Dalian Maritime University

Broad Learning System (BLS) that aims to offer an alternative way of learning in deep structure is proposed in this paper. Deep structure and learning suffer from a time-consuming training process because of a large number of connecting parameters in filters and layers. Moreover, it encounters a complete retraining process if the structure is not sufficient to model the system. The BLS is established in the form of a flat network, where the original inputs are transferred and placed as "mapped features" in feature nodes and the structure is expanded in wide sense in the "enhancement nodes." The incremental learning algorithms are developed for fast remodeling in broad expansion without a retraining process if the network deems to be expanded. Two incremental learning algorithms are given for both the increment of the feature nodes (or filters in deep structure) and the increment of the enhancement nodes. The designed model and algorithms are very versatile for selecting a model rapidly. In addition, another incremental learning is developed for a system that has been modeled encounters a new incoming input. Specifically, the system can be remodeled in an incremental way without the entire retraining from the beginning. Satisfactory result for model reduction using singular value decomposition is conducted to simplify the final structure. Compared with existing deep neural networks, experimental results on the Modified National Institute of Standards and Technology database and NYU NORB object recognition dataset benchmark data demonstrate the effectiveness of the proposed BLS.

Underwater images typically suffer from color deviations and low visibility due to the wavelength-dependent light absorption and scattering. To deal with these degradation issues, we propose an efficient and robust underwater image enhancement method, called MLLE. Specifically, we first locally adjust the color and details of an input image according to a minimum color loss principle and a maximum attenuation map-guided fusion strategy. Afterward, we employ the integral and squared integral maps to compute the mean and variance of local image blocks, which are used to adaptively adjust the contrast of the input image. Meanwhile, a color balance strategy is introduced to balance the color differences between channel a and channel b in the CIELAB color space. Our enhanced results are characterized by vivid color, improved contrast, and enhanced details. Extensive experiments on three underwater image enhancement datasets demonstrate that our method outperforms the state-of-the-art methods. Our method is also appealing in its fast processing speed within 1s for processing an image of size 1024×1024×3 on a single CPU. Experiments further suggest that our method can effectively improve the performance of underwater image segmentation, keypoint detection, and saliency detection. The project page is available at https://li-chongyi.github.io/proj_MMLE.html.

Optical biosensors have exhibited worthwhile performance in detecting biological systems and promoting significant advances in clinical diagnostics, drug discovery, food process control, and environmental monitoring. Without complexity in their pretreatment and probable influence on the nature of target molecules, these biosensors have additional advantages such as high sensitivity, robustness, reliability, and potential to be integrated on a single chip. In this review, the state of the art optical biosensor technologies, including those based on surface plasmon resonance (SPR), optical waveguides, optical resonators, photonic crystals, and optical fibers, are presented. The principles for each type of biosensor are concisely introduced and particular emphasis has been placed on recent achievements. The strengths and weaknesses of each type of biosensor have been outlined as well. Concluding remarks regarding the perspectives of future developments are discussed.

Autonomous surface vehicles (ASVs) are marine vessels capable of performing various marine operations without a crew in a variety of cluttered and hostile water/ocean environments. For complex missions, there are increasing needs for deploying a fleet of ASVs instead of a single one to complete difficult tasks. Cooperative operations with a fleet of ASVs offer great advantages with enhanced capability and efficacy. Despite various application potentials, coordinated motion control of ASVs pose great challenges due to the multiplicity of ASVs, complexity of intravehicle interactions and fleet formation with collision avoidance requirements, and scarcity of communication bandwidths in sea environments. Coordinated control of multiple ASVs has received considerable attention in the last decade. This article provides an overview of recent advances in coordinated control of multiple ASVs. First, some challenging issues and scenarios in motion control of ASVs are presented. Next, coordinated control architecture and methods of multiple ASVs are briefly discussed. Then, recent results on trajectory-guided, path-guided, and target-guided coordinated control of multiple ASVs are reviewed in detail. Finally, several theoretical and technical issues are suggested to direct future investigations including network-based coordination, event-triggered coordination, collision-free coordination, optimization-based coordination, data-driven coordination of ASVs, and task-region-oriented coordination of multiple ASVs and autonomous underwater vehicles.

SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from Synthetic Aperture Radar (SAR) imagery based on deep learning (DL). According to our investigation, up to 46.59% of the total 161 public reports confidently select SSDD to study DL-based SAR ship detection. Undoubtedly, this situation reveals the popularity and great influence of SSDD in the SAR remote sensing community. Nevertheless, the coarse annotations and ambiguous standards of use of its initial version both hinder fair methodological comparisons and effective academic exchanges. Additionally, its single-function horizontal-vertical rectangle bounding box (BBox) labels can no longer satisfy the current research needs of the rotatable bounding box (RBox) task and the pixel-level polygon segmentation task. Therefore, to address the above two dilemmas, in this review, advocated by the publisher of SSDD, we will make an official release of SSDD based on its initial version. SSDD’s official release version will cover three types: (1) a bounding box SSDD (BBox-SSDD), (2) a rotatable bounding box SSDD (RBox-SSDD), and (3) a polygon segmentation SSDD (PSeg-SSDD). We relabel ships in SSDD more carefully and finely, and then explicitly formulate some strict using standards, e.g., (1) the training-test division determination, (2) the inshore-offshore protocol, (3) the ship-size reasonable definition, (4) the determination of the densely distributed small ship samples, and (5) the determination of the densely parallel berthing at ports ship samples. These using standards are all formulated objectively based on the using differences of existing 75 (161 × 46.59%) public reports. They will be beneficial for fair method comparison and effective academic exchanges in the future. Most notably, we conduct a comprehensive data analysis on BBox-SSDD, RBox-SSDD, and PSeg-SSDD. Our analysis results can provide some valuable suggestions for possible future scholars to further elaborately design DL-based SAR ship detectors with higher accuracy and stronger robustness when using SSDD.

A robust adaptive tracking control approach is presented for a class of strict-feedback single-input-single-output nonlinear systems. By employing radial-basis-function neural networks to account for system uncertainties, the proposed scheme is developed by combining "dynamic surface control" and "minimal learning parameter" techniques. The key features of the algorithm are that, first, the problem of "explosion of complexity" inherent in the conventional backstepping method is avoided, second, the number of parameters updated online for each subsystem is reduced to 2, and, third, the possible controller singularity problem in the approximation-based adaptive control schemes with feedback linearization technique is removed. These features result in a much simpler adaptive control algorithm, which is convenient to implement in applications. In addition, it is shown via input-to-state stability theory and small gain approach that all signals in the closed-loop system are semiglobal uniformly ultimately bounded. Finally, three simulation examples are used to demonstrate the effectiveness of the proposed scheme.

In this brief, we consider the formation control problem of underactuated autonomous surface vehicles (ASVs) moving in a leader-follower formation, in the presence of uncertainties and ocean disturbances. A robust adaptive formation controller is developed by employing neural network and dynamic surface control technique. The stability of the design is proven via Lyapunov analysis where semiglobal uniform ultimate boundedness of the closed-loop signals is guaranteed. The advantages of the proposed formation controller are that: first, the proposed method only uses the measurements of line-of-sight range and angle by local sensors, no other information about the leader is required for control implementation; second, the developed neural formation controller is able to capture the vehicle dynamics without exact information of coriolis and centripetal force, hydrodynamic damping and disturbances from the environment. Comparative analysis with a model-based approach is given to demonstrate the effectiveness of the proposed method.

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.

In this paper, an adaptive fuzzy backstepping dynamic surface control (DSC) approach is developed for a class of multiple-input-multiple-output nonlinear systems with immeasurable states. Using fuzzy-logic systems to approximate the unknown nonlinear functions, a fuzzy state observer is designed to estimate the immeasurable states. By combining adaptive-backstepping technique and DSC technique, an adaptive fuzzy output-feedback backstepping-control approach is developed. The proposed control method not only overcomes the problem of "explosion of complexity" inherent in the backstepping-design methods but also overcomes the problem of unavailable state measurements. It is proved that all the signals of the closed-loop adaptive-control system are semiglobally uniformly ultimately bounded, and the tracking errors converge to a small neighborhood of the origin. Simulation results are provided to show the effectiveness of the proposed approach.

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.

In this paper, an adaptive fuzzy backstepping output-feedback tracking control approach is proposed for a class of multi-input and multi-output (MIMO) stochastic nonlinear systems. The MIMO stochastic nonlinear systems under study are assumed to possess unstructured uncertainties, unknown dead-zones, and unknown control directions. By using a linear state transformation, the unknown control coefficients and the unknown slopes characteristic of the dead-zones are lumped together, and the original system is transformed to a new system on which the control design becomes feasible. Fuzzy logic systems are used to approximate the unstructured uncertainties, and a fuzzy state observer is designed to estimate the unmeasured states. By introducing a special Nussbaum gain function into the backstepping control design, a stable adaptive fuzzy output-feedback tracking control scheme is developed. The main features of the proposed adaptive control approach are that it can guarantee the stability of the closed-loop system, and the tracking errors converge to a small neighborhood of zero. Moreover, it can solve the problems of unknown control direction, unknown dead-zone, and unmeasured states simultaneously. Two simulation examples are provided to show the effectiveness of the proposed approach.

Due to their unique characteristics, nanoparticles are increasingly used in agricultural production through foliage spraying and soil application. The use of nanoparticles can improve the efficiency of agricultural chemicals and reduce the pollution caused by the use of agricultural chemicals. However, introducing nanoparticles into agricultural production may pose risks to the environment, food and even human health. Therefore, it is crucial to pay attention to the absorption migration, and transformation in crops, and to the interaction with higher plants and plant toxicity of nanoparticles in agriculture. Research shows that nanoparticles can be absorbed by plants and have an impact on plant physiological activities, but the absorption and transport mechanism of nanoparticles is still unclear. This paper summarizes the research progress of the absorption and transportation of nanoparticles in plants, especially the effect of size, surface charge and chemical composition of nanoparticle on the absorption and transportation in leaf and root through different ways. This paper also reviews the impact of nanoparticles on plant physiological activity. The content of the paper is helpful to guide the rational application of nanoparticles in agricultural production and ensure the sustainability of nanoparticles in agricultural production.

In this paper, a composite adaptive fuzzy output-feedback control approach is proposed for a class of single-input and single-output strict-feedback nonlinear systems with unmeasured states and input saturation. Fuzzy logic systems are utilized to approximate the unknown nonlinear functions, and a fuzzy state observer is designed to estimate the unmeasured states. By utilizing the designed fuzzy state observer, a serial-parallel estimation model is established. Based on adaptive backstepping dynamic surface control technique and utilizing the prediction error between the system states observer model and the serial-parallel estimation model, a new fuzzy controller with the composite parameters adaptive laws are developed. It is proved that all the signals of the closed-loop system are bounded and the system output can follow the given bounded reference signal. A numerical example and simulation comparisons with previous control methods are provided to show the effectiveness of the proposed approach.

Autonomous underwater vehicles (AUVs) are submersible underwater vehicles controlled by onboard computers. AUV formation is a cooperative control which focuses on controlling multiple AUVs to move in a group while executing tasks. In contrast to a single AUV, multi-AUV formation represents higher efficiency and better stability for many applications, such as oil and gas industries, hydrographic surveys, and military missions, etc. To achieve better formation, there are several key factors, including AUV performance, formation control, and communication capability. However, most studies in the field of AUV formation mainly focus on formation control methods. We observe that the research of communication capability and AUV performance of multiple AUV formation is still in an early stage. It is beneficial to researchers to present a comprehensive survey of the state of the art of AUV formation research and development. In this paper, we study AUV, formation control, and underwater acoustic communication capability in detail. We propose a classification framework with three dimensions, including AUV performance, formation control, and communication capability. This framework provides a comprehensive classification method for future AUV formation research. It also can be used to compare different methods and help engineers choose suitable formation methods for various applications. Moreover, our survey discusses formation architecture with communication constraints and we identify some common misconceptions and questionable research for formation control related to communication.

In this paper, an adaptive fuzzy decentralized output feedback control design is presented for a class of interconnected nonlinear pure-feedback systems. The considered nonlinear systems contain unknown nonlinear uncertainties and the states are not necessary to be measured directly. Fuzzy logic systems are employed to approximate the unknown nonlinear functions, and then a fuzzy state observer is designed and the estimations of the immeasurable state variables are obtained. Based on the adaptive backstepping dynamic surface control design technique, an adaptive fuzzy decentralized output feedback control scheme is developed. It is proved that all the variables of the resulting closed-loop system are semi-globally uniformly ultimately bounded, and also that the observer and tracking errors are guaranteed to converge to a small neighborhood of the origin. Some simulation results and comparisons with the existing results are provided to illustrate the effectiveness and merits of the proposed approach.

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.

This paper is concerned with the event-triggered finite-time control problem for networked switched linear systems by using an asynchronous switching scheme. Not only the problem of finite-time boundedness, but also the problem of input-output finite-time stability is considered in this paper. Compared with the existing event-triggered results of the switched systems, a new type of event-triggered condition is proposed. Sufficient conditions are established to guarantee the event-based asynchronous closed-loop systems are both finite-time bounded and input-output finite-time stable. A set of event-triggered finite-time bounded and input-output finite-time stabilizing controllers are designed under the asynchronous control scheme. It is revealed that the triggered thresholds determine the number of sampling points transmitted to the controller, and the smaller triggered parameters indicate the less-sampled data needed to be transmitted to the controller under the event-triggered scheme. Finally, a boost converter circuit is applied to bring out the advantages of the proposed control scheme.

In this paper, a hybrid fuzzy adaptive output feedback control design approach is proposed for a class of multiinput and multioutput strict-feedback nonlinear systems with unknown time-varying delays, unmeasured states, and input saturation. First, fuzzy logic systems are employed to approximate unknown nonlinear functions in the system. Next, a smooth function is used to approximate the input saturation and an adaptive fuzzy state observer is constructed to solve the problem of unmeasured states. Based on the designed adaptive fuzzy state observer, a serial-parallel estimation model is established. By applying adaptive fuzzy dynamic surface control technique and utilizing the prediction error between the system states observer model and the serial-parallel estimation model, a new fuzzy controller with the composite parameters adaptive laws is developed based on Lyapunov-Krasovskii functional. It is proved that all variables of the closed-loop system are bounded and the system outputs can follow the given bounded reference signals as close as possible. A simulation example is provided to further show the effectiveness of this novel control scheme.

In this paper, a robust adaptive tracking control problem is discussed for a general class of strict-feedback uncertain nonlinear systems. The systems may possess a wide class of uncertainties referred to as unstructured uncertainties, which are not linearly parameterized and do not have any prior knowledge of the bounding functions. The Takagi-Sugeno type fuzzy logic systems are used to approximate the uncertainties. A unified and systematic procedure is employed to derive two kinds of novel robust adaptive tracking controllers by use of the input-to-state stability (ISS) and by combining the backstepping technique and generalized small gain approach. One is the robust adaptive fuzzy tracking controller (RAFTC) for the system without input gain uncertainty. The other is the robust adaptive fuzzy sliding tracking controller (RAFSTC) for the system with input gain uncertainty. Both algorithms have two advantages, those are, semi-global uniform ultimate boundedness of adaptive control system in the presence of unstructured uncertainties and the adaptive mechanism with minimal learning parameterizations. Four application examples, including a pendulum system with motor, a one-link robot, a ship roll stabilization with actuator and a single-link manipulator with flexible joint, are used to demonstrate the effectiveness and performance of proposed schemes.

A novel nonlinear sliding mode control approach dealing with the formation control of under-actuated ships is presented in this paper. To avoid the singularity problem, state space of the system is partitioned into two regions, with one region bounded for terminal sliding mode control and its complement singular for that. And a linear auxiliary sliding mode controller is designed for system trajectories starting from the complement region. With the application of nonlinear sliding mode control approach and finite-time stability theory, a distributed controller is designed for individual under-actuated ship to achieve the given formation pattern within a finite time. Finally, two simulation examples are provided to verify the effectiveness and performance of the proposed approach.