Search

Medical visual question answering (VQA) aims to correctly answer a clinical question related to a given medical image. Nevertheless, owing to the expensive manual annotations of medical data, the lack of labeled data limits the development of medical VQA. In this paper, we propose a simple yet effective data augmentation method, VQAMix, to mitigate the data limitation problem. Specifically, VQAMix generates more labeled training samples by linearly combining a pair of VQA samples, which can be easily embedded into any visual-language model to boost performance. However, mixing two VQA samples would construct new connections between images and questions from different samples, which will cause the answers for those new fabricated image-question pairs to be missing or meaningless. To solve the missing answer problem, we first develop the Learning with Missing Labels (LML) strategy, which roughly excludes the missing answers. To alleviate the meaningless answer issue, we design the Learning with Conditional-mixed Labels (LCL) strategy, which further utilizes language-type prior to forcing the mixed pairs to have reasonable answers that belong to the same category. Experimental results on the VQA-RAD and PathVQA benchmarks show that our proposed method significantly improves the performance of the baseline by about 7% and 5% on the averaging result of two backbones, respectively. More importantly, VQAMix could improve confidence calibration and model interpretability, which is significant for medical VQA models in practical applications. All code and models are available at https://github.com/haifangong/VQAMix.

Knowledge Graph (KG) is identified as a major area in artificial intelligence, which is used for many real-world applications. The task of knowledge graph reasoning has been widely used and proven to be effective, which aims to find these reasonable paths for various relations to solve the issue of incompleteness in KGs. However, many previous works on KG reasoning, such as path-based or reinforcement learning-based methods, are too reliant on the pre-training, where the paths from the head entity and the target entity must be given to pre-train the model, which would easily lead the model to overfit on the given paths seen in the pre-training. To address this issue, we propose a novel reasoning model named MemoryPath with a deep reinforcement learning framework, which incorporates Long Short Term Memory (LSTM) and graph attention mechanism to form the memory component. The well-designed memory component can get rid of the pre-training so that the model doesn’t depend on the given target entity for training. A tailored mechanism of reinforcement learning is presented in this proposed deep reinforcement framework to optimize the training procedure, where two metrics, Mean Selection Rate (MSR) and Mean Alternative Rate (MAR), are defined to quantitatively measure the complexities of the query relations. Meanwhile, three different training mechanisms, Action Dropout, Reward Shaping and Force Forward, are proposed to optimize the training process of the proposed MemoryPath. The proposed MemoryPath is validated on two datasets from FB15K-237 and NELL-995 on different tasks including fact prediction, link prediction and success rate in finding paths. The experimental results demonstrate that the tailored mechanism of reinforcement learning make the MemoryPath achieves state-of-the-art performance comparing with the other models. Also, the qualitative analysis indicates that the MemoryPath can store the learning process and automatically find the promising paths for a reasoning task during the training, and shows the effectiveness of the memory component.

Different-level dynamic linear system (DLDLS) is an interesting and challenging topic due to its complicated structure and time-variant characteristic. To solve this difficult problem, the equivalency of solutions at different levels is analyzed and obtained via zeroing neural network (ZNN) method. Based on the equivalency, a continuous ZNN model is proposed to solve the continuous DLDLS. For easier hardware realization, a new Zhang et al. discretization formula with high precision is proposed for the continuous ZNN model discretization, and the corresponding new discrete ZNN (NDZNN) model is proposed to solve discrete DLDLS. Note that the NDZNN model satisfies the requirement of real-time computation because it has the online ability to predict the solution for the future instant. Furthermore, the problems of robot manipulator control with additional restrictions (e.g., joint damage) are formulated as specific discrete DLDLS, and the proposed NDZNN model is employed to solve such problems. Simulation results substantiate the effectiveness of NDZNN model.

In this paper, we consider a special kind of time-dependent nonlinear system that includes different-level subsystems (i.e., a subsystem with respect to time-dependent solution and a subsystem with respect to its time derivative). To solve this kind of time-dependent nonlinear system, an equivalency between different-level subsystems is proposed and termed as zeroing equivalency based on the zeroing neural network method. This kind of time-dependent nonlinear system can be solved in a discrete-time manner with future-instant solution predicted at current instant based on the zeroing equivalency and a discretization formula. Prediction ability can perfectly meet the requirements of real-time computation, which is crucial in engineering fields. In addition, different-level algorithms are further employed to solve the problem of robotic system control considering additional restrictions. The position tracking control and end-effector orientation control are simultaneously achieved with even fault tolerance by utilizing the proposed algorithms.

Previous works provide a few effective discretization formulas for zeroing neural network (ZNN), of which the precision is a square pattern. However, those formulas are separately developed via many relatively blind attempts. In this paper, general square-pattern discretization (SPD) formulas are proposed for ZNN via the idea of the second-order derivative elimination. All existing SPD formulas in previous works are included in the framework of the general SPD formulas. The connections and differences of various general formulas are also discussed. Furthermore, the general SPD formulas are used to solve future optimization under linear equality constraints, and the corresponding general discrete ZNN models are proposed. General discrete ZNN models have at least one parameter to adjust, thereby determining their zero stability. Thus, the parameter domains are obtained by restricting zero stability. Finally, numerous comparative numerical experiments, including the motion control of a PUMA560 robot manipulator, are provided to substantiate theoretical results and their superiority to conventional Euler formula.

Thyroid nodule segmentation in ultrasound images is a valuable and challenging task, and it is of great significance for the diagnosis of thyroid cancer. Due to the lack of the prior knowledge of thyroid region perception, the inherent low contrast of ultrasound images and the complex appearance changes between different frames of ultrasound video, existing automatic segmentation algorithms for thyroid nodules that directly apply semantic segmentation techniques can easily mistake non-thyroid areas as nodules. In this work, we propose a thyroid region prior guided feature enhancement network (TRFE-Net) for thyroid nodule segmentation. In order to facilitate the development of thyroid nodule segmentation, we have contributed TN3k: an open-access dataset of thyroid nodule images with high-quality nodule masks labeling. Our proposed method is evaluated on TN3k and shows outstanding performance compared with existing state-of the-art algorithms. Source code and data are available1.

Differing from the common linear matrix equation, the future different-level linear matrix system is considered, which is much more interesting and challenging. Because of its complicated structure and future-computation characteristic, traditional methods for static and same-level systems may not be effective on this occasion. For solving this difficult future different-level linear matrix system, the continuous different-level linear matrix system is first considered. On the basis of the zeroing neural network (ZNN), the physical mathematical equivalency is thus proposed, which is called ZNN equivalency (ZE), and it is compared with the traditional concept of mathematical equivalence. Then, on the basis of ZE, the continuous-time synthesis (CTS) model is further developed. To satisfy the future-computation requirement of the future different-level linear matrix system, the 7-instant discrete-time synthesis (DTS) model is further attained by utilizing the high-precision 7-instant Zhang et al. discretization (ZeaD) formula. For a comparison, three different DTS models using three conventional ZeaD formulas are also presented. Meanwhile, the efficacy of the 7-instant DTS model is testified by the theoretical analyses. Finally, experimental results verify the brilliant performance of the 7-instant DTS model in solving the future different-level linear matrix system.

Parental care in early childhood is viewed as one of the most important factors that help foster children&rsquo, s abilities. Using two nationally representative datasets collected in China, this paper examines the effects of parental absence on the short-term in-school outcomes and long-term educational achievement of left-behind children. The results show that parental absence is negatively associated with the development of left-behind children. Left-behind children have a lower cognitive test score and academic test score, and they are also less likely to attend a college. In particular, a mother&rsquo, s absence seems to have persistent negative effects on children&rsquo, s development. Mechanism analyses show that parental absence may result in a less healthy mental status of children and reduce children&rsquo, s efforts in class. However, we do not find significant evidence that the exposure to left-behind children in class lowers the in-school outcomes of children.

China's fallow compensation policy is known to be relatively simple and unsophisticated, and in much need of improvement. In seeking such improvement, this paper designed some alternative compensation schemes that include recultivation insurance, priority right of participation in the fallowing work or free agricultural inputs, but lower income subsidy, and reported on a choice experiment of alternatives with 421 peasant-farming households in Chaling County, Hunan Province – a fallow area of heavy-metal-contaminated farmland. A mixed logit model was used to compare the choices made between pilot and non-pilot villages, and the influencing factors involved. The results showed that most farmers preferred the alternative compensation schemes to the current policy, and income subsidy was not the only factor affecting their choices, which indicated recultivation insurance and a longer period of free agricultural inputs were also important. However, the preferences differed between pilot and non-pilot village farmers, in which the pilot village farmers were more willing to accept less income subsidy in favor of increased recultivation insurance and an extended period of free agricultural inputs. By contrast, non-pilot village farmers preferred to adopt an alternative compensation scheme with a priority right of participation in the fallowing work and high level of income subsidy. The possible reason for the differences was that the publicity and training activities provided by the government had changed the preferences of pilot village farmers. Generally, the effects of various forms of economic compensation and single cash payment were different about fallow compensation policy, and the preferences of farmers from different backgrounds might also vary from person to person. Different regions needed to design the fallow compensation policy according to practical problems in the use of farmland and farmers' preferences.

Discrete time-varying linear system (LS) is a fundamental topic in science and engineering. However, conventional methods essentially designed for time-invariant LS generally assume that LS is time-invariant during a small time interval (i.e., sampling gap) for solving time-varying LS. This assumption quite limits their precision because of the existing of lagging errors. Discarding this assumption, Zhang neural dynamics (ZND) method improves the precision for LS solving, which is a great alternative for the solving of discrete time-varying problems. Note that precision solutions to discrete time-varying problems depend on discretization formulas. In this paper, we propose a new ZND model to solve the discrete time-varying LS. The discrete time-varying division is a special case of discrete time-varying LS with the solution being a scalar while it is usually studied alone. Considering the above inner connection, we further propose a special model for solving the discrete time-varying division. Moreover, as an application of discrete time-varying LS, the discrete time-varying quadratic programming (QP) subject to LS is also studied. The convergence and precision of proposed models are guaranteed by theoretical analyses and substantiated by numerous numerical experiments.

This paper mainly discusses the asymptotic properties of quantile regression processes. In view of the exponential tightness and convexity argument, we prove the quantile regression estimat...

Goal ordering is very important for the incremental planning, and special attention has been paid to determine the ordering constraints between the atomic goals to achieve the orderings for all possible plans. However, not all goal orderings work well on most benchmarks. This paper introduces a new-class goal ordering, called the admissible goal ordering, which is less restrictive and matches with the characteristics of most benchmarks better than the existing goal orderings. Since the proposed ordering relation is hard to decide, an approximate approach for computing the admissible ordering relation that can be determined in polynomial time is presented. Furthermore, an algorithm for extraction of the total-ordered subsets of goals based on the admissible relation is developed. The total-ordered subsets lead to the partition of an original task into smaller subtasks that can be incrementally planned. The experimental results obtained by using almost all propositional STRIPS benchmarks from the international planning competitions show that the proposed goal ordering can significantly improve the planning performance compared with the state-of-the-art satisficing planning system. In comparison with the reasonable ordering and no-goal ordering, the performance improvements in the proposed ordering are substantial and almost dramatic on larger tasks.

Improvement of the real-time performance of tracking control is increasingly desirable. It is a routine for most conventional algorithms that the control input at current time instant is to track the current desired output. However, lagging errors resulting from computational time and the fluctuation of the desired output exist for the tracking control. Different from conventional algorithms, a look-ahead scheme of zeroing dynamics (ZD) is established in this paper to achieve the real-time tracking control of both serial and parallel manipulators. With the exploitation of data at current time and that in history, the control inputs generated by the proposed ZD algorithms never lead to lagging errors with the source from the inevitable computational time. To tackle prediction errors for ZD algorithms, a new high-precision discretization formula, as an essential part of ZD algorithms, is presented to confine the prediction error in an ignorable range in comparison with lagging errors.

Finite difference schemes have been widely studied because of their fundamental role in numerical analysis. However, most finite difference formulas in the literature are not suitable for discrete time-varying problems because of intrinsic limitations and their relatively low precision. In this paper, a high-precision 1-step-ahead finite difference formula is developed. This 5-instant finite difference (5-IFD) formula is used to approximate and discretize first-order derivatives, and it helps us to compute discrete time-varying generalized matrix inverses. Furthermore, as special cases of generalized matrix inverses, time-varying matrix inversion, and scalar reciprocals are generally deemed as independent problems and studied separately, which are solved unitedly in this paper. The precision of the 5-IFD formula and the convergence behavior of the corresponding discrete-time models are derived theoretically and shown in numerical experiments. Conventional useful formulas, such as the Euler forward finite difference (EFFD) formula and the 4-instant finite difference (4-IFD) formula are also used for comparisons and to show the superiority of the 5-IFD formula.

Nonlinear optimization is widely important for science and engineering. Most research in optimization has dealt with static nonlinear optimization while little has been done on time-varying nonlinear optimization problems. These are generally more complicated and demanding. We study time-varying nonlinear optimizations with time-varying linear equality constraints and adapt Z-type neural-dynamics (ZTND) for solving such problems. Using a Lagrange multipliers approach we construct a continuous ZTND model for such time-varying optimizations. A new four-instant finite difference (FIFD) formula is proposed that helps us discretize the continuous ZTND model with high accuracy. We propose the FDZTND-K and FDZTND-U discrete models and compare their quality and the advantage of the FIFD formula with two standard Euler-discretization ZTND models, called EDZTND-K and EDZTND-U that achieve lower accuracy. Theoretical convergence of our continuous and discrete models is proved and our methods are tested in numerical experiments. For a real world, we apply the FDZTND-U model to robot motion planning and show its feasibility in practice.

This paper mainly discusses the asymptotic behaviours on the lasso-type estimators for diffusion-type processes with a small noise. By constructing the objective function on the estimation, in view of convexity argument, it is proved that the estimator for different values of γ satisfies the iterated logarithm law. The result also presents the exponential convergence principle for the estimator converging to the true value.

Solving for inverse-like dynamic matrices of variables and derivatives is exciting and challenging. Although it may be encountered in the fields of industrial control or scientific research, it has not been widely studied because of its complexity and difficulty. In this work, to solve this problem, the Zhang neural dynamics (ZND, or called, zeroing neural dynamics) method is employed to the equivalent transformation of the original problem, and a model termed ZND equivalency (ZE) model is proposed and investigated. Meanwhile, a derivative dynamics (DD) model is proposed for comparison purposes. In order to facilitate the implementation of digital hardware, a five- instant Zhang et al discretization (ZeaD) formula is presented. Thus, two discrete models termed discrete-time ZE model and discrete-time DD model (in short DZE model and DDD model, respectively) are proposed by using the presented ZeaD formula. Theoretical analysis and numerical experimental results indicate the good performance, accuracy and superiority of the DZE model.

In this paper, for the purpose of finding square root of a time-dependent matrix, a new discrete-time zeroing neuronet (DTZN) is proposed. Firstly, the problem of square root finding of time-dependent matrix is formulated. Then, an explicit continuous-time zeroing neuronet (CTZN) is derived from the problem formulation equation via vectorization technique. Furthermore, based on Taylor expansion, we present a 5-Step Zhang time-discretization (ZTD) formula. The ZTD is used to approximate the 1st-order derivative of the object, of which the truncational error is proportional to the cube of the sampling period. Finally, the 5-Step DTZN for solving the square root of a time-dependent matrix is acquired by using the presented 5- Step ZTD formula to discretize the CTZN. Theoretical analyses shown stable and convergent performance of the proposed 5- Step DTZN for solving the square root of a time-dependent matrix. Computer experiments results present the stability and convergence of the obtained DTZN for solving square root of time-dependent matrix with the maximum steady-state residual errors proportional to the fourth power of sampling period. By comparison with the DTZNs using Euler formula and the previous 5-Step discretization formula, the proposed 5-Step DTZN has an advantage in residual error. In addition, the influences of step size and sampling period are illustrated by computer experiments results.

In this paper, a novel discrete-time zeroing dynamics (or termed, discrete-time Zhang dynamics, DTZD) model is proposed and analyzed for solving generalized Sylvester future matrix system (GSFMS). First of all, inspired by Kronecker product and vectorization techniques, we convert the GSFMS to a future matrix-vector equation. Secondly, a discretization formula (termed Zhang et al discretization formula, ZeaD formula) is presented, and a novel DTZD model is proposed for solving the GSFMS. In addition, theoretical analyses on the convergence and precision of the DTZD model are presented, and the comparative numerical experiments further substantiate the efficacy and superiority of the DTZD model.

In this paper, a new discrete-time zeroing-dynamics (or termed, Zhang-dynamics, ZD) model is proposed, analyzed and investigated for solving generalized-Sylvester-type future linear matrix inequality (GS-type FLMI). First of all, based on ZD design formula, a continuous-time ZD (CTZD) model, i.e., CTZD-I model, is proposed for solving generalized-Sylvester-type continuous-time linear matrix inequality (GS-type CTLMI). Secondly, a five-node Zhang et al discretization formula (ZeaD formula, also termed Zhang et al time-discretization or Zhang time-discretization [ZTD] formula) is presented for the first-order derivative approximation with higher computational precision. Then, by exploiting the presented ZeaD formula, a novel discrete-time ZD (DTZD) model, i.e., ZeaD-type DTZD-I model, is proposed, analyzed and investigated for solving GS-type FLMI. Theoretical analyses on the convergence and precision of the proposed ZeaD-type DTZD-I model are presented. Comparative numerical experimental results further substantiate the efficacy and superiority of proposed ZeaD-type DTZD-I model.

The goal of knowledge representation learning is to embed entities and relations into a low-dimensional, continuous vector space. How to push a model to its limit and obtain better results is of great significance in knowledge graph's applications. We propose a simple and elegant method, Trans-DLR, whose main idea is dynamic learning rate control during training. Our method achieves remarkable improvement, compared with recent GAN-based method. Moreover, we introduce a new negative sampling trick which corrupts not only entities, but also relations, in different probabilities. We also develop an efficient way, which fully utilizes multiprocessing and parallel computing, to speed up evaluation of the model in link prediction tasks. Experiments show that our method is effective., 5 pages, 1 figure, has been accepted as a conference paper of the 3rd IEEE International Conference on Computational Intelligence and Applications (ICCIA 2018)

The synchronization of chaotic systems has been studied recently due to its fundamental role in engineering fields. However, many conventional synchronization controllers are designed without considering the parameter perturbation, model uncertainty or external disturbance and the design processes of most conventional controllers are relatively quite complicated. Motivated by the above considerations and inspired by the zeroing dynamics (ZD) method, a quite simple and effective ZD-achieving controller is designed for the synchronization of chaotic systems with the simultaneous existence of parameter perturbation, model uncertainty and external disturbance. Theoretical analysis and numerical simulations show the strong robustness of the ZD-achieving controller, and show that the precision can be enhanced by adjusting the value of the parameter in the controller. Moreover, a modified ZD-achieving controller is designed to further improve the ZD-achieving controller. Besides, for comparison, the conventional ZD-derived controller and the linear active controller are presented. Finally, both the synchronization of two isomorphic chaos systems and the synchronization of two heteroideous chaos systems are investigated to substantiate the effectiveness and superiority of the ZD-achieving controller.

This paper considers the output tracking control of general-form single-input single-output (SISO) nonlinear system, which may encounter the problem of division by zero (DBZ). First, via the Zhang dynamics (ZD) method, a ZD controller is proposed. Then, based on the ZD controller with the aid of gradient dynamics (GD) method, a Zhang-gradient (ZG) controller is proposed. For comparison, the conventional input-output linearization (IOL) controller is presented. The ZD, ZG and IOL controllers are compared in different relative-degree cases (i.e., the standard relative-degree case, the loose relative-degree case and the DBZ relative-degree case). Note that the ZG controller is valid in three relative-degree cases, while the ZD and IOL controllers are valid only in the standard relative-degree case and the loose relative-degree case. In addition, performances of ZD and ZG controllers are guaranteed via theoretical analyses and computer simulations for the output tracking of general-form nonlinear system with the DBZ problem conquered.

Inevitable noises and limited computational time are major issues for time-variant matrix inversion in practice. When designing a time-variant matrix inversion algorithm, it is highly demanded to suppress noises without violating the performance of real-time computation. However, most existing algorithms only consider a nominal system in the absence of noises, and may suffer from a great computational error when noises are taken into account. Some other algorithms assume that denoising has been conducted before computation, which may consume extra time and may not be suitable in practice. By considering the above situation, in this paper, an enhanced discrete-time Zhang neural network (EDTZNN) model is proposed, analyzed and investigated for time-variant matrix inversion. For comparison, an original discrete-time Zhang neural network (ODTZNN) model is presented. Note that the EDTZNN model is superior to ODTZNN model in suppressing various kinds of bias noises. Moreover, theoretical analyses show the convergence of the proposed EDTZNN model in the presence of various kinds of bias noises. In addition, numerical experiments including an application to robot motion planning are provided to substantiate the efficacy and superiority of the proposed EDTZNN model for time-variant matrix inversion.

This paper mainly discusses the asymptotic behaviors on the minimizers of convex processes. In view of the convexity argument, it is proved that the minimizers of convex processes with parameterized objective functions satisfy the functional moderate deviation principle. As some applications, the estimators in two basic models (threshold regression models and stochastic dynamical systems) are studied. In particular, the exponential convergence principles on the estimators converging to true parameters are proved.

Knowledge Graph (KG) reasoning aims at finding reasoning paths for relations, in order to solve the problem of incompleteness in KG. Many previous path-based methods like PRA and DeepPath suffer from lacking memory components, or stuck in training. Therefore, their performances always rely on well-pretraining. In this paper, we present a deep reinforcement learning based model named by AttnPath, which incorporates LSTM and Graph Attention Mechanism as the memory components. We define two metrics, Mean Selection Rate (MSR) and Mean Replacement Rate (MRR), to quantitatively measure how difficult it is to learn the query relations, and take advantages of them to fine-tune the model under the framework of reinforcement learning. Meanwhile, a novel mechanism of reinforcement learning is proposed by forcing an agent to walk forward every step to avoid the agent stalling at the same entity node constantly. Based on this operation, the proposed model not only can get rid of the pretraining process, but also achieves state-of-the-art performance comparing with the other models. We test our model on FB15K-237 and NELL-995 datasets with different tasks. Extensive experiments show that our model is effective and competitive with many current state-of-the-art methods, and also performs well in practice.

Nowadays, matrix factorization(MF) has been widely adopted in industry and research as a classical collaborative filtering (CF) algorithm. Unfortunately, the dot product adopted by matrix factorization is against the triangle inequality, which is one of the main reasons why this model is opposed. To address the issue, we propose a recommendation algorithm combining metric learning and mf in the paper. It transforms users’ preferences into distances, using Euclidean distance which satisfies triangular inequalities instead of traditional dot products, then directly decomposes the distance matrix into latent factor matrices of users and items. A multi-layer feedforward neural network is adopted for learning the model. Extensive experiments on two real-world datasets show that the proposed model is obviously superior to some advanced models based on matrix factorization.

Different-level quadratic minimization (DLQM) is a novel-form optimization, hidden in diverse fields but not easy to be perceived. In this work, the basis solution of exemplar DLQM is proposed and investigated. First of all, through derivation of objective function with respect to high-level variable, the basis solution is obtained in a division expression, of which the denominator may be zero. Therefore, division-by-zero (DBZ) is attempted to be solved in this work. Three different methods [i.e., switching technique, Tikhonov regularization, and gradient dynamics (GD)] are applied to solving DBZ. Furthermore, numerical experiments of remedy solutions based on the methods are conducted.

As machinery transmission devices, motors are commonly utilized in robot systems and may significantly affect the dynamic characteristics and stability of robot systems. In view of the fundamental role of the one-link rigid robot system, this paper investigates the tracking control of such a system with motor dynamics. Based on Zhang dynamics (ZD), a new kind of ZD controller is developed and investigated for achieving the tracking-control purpose. Besides, the characteristics and differences of the ZD method compared with other conventional methods are presented. Moreover, theoretical analysis and result are also presented to guarantee the global and exponential convergence performance of the ZD controller.

Being two famous neural networks, the error back-propagation (BP) algorithm based neural networks (i.e., BP-type neural networks, BPNNs) and Hopfield-type neural networks (HNNs) have been proposed, developed, and investigated extensively for scientific research and engineering applications. They are different from each other in a great deal, in terms of network architecture, physical meaning and training pattern. In this paper of literature-review type, we present in a relatively complete and creative manner the common natures of learning between BP-type and Hopfield-type neural networks for solving various (mathematical) problems. Specifically, comparing the BPNN with the HNN for the same problem-solving task, e.g., matrix inversion as well as function approximation, we show that the BPNN weight-updating formula and the HNN state-transition equation turn out to be essentially the same. Such interesting phenomena promise that, given a neural-network model for a specific problem solving, its potential dual neural-network model can thus be developed.

This study investigates the tracking-control problems of the Lorenz, Chen and Lu chaotic systems. Note that the input–output linearisation method cannot solve these tracking-control problems because of the existence of singularities, at which such chaotic systems fail to have a well-defined relative degree. By combining Zhang dynamics and gradient dynamics, an effective controller-design method, termed Zhang-gradient (ZG) method, is proposed for tracking control of the three chaotic systems. This ZG method, with singularities conquered, is capable of solving the tracking-control problems of the chaotic systems. Both theoretical analyses and simulative verifications substantiate that the tracking controllers based on the ZG method can achieve satisfactory tracking accuracy and successfully conquer singularities encountered during the tracking-control process.

In halftone image data hiding, pixel pairs containing master pixels and slave pixels are common operating units. In most previous researches, master pixels are selected at a set of pseudo-random locations, which degrade the image quality. In this paper, a secure halftone image steganographic scheme based on pair swapping is presented, which aims at minimizing the embedding distortions. Different from most previous researches, there is no master-slave relationship in the proposed scheme and the steganographic performance depends on the selection of pixel pairs instead of slave pixels. Based on a human visual system (HVS) model of halftone images, the superiority of pair swapping is proved and vertical swapping is further demonstrated to be the optimal way to improve visual quality among all pair swapping strategies. Finally, a statistical model is developed to predict the vertical pair pattern by considering its neighboring region, based on which, a distortion measurement is proposed to evaluate the embedding distortions on both vision and statistics. To play the advantage of the distortion measurement, syndrome-trellis code (STC) is employed to minimize the embedding distortions. Experimental results show that the proposed steganographic scheme achieves high statistical security with high embedding capacity without degrading the visual quality.

This paper mainly discusses the asymptotic properties of multi-casting autoregressive processes. By using the m -dependence of random vectors, we prove that the least squares (LS) estimator of the unknown parameters satisfies the moderate deviation principle. Two examples of regular cases are also presented.

In this work, we discuss the rate of convergence of one-dimensional random walks in a random environment. Using the hitting time decomposition, we prove that the speed of escape of random walks satisfies the quenched law of the iterated logarithm in a standard way.

An earthquake-forecasting attempt is presented in this work via combining the weights and structure policy (WASP) and addition-subtraction frequency (ASF) algorithms. Specifically, based on the application of three-layer feedforward neuronets equipped with WASP algorithm, further using ASF algorithm, this work attempts to forecast a Japan earthquake with Mj 7.2 or above. Note that past earthquake dates are the only data used in this study. The feasibility and effectiveness of this attempt are verified via the numerical experiments with consistency analysis on obtained dates. Besides, according to the experimental results, an earthquake with Mj 7.2 or above may occur in August 2016 in Japan. Furthermore, with the highest possibility, the date of such an earthquake may occur is August 9, 2016.

Zhang neural network (ZNN) has shown powerful abilities to solve a great variety of time-varying problems in the real domain. In this paper, to solve the time-varying complex quadratic programming (QP) problems in the complex domain, a new type of complex-valued ZNN is further developed and investigated. Specifically, by defining two different complex-valued error functions (termed Zhang functions), two complex ZNN models are proposed and investigated for solving the time-varying complex QP subject to complex-valued linear-equality constraints. It is theoretically proved that such two complex ZNN models globally and exponentially converge to the time-varying theoretical optimal solution of the time-varying complex QP. For comparison, the conventional gradient neural network (GNN) is developed from the real to the complex domains and then is exploited for solving the time-varying complex QP problems. Computational simulation results verify the efficacy of complex ZNN models for solving the time-varying complex QP problems. Besides, the superiorities of complex ZNN models are substantiated, as compared with complex GNN ones.

Solving nonlinear equations has become increasingly significant and indispensable in many disciplines. In the recent decade, two powerful methods, the Zhang dynamics (ZD) method and the gradient dynamics (GD) method have been extensively investigated and implemented in solving nonlinear equations. In addition, some conventional methods, such as the dynamic relaxation method (DRM), redundant manipulators dynamics (RMD), and Langevin dynamics (LD), can also be applied to solve nonlinear equations. In this paper, we propose four novel types of systems based on the ZD method, the GD method and the hybrid dynamics methods to solve nonlinear equations in time-invariant and time-variant situations, respectively. In addition, it is worth pointing out that, by comparison, the four proposed systems depicted in the second-order dynamics are evidently quite different from and more general than some other conventional systems/dynamics for solving nonlinear equations, which all constitute the unified second-order methodology for nonlinear equations solving.

Optical access networks, metro networks and mobile data networks are facing rapidly evolving demands, not only is it essential to satisfy the unyielding need for increased user bandwidths, but future networks must also support the growing wide variation in traffic dynamics and characteristics, due to various emerging technologies, such as cloud-based services, the Internet-of-Things (IoT) and 5G mobile systems, and due to growing trends, such as the proliferation of mobile devices and the rapidly increasing popularity of video-on-demand services. To be cost-effective and commercially sustainable, future optical networks must offer features, such as, dynamic reconfigurability, highly efficient use of network resources, elastic bandwidth provisioning with fine granularity, network sliceabilty and software defined networking (SDN). To meet these requirements Cloud Access Networks (CANs) are proposed which require a number of flexible, adaptive and reconfigurable networking elements. By exploiting digital signal processing (DSP) we have proposed a digital orthogonal filter-based multiplexing technique to implement CANs with multiplexed, independent optical channels at the wavelength, sub-wavelength, and orthogonal sub-band levels. This paper reviews the overall CAN concept, the operating principles of the various CAN network elements and presents an overview of the research work we have undertaken in order to validate the feasibility of the proposed technologies which includes real-time DSP-based demonstrations.

In this article, the authors mainly discuss the law of large number under Kalikow's condition for multi-dimensional random walks in random environment with holding times. The authors give an expression to the escape speed of random walks in terms of the Lyapounov exponents, which have been precisely used in the context of large deviation.

We consider the occupation time variance in the asymmetric exclusion process. In the case where the mean m ≠ 0 (m is the mean hopping rate) and ρ = 1/2 (ρ is the filling probability for a state), we find that the variance is bounded above by O(t3/2).