Search

In the current scenario, the research perspective on esophageal cancer becomes severe, high-prognosis malignancy; poor prognosis is primarily attributed to the fact that most tumors remain asymptomatic and unrelated before it grows through the esophagus. Significant decreases in mortality from esophageal cancer may require effective approaches to detect and nurse more patients at early, curable stages. A new Improved Empirical Wavelet Transform (IEWT) dependent on feature extraction approach and a consistent homology for the diagnosis of early esophageal endoscopic cancer have been proposed in this article. The approach is to convert an input endoscope image into CIE colored spaces L * x * y, and the x* and y* components to create a fusion image for analysis. Further, the two kinds of wavelets are obtained by adding the two forms to the fusion signal. Another is the lower-frequency component provided by the improved empirical wavelet transformation of the wave, and the other is the high- components generated from the Deep Learning-based Complex Empirical Wavelet Transformation (DL-CEWT). The fractal sizes are determined using the box interpolation method for each small block, and the abnormal regions are defined for the basis of their fractal sizes. Binary pictures are obtained by the complex threshold in each frequency variable and then divided into small blocks in every binary image. Using the homology of every block to obtain the new features in the entry image. The extraction strategies for this application are comprehensive and preliminary findings indicate that the method is effective for the early detection of esophageal cancer in an image.

The pursuit-evasion problem is common in both nature and the artificial intelligence area. We consider the multi-player pursuit-evasion problem of multiple pursuers with communication constraints on an evader. Besides, the velocity of all pursuers is varying, and the initial positions do not need to be on the circle. The conditions for successful capture, including distance conditions and quantity conditions, are defined in this paper. Furthermore, the capture strategy and escape strategy are designed from the biological-inspired perspective. We realize collision avoidance, gathering, and direction alignment between pursuers by introducing repulsion, attraction, and alignment functions in the pursuer strategy. Then, we observe the sharp phase-transition between the capture zone and escape zone and fit the relevant phase-transition lines by varying the repulsion-coefficient and attraction-coefficient. Based on the coherent analysis for pursuit-evasion behaviour, the relationship between the parameters and the outcome can be obtained.

In this paper, impact time constrained guidance (ITCG) laws are proposed using a range-based line-of-sight (LOS) shaping strategy. The relative motion of missile and target is described in a polar coordinate, where the LOS angle can be shaped as a polynomial function of range-to-go. A third-order polynomial function is selected according to the number of constraints. Coefficients of the polynomial function are determined by the boundary conditions and solved through a simple integral equation, which facilitates the onboard implementation. Guidance command is designed in a state feedback form to track the shaped trajectory. The proposed guidance law shows advantageous features over several similar polynomial shaping based guidance laws. Multiple simulation studies demonstrate the effectiveness of the proposed guidance law.

In this paper, the fault diagnosis and health monitoring techniques based on machine learning are investigated before the research. Then, the dynamic model of the quadrotor is analyzed and the most important relationship between the IMU and motor outputs are given. Afterwards, the high-coupling and nonlinear link between units are mapped into an implicit network APN based on LSTM neural network. Predictions and train are made based on the data set collected from the practical and HITL flight log. Finally, the feasibility of the health management is verified during the fault simulation and the a possible solution is given against the common error.

In this paper, the fault diagnosis and health management of fixed-wing UAVs are investigated based on the deep learning technique. The proposed method includes 5 models: flight data generation model, sample training prediction model based on the Long Short-Term Memory (LSTM) network, prediction model based on the grey model, combined prediction model and health calculation and management model. The realtime output of the health prediction value of the fixed-wing UAVs can be obtained, which makes it possible to take remedial action before the fault occurs. And numerical simulations demonstrate the feasibility of the proposed method. Keywords: LSTM, grey model, fault diagnosis, health prediction, fixed-wing UAVs

The cooperative control problem of hydraulic synchronous lifting system consisting of multiple cylinders is studied in this paper. The hydraulic cylinders are assumed to be equipped with wireless data transfer units and can exchange information with their neighboring cylinders. Based on the leader-follower structure, a distributed control protocol is designed for each follower to track the states of the leader utilizing information of local neighbors. Furthermore, adaptive control method is adopted to estimate the upper bound of the leaders unknown control input and external disturbances. Sufficient conditions are derived to guarantee the tracking errors converge to zero by Lyapunov stability theory. Finally, numerical simulations are carried out to illustrate the effectiveness of the theoretical results.

In this paper, we study the adaptive optimal consensus control of leaderless multi-agent systems (MASs) with heterogeneous dynamics. First, the consensus control problem is converted into a graphical minimax game problem and the corresponding algebraic Riccati equation (ARE) for each agent is obtained. Then, an on-policy reinforcement learning algorithm is proposed to online learn the optimal control policy without requiring the system dynamics. A certain rank condition is established to guarantee the convergence of the proposed online learning algorithm to the unique solution of the ARE. Finally, the effectiveness of the proposed algorithm is demonstrated through a numerical simulation.

This paper focuses on event-triggered consensus control for multi-agent systems subject to undesirable sensor signals. First, a descriptor observer is developed for each agent to estimate the sensor fault and the estimation error can be reduced to be small enough by tuning an nonsingular suppression matrix. Then, leader-follower event-triggered consensus protocol is designed for each agent under directed topology. By virtue of the Jordan form of the Laplacian matrix, the stability conditions are derived using Lyapunov analysis. Zeno behavior can be excluded for all agents. Finally, numerical simulations are conducted to demonstrate the effectiveness of the proposed design.

A cooperative guidance law for missile group with a leader is proposed in this paper. Cooperative guidance is divided into state cooperation stage and Proportional Navigation Guidance (PNG) stage with suppressed guidance command jump at switch point. State cooperation is achieved through cooperative state tracking of a leader missile, where the dynamic of guidance is linerized by adding two auxiliary state variables and a linear cooperative tracking algorithm is adopted. PNG is adopted to accomplish the cooperative impact, because state cooperation stage can not guide missiles to realize the final impact. In the linezrized guidance model, guidance command will be singular when leading angle tends to zero, which is necessary in the terminal stage of guidance.

The fully distributed robust formation control of unmanned helicopters (UHs) with external disturbances and model uncertainty capability is investigated. In the position loop and the attitude loop, continuous fast robust controllers are proposed, and an integral filter is introduced between two loop. The stability of the whole closed-loop system is guaranteed through Lyapunov theory and input-to-state stability (ISS). Compared to the previous related works, our main contribution is that the proposed adaptive control strategy is fully distributed and scalable, which is independent any global information of the network graph and is independent of the UHs’s scale and we proved the stability of the closed-loop. Finally, the effectiveness and superiority of the designed strategy are demonstrated by numerical simulations.

With a view to restoring image details of heavily hazy images, we propose an adaptive contrast enhancement algorithm specifically for haze removal. It is composed of 3 parts. The first part is to segment the input image into flat background of air space and foreground which is the rest of the image. A specific gradient matrix is defined to generate a gradient feature value to identify the pixels of very weak signals with the presence of noise of similar amplitude. In the second part, a CLAHE-based method is developed and applied to the foreground to provide a stronger enhancement to weaker signal variations while the background is protected from noise enhancement. A specifically designed filter is then applied to remove noise caused by the discontinuity between the foreground and background areas, while preserving the enhanced image details. The proposed algorithm has been tested and its effectiveness has been proven by the test results.

This paper investigates the remote state estimation issue for the jump Markov nonlinear systems (JMNLSs) with the stochastic event-triggered transmission strategy. For the purpose of saving the scarce network resources, the stochastic event-triggered communication is employed to cut down the number of measurement transmission. The interacting multiple model (IMM) scheme is incorporated due to its strength in alleviating computational burden encountered in the multiple model state estimation problem. In addition, the estimated measurement is utilized to update the mode probability in IMM-based filter when the current measurement is not available to the remote estimators. The proposed algorithm is applied in a two-dimensional maneuvering target tracking problem and the simulation results are presented, which validates the usefulness of the developed scheme.

According to the current situation of preschool teachers’ mental health and education background in Chongqing, this paper investigates the correlation between the influencing factors of different education background on preschool teachers’ mental health level, and analyzes whether the influence of different education background on the mental health level is different. Using the SCL90 mental health test scale and computer software SPSS, a stratified random sampling method was carried out in Chongqing. Taking 500 kindergarten teachers in 20 kindergartens as survey samples, the results of 98 questions in two dimensions involved in the questionnaire were summarized and analyzed. Finally, there are 410 valid questionnaires, 33.66% of them have mental health problems. The main mental health problems of preschool teachers are anxiety, interpersonal sensitivity, obsessive-compulsive symptoms and somatization. Chi square analysis of preschool teachers’ education background and mental health level showed that x2 value was 7.423, P value was 0.006, less than 0.5. There was significant difference in the mental health level of preschool teachers with different education background. It can be seen from this that the causes of the mental health problems faced by preschool teachers with different education background will be different, and the influence of the same cause on the mental health of preschool teachers with different education background will be different. According to the different education background, corresponding strategies should be taken for the mental health level of preschool teachers with different education background.

This paper investigates finite-time attitude consensus of multi-spacecraft systems with input delay using fullorder sliding mode control. First, the kinematic and dynamic models of spacecraft attitude with disturbance are provided. Then, full-order sliding mode protocol is used to solve the consensus problem. The algorithm is consisted of two layers of sliding mode surfaces, the outer terminal sliding mode manifold and inner fast nonsingular terminal sliding mode manifold. On basis of the control algorithm, this paper considers the input delay of the system, thus a distributed observer is proposed to reduce communication burden and guarantee finite-time convergence, which is proved by Lyapunov stability analysis. Finally, a simulation example is provided to demonstrate the validity the proposed control algorithm.

This paper investigates a distributed homing guidance law for salvo attack in presence of large actuator delay. The nonlinear guidance model is initially converted to a second-order integrator system with the states of $r/V$ and $cos \sigma$, which turns the time-to-go coordination problem to a consensus flavor. By virtue of this framework, the cooperative guidance problem under actuator delay can be addressed through an observer-based consensus algorithm with input delay. In order to further avoid the singularity issue, terminal phase using PNG law is also adopted. Numerical simulations are conducted to showcase the effectiveness of the proposed guidance method.

In response to the incidents of drones interfering with normal flights in recent years, we propose a strategy for the cooperative pursuit of single evader using multiple pursuers. First, in the case where the evader’s position is known exactly, the tracking strategy based on the area-minimization policy is provided for a group of pursuers tracking a single evader. Then, the tracking strategy considering the evader’s position uncertainties is proposed. After that, simulation results are provided to show the effectiveness of the proposed strategies. Finally, we point out the work that needs to be done in the future.

With the arrival of the era of big data, the cooperation between tourism and new media is becoming more and more extensive. Big data contains great value and is a valuable asset for enterprises. But it also brings great challenges to personal privacy protection. Firstly, this paper introduces the related concepts of personal privacy protection in the era of big data, then analyzes the subjects of tourism data collection and analysis, namely OTA, third-party software companies, tourism supervision departments and other individuals or organizations, and finally discusses the countermeasures for protecting personal privacy of tourism consumption in the data age, mainly from four aspects: industry self-discipline, relevant laws and regulations, industry supervision and protection consciousness.

In this paper, the weighted average consensus-based unscented Kalman filtering combined with event-triggered communication mechanism is developed. Each sensor node chooses to transmit its latest measurement update to the corresponding remote estimator based on its own event-triggering condition. A sufficient condition is derived to guarantee that the estimation error is bounded in mean square. Finally, an illustrative example is presented to demonstrate the feasibility and effectiveness of the proposed algorithm.

In this paper, a low-cost vision-based autonomous landing architecture for an unmanned aerial vehicle (UAV) on a moving platform is presented. First, a novel landing pad was designed for a monocular camera to robustly detect the pad in both high and low altitudes. In order to solve mirror effect and occasional misidentification, a 3D points cluster algorithm for relative position estimation is presented. Second, the dynamics of the quadrotor is simplified for this lading task and a PD controller is designed based on the estimated relative position. Finally, the low-cost system architecture of the quadrotor and the experiment results are both presented to show the effectiveness of the proposed method.

This paper deals with the consensus disturbance rejection problem for systems subject to delay and unknown parameter. Three main problems are considered. The first problem is how to deal with input delay. Due to the communication condition, the delays could be large or small, so it is difficult to use the robust technique to deal with. The second problem is the disturbance rejection. The disturbance under consideration are unknown constant disturbances or sinusoidal functions with unknown amplitudes and phases. Third, we consider the unknown graph algebraic connectivity case. This assumption is useful since fully distributed controller can only be designed without this global information. Predictor feedback method and predictor observer design method are both used to deal with the delay. Disturbance observer-based control (DOBC) strategy is used to estimate the disturbance and adaptive technique is applied to estimate the graph algebraic connectivity. Finally, consensus disturbance rejection controllers are designed for all the agents and the consensus can be achieved with certain condition derived from the Lyapunov analysis.

Segmentation of a moving foreground from video sequences, in the presence of a rapidly changing background, is a difficult problem. In this paper, a novel technique for an effective segmentation of the moving foreground from video sequences with a dynamic background is developed. The segmentation problem is treated as a problem of classifying the foreground and background pixels of a video frame using the color components of the pixels as multiple features of the images. The gray levels of the pixels and the hue and saturation level components in the HSV representation of the pixels of a frame are used to form a scalar-valued feature image. This feature image incorporating multiple features of the pixels is then used to devise a simple classification scheme in the framework of a support vector machine classifier. Unlike some other data classification approaches for foreground segmentation in which a priori knowledge of the shape and size of the moving foreground is essential, in the proposed method, training samples are obtained in an automatic manner. In order to assess the effectiveness of the proposed method, the new scheme is applied to a number of video sequences with a dynamic background and the results are compared with those obtained by using other existing methods. The subjective and objective results show the superiority of the proposed scheme in providing a segmented foreground binary mask that fits more closely with the corresponding ground truth mask than those obtained by the other methods do.

In this paper, a composite weighted average consensus filtering algorithm (CWACF) is proposed by applying multiple heterogeneous nonlinear filters. In light of the sensors’ different sensing accuracy and computational capability, extended Kalman filter (EKF) and sparse-grid quadrature filter (SGQF) are compositely adopted on different sensors as local filters. Then, estimation from neighbours are fused based on the weighted average consensus framework to attain better estimation performance. Moreover, it has been proved that the estimation error is exponentially bounded in mean square. The performance of the proposed algorithm and distributed extended Kalman filtering (DEKF) are compared by a target localization case through a sensor network.

In this paper, distributed coverage optimization and control problem with collision avoidance and parameter estimation are studied. First, we consider the case that the density function $\phi(q)$ is known by all the robots in the network. By using the interaction term of Voronoi neighbour, coverage optimization and control protocols are designed in a distributed way such that the best position of each robot can be determined and all the robots can move to the best positions without collision. Then, we consider the case that the density function $\phi(q)$ is not known by the robots. By using the adaptive technique, the density function $\phi(q)$ can be estimated in a fast and distributed way. Finally, the proposed coverage control scheme are applied to remote sensing for precision farming and the effectiveness of the strategy is validated through some simulation results.

To deal with leader-follower formation of multi-agent systems with a leader whose dynamics are unknown, a consensus based method is presented to achieve formation keeping for a directed graph. We divide the followers into two parts according to path distance. For the followers connected to the leader, a state-feedback regulation is applied. Then the directed graph is reconstructed and a consensus based method is designed. The controller is implemented in a fully distributed form because each follower only uses the relative and local information. Finally, numerical simulations applying this method to time-varying formation and trajectory tracking are performed. The results validate the effectiveness of the proposed method.

It is extremely essential for carrying out efficient electricity trading to research the integrated management of electricity purchasing and selling resources on the premise of power and electricity balance and safe and stable operation of the basic premise of the grid. This paper studies the intrinsic relationship between the purchase and sale of resources, and establishes the purchase' optimization model considering the trading space of interruptible load under the integration of electricity purchasing and selling resources, achieving the overall plan of purchase and sale resources, improving the level of optimal resource allocation, effectively reducing purchasing cost at peak blocks. At the same time, integrating sale resources into the original purchase plan meets the new direction of power transaction development under the new electricity market conditions, embodying the intelligent and interactive of modern grid. The case study shows that the model can effectively use sale resources to ease the contradiction between supply and demand and optimize the existing electricity purchasing plan.

This study designs an automatic monitoring system for non-contact measurement of the surround rock deformation in underground tunnels in an unattended operation mode. This system can automatically and periodically monitor the deformation of the surrounding rocks in underground tunnels with low power consumption, and write the monitored deformation data to the TF card in the format of.txt. Accordingly, the surveyors only need to get the monitoring data from the TF card regularly and analyze the surrounding rocks' deformation trend.

This paper investigates the collision avoidance problem in formation control. First, a collision avoidance algorithm is proposed by using the gradient-based method. Then, a collision-free consensus based formation protocol is developed for a group of second-order systems with the aid of graph theory. In particular, the formation protocol is designed only based on the relative information obtained via the network connection, without the global information of the agents. Finally, simulation results with different topologies verify the effectiveness of the proposed algorithms.

In this paper, we present a novel distributed coverage control scheme with collision avoidance based on consensus approach and potential field. The computational geometry of spatial structures is exploited using centroidal Voronoi tessellation and the locational optimization problem is introduced in a distributed fashion. By using the interaction term of Voronoi neighbour, a distributed protocol is proposed based on consensus strategy to solve the extended locational optimization problem. Distributed potential field is then applied for collision avoidance of the robotic group in an unknown environment and the performance of the proposed control strategy is guaranteed by using Lyapunov stability analysis. Finally, theoretical results are validated through simulations on a group of mobile robots.

This paper deals with the fixed-time consensus for multi-agent systems with input delay. First, finite-time stability for single system with input delay is given with the aid of Artstein model reduction method. Then, two finite-time nonlinear consensus protocols are constructed for multi-agent systems with input delay using the Lyapunov functionals. In particular, the settling-time of the second consensus protocols is independent on the system initial states such that the convergence time can be designed or estimated. Finally, a simulation study is given to validate the proposed control design.

The microstructure and interfacial IMC layer of Cu/SACPG/Cu and Cu/SAC0307/Cu solder joints were comparatively investigated after thermal aging at 150°C for 0h, 24h, 168h and 500h, respectively. Results show that the morphology of IMC at the interface of Cu/SAC0307/Cu solder joint was consistent with that at the interface of Cu/SACPG/Cu joint, which indicates that the addition of P and Ge had little effect on the IMC formation. The tiny particles attached to the Cu 6 Sn 5 were Ag 3 Sn phase and Ge from the study of three dimensional morphology of IMC. The addition of trace P and Ge in the alloy reduced the thickness of IMC layer and decreased the growth rate of IMC layer with aging time increasing, and had lower impact on the growth rate of IMC layer of Cu 3 Sn.

This paper presents an ℒ 1 adaptive controller to achieve the trajectory tracking for a quadrotor helicopter. The designed controller is based on nonlinear feed-forward compensations and uses a typical nonlinear quadrotor model considering uncertain inertial parameters and external disturbances. The ℒ 1 adaptive control design is slightly modified to comply with the position error dynamic and the attitude dynamic. The proposed ℒ 1 adaptive controller yields uniformly verifiable bounds on the transient and steady state tracking error for any designated bounded reference trajectory. In the presence of a fast adaptation, the adaptive controller with low-pass filters compensates for uncertainties and bounded disturbances in a particular frequency range. Finally, simulation results are included to validate the effectiveness of this control design.

This paper addresses the disturbance rejection problem for a class of linear systems in the presence of input delay via DOBC approach. Truncated predictor feedback method is applied to deal with the input delay based on the estimate of state and external disturbance, and further endeavours are made to ensure the extra integral terms of the system state and external disturbance due to the input delay are properly considered using Krasovskii functionals. With the tool of Lyapunov functions, the stability of the closed-loop system is proved under sufficient conditions. A simulation study is given to validate the proposed control design.

In this paper, perceived value is used as an intermediate variable to test the impact of Electronic Word-of-Mouth (eWOM) on the tourists' decision-making of online travel booking. It builds a conceptual model and carries out empirical research, on the basis of sample investigation, analyzes data by applying the structural equation. The research conclusion shows that the quality and credibility of eWOM has a significant promoting effect on the perceived value of tourists' eWOM, the relevance, comprehensiveness and timeliness of tourists' eWOM have significantly positive correlation with the perceived value of tourists' eWOM, the attraction of tourists' eWOM has a significant impact on the perceived value of tourists' eWOM, the tourists' perceived value of eWOM is positively correlated with online travel booking. On the basis of the above, some useful suggestions are put forward for the online travel agencies.

This paper addresses the disturbance rejection problem for active magnetic bearing (AMB) systems via DOBC approach. A linearized model of AMB system with unmatched disturbance is proposed in state space form. Based on the model we present, a method which estimates and actively rejects disturbance with disturbance observer and feedback controller is proposed. Simulation results show the performance of the system in presence of unknown disturbance.

In this paper, we propose an adaptive, DCT based, blind image watermarking algorithm. The adaptability is developed, while exploring the properties of the human visual system (HVS), to embed robust watermarks in DCT matrices while making them the least visible in the space domain. In the algorithm, binary watermarks are embedded in image blocks having gray level variations sufficient to mask a certain level of signal alterations. The orientations of the variations in such a block are detected by examining the locations of the most significant DCT coefficients in the matrix and a particular DCT coefficient is then chosen for watermark embedding with a view to making the gray level changes resulting from the embedding have a similar orientation with the original image signal to mask the watermark better. Moreover, the embedding strength is made to depend on the DC component, as it indicates the brightness of the image block, to further reduce the visibility of the watermark. The algorithm is computationally simple because it extracts the needed features directly from the DCT coefficients. Simulation results show that the algorithm is highly robust against JPEG compression even at low quality factors while maintaining high visual quality. Furthermore, the computational simplicity of the algorithm makes it very useful in real-time applications.