mechanism driven by the learning performance evaluation signal is applied to learn the system dynamics. By selecting the terminal sliding mode

Visual question answering (VQA) that involves understanding an image and paired questions develops very quickly with the boost of deep learning in relevant research fields, such as natural language processing and computer vision. Existing works highly rely on the knowledge of the data set. However, some questions require more professional cues other than the data set knowledge to answer questions correctly

In the field of computer vision, without sufficient labeled images, it is challenging to train an accurate model. However, through visual adaptation from source to target domains, a relevant labeled dataset can help solve such problem. Many methods apply adversarial learning to diminish cross-domain distribution difference. They are able to greatly enhance the performance on target classification tasks

Attention is an increasingly popular mechanism used in a wide range of neural architectures. The mechanism itself has been realized in a variety of formats. However, because of the fast-paced advances in this domain, a systematic overview of attention is still missing. In this article, we define a unified model for attention architectures in natural language processing, with a focus on those designed

Composite function optimization problem often arises in machine learning known as regularized empirical minimization. We introduce the acceleration technique to the Newton-type proximal method and propose a novel algorithm called accelerated proximal subsampled Newton method (APSSN). APSSN only subsamples a small subset of samples to construct an approximate Hessian that achieves computational efficiency

This article applies a singular perturbation theory to solve an optimal linear quadratic tracker problem for a continuous-time two-time-scale process. Previously, singular perturbation was applied for system regulation. It is shown that the two-time-scale tracking problem can be separated into a linear-quadratic tracker (LQT) problem for the slow system and a linear-quadratic regulator (LQR) problem

This article considers global exponential synchronization almost surely (GES a.s.) for a class of switched discrete-time neural networks (DTNNs). The considered system switches from one mode to another according to transition probability (TP) and evolves with mode-dependent average dwell time (MDADT), i.e., TP-based MDADT switching, which is more practical than classical average dwell time (ADT) switching

A continuous stirred-tank reactor (CSTR) system is widely applied in wastewater treatment processes. Its control is a challenging industrial-process-control problem due to great difficulty to achieve accurate system identification. This work proposes a deep learning-based model predictive control (DeepMPC) to model and control the CSTR system. The proposed DeepMPC consists of a growing deep belief

Semantic-preserving hashing establishes efficient multimedia retrieval by transferring knowledge from original data to hash codes so that the latter can preserve the underlying visual and semantic similarities. However, it becomes a crucial bottleneck: how to effectively bridge the trilateral domain gaps (i.e., the visual, semantic, and hashing spaces) to further improve the retrieval accuracy. In

In this article, the synchronous fault-tolerant near-optimal control strategy design problem is studied for a class of discrete-time nonlinear pursuit-evasion (PE) games. In the studied PE game, the input saturation phenomenon and possible actuator fault are simultaneously taken into consideration. To accelerate the estimation speed, a novel nonlinear fault estimator is designed by introducing a nonlinear

In this article, the exponential stability problem for fractional-order complex multi-links networks with aperiodically intermittent control is considered. Using the graph theory and Lyapunov method, two theorems, including a Lyapunov-type theorem and a coefficient-type theorem, are given to ensure the exponential stability of the underlying networks. The theoretical results show that the exponential

Text segmentation is a fundamental step in natural language processing (NLP) and information retrieval (IR) tasks. Most existing approaches do not explicitly take into account the facet information of documents for segmentation. Text segmentation and facet annotation are often addressed as separate problems, but they operate in a common input space. This article proposes FTS, which is a novel model

Recent techniques built on generative adversarial networks (GANs), such as cycle-consistent GANs, are able to learn mappings among different domains built from unpaired data sets, through min-max optimization games between generators and discriminators. However, it remains challenging to stabilize the training process and thus cyclic models fall into mode collapse accompanied by the success of discriminator

The aim of unsupervised domain adaptation is to leverage the knowledge in a labeled (source) domain to improve a model's learning performance with an unlabeled (target) domain--the basic strategy being to mitigate the effects of discrepancies between the two distributions. Most existing algorithms can only handle unsupervised closed set domain adaptation (UCSDA), i.e., where the source and target domains

Although increasing hidden layers can improve the ability of a neural network in modeling complex nonlinear relationships, deep layers may result in degradation of accuracy due to the problem of vanishing gradient. Accuracy degradation limits the applications of deep neural networks to predict continuous variables with a small sample size and/or weak or little invariance to translations. Inspired by

Dense medium separation (DMS) is of great significance for coal cleaning. The DMS control system always involves dense medium density adjustment and ash content control that are operating on fast and slow time scales, respectively. The inherent time-varying and strongly nonlinear characteristics of the DMS process give rise to challenges for the design of this multitime scale control system. To address

Iterative learning control (ILC) can synthesize the feedforward control signal for the trajectory tracking control of a repetitive task, even when the system has strong nonlinear dynamics. This makes ILC be one of the most popular methods for trajectory tracking control. Restriction on a repetitive task, however, limits its application to multiple trajectories. This article proposes a neural-network-based

This article concentrates on dealing with distributed control problems for second-order signed networks subject to not only cooperative but also antagonistic interactions. A distributed control protocol is proposed based on the nearest neighbor rules, with which necessary and sufficient conditions are developed for consensus of second-order signed networks whose communication topologies are described

Bottom-up-fabricated crossbars promise superior circuit density and 3-D integrability compared with the traditional CMOS-based implementations. However, their inherent stochasticity presents difficulties in building complex circuits from components that demand precise patterning and high registration accuracies. With fewer terminals than active devices, passive components offer higher device densities

Person reidentification (reID) by convolutional neural network (CNN)-based networks has achieved favorable performance in recent years. However, most of existing CNN-based methods do not take full advantage of spatial-temporal context modeling. In fact, the global spatial-temporal context can greatly clarify local distractions to enhance the target feature representation. To comprehensively leverage

In this article, we propose a general model for plane-based clustering. The general model reveals the relationship between cluster assignment and cluster updating during clustering implementation, and it contains many existing plane-based clustering methods, e.g., k-plane clustering, proximal plane clustering, twin support vector clustering, and their extensions. Under this general model, one may obtain

Deep learning has achieved incredible success over the past years, especially in various challenging predictive spatiotemporal analytics (PSTA) tasks, such as disease prediction, climate forecast, and traffic prediction, where intrinsic dependence relationships among data exist and generally manifest at multiple spatiotemporal scales. However, given a specific PSTA task and the corresponding data set

This article is concerned with the challenge of guaranteeing output constraints for fault-tolerant control (FTC) of a class of unknown multi-input single-output (MISO) nonlinear systems in the presence of actuator faults. Most industrial systems are equipped with redundant actuators and a fault detection-isolation mechanism for accommodating unexpected actuator faults. To simplify the system design

Matching and registration between aerial images and prestored road landmarks are critical techniques to enhance unmanned aerial system (UAS) navigation in the global positioning system (GPS)-denied urban environments. Current registration processes typically consist of two separate stages of road extraction and road registration. These two-stage registration approaches are time-consuming and less robust

We present a three-step method to perform system identification and optimal control of nonlinear systems. Our approach is mainly data-driven and does not require active excitation of the system to perform system identification. In particular, it is designed for systems for which only historical data under closed-loop control are available and where historical control commands exhibit low variability

Time series clustering is usually an essential unsupervised task in cases when category information is not available and has a wide range of applications. However, existing time series clustering methods usually either ignore temporal dynamics of time series or isolate the feature extraction from clustering tasks without considering the interaction between them. In this article, a time series clustering

Real-time event summarization (RES) aims at extracting a handful of document updates from an overwhelming document stream as the real-time event summary that tracks and summarizes the evolving event of interest. It has been attracting much attention, especially with the growth of streaming applications. Despite the effectiveness of previous studies, obtaining relevant, nonredundant, and timely event

Adaptive resonance theory (ART) networks, including developmental resonance network (DRN), basically use a vigilance parameter as a hyperparameter to determine whether a current input can belong to any existing categories or not. The problem here is that the clustering quality of those networks is sensitive to the vigilance parameter so that the users are required to fine-tune the parameter delicately

Continual learning models allow them to learn and adapt to new changes and tasks over time. However, in continual and sequential learning scenarios, in which the models are trained using different data with various distributions, neural networks (NNs) tend to forget the previously learned knowledge. This phenomenon is often referred to as catastrophic forgetting. The catastrophic forgetting is an inevitable

Model-based reinforcement learning (MBRL) has been proposed as a promising alternative solution to tackle the high sampling cost challenge in the canonical RL, by leveraging a system dynamics model to generate synthetic data for policy training purpose. The MBRL framework, nevertheless, is inherently limited by the convoluted process of jointly optimizing control policy, learning system dynamics, and

In deep face recognition, the commonly used softmax loss and its newly proposed variations are not yet sufficiently effective to handle the class imbalance and softmax saturation issues during the training process while extracting discriminative features. In this brief, to address both issues, we propose a class-variant margin (CVM) normalized softmax loss, by introducing a true-class margin and a

Symbolic regression is a powerful technique to discover analytic equations that describe data, which can lead to explainable models and the ability to predict unseen data. In contrast, neural networks have achieved amazing levels of accuracy on image recognition and natural language processing tasks, but they are often seen as black-box models that are difficult to interpret and typically extrapolate

Recent research on single image super-resolution (SISR) has achieved great success due to the development of deep convolutional neural networks. However, most existing SISR methods merely focus on super-resolution of a single fixed integer scale factor. This simplified assumption does not meet the complex conditions for real-world images which often suffer from various blur kernels or various levels

This article is dedicated to designing a novel periodic impulsive control strategy for producing globally exponentially stable periodic solutions for switched neural networks with discrete and finite distributed time-varying delays. First, tunable parameters and cubic convex combination approach are proposed to study the globally exponential convergence of switched neural networks. Second, a sufficient

Iterative learning model predictive control (ILMPC) has been recognized as an effective approach to realize high-precision tracking for batch processes with repetitive nature because of its excellent learning ability and closed-loop stability property. However, as a model-based strategy, ILMPC suffers from the unavailability of accurate first principal model in many complex nonlinear batch systems

This article investigates the Lagrange exponential stability and the Lyapunov exponential stability of memristive neural networks with discrete and distributed time-varying delays (DMNNs). By means of inequality techniques, theories of the M-matrix, and the comparison strategy, the Lagrange exponential stability of the underlying DMNNs is considered in the sense of Filippov, and the globally exponentially

This article presents a control scheme for the robot manipulator's trajectory tracking task considering output error constraints and control input saturation. We provide an alternative way to remove the feasibility condition that most BLF-based controllers should meet and design a control scheme on the premise that constraint violation possibly happens due to the control input saturation. A bounded

Ordinal regression (OR) is one of the most important machine learning tasks. The kernel method is a major technique to achieve nonlinear OR. However, traditional kernel OR solvers are inefficient due to increased complexity introduced by multiple ordinal thresholds as well as the cost of kernel computation. Doubly stochastic gradient (DSG) is a very efficient and scalable kernel learning algorithm

We propose a novel unsupervised anomaly detection algorithm that can work for sequential data from any complex distribution in a truly online framework with mathematically proven strong performance guarantees. First, a partitioning tree is constructed to generate a doubly exponentially large hierarchical class of observation space partitions, and every partition region trains an online kernel density

In this article, we propose a novel model for constrained clustering, namely, the dissimilarity propagation-guided graph-Laplacian principal component analysis (DP-GLPCA). By fully utilizing a limited number of weakly supervisory information in the form of pairwise constraints, the proposed DP-GLPCA is capable of capturing both the local and global structures of input samples to exploit their characteristics

Image denoising is a challenging inverse problem due to complex scenes and information loss. Recently, various methods have been considered to solve this problem by building a well-designed convolutional neural network (CNN) or introducing some hand-designed image priors. Different from previous works, we investigate a new framework for image denoising, which integrates edge detection, edge guidance

We propose a semi-supervised generative model, SeGMA, which learns a joint probability distribution of data and their classes and is implemented in a typical Wasserstein autoencoder framework. We choose a mixture of Gaussians as a target distribution in latent space, which provides a natural splitting of data into clusters. To connect Gaussian components with correct classes, we use a small amount

Active learning is an important learning paradigm in machine learning and data mining, which aims to train effective classifiers with as few labeled samples as possible. Querying discriminative (informative) and representative samples are the state-of-the-art approach for active learning. Fully utilizing a large amount of unlabeled data provides a second chance to improve the performance of active

Semisupervised clustering methods improve performance by randomly selecting pairwise constraints, which may lead to redundancy and instability. In this context, active clustering is proposed to maximize the efficacy of annotations by effectively using pairwise constraints. However, existing methods lack an overall consideration of the querying criteria and repeatedly run semisupervised clustering to

The performance of a classifier in a brain-computer interface (BCI) system is highly dependent on the quality and quantity of training data. Typically, the training data are collected in a laboratory where the users perform tasks in a controlled environment. However, users' attention may be diverted in real-life BCI applications and this may decrease the performance of the classifier. To improve the

Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy. Given a proper deep learning framework, it is generally possible to increase the depth or layer width to achieve a higher level of accuracy. However, the huge number of model parameters imposes more computational and memory usage overhead and leads to the parameter redundancy. In this article, we address