Showing papers in "IEEE Transactions on Systems, Man, and Cybernetics in 2020"

Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications

Abstract: Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms, however, have faced great challenges when dealing with high-dimensional environments. The recent development of deep learning has enabled RL methods to drive optimal policies for sophisticated and capable agents, which can perform efficiently in these challenging environments. This article addresses an important aspect of deep RL related to situations that require multiple agents to communicate and cooperate to solve complex tasks. A survey of different approaches to problems related to multiagent deep RL (MADRL) is presented, including nonstationarity, partial observability, continuous state and action spaces, multiagent training schemes, and multiagent transfer learning. The merits and demerits of the reviewed methods will be analyzed and discussed with their corresponding applications explored. It is envisaged that this review provides insights about various MADRL methods and can lead to the future development of more robust and highly useful multiagent learning methods for solving real-world problems.

Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification

Abstract: Convolutional neural networks (CNNs) have gained remarkable success on many image classification tasks in recent years. However, the performance of CNNs highly relies upon their architectures. For the most state-of-the-art CNNs, their architectures are often manually designed with expertise in both CNNs and the investigated problems. Therefore, it is difficult for users, who have no extended expertise in CNNs, to design optimal CNN architectures for their own image classification problems of interest. In this article, we propose an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks. The most merit of the proposed algorithm remains in its “automatic” characteristic that users do not need domain knowledge of CNNs when using the proposed algorithm, while they can still obtain a promising CNN architecture for the given images. The proposed algorithm is validated on widely used benchmark image classification datasets, compared to the state-of-the-art peer competitors covering eight manually designed CNNs, seven automatic + manually tuning, and five automatic CNN architecture design algorithms. The experimental results indicate the proposed algorithm outperforms the existing automatic CNN architecture design algorithms in terms of classification accuracy, parameter numbers, and consumed computational resources. The proposed algorithm also shows the very comparable classification accuracy to the best one from manually designed and automatic + manually tuning CNNs, while consuming fewer computational resources.

Observer-Based Adaptive Fuzzy Tracking Control for Strict-Feedback Nonlinear Systems With Unknown Control Gain Functions

Abstract: This article investigates the adaptive fuzzy output-feedback backstepping control design problem for uncertain strict-feedback nonlinear systems in the presence of unknown virtual and actual control gain functions and unmeasurable states. A fuzzy state observer is designed via fuzzy-logic systems, thus the unmeasurable states are estimated based on the designed fuzzy state observer. By constructing the logarithm Lyapunov functions and incorporating the property of the fuzzy basis functions and bounded control design technique into the adaptive backstepping recursive design, a novel observer-based adaptive fuzzy output-feedback control method is developed. The proposed fuzzy adaptive output-feedback backstepping control scheme can remove the restrictive assumptions in the previous literature that the virtual control gains and actual control gain functions must be constants. Furthermore, it can make the control system be semiglobally uniformly ultimately boundedness (SGUUB) and keep the observer and tracking errors to remain in a small neighborhood of the origin. The numerical simulation example is presented to validate the effectiveness of the proposed control scheme and theory.

Distributed Event-Triggered Estimation Over Sensor Networks: A Survey

Abstract: An event-triggered mechanism is of great efficiency in reducing unnecessary sensor samplings/transmissions and, thus, resource consumption such as sensor power and network bandwidth, which makes distributed event-triggered estimation a promising resource-aware solution for sensor network-based monitoring systems. This paper provides a survey of recent advances in distributed event-triggered estimation for dynamical systems operating over resource-constrained sensor networks. Local estimates of an unavailable state signal are calculated in a distributed and collaborative fashion based on only invoked sensor data. First, several fundamental issues associated with the design of distributed estimators are discussed in detail, such as estimator structures, communication constraints, and design methods. Second, an emphasis is laid on recent developments of distributed event-triggered estimation that has received considerable attention in the past few years. Then, the principle of an event-triggered mechanism is outlined and recent results in this subject are sorted out in accordance with different event-triggering conditions. Third, applications of distributed event-triggered estimation in practical sensor network-based monitoring systems including distributed grid-connected generation systems and target tracking systems are provided. Finally, several challenging issues worthy of further research are envisioned.

SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation

Abstract: One-shot image semantic segmentation poses a challenging task of recognizing the object regions from unseen categories with only one annotated example as supervision. In this article, we propose a simple yet effective similarity guidance network to tackle the one-shot (SG-One) segmentation problem. We aim at predicting the segmentation mask of a query image with the reference to one densely labeled support image of the same category. To obtain the robust representative feature of the support image, we first adopt a masked average pooling strategy for producing the guidance features by only taking the pixels belonging to the support image into account. We then leverage the cosine similarity to build the relationship between the guidance features and features of pixels from the query image. In this way, the possibilities embedded in the produced similarity maps can be adopted to guide the process of segmenting objects. Furthermore, our SG-One is a unified framework that can efficiently process both support and query images within one network and be learned in an end-to-end manner. We conduct extensive experiments on Pascal VOC 2012. In particular, our SG-One achieves the mIoU score of 46.3%, surpassing the baseline methods.

Detection of Power Line Insulator Defects Using Aerial Images Analyzed With Convolutional Neural Networks

Abstract: As the failure of power line insulators leads to the failure of power transmission systems, an insulator inspection system based on an aerial platform is widely used. Insulator defect detection is performed against complex backgrounds in aerial images, presenting an interesting but challenging problem. Traditional methods, based on handcrafted features or shallow-learning techniques, can only localize insulators and detect faults under specific detection conditions, such as when sufficient prior knowledge is available, with low background interference, at certain object scales, or under specific illumination conditions. This paper discusses the automatic detection of insulator defects using aerial images, accurately localizing insulator defects appearing in input images captured from real inspection environments. We propose a novel deep convolutional neural network (CNN) cascading architecture for performing localization and detecting defects in insulators. The cascading network uses a CNN based on a region proposal network to transform defect inspection into a two-level object detection problem. To address the scarcity of defect images in a real inspection environment, a data augmentation method is also proposed that includes four operations: 1) affine transformation; 2) insulator segmentation and background fusion; 3) Gaussian blur; and 4) brightness transformation. Defect detection precision and recall of the proposed method are 0.91 and 0.96 using a standard insulator dataset, and insulator defects under various conditions can be successfully detected. Experimental results demonstrate that this method meets the robustness and accuracy requirements for insulator defect detection.

Dynamic Event-Triggered Distributed Coordination Control and its Applications: A Survey of Trends and Techniques

Abstract: Distributed coordination control is the current trend in networked systems and finds prosperous applications across a variety of fields, such as smart grids and intelligent transportation systems. One fundamental issue in coordinating and controlling a large group of distributed and networked agents is the influence of intermittent interagent interactions caused by constrained communication resources. Event-triggered communication scheduling stands out as a promising enabler to strike a balance between the desired control performance and the satisfactory resource efficiency. What distinguishes dynamic event-triggered scheduling from traditional static event-triggered scheduling is that the triggering mechanism can be dynamically adjusted over time in accordance with both available system information and additional dynamic variables. This article provides an up-to-date overview of dynamic event-triggered distributed coordination control. The motivation of dynamic event-triggered scheduling is first introduced in the context of distributed coordination control. Then some techniques of dynamic event-triggered distributed coordination control are discussed in detail. Implementation and design issues are well addressed. Furthermore, this article exemplifies two applications of dynamic event-triggered distributed coordination control in the fields of microgrids and automated vehicles. Several challenges are suggested to direct the future research.

An Enhanced MSIQDE Algorithm With Novel Multiple Strategies for Global Optimization Problems

Abstract: Quantum-inspired differential evolution (QDE) is an evolutionary algorithm, which can effectively solve complex optimization problems. However, sometimes, it easily leads to premature convergence and low search ability and falls to local optima. To overcome these problems, based on the MSIQDE (improved QDE with multistrategies) algorithm, an enhanced MSIQDE algorithm based on mixing multiple strategies, namely, EMMSIQDE is proposed in this article. In the EMMSIQDE, a new differential mutation strategy of a difference vector is proposed to enhance the search ability and descent ability. Then, a new multipopulation mutation evolution mechanism is designed to ensure the relative independence of each subpopulation and the population diversity. The feasible solution space transformation strategy is used to achieve the optimal solution by mapping the quantum chromosome from a unit space to solution space. Finally, some multidimensional unimodal and multimodal functions are selected to demonstrate the optimization performance of EMMSIQDE. The results demonstrate that the EMMSIQDE is significantly better than the DE, QDE, QGA, and MSIQDE, and has better optimization ability, scalability, efficiency, and stability.

Memory-Based Event-Triggering H ∞ Load Frequency Control for Power Systems Under Deception Attacks

Abstract: This article proposes a memory-based event-triggering $H_{\infty }$ load frequency control (LFC) method for power systems through a bandwidth-constrained open network. To overcome the bandwidth constraint, a memory-based event-triggered scheme (METS) is first proposed to reduce the number of transmitted packets. Compared with the existing memoryless event-triggered schemes, the proposed METS has the advantage to utilize series of the latest released signals. To deal with the random deception attacks induced by open networks, a networked power system model is well established, which couples the effects of METS and random deception attacks in a unified framework. Then, a sufficient stabilization criterion is derived to obtain the memory $H_{\infty }$ LFC controller gains and event-triggered parameters simultaneously. Compared with existing memoryless LFC, the control performance is greatly improved since the latest released dynamic information is well utilized. Finally, an illustrative example is used to show the effectiveness of the proposed method.

A Survey of Optimization Methods From a Machine Learning Perspective

Abstract: Machine learning develops rapidly, which has made many theoretical breakthroughs and is widely applied in various fields. Optimization, as an important part of machine learning, has attracted much attention of researchers. With the exponential growth of data amount and the increase of model complexity, optimization methods in machine learning face more and more challenges. A lot of work on solving optimization problems or improving optimization methods in machine learning has been proposed successively. The systematic retrospect and summary of the optimization methods from the perspective of machine learning are of great significance, which can offer guidance for both developments of optimization and machine learning research. In this article, we first describe the optimization problems in machine learning. Then, we introduce the principles and progresses of commonly used optimization methods. Finally, we explore and give some challenges and open problems for the optimization in machine learning.

Event-Triggered Adaptive Tracking Control for Multiagent Systems With Unknown Disturbances

Abstract: This paper considers the event-triggered tracking control problem of nonlinear multiagent systems with unknown disturbances. The event-triggering mechanism is considered in the controller update, which decreases the amount of communication and reduces the frequency of the controller update in practice. By designing a disturbance observer, the unknown external disturbances are estimated. Moreover, a part of adaptive parameters are only dependent on the number of followers, which weakens the computational burden. It is shown that all the signals are bounded, and the consensus tracking errors are located in a small neighborhood of the origin based on the Lyapunov stability theory and backstepping approach. Finally, the effectiveness of the approach proposed in this paper is proved by simulation results.

Fuzzy Broad Learning System: A Novel Neuro-Fuzzy Model for Regression and Classification

Abstract: A novel neuro-fuzzy model named fuzzy broad learning system (BLS) is proposed by merging the Takagi–Sugeno (TS) fuzzy system into BLS. The fuzzy BLS replaces the feature nodes of BLS with a group of TS fuzzy subsystems, and the input data are processed by each of them. Instead of aggregating the outputs of fuzzy rules produced by every fuzzy subsystem into one value immediately, all of them are sent to the enhancement layer for further nonlinear transformation to preserve the characteristic of inputs. The defuzzification outputs of all fuzzy subsystem and the outputs of enhancement layer are combined together to obtain the model output. The ${k}$ -means method is employed to determine the centers of Gaussian membership functions in antecedent part and the number of fuzzy rules. The parameters that need to be calculated in a fuzzy BLS are the weights connecting the outputs of enhancement layer to model output and the randomly initialized coefficients of polynomials in consequent part in fuzzy subsystems, which can be calculated analytically. Therefore, fuzzy BLS retains the fast computational nature of BLS. The proposed fuzzy BLS is evaluated by some popular benchmarks for regression and classification, and compared with some state-of-the-art nonfuzzy and neuro-fuzzy approaches. The results indicate that fuzzy BLS outperforms other models involved. Moreover, fuzzy BLS shows advantages over neuro-fuzzy models regarding to the number of fuzzy rules and training time, which can ease the problem of rule explosion to some extent.

Resilient Control Design Based on a Sampled-Data Model for a Class of Networked Control Systems Under Denial-of-Service Attacks

Abstract: This article is concerned with designing resilient state feedback controllers for a class of networked control systems under denial-of-service (DoS) attacks. The sensor samples system states periodically. The DoS attacks usually prevent those sampled signals from being transmitted through a communication network. A logic processor embedded in the controller is introduced to not only receive sampled signals but also capture information on the duration time of each DoS attack. Note that the duration time of DoS attacks is usually both lower and upper bounded. Then the closed-loop system is modeled as an aperiodic sampled-data system closely related to both lower and upper bounds of duration time of DoS attacks. By introducing a novel looped functional, which caters for the $N$ -order canonical Bessel–Legendre inequalities, some $N$ -dependent stability criteria are presented for the resultant closed-loop system. It is worth pointing out that a number of identity formulas are uncovered, which enable us to apply the notable free-weighting matrix approach to derive less conservative stability criteria. A linear-matrix-inequality-based criterion is provided to design stabilizing state-feedback controllers against DoS attacks. A satellite control system is given to demonstrate the effectiveness of the proposed method.

Adaptive Consensus Control of Linear Multiagent Systems With Dynamic Event-Triggered Strategies

Abstract: This paper is concerned with event-triggered consensus of general linear multiagent systems (MASs) in leaderless and leader-following networks, respectively, in the framework of adaptive control. A distributed dynamic event-triggered strategy is first proposed, in which an auxiliary parameter is introduced for each agent to regulate its threshold dynamically. The time-varying threshold ensures less triggering instants, compared with the traditional static one. Then under the proposed event-triggered strategy, a distributed adaptive consensus protocol is formed including the updating law of the coupling strength for each agent. Some criteria are derived to guarantee leaderless or leader-following consensus for MASs with general linear dynamics, respectively. Moreover, it is proved that the triggering time sequences do not exhibit Zeno behavior. Finally, the effectiveness of the proposed dynamic event-triggered control mechanism combined with adaptive control is validated by two examples.

Event-Triggered Consensus Control for Multi-Agent Systems Against False Data-Injection Attacks

Abstract: In this article, the event-triggered security consensus problem is studied for time-varying multiagent systems (MASs) against false data-injection attacks (FDIAs) and parameter uncertainties over a given finite horizon. In the process of information transmission, the malicious attacker tries to inject false signals to destroy consensus by compromising the integrity of measurements and control signals. The randomly occurring stealthy FDIAs on sensors and actuators are modeled by the Bernoulli processes. In order to reduce the unnecessary utilization of communication resources, an event-triggered control mechanism with state-dependent threshold is adopted to update the control input signal. The main objective of this article is to design a controller such that, under randomly occurring FDIAs and admissible parameter uncertainties, the MASs achieve consensus. By utilizing stochastic analysis method, two sufficient criteria are derived to ensure that the prescribed $H_{\infty }$ consensus performance can be achieved. Then, the desired controller gains are derived by solving recursive linear matrix inequalities. Simulation results are presented to illustrate the effectiveness and applicability of the proposed control method.

Making Sense of Spatio-Temporal Preserving Representations for EEG-Based Human Intention Recognition

Abstract: Brain–computer interface (BCI) is a system empowering humans to communicate with or control the outside world with exclusively brain intentions. Electroencephalography (EEG)-based BCI is one of the promising solutions due to its convenient and portable instruments. Despite the extensive research of EEG in recent years, it is still challenging to interpret EEG signals effectively due to its nature of noise and difficulties in capturing the inconspicuous relations between EEG signals and specific brain activities. Most existing works either only consider EEG as chain-like sequences while neglecting complex dependencies between adjacent signals or requiring complex preprocessing. In this paper, we introduce two deep learning-based frameworks with novel spatio-temporal preserving representations of raw EEG streams to precisely identify human intentions. The two frameworks consist of both convolutional and recurrent neural networks effectively exploring the preserved spatial and temporal information in either a cascade or a parallel manner. Extensive experiments on a large scale movement intention EEG dataset (108 subjects, 3 145 160 EEG records) have demonstrated that the proposed frameworks achieve high accuracy of 98.3% and outperform a set of state-of-the-art and baseline models. The developed models are further evaluated with a real-world brain typing BCI and achieve a recognition accuracy of 93% over five instruction intentions suggesting good generalization over different kinds of intentions and BCI systems.

Multiple-Attribute Group Decision-Making Based on q-Rung Orthopair Fuzzy Power Maclaurin Symmetric Mean Operators

Abstract: To be able to describe more complex fuzzy uncertainty information effectively, the concept of ${q}$ -rung orthopair fuzzy sets ( ${q}$ -ROFSs) was first proposed by Yager. The ${q}$ -ROFSs can dynamically adjust the range of indication of decision information by changing a parameter ${q}$ based on the different hesitation degree from the decision-makers, where ${q} {\ge } {1}$ , so they outperform the traditional intuitionistic fuzzy sets and Pythagorean fuzzy sets. In real decision-making problems, there is often an interaction phenomenon between attributes. For aggregating these complex fuzzy information, the Maclaurin symmetric mean (MSM) operator is more superior by considering interrelationships among attributes. In addition, the power average (PA) operator can reduce the effects of extreme evaluating data from some experts with prejudice. In this paper, we introduce the PA operator and the MSM operator based on ${q}$ -rung orthopair fuzzy numbers ( ${q}$ -ROFNs). Then, we put forward the ${q}$ -rung orthopair fuzzy power MSM ( ${q}$ -ROFPMSM) operator and the ${q}$ -rung orthopair fuzzy power weighed MSM ( ${q}$ -ROFPWMSM) operator of ${q}$ -ROFNs and present some of their properties. Finally, we present a novel multiple-attribute group decision-making (MAGDM) method based on the ${q}$ -ROFPWA and the ${q}$ -ROFPWMSM operators. The experimental results show that the novel MAGDM method outperforms the existing MAGDM methods for dealing with MAGDM problems.

Robust Graph Learning From Noisy Data

Abstract: Learning graphs from data automatically have shown encouraging performance on clustering and semisupervised learning tasks. However, real data are often corrupted, which may cause the learned graph to be inexact or unreliable. In this paper, we propose a novel robust graph learning scheme to learn reliable graphs from the real-world noisy data by adaptively removing noise and errors in the raw data. We show that our proposed model can also be viewed as a robust version of manifold regularized robust principle component analysis (RPCA), where the quality of the graph plays a critical role. The proposed model is able to boost the performance of data clustering, semisupervised classification, and data recovery significantly, primarily due to two key factors: 1) enhanced low-rank recovery by exploiting the graph smoothness assumption and 2) improved graph construction by exploiting clean data recovered by RPCA. Thus, it boosts the clustering, semisupervised classification, and data recovery performance overall. Extensive experiments on image/document clustering, object recognition, image shadow removal, and video background subtraction reveal that our model outperforms the previous state-of-the-art methods.

Temporal Pattern-Aware QoS Prediction via Biased Non-Negative Latent Factorization of Tensors

Abstract: Quality-of-service (QoS) data vary over time, making it vital to capture the temporal patterns hidden in such dynamic data for predicting missing ones with high accuracy However, currently latent factor (LF) analysis-based QoS-predictors are mostly defined on static QoS data without the consideration of such temporal dynamics To address this issue, this paper presents a biased non-negative latent factorization of tensors (BNLFTs) model for temporal pattern-aware QoS prediction Its main idea is fourfold: 1) incorporating linear biases into the model for describing QoS fluctuations; 2) constraining the model to be non-negative for describing QoS non-negativity; 3) deducing a single LF-dependent, non-negative, and multiplicative update scheme for training the model; and 4) incorporating an alternating direction method into the model for faster convergence The empirical studies on two dynamic QoS datasets from real applications show that compared with the state-of-the-art QoS-predictors, BNLFT represents temporal patterns more precisely with high computational efficiency, thereby achieving the most accurate predictions for missing QoS data

Fault-Tolerant Consensus Tracking Control for Linear Multiagent Systems Under Switching Directed Network

Abstract: In this paper, for linear leader–follower networks with multiple heterogeneous actuator faults, including partial loss of effectiveness fault and actuator bias fault, a cooperative fault-tolerant control (CFTC) approach is developed. Assume that the interaction network topology among all nodes is a switching directed graph. To address the difficulty of designing the distributed compensation control laws under the time-varying asymmetrical network structure, a novel distributed-reference-observer-based fault-tolerant tracking control approach is established, under which the global tracking errors are proved to be asymptotically convergent in the presence of actuator failures. First, by constructing a group of distributed reference observers based on neighborhood state information, all followers can estimate the leader’s state trajectories directly. Second, a decentralized adaptive fault-tolerant tracking controller via local estimation is designed to achieve the global synchronization. Furthermore, the reliable coordination problem under switching directed topology with intermittent communications is solved by utilizing the presented CFTC approach. Finally, the effectiveness of the proposed coordination control protocol is illustrated by its applications to a networked aircraft system.

Prescribed Performance Cooperative Control for Multiagent Systems With Input Quantization

Abstract: This paper studies the quantized cooperative control problem for multiagent systems with unknown gains in the prescribed performance. Different from the finite-time control, a speed function is designed to realize that the tracking errors converge to a prescribed compact set in a given finite time for multiagent systems. Meanwhile, we consider the problem of unknown gains and input quantization, which can be addressed by using a lemma and Nussbaum function in cooperative control. Moreover, the fuzzy logic systems are proposed to approximate the nonlinear function defined on a compact set. A distributed controller and adaptive laws are constructed based on the Lyapunov stability theory and backstepping method. Finally, the effectiveness of the proposed approach is illustrated by some numerical simulation results.

Incomplete Multiview Spectral Clustering With Adaptive Graph Learning

Abstract: In this paper, we propose a general framework for incomplete multiview clustering. The proposed method is the first work that exploits the graph learning and spectral clustering techniques to learn the common representation for incomplete multiview clustering. First, owing to the good performance of low-rank representation in discovering the intrinsic subspace structure of data, we adopt it to adaptively construct the graph of each view. Second, a spectral constraint is used to achieve the low-dimensional representation of each view based on the spectral clustering. Third, we further introduce a co-regularization term to learn the common representation of samples for all views, and then use the ${k}$ -means to partition the data into their respective groups. An efficient iterative algorithm is provided to optimize the model. Experimental results conducted on seven incomplete multiview datasets show that the proposed method achieves the best performance in comparison with some state-of-the-art methods, which proves the effectiveness of the proposed method in incomplete multiview clustering.

Adaptive Fuzzy Finite-Time Control of Nonlinear Systems With Actuator Faults

Abstract: This paper addresses the trajectory tracking control problem of a class of nonstrict-feedback nonlinear systems with the actuator faults. The functional relationship in the affine form between the nonlinear functions with whole state and error variables is established by using the structure consistency of intermediate control signals and the variable-partition technique. The fuzzy control and adaptive backstepping schemes are applied to construct an improved fault-tolerant controller without requiring the specific knowledge of control gains and actuator faults, including both stuck constant value and loss of effectiveness. The proposed fault-tolerant controller ensures that all signals in the closed-loop system are semiglobally practically finite-time stable and the tracking error remains in a small neighborhood of the origin after a finite period of time. The developed control method is verified through two numerical examples.

Learning Graph Embedding With Adversarial Training Methods

Abstract: Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph-analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding distribution of the latent codes, which unfortunately may lead to inferior representation in many cases. In this article, we present a novel adversarially regularized framework for graph embedding. By employing the graph convolutional network as an encoder, our framework embeds the topological information and node content into a vector representation, from which a graph decoder is further built to reconstruct the input graph. The adversarial training principle is applied to enforce our latent codes to match a prior Gaussian or uniform distribution. Based on this framework, we derive two variants of the adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, and adversarially regularized variational graph autoencoder (ARVGA), to learn the graph embedding effectively. We also exploit other potential variations of ARGA and ARVGA to get a deeper understanding of our designs. Experimental results that compared 12 algorithms for link prediction and 20 algorithms for graph clustering validate our solutions.

Adaptive Fuzzy Control With High-Order Barrier Lyapunov Functions for High-Order Uncertain Nonlinear Systems With Full-State Constraints

Abstract: This paper focuses on the practical output tracking control for a category of high-order uncertain nonlinear systems with full-state constraints. A high-order tan-type barrier Lyapunov function (BLF) is constructed to handle the full-state constraints of the control systems. By the BLF and combining a backstepping design technique, an adding a power integrator, and a fuzzy control, the proposed approach can control high-order uncertain nonlinear system with full-state constraints. A novel controller is designed to ensure that the tracking errors approach to an arbitrarily small neighborhood of zero, and the constraints on system states are not violated. The numerical example demonstrates effectiveness of the proposed control method.

Feature Extraction for Classification of Hyperspectral and LiDAR Data Using Patch-to-Patch CNN

Abstract: Multisensor fusion is of great importance in Earth observation related applications For instance, hyperspectral images (HSIs) provide wealthy spectral information while light detection and ranging (LiDAR) data provide elevation information, and using HSI and LiDAR data together can achieve better classification performance In this paper, an unsupervised feature extraction framework, named as patch-to-patch convolutional neural network (PToP CNN), is proposed for collaborative classification of hyperspectral and LiDAR data More specific, a three-tower PToP mapping is first developed to seek an accurate representation from HSI to LiDAR data, aiming at merging multiscale features between two different sources Then, by integrating hidden layers of the designed PToP CNN, extracted features are expected to possess deeply fused characteristics Accordingly, features from different hidden layers are concatenated into a stacked vector and fed into three fully connected layers To verify the effectiveness of the proposed classification framework, experiments are executed on two benchmark remote sensing data sets The experimental results demonstrate that the proposed method provides superior performance when compared with some state-of-the-art classifiers, such as two-branch CNN and context CNN

Predicting COVID-19 in China Using Hybrid AI Model

Abstract: The coronavirus disease 2019 (COVID-19) breaking out in late December 2019 is gradually being controlled in China, but it is still spreading rapidly in many other countries and regions worldwide. It is urgent to conduct prediction research on the development and spread of the epidemic. In this article, a hybrid artificial-intelligence (AI) model is proposed for COVID-19 prediction. First, as traditional epidemic models treat all individuals with coronavirus as having the same infection rate, an improved susceptible–infected (ISI) model is proposed to estimate the variety of the infection rates for analyzing the transmission laws and development trend. Second, considering the effects of prevention and control measures and the increase of the public’s prevention awareness, the natural language processing (NLP) module and the long short-term memory (LSTM) network are embedded into the ISI model to build the hybrid AI model for COVID-19 prediction. The experimental results on the epidemic data of several typical provinces and cities in China show that individuals with coronavirus have a higher infection rate within the third to eighth days after they were infected, which is more in line with the actual transmission laws of the epidemic. Moreover, compared with the traditional epidemic models, the proposed hybrid AI model can significantly reduce the errors of the prediction results and obtain the mean absolute percentage errors (MAPEs) with 0.52%, 0.38%, 0.05%, and 0.86% for the next six days in Wuhan, Beijing, Shanghai, and countrywide, respectively.

Weakly Supervised Deep Learning for Whole Slide Lung Cancer Image Analysis

Abstract: Histopathology image analysis serves as the gold standard for cancer diagnosis. Efficient and precise diagnosis is quite critical for the subsequent therapeutic treatment of patients. So far, computer-aided diagnosis has not been widely applied in pathological field yet as currently well-addressed tasks are only the tip of the iceberg. Whole slide image (WSI) classification is a quite challenging problem. First, the scarcity of annotations heavily impedes the pace of developing effective approaches. Pixelwise delineated annotations on WSIs are time consuming and tedious, which poses difficulties in building a large-scale training dataset. In addition, a variety of heterogeneous patterns of tumor existing in high magnification field are actually the major obstacle. Furthermore, a gigapixel scale WSI cannot be directly analyzed due to the immeasurable computational cost. How to design the weakly supervised learning methods to maximize the use of available WSI-level labels that can be readily obtained in clinical practice is quite appealing. To overcome these challenges, we present a weakly supervised approach in this article for fast and effective classification on the whole slide lung cancer images. Our method first takes advantage of a patch-based fully convolutional network (FCN) to retrieve discriminative blocks and provides representative deep features with high efficiency. Then, different context-aware block selection and feature aggregation strategies are explored to generate globally holistic WSI descriptor which is ultimately fed into a random forest (RF) classifier for the image-level prediction. To the best of our knowledge, this is the first study to exploit the potential of image-level labels along with some coarse annotations for weakly supervised learning. A large-scale lung cancer WSI dataset is constructed in this article for evaluation, which validates the effectiveness and feasibility of the proposed method. Extensive experiments demonstrate the superior performance of our method that surpasses the state-of-the-art approaches by a significant margin with an accuracy of 97.3%. In addition, our method also achieves the best performance on the public lung cancer WSIs dataset from The Cancer Genome Atlas (TCGA). We highlight that a small number of coarse annotations can contribute to further accuracy improvement. We believe that weakly supervised learning methods have great potential to assist pathologists in histology image diagnosis in the near future.

Observer-Based Event-Triggered Control for Networked Linear Systems Subject to Denial-of-Service Attacks

Abstract: This paper is concerned with the observer-based event-triggered control for a continuous networked linear system subject to denial-of-service (DoS) attacks, where the attacks are launched periodically to block the data transmission in control channels. First, a new observer state-based resilient event-triggering scheme is developed in the presence of DoS attacks. Second, a novel event-based switched system model is established by considering the effect of the event-triggering scheme and DoS attacks simultaneously. By virtue of this new model combined with a piecewise Lyapunov–Krasovskii functional method, the sufficient conditions are derived to guarantee exponential stability of the resulting switched system. It is shown that the proposed results can establish a quantitative relationship among the launching/sleeping periods of the attacks, the event-triggering parameters, the sampling period, and the exponential decay rate. Third, criteria for designing a desired observer-based event-triggered controller are provided and expressed in terms of a set of linear matrix inequalities. Finally, an offshore structure model is presented to illustrate the efficiency of the developed control method.

Output-Feedback Cooperative Formation Maneuvering of Autonomous Surface Vehicles With Connectivity Preservation and Collision Avoidance

Abstract: In this paper, a cooperative time-varying formation maneuvering problem with connectivity preservation and collision avoidance is investigated for a fleet of autonomous surface vehicles (ASVs) with position–heading measurements. Each vehicle is subject to unknown kinetics induced by internal model uncertainty and external disturbances. At first, a nonlinear state observer is used to recover the unmeasured linear velocity and yaw rate as well as unknown uncertainty and disturbances. Then, observer-based cooperative time-varying formation maneuvering control laws are designed based on artificial potential functions, nonlinear tracking differentiators, and a backstepping technique. The stability of closed-loop distributed formation control system is analyzed based on input-to-state stability and cascade stability. The salient features of the proposed method are as follows. First, cooperative time-varying formation maneuvering with the capability of connectivity preservation and collision avoidance can be achieved in the absence of velocity measurements. Second, the complexity of the cooperative time-varying formation maneuvering control laws is reduced without resorting to dynamic surface control. Third, the uncertainty and disturbance are actively rejected in the presence of position–heading measurements. Simulation results are given to substantiate the proposed output feedback control method for cooperative time-varying formation maneuvering of ASVs with connectivity preservation and collision avoidance.