Search

This article develops a novel cost function (performance index function) to overcome the obstacles in solving the optimal tracking control problem for a class of nonlinear systems with known system dynamics via adaptive dynamic programming (ADP) technique. For the traditional optimal control problems, the assumption that the controlled system has zero equilibrium is generally required to guarantee the finiteness of an infinite horizon cost function and a unique solution. In order to solve the optimal tracking control problem of nonlinear systems with nonzero equilibrium, a specific cost function related to tracking errors and their derivatives is designed in this article, in which the aforementioned assumption and related obstacles are removed and the controller design process is simplified. Finally, comparative simulations are conducted on an inverted pendulum system to illustrate the effectiveness and advantages of the proposed optimal tracking control strategy.

In this article, a combined gradient descent-Barzilai Borwein (GD-BB) algorithm and radial basis function neural network (RBFNN) output tracking control strategy was proposed for a family of nonlinear systems with unknown drift function and control input gain function. In such a method, a neural network (NN) is used to approximate the controller directly. The main merits of the proposed strategy are given as follows: first, not only the NN parameters, such as weights, centers, and widths but also the learning rates of NN parameter updating laws are updated online via the proposed learning algorithm based on Barzilai-Borwein technique; and second, the controller design process can be further simplified, the controller parameters that should be tuned can be greatly reduced. Theoretical analysis about the stability of the closed-loop system is manifested. In addition, simulations were conducted on a numerical discrete time system and an inverted pendulum system to validate the presented control strategy.

This article investigates the adaptive fuzzy control algorithm for a class of large-scale switched fractional-order nonlinear nonstrict feedback systems. In this algorithm, we utilize fuzzy-logic systems (FLSs) to approximate the complicated unknown nonlinear functions. Based on the fractional Lyapunov stability rules, a virtual control law is presented. A fuzzy adaptive decentralized control method is developed under the technique of the Lyapunov function. Under the operation of the proposed algorithm, the stability of the proposed systems and the control performance can be guaranteed. Finally, simulation results are presented to illustrate the feasibility and effectiveness of the proposed method.

In this paper, sparse autoencoder in deep learning is integrated into the compressed sensing (CS) theory, and a reconstruction algorithm is designed based on the biological mechanism of human brain synaptic connections. The compressive sampling process is modeled as a neural network model. Then a biological mechanism-inspired stacked Long Short-Term Memory (LSTM) network model is proposed as a reconstruction algorithm of CS theory. Consequently, a compressed sensing network (ComsensNet) model is introduced, by integrating the compressive sampling process and reconstruction algorithm. ComsensNet can provide a bridge between sparse autoencoder in deep learning, synapses in human brain neurons and the CS theory. A deep neural network is designed based on the synaptic biological mechanism of human brain neurons, and then combine with the theory of compressed sensing. The effectiveness of ComsensNet is investigated by using acquired pressure data from the human body model. Experimental results demonstrate that the biological mechanisminspired stacked LSTM network in ComsensNet can improve the reconstruction accuracy compared to other reconstruction algorithms.

In mobile Internet ecosystem, Mobile Users (MUs) purchase wireless data services from Internet Service Provider (ISP) to access to Internet and acquire the interested content services (e.g., online game) from Content Provider (CP). The popularity of intelligent functions (e.g., AI and 3D modeling) increases the computation-intensity of the content services, leading to a growing computation pressure for the MUs' resource-limited devices. To this end, edge computing service is emerging as a promising approach to alleviate the MUs' computation pressure while keeping their quality-of-service, via offloading some computation tasks of MUs to edge (computing) servers deployed at the local network edge. Thus, Edge Service Provider (ESP), who deploys the edge servers and offers the edge computing service, becomes an upcoming new stakeholder in the ecosystem. In this work, we study the economic interactions of MUs, ISP, CP, and ESP in the new ecosystem with edge computing service, where MUs can acquire the computation-intensive content services (offered by CP) and offload some computation tasks, together with the necessary raw input data, to edge servers (deployed by ESP) through ISP. We first study the MU's Joint Content Acquisition and Task Offloading (J-CATO) problem, which aims to maximize his long-term payoff. We derive the off-line solution with crucial insights, based on which we design an online strategy with provable performance. Then, we study the ESP's edge service monetization problem. We propose a pricing policy that can achieve a constant fraction of the ex-post optimal revenue with an extra constant loss for the ESP. Numerical results show that the edge computing service can stimulate the MUs' content acquisition and improve the payoffs of MUs, ISP, and CP., Comment: This is an online technical report

In this paper, the finite-time adaptive fuzzy state-feedback tracking control problem for the pure-feedback system with full-state constraints is studied. In order to transform the pure-feedback form into system strict-feedback case, the Mean-Value Theorem is introduced. By employing finite-time-stable like function and state transformation for output tracking error, the output tracking error converges to a predefined set in a fixed finite interval. To tackle the problem of state constraints, integral Barrier Lyapunov functions are utilized to guarantee that the state variables remain within the prescribed constraints with feasibility check. Fuzzy logic systems are utilized in this paper to approximate nonlinear uncertainties. In addition, all the signals in the system are guaranteed to be semi-global ultimately uniformly bounded. Finally, two simulation examples are given to show the effectiveness of the proposed control strategy.

This paper studies the disturbance observer-based adaptive fuzzy finite-time control issue of strict-feedback nonlinear systems. Specifically, to meet practical application requirement, the finite-time prescribed performance is considered, which can guarantee the tracking error enters into the prescribed bounded set in a known time. A disturbance observer is proposed to estimate the external disturbance. It is proved that the closed-loop system is semi-globally practically finite-time stable. Finally, simulation studies for a one-link manipulator are shown to verify the effectiveness of the proposed approach.

Airborne Distributed Coherent Aperture Radar (ADCAR) is one of the most promising next-generation radars to significantly improve target detection and discrimination abilities. However, time and phase synchronization among unit radars should be done before an ADCAR is intended to cohere on a potential target. To address this problem, a time and phase synchronization technique using clutter observations is proposed in this paper. Clutter returns from different azimuths and elevations on the surface of the earth are employed to calibrate system uncertainties. Two stages are mainly considered: a scene registration among range-Doppler units from different transmit/receive pairs is performed to enhance the clutter coherence in the first stage, followed by a joint estimation of those synchronization errors in the second stage. To relieve the computational burden, a novel Separable and Sequential Estimation (SSE) method is provided to separate the unknowns at the sacrifice of a range-Doppler unit. Moreover, performance analyses including the clutter coherence ability, estimation lower bound, and signal coherence loss are also performed. Finally, simulation results indicate that ADCAR time and phase synchronization is realized by using our methods.

This article investigates the command filtering-based event-triggered adaptive fuzzy control problem for a class of stochastic nonlinear systems with stochastic faults and input saturation. The unknown nonlinear functions and system dynamic changes that caused by stochastic faults are approximated by fuzzy logic systems (FLSs). In order to reduce the computational burden, the command filtering design technique is incorporated into the adaptive fuzzy event-triggered control strategy. Finally, the effectiveness of the proposed method is verified by simulation studies, in which the uniform ultimate boundedness of the system is guaranteed and all the signals in the closed-loop system are bounded.

Edge computing in vehicles is emerging as an essential candidate for the Internet of Vehicles (IoV) to improve traffic efficiency. The proliferation of IoV pushes the horizon of edge computing. The social features and connections among vehicles are significant for traffic efficiency solutions. However, it is quite challenging to perform collaborative edge computing (CEC) for social IoV systems because of network heterogeneity, vehicle mobility, user selfishness, privacy, and so on. This article focuses on the CEC, in the social IoV system to alleviate urban traffic congestion. Recent research reveals that intelligent traffic lights control through city-wide mobile edge computing (MEC) servers can reduce vehicles' average waiting time at signal intersections. This article has focused on a CEC-based traffic management system (CEC-TMS) to reduce the average waiting time. It utilizes multiagent-based deep reinforcement learning (DRL) for the MEC servers that interact with IoV and traffic lights to generate dynamic green waves at congested intersections. Results demonstrate the effectiveness of the proposed system under the paradigm of multiagent DRL.

An adaptive fuzzy decentralized control algorithm is developed in this article for interconnected nonlinear large-scale systems with unmodeled dynamics. This method is proposed by applying a fuzzy logic system (FLS) to identify unknown nonlinear functions. In addition, dynamic signals are introduced in design process of the backstepping to compensate the effect of unmodeled dynamics. A novel adaptive state feedback control algorithm is proposed with the help of Lyapunov function. Then, the state feedback control algorithm is extended to the case of output feedback by constructing a fuzzy state observer with FLSs. The large-scale and closed-loop nonlinear system is ensured to be semi-global uniformly ultimately bounded (SGUUB). Apart from this, all signals are guaranteed to be bounded. Both numerical and practical simulation examples are utilized to elaborate the feasibility of the developed control algorithms.

The ``shared head for classification and localization'' (sibling head) has been leading the fashion of the object detection community over the past years. However, the article by Song et al. (2020) found that there is a spatial misalignment between the two object functions of sibling head and proposed an operator called task-aware spatial disentanglement (TSD) to decouple the classification and regression from the spatial dimension by generating two disentangled proposals. But there are two problems in applying TSD to detecting rotated objects. The first problem is that the deformable pooling with the disentangled proposals in TSD is not rotation-invariant. The second problem is that the angle offset is not considered when getting the disentangled proposals. To address the above problems, we propose a rotation-invariant TSD (RITSD) method. The proposed method adopts the rotation-invariant deformable pooling and angle offset learning when getting region-of-interest (RoI) features. Considering the rotated anchor increases the computational burden and training time, we use a three-stage backbone that first utilizes horizontal proposals to obtain rotated proposals and then obtains the predicted rotated bounding boxes. Finally, detailed ablation studies on our collected dataset and HRSC2016 were performed to demonstrate the feasibility and superiority of our proposed method. From the heatmap, we find the features of near bow and stern areas are beneficial for classification and the side areas of ships are good at bounding box regression.

This paper investigated the adaptive fuzzy finite-time control problem for a class of high-order stochastic nonlinear systems with a class of exponential type prescribed performance function. It is assumed that the nonlinear functions in the controlled plant are unknown, in which fuzzy logic systems (FLSs) are utilized due to the approximation ability of any unknown continuous functions with arbitrary approximation errors. Based on the FLSs and backstepping design technique, an novel adaptive fuzzy tracking control strategy is proposed to guarantee that the closed-loop nonlinear system is semi-globally finite-time stable in probability via Lyapunov stability theory and It ${\hat o}$ formula. Compared with existing results, the transformed error signal was regarded as a stochastic variable. In addition, the expressions of the first and second-order partial derivatives of the transformed error signals are given in this paper. Finally, a simulation example with different covariance values is given to show the effectiveness of the proposed control strategy.

This article investigates the adaptive fuzzy control problem for a class of stochastic nonlinear systems with the risk-sensitive performance index. The desired cost level of the risk-sensitive index, which could be arbitrarily small, is guaranteed by the solution of a specified Hamilton–Jacobi–Bellman (HJB) equation. By considering the unknown uncertainties of the stochastic nonlinear systems, a novel adaptive fuzzy risk-sensitive control method is proposed, which guarantees the input-to-state stability of the system. In addition, the proposed control strategy also reduces the conservatism of the existing adaptive robust control method. Finally, the effectiveness of the proposed approach is verified by a simulation example of one-link manipulator.

This article investigates the adaptive learning control problem for a class of nonlinear autonomous underwater vehicles (AUVs) with unknown uncertainties. The unknown nonlinear functions in the AUVs are approximated by radial basis function neural networks (RBFNNs), in which the weight updating laws are designed via gradient descent algorithm. The proposed gradient descent-based control scheme guarantees the semiglobal uniform ultimate boundedness (SUUB) of the system and the fast convergence of the weight updating laws. In order to reduce the computational burden during the backstepping control design process, the command-filter-based design technique is incorporated into the adaptive learning control strategy. Finally, simulation studies are given to demonstrate the effectiveness of the proposed method.

Internet of things (IoT) has been developed and applied rapidly because of its huge commercial value in recent years. However, security problem has become a key factor restricting the development of IoT. The nodes of IoT are easy to be impersonated or replaced when attacked, which leads to the mistake of the uploaded data, the abnormal use of the application, and so on. Identifying the authenticity of the data submitted by the nodes is the top priority. We propose a scheme to verify the authenticity of multinode data. In this scheme, the authenticity of node data is checked through visual secret recovery and XOR operation together. The least significant bit (lsb) operation converts data from nodes into a bit, which improves the efficiency of data verification and reduces the risk of data leakage. This scheme achieves the purpose of verifying the data provided by the node, which avoids malicious attacks from illegal nodes. By analyzing the experiment result and comparing with other works, our scheme has the advantages of high verification efficiency, lightweight storage of nodes, and security verification.

Particle swarm optimization (PSO) has been employed to solve numerous real-world problems because of its strong optimization ability and easy implementation. However, PSO still has some shortcomings in solving complicated optimization problems, such as premature convergence and poor balance between global exploration and local exploitation. A novel hybrid particle swarm optimization using adaptive strategy (ASPSO) is developed to address associated difficulties. The contribution of ASPSO is threefold: (1) a chaotic map and an adaptive position updating strategy to balance exploration behavior and exploitation nature in the search progress; (2) elite and dimensional learning strategies to enhance the diversity of the population effectively; (3) a competitive substitution mechanism to improve the accuracy of solutions. Based on various functions from CEC 2017, the numerical experiment results demonstrate that ASPSO is significantly better than the other 16 optimization algorithms. Furthermore, we apply ASPSO to a typical industrial problem, the optimization of melt spinning progress, where the results indicate that ASPSO performs better than other algorithms.

In this paper, the tracking control problem of a three degrees of freedom (3-DOF) helicopter with unknown actuator faults, model uncertainties and external time-varying disturbances is solved by us...

This article investigates the problem of adaptive fuzzy decentralized tracking control design for a class of large-scale interconnected nonlinear systems with network-induced input time delay. First, fuzzy logic systems are used to approximate the unknown nonlinear functions. Then, a newly defined filtered error is introduced to compensate the network-induced delay, and a novel adaptive fuzzy decentralized control strategy is proposed to guarantee the uniform ultimate boundedness of the closed-loop nonlinear system. Finally, a simulation example is given to further demonstrate the effectiveness of the proposed method.

This article proposes a novel modeling and path planning framework to tackle a new problem, named road-network persistent surveillance problem (RPSP), in which the occurrence location and probability of the events are unknown. To capture such events, an unmanned ground vehicle (UGV) with certain detection ability must move along the road-network with different monitoring priorities to persistently monitor them. First, we presented an event-oriented modeling method to formulate the new problem. The monitoring effect of the road-network is quantified by uncertainty, which takes the detection ability of the sensor, the detection interval, and the monitoring weight into account. Based on the proposed model, we then designed a heuristic path planning algorithm from a decision-making perspective, which enables a UGV to persistently monitor the viewpoints of the road-network without traversing them. The simulation results and analysis demonstrate the feasibility and superiority of the proposed approach. Note to Practitioners —This article was motivated by developing an effective solution for unmanned ground vehicle (UGV) to execute road-network persistent surveillance tasks under outdoor circumstances. To the best of our knowledge, there is no other consideration dealing with this problem. To capture spatiotemporal random events, we proposed a new approach that enables UGV to persistently monitor an area with road-network performing in the weighted mode. Distinguished from the traditional path planning methods in the literature, the proposed approach considered the detection ability of the UGV. Consequently, the so-called “area-to-area” planning approach does not require traversing all the viewpoints. The approach can be used in road-network with any topology. Moreover, the difficulty in modeling road-network from the actual environment is degraded, and compared with the existing patrolling methods, the monitoring efficiency of the proposed approach is improved obviously.

Deep subspace clustering (DSC) network which uses deep auto-encoders (DAE) mapping raw data into a latent space for clustering has achieved significant performance. However, when it comes to graph-based clustering, it fails to encode the node attribute and graph structure simultaneously, which degrades the clustering performance. Meanwhile, existing graph convolutional network (GCN) based clustering methods usually do not have a clustering-oriented objection function since the process of learning representation and clustering are separated. In addition, both aforementioned methods can neither catch the multi-scale information nor use the current clustering labels effectively, which lead to the suboptimal performance. To this end, we proposed a novel end-to-end framework called Multi-Scale Graph Attention Subspace Clustering Network (MSGA). By employing a novel GCN-based feature extraction module, it can effectively capture the node representation on graph-based datasets. Moreover, a multi-scale self-expression module is designed for obtaining a more discriminative coefficient representation from each layer of the encoder and a self-supervised module is introduced for supervising the learning of node representation. Specifically, we train and optimize them in a unified framework so that different modules can benefit from each other. Extensive experiments demonstrate the superiority of our method compared with several state-of-the-art methods.

Sparse recovery (SR) based space‐time adaptive processing (STAP) methods have received much attention recently due to their dramatically reduced requirements of training samples. However, most of the existing SR‐STAP algorithms suffer from the off‐grid effect induced by the discretisation of angle‐Doppler plane. To eliminate this effect and improve the performance of clutter suppression, a novel gridless mixed‐norm minimisation (MNM) based STAP algorithm is proposed. Unlike previous grid‐based SR‐STAP methods, the clutter covariance matrix (CCM) is estimated in continuous domain by solving a semidefinite programme (SDP), which is established by utilising the properties of the CCM and the compact formulation of MNM. Furthermore, to reduce the computational burden of solving this SDP, a fast iterative algorithm via the framework of the alternating direction method of multipliers (ADMM) is also derived, where the unknown parameters are iteratively updated with closed‐form expressions. Simulation results show that our proposed algorithm achieves better performance of clutter suppression and target detection with lower computational complexity.

Space dynamic communication base stations are characterized by high mobility, flexible deployment and wide coverage. It has a wide range of needs in the fields of emergency communication, earthquake relief and island communication. To solve the problem of a limited number of users due to the limited bandwidth of space base stations, so we should improve the reliability and efficiency of data transmission between space mobile base stations. According to the characteristics of the airship platform, a blimp-borne laser communication terminal applied to space dynamic base stations is designed to meet the demand for bi-directional transmission of 5G signal laser carriers in space between airships. The experimental results show that the blimp-borne laser communication terminal achieves an overall technical index of capture probability is better than 98%, the average capture time is 5s, the tracking accuracy is better than 6–15 μrad, the communication rate is 2.5 Gbps and BER is 1E-7. In order to realize the real-time evaluation of the performance of laser communication system under the turbulent channel and guide the research of anti-turbulence fading method, a real-time test method of communication channel turbulence characteristics based on the principle of light intensity scintillation is proposed. And the real-time test of turbulence characteristics of airship inclined link and the horizontal link is completed. The research results play a positive role in promoting the development of 5G mobile technology and space optical communication technology.

This letter introduces the combination and separation of the waveforms in the simultaneous transmission of a communication signal and ranging signal. A novel iterative cancellation receiver relating to threshold detection and an iterative loop is proposed to counteract the mutual interference caused by waveform separation. The separated communication signal and ranging signal serve as the prior condition for each other to achieve the virtuous cycle, that is to say the lower communication bit error rate (BER) makes the separated ranging signal more accurate, while the smaller ranging phase offset allows it to have a weaker interference on the communication signal. The BER and ranging jitter results corroborated by Monte Carlo simulation show that the proposed iterative cancellation receiver exhibits higher communication reliability and ranging accuracy compared to the traditional receiver. Moreover, the performance gain is more prominent with the decrease of preset threshold or the increase of ranging modulation index.

Purpose Limited-angle computed tomography is a challenging but important task in certain medical and industrial applications for nondestructive testing. The limited-angle reconstruction problem is highly ill-posed and conventional reconstruction algorithms would introduce heavy artifacts. Various models and methods have been proposed to improve the quality of reconstructions by introducing different priors regarding to the projection data or ideal images. However, the assumed priors might not be practically applicable to all limited-angle reconstruction problems. Convolutional neural network (CNN) exhibits great promise in the modeling of data coupling and has recently become an important technique in medical imaging applications. Although existing CNN methods have demonstrated promising results, their robustness is still a concern. In this paper, in light of the theory of visible and invisible boundaries, we propose an alternating edge-preserving diffusion and smoothing neural network (AEDSNN) for limited-angle reconstruction that builds the visible boundaries as priors into its structure. The proposed method generalizes the alternating edge-preserving diffusion and smoothing (AEDS) method for limited-angle reconstruction developed in the literature by replacing its regularization terms by CNNs, by which the piecewise constant assumption assumed by AEDS is effectively relaxed. Methods The AEDSNN is derived by unrolling the AEDS algorithm. AEDSNN consists of several blocks, and each block corresponds to one iteration of the AEDS algorithm. In each iteration of the AEDS algorithm, three subproblems are sequentially solved. So, each block of AEDSNN possesses three main layers: data matching layer, x -direction regularization layer for visible edges diffusion, and y -direction regularization layer for artifacts suppressing. The data matching layer is implemented by conventional ordered-subset simultaneous algebraic reconstruction technique (OS-SART) reconstruction algorithm, while the two regularization layers are modeled by CNNs for more intelligent and better encoding of priors regarding to the reconstructed images. To further strength the visible edge prior, the attention mechanism and the pooling layers are incorporated into AEDSNN to facilitate the procedure of edge-preserving diffusion from visible edges. Results We have evaluated the performance of AEDSNN by comparing it with popular algorithms for limited-angle reconstruction. Experiments on the medical dataset show that the proposed AEDSNN effectively breaks through the piecewise constant assumption usually assumed by conventional reconstruction algorithms, and works much better for piecewise smooth images with nonsharp edges. Experiments on the printed circuit board (PCB) dataset show that AEDSNN can better encode and utilize the visible edge prior, and its reconstructions are consistently better compared to the competing algorithms. Conclusions A deep-learning approach for limited-angle reconstruction is proposed in this paper, which significantly outperforms existing methods. The superiority of AEDSNN consists of three aspects. First, by the virtue of CNN, AEDSNN is free of parameter-tuning. This is a great facility compared to conventional reconstruction methods; Second, AEDSNN is quite fast. Conventional reconstruction methods usually need hundreds even thousands of iterations, while AEDSNN just needs three to five iterations (i.e., blocks); Third, the learned regularizer by AEDSNN enjoys a broader application capacity, which could work well with piecewise smooth images and surpass the piecewise constant assumption frequently assumed for computed tomography images.

Employing multi-antenna rate-splitting (RS) at the transmitter and successive interference cancellation (SIC) at the receivers, has emerged as a powerful transceiver strategy for multi-antenna networks. In this paper, we design RS precoders for an overloaded multicarrier multigroup multicast downlink system, and analyse the error performance. RS splits each group message into degraded and designated parts. The degraded parts are combined and encoded into a degraded stream, while the designated parts are encoded in designated streams. All streams are precoded and superimposed in a non-orthogonal fashion before being transmitted over the same time-frequency resource. We first derive the optimized RS-based precoder, where the design philosophy is to achieve a fair user group rate for the considered scenario by solving a joint max-min fairness and sum subcarrier rate optimization problem. Comparing with other precoding schemes including the state-of-the-art multicast transmission scheme, we show that the RS precoder outperforms its counterparts in terms of the fairness rate, with Gaussian signalling, i.e., idealistic assumptions. Then we integrate the optimized RS precoder into a practical transceiver design for link-level simulations (LLS), with realistic assumptions such as finite alphabet inputs and finite code block length. The performance metric becomes the coded bit error rate (BER). In the system under study, low-density parity-check (LDPC) encoding is applied at the transmitter, and iterative soft-input soft-output detection and decoding are employed at the successive interference cancellation based receiver, which completes the LLS processing chain and helps to generate the coded error performance results which validate the effectiveness of the proposed RS precoding scheme compared with benchmark schemes, in terms of the error performance. More importantly, we unveil the corresponding relations between the achievable rate in the idealistic case and coded BER in the realistic case, e.g., with finite alphabet input, for the RS precoded multicarrier multigroup multicast scenario.

With the development of artificial intelligence, public cloud service platforms have begun to provide common pretrained object recognition models for public use. In this study, a dynamic vehicle path-planning system is developed, which uses several general pretrained cloud models to detect obstacles and calculate the navigation area. The Euclidean distance and the inequality based on the detected marker box data are used for vehicle path planning. Experimental results show that the proposed method can effectively identify the driving area and plan a safe route. The proposed method integrates the bounding box information provided by multiple cloud object detection services to detect navigable areas and plan routes. The time required for cloud-based obstacle identification is 2 s per frame, and the time required for feasible area detection and action planning is 0.001 s per frame. In the experiments, the robot that uses the proposed navigation method can plan routes successfully.

This paper focuses on finite‐time synchronization and parameters identification in the Markovian switching complex delayed network with multiple weights. Considering the control cost required for network synchronization, finite‐time control technique and pinning control strategy are adopted. Based on these methods, when finite‐time synchronization of the network is achieved, the unknown parameters of the system can also be identified in finite time. In addition, in order to solve the problem of the network performance change caused by network topology switching, an Optimal Nodes Selection Control Strategy (ONSCS) is proposed. On the one hand, finite‐time synchronization and identification of the network can be realized faster, on the other hand, it also further reduces the energy consumption and control cost of the network. Finally, two sets of comparative numerical simulations are given to prove the superiority and applicability of the proposed ONSCS.

Determining the trajectories of all vehicles on freeways is a challenging yet critical topic as trajectories reflect the characteristics of traffic flow and serve as a good basis for traffic manage...

Remote sensing technology is an effective tool for sensing the earth’s surface. With the continuous improvement of remote sensing technology, remote sensing detectors can obtain more spectral and spatial information, including clear feature contours, complex texture features and spatial layout rules. This information was detected in mineral resources. Surface substance identification, water pollution information monitoring and many other aspects have played an important role. The coding algorithm and defects, storage algorithm and interference from atmospheric cloud radiation information during the imaging process lead to varying degrees of distortion and deterioration of remote sensing images during imaging, transmission and storage. This makes it difficult to process, analyze and apply remote sensing images. Therefore, the design of a reasonable remote sensing image quality evaluation method is not only conducive to the remote sensing image quality evaluation in the real-time processing system of remote sensing image, but also conducive to the optimization of remote sensing image system and image processing algorithm. The application is worthwhile. In this paper, the deteriorating features of remote sensing images will change the statistical distribution. We propose a method for evaluating the quality of remote sensing images in depth learning. Feature learning and blurring as well as noise intensity classification for image remote sensing using convolutional neural network are carried out. The evaluation model is modified by masking effect and perceptual weighting factor, and the quality evaluation results of remote sensing images are obtained according to human vision. The research shows that this method can effectively solve the problem of removing and evaluating the noise of remote sensing image, and can effectively and accurately evaluate the quality of remote sensing image. It is also consistent with subjective assessment and human perception.

To improve the space‐time adaptive processing (STAP) performance of airborne radar in complex environment, a generalised eigenvalue reweighting covariance matrix estimation algorithm called GERCM is proposed here. First, the interference plus noise (IPN) covariance matrix of cell under test (CUT) data is estimated by the selected target‐free training samples around the CUT with the sample covariance matrix method. Then, with the component decompositions of the selected training samples and the assumption of approximately equal subspace, the IPN covariance matrix of CUT data is reformulated by the eigenvector matrix, eigenvalue matrix, and the eigenvalue reweighting vector. Subsequently, based on the modified covariance matching estimation criterion, the eigenvalue reweighting vector is estimated by solving the redesigned convex optimisation problem with the Lagrange dual method. Finally, the STAP weight vector is calculated to process the CUT data. The proposed algorithm can obtain a relatively accurate IPN covariance matrix of CUT data by sufficiently utilising the non‐homogeneous training samples and can effectively protect the moving targets in CUT data, which can be applied to airborne radar with arbitrary array structure and antenna configuration. Simulation results and performance analyses based on the multi‐channel airborne radar measurement data demonstrate the effectiveness of the proposed GERCM algorithm.

Background Fragment libraries play a key role in fragment-assembly based protein structure prediction, where protein fragments are assembled to form a complete three-dimensional structure. Rich and accurate structural information embedded in fragment libraries has not been systematically extracted and used beyond fragment assembly. Methods To better leverage the valuable structural information for protein structure prediction, we extracted seven types of structural information from fragment libraries. We broadened the usage of such structural information by transforming fragment libraries into protein-specific potentials for gradient-descent based protein folding and encoding fragment libraries as structural features for protein property prediction. Results Fragment libraires improved the accuracy of protein folding and outperformed state-of-the-art algorithms with respect to predicted properties, such as torsion angles and inter-residue distances. Conclusion Our work implies that the rich structural information extracted from fragment libraries can complement sequence-derived features to help protein structure prediction.

A generic framework is proposed for fault detection and recovery (FDR) in automated driving systems (ADSs) with inertial sensors, which is based on multitask one-dimensional convolutional neural networks (MONN). FDR plays an important role for safe and robust vehicle controls in driver-assistance and ADSs. Although model-based fault detection and recovery methods are well established in the literature, they need accurate model description and are often designed under ideal conditions. Data-driven fault diagnosis, however, might overlook apparent physical relations among sensors. In order to take advantage of both approaches, dynamic relations among measured physical quantities and temporal finite differences are introduced in a MONN as additional features. The proposed algorithm achieved more reliable performance and outperformed considered state-of-the-art methods under various testing conditions. Extensive experiments were conducted to empirically show the effectiveness of the proposed generic FDR framework.

This paper investigates a novel strategy which can address the fault-tolerant control (FTC) problem for nonlinear strict-feedback systems containing actuator saturation, unknown external disturbances, and faults related to actuators and components. In such method, the unknown dynamics including faults and disturbances are approximated by resorting to Neural-Networks (NNs) technique. Meanwhile, a back-stepping technique is employed to build a fault-tolerant controller. It should be stressed that the main advantage of this strategy is that the NN weights are updated online based on gradient descent (GD) algorithm by minimizing the cost function with respect to NNs approximation error rather than regarding weights as adaptive parameters, which are designed according to Lyapunov theory. In addition, the convergence proof of NN weights and the stability proof of the proposed FTC method are given. Finally, simulation is performed to demonstrate the effectiveness of the proposed strategy in dealing with unknown external disturbances, actuator saturation and the faults related to the components and actuators, simultaneously.

In this study, a simple technology for a self-driving system called “driver assistance system” is developed based on embedded image identification. The system consists of a camera, a Raspberry Pi board, and OpenCV. The camera is used to capture lane images, and the image noise is overcome through color space conversion, grayscale, Otsu thresholding, binarization, erosion, and dilation. Subsequently, two horizontal lines parallel to the X-axis with a fixed range and interval are used to detect left and right lane lines. The intersection points between the left and right lane lines and the two horizontal lines can be obtained, and can be used to calculate the slopes of the left and right lanes. Finally, the slope change of the left and right lanes and the offset of the lane intersection are determined to detect the deviation. When the angle of lanes changes drastically, the driver receives a deviation warning. The results of this study suggest that the proposed algorithm is 1.96 times faster than the conventional algorithm.

Due to the complexity of real environments, it is hard to detect toxic and harmful gases by sensors. To address such an issue, an artificial olfactory system is promoted, emulating the function of the human nose by means of gas sensors and an inference system. In this work, an artificial olfactory inference system based on memristive devices is developed to classify four gases (ethanol, methane, ethylene, and carbon monoxide) with 10 different concentrations. First, the spike trains converted from signals of the sensor array are inputted to a reservoir computing (RC) system based on volatile memristive devices, which extracts spatiotemporal features; then the features are processed by a classifier based on nonvolatile memristive devices; the output of the classifier indicates the classification result. Moreover, to reduce the device number and the power consumption, three strategies are applied to reduce the extracted features from the RC system. Eventually, the olfactory inference system successfully identifies the gases with a high accuracy of 95%.

In order to reduce the dimension of wind farm model and improve the simulation efficiency under the premise of ensuring the accuracy, this article proposes a dynamic equivalent method for permanent magnet synchronous generator (PMSG) based wind farm cluster utilizing the adaptive extended Kalman filters. Combining the dynamic model of PMSG, the equivalent wind turbine parameters that need to be identified are incorporated into the extended state variables, and an online parameters identification method based on extended Kalman filter (EKF) theory is put forward. To eliminate the influence of random noise on the accuracy of identification, the adaptive technology is introduced into EKF to estimate the process and measurement noise covariance in real time through the Sage–Husa estimator. Thus, a wind farm cluster equivalent model is obtained. Finally, the effectiveness and robustness of the proposed method are verified by time-domain simulation and frequency-domain simulation in IEEE 39-bus system.

Vehicle steer-by-wire system (SBW) can improve the handling stability, passive safety, active safety and drive comfort significantly, which becomes a hot topic in research. However, the safety problem of SBW is one of the most critical problem in its practical application. In order to solve the safety reliability problem of SBW, a dual-redundancy steer-by-wire system (DSBW) is proposed in this paper by applying the redundancy theory, in which no system failure is achieved when any single random electrical fault occurs, showing that DSBW is a system-level dual-redundancy system rather than a system with local redundancy. Finally, a DSBW prototype is manufactured to prove its high safety reliability. Fault injection experiments of the system are performed, in which DSBW works normally when any single electrical fault occurs.

Summary In this article, a decentralized optimal tracking control strategy is proposed for a class of nonlinear systems with tracking error constraints by utilizing adaptive dynamic programming (AD...

In this article, we focus on a wireless-powered body area network in which the simultaneous wireless information and power transfer (SWIPT) technique is adopted. We consider two scenarios based on whether sensor nodes (SNs) are equipped with battery. For the first time, energy consumption minimization with throughput heterogeneity (ECM-TH) problem is addressed for both scenarios. For the battery-free scenario, a low-complexity time allocation scheme is proposed. This scheme solves the ECM-TH problem based on a hybrid method of gradient descent and bisection search algorithms. Consequently, compared with the interior-point method, our scheme has a lower computational complexity for the same energy consumption performance of the network. For the battery-assisted scenario, the nonconvex ECM-TH problem is first transformed into a convex optimization problem by introducing auxiliary variables. Then, a joint time and power allocation scheme based on the Lagrange dual subgradient method is proposed to solve it. Compared with the battery-free scenario, energy consumption and outage probability are both decreased in the battery-assisted scenario. Moreover, we address a special case wherein the feasible set of the above-mentioned ECM-TH problems may be empty owing to poor channel conditions or high throughput requirements of SNs.

To improve the clutter suppression performance of airborne radar in heterogeneous environment, a robust refined training sample reweighting space–time adaptive processing (STAP) method called RRSRW is proposed here. First, some target‐free training samples around the cell under test (CUT) are selected and the corresponding clutter dictionary matrices are constructed using the radar system parameters. Then, the clutter patch amplitudes and array error for selected training samples are simultaneously estimated through the formulated constrained least squares problem. Subsequently, based on the covariance matching estimation criterion, the local weighting coefficients for selected training samples are estimated by the redesigned convex optimisation problem. Finally, the STAP weight vector is calculated to process the CUT data. The proposed method is robust to array error and can effectively protect the moving targets in CUT data, which is free of hyper‐parameters and has global convergence properties. Simulation results demonstrate that the proposed RRSRW method can effectively suppress the strong ground clutter and greatly improve the detection performance of moving targets in heterogeneous environment.

In recent years, deep convolution neural network has been widely used in image super-resolution and achieved great performance. As the network becomes deeper and deeper, the accuracy of reconstruction is higher and higher. However, it also brings a large increase in the number of parameters and computational complexity, which makes the practical application more and more difficult. In this paper, we propose an efficient image super-resolution method based on fusion diversion network (FDN), where diversion and fusion block serves as the basic build module. By using the fusion and diversion mechanism, the information can be fully interactive and transferred in the network, and the expression ability of the model can be effectively improved. Extensive experimental results show that even with much fewer layers, the proposed FDN achieves the competitive results in both accuracy and speed.

This paper concerns with the stability analysis for a class of discrete-time switched Takagi–Sugeno (T–S) fuzzy systems. By establishing a semitime-dependent Lyapunov function and exploring the property of mode-dependent average dwell-time switching, improved stability criteria are provided for switched T–S fuzzy systems containing both stable and unstable modes. Then, slow and fast switching strategies are designed, which are adopted for stable and unstable subsystems, respectively. Especially, we also provide the stability conditions for switched systems with all modes stable and unstable. Finally, the validities and advantages of provided techniques are illustrated by some simulation examples.

This article investigates the adaptive fuzzy fault-tolerant control problem for a class of strict-feedback stochastic nonlinear systems with quantized input signal. A hysteretic quantizer is utilized to avoid chattering caused by quantized input signals. The fuzzy-logic systems are utilized to approximate the unknown nonlinear functions and also to construct the fuzzy state observer, which is used to estimate the immeasurable state vector. The actuator faults considered in this article are loss of effectiveness and lock-in-place faults. By using the Lyapunov stability theory, the closed-loop stochastic nonlinear system is guaranteed to be stable in probability, and all the signals of the closed-loop system are bounded in probability in the presence of quantized input and actuator faults. Finally, a simulation example is given to verify the validity of the proposed control strategy.

The commutation failure of Line Commutated Converter-High Voltage Direct Current (LCC-HVDC) cannot be avoided. This paper presents a novel transient stability assessment approach for AC/DC hybrid system considering continuous commutation failure. First, the conception and mathematical background of Maximum Lyapunov Exponent (MLE) of switching system is introduced, and the switching compensation matrix is derived. Next, the switching system model of AC/DC hybrid system considering continuous commutation failure caused by AC faults is established. On the basis of switching compensation, the MLE of switching system is calculated accurately, and the MLE based criteria are proposed to assess the transient stability of the switching system. Finally, the modified 39-bus system with LCC-HVDC added and the real power system are used as test systems to investigate the validity and effectiveness of the proposed transient stability assessment approach.