This paper develops a new Tourist Route Planning (TRP) model by incorporating the entrance fees and the experience values of scenic spots, the travelling costs between scenic spots, and the budget of the tourist. Resultantly, the new TRP aims at finding an optimal route by maximizing the travelling experience value of the tourist with the constraint that the total cost of the route including the travelling costs and the spot entrance fees does not exceed the given budget. To effectively solve this new TRP, this paper adapts the five classical ant colony optimization algorithms (ACO), namely ant system (AS), elite AS (EAS), rank-based AS (RAS), max-min AS (MMAS), and ant colony system (ACS). To this end, this paper first introduces a new heuristic information measure by integrating the experience values and the entrance fees of the scenic spots, and the traveling costs between scenic spots. Further, a new local search strategy encompassing 2-opt and one spot insertion operator is designed to further improve the quality of the route under the budget constraint. Abundant experiments have been carried out on various TRP instances of three scales, namely small-scale, medium-scale, and large-scale, involving different numbers of scenic spots and different settings of budgets. The experimental results demonstrate that all the adapted five ACO algorithms are very effective for addressing the new TRP. Among them, RAS performs the best on small-scale TRP instances, and ACS obtains the best results on medium-scale TRP instances, while MMAS is the most effective one in addressing large-scale TRP instances.

The integration of vehicle-to-everything (V2X) and Internet of Vehicles (IoV) technologies is reshaping vehicular communication, necessitating robust protocols capable of supporting low-power and lossy networks (LLNs). The routing protocol for low-power and lossy networks (RPLs) plays a vital role in enhancing data exchange efficiency and reliability within dynamic vehicular environments. However, RPL faces significant security challenges when adapted to vehicular networks, which differ markedly from the less hostile environments originally envisioned for RPL. In this article, we analyze the security vulnerabilities of RPL in the complex interactive environment of vehicular networks. Specifically, we introduce a novel deep learning-based dynamic attack algorithm to expose the limitations of existing defense mechanisms and highlight RPL’s security vulnerabilities in IoV applications. The experimental results reveal that the proposed attack outperforms traditional attacks in multiple metrics, increasing packet loss by 43%, end-to-end delay by 300%, and reducing link quality throughput by 60% and vehicle node battery life by 50%. Even with in place defense mechanisms, our attack demonstrates greater effectiveness 70% over traditional methods, including version number attacks, wormhole attacks, and DIS flooding attacks. These findings underscore the insufficiency of current security measures and confirm the urgent need for advanced protective strategies to safeguard RPL deployments, particularly in complex IoV communication scenarios.

This study proposes an innovative generative adversarial network (GAN)-based downscaling model for precipitation, named PSRGAN, which aims to enhance the spatial resolution of meteorological data using deep learning techniques. The PSRGAN model integrates a multi-scale feature fusion module (Rception), an attention mechanism (KAM), and the generator-discriminator framework of GANs to address challenges such as data sparsity and spatiotemporal correlations that traditional precipitation super-resolution methods struggle with. By extracting multi-scale spatial features, PSRGAN improves the model’s ability to detect key precipitation regions and enhances the accuracy of predicting extreme precipitation events.The model is trained and tested using low- and high-resolution simulated datasets based on regional climate models, with performance evaluated through various metrics. The experimental results demonstrate that PSRGAN achieves strong performance in the precipitation downscaling task.

Ant Colony Optimization (ACO) has witnessed great success in tackling the Traveling Salesman Problem (TSP). In ACO, ants involved in the pheromone update play pivotal roles in its optimization effectiveness. Along this road, this paper designs an ant selection mechanism along with a non-linear weight method for ACO to update the pheromone effectively, leading to a novel ACO, called NLW-ACO. Particularly, NLW-ACO leverages the fitness values of ants to assign each ant a selection probability. Then, it adaptively chooses ants for pheromone update. Subsequently, a nonlinear weight is assigned to each selected ant based on its fitness value to update the pheromone matrix. Resultantly, better ants have higher selection probabilities and larger weights to take part in the pheromone update. This leads to that NLW-ACO compromises search convergence and search diversity appropriately to seek for the optimum. Experiments have been carried out on 10 TSP instances of diverse scales. The experimental findings substantiate that NLW-ACO significantly outperforms the 5 typical ACO methods, especially on large-scale TSP problems.

Leading exemplars play significant roles in updating particles to seek optimal solutions for Particle Swarm Optimization (PSO). Along this road, this paper devises an Individual-level Dominant Exemplar Selection (IDES) framework for PSO, giving rise to a new PSO variant named IDESPSO. Specifically, instead of using their own personally best positions and the globally best position of the entire swarm to update particles, IDES first randomly chooses two different exemplars for each particle from all personally best positions. Then, it compares the two selected exemplars with the personally best position of this particle. Based on the comparison results, different updating strategies are utilized to update different particles. This method notably enriches the variety among the chosen leading exemplars, thereby substantially bolstering the updating diversity of particles. Under IDES, this paper further develops seven selection strategies to help IDESPSO pick up promising exemplars for particles to evolve. Specifically, the seven selection schemes are the roulette wheel selection, the tournament selection, and five hybridizations of two basic models. A series of experiments have been undertaken on the universally used CEC2014 problem suite to compare IDESPSO with the seven selection schemes and two classic PSOs. The empirical results show that IDESPSO paired with anyone of the seven selection methods, markedly outperforms the two classical PSO variants, highlighting its significant performance.

This article focuses on the task of Multi-Modal Summarization with Multi-Modal Output for China JD.COM e-commerce product description containing both source text and source images. In the context learning of multi-modal (text and image) input, there exists a semantic gap between text and image, especially in the cross-modal semantics of text and image. As a result, capturing shared cross-modal semantics earlier becomes crucial for multi-modal summarization. However, when generating the multi-modal summarization, based on the different contributions of input text and images, the relevance and irrelevance of multi-modal contexts to the target summary should be considered, so as to optimize the process of learning cross-modal context to guide the summary generation process and to emphasize the significant semantics within each modality. To address the aforementioned challenges, Multization has been proposed to enhance multi-modal semantic information by multi-contextually relevant and irrelevant attention alignment. Specifically, a Semantic Alignment Enhancement mechanism is employed to capture shared semantics between different modalities (text and image), so as to enhance the importance of crucial multi-modal information in the encoding stage. Additionally, the IR-Relevant Multi-Context Learning mechanism is utilized to observe the summary generation process from both relevant and irrelevant perspectives, so as to form a multi-modal context that incorporates both text and image semantic information. The experimental results in the China JD.COM e-commerce dataset demonstrate that the proposed Multization method effectively captures the shared semantics between the input source text and source images, and highlights essential semantics. It also successfully generates the multi-modal summary (including image and text) that comprehensively considers the semantics information of both text and image.

The cubature Kalman filter (CKF) overcomes the limitations of the Kalman filter in strong nonlinear systems, which has been widely used in many fields. However, in practical engineering, the abnormal measurement information obtained by the sensor causes the measurement noise covariance to change, which may deteriorate the filtering performance and even cause the filter failure. The fault-tolerant filter can deal with the state estimation problem for the systems with abnormal measurements. The key of the fault-tolerant filter is to forcefully correct filter innovation by using a fading factor. The fault-tolerant filter technology has been extensively applied in many practical systems, but it is still lack of reasonable theoretical analysis. To this end, the measurement noise model is established and the magnitude of the noise deviation is analyzed. The filtering performance under abnormal measurement is analyzed by three mean squared errors (MSEs), which are the ideal MSE, the filter calculated MSE and the true MSE. In order to solve the influence of sampling approximation deviation of CKF on fault detection, an improved fault detection algorithm is proposed. The performance of fault-tolerant CKF is analyzed from two views. The first view is about comparing the filter calculated MSEs of CKF and of fault-tolerant CKF, the second view is about comparing the relative closeness of the filter calculated MSE to the true MSE for the two algorithms. Numerical examples further verify these conclusions.

Accuracy and speed are the most important indexes for evaluating many object tracking algorithms. However, when constructing a deep fully convolutional neural network (CNN), the use of deep network feature tracking will cause tracking drift due to the effects of convolution padding, receptive field (RF), and overall network step size. The speed of the tracker will also decrease. This article proposes a fully convolutional siamese network object tracking algorithm that combines the attention mechanism with the feature pyramid network (FPN), and uses heterogeneous convolution kernels to reduce the amount of calculations (FLOPs) and parameters. The tracker first uses a new fully CNN to extract image features, and introduces a channel attention mechanism in the feature extraction process to improve the representation ability of convolutional features. Then use the FPN to fuse the convolutional features of high and low layers, learn the similarity of the fused features, and train the fully CNNs. Finally, the heterogeneous convolutional kernel is used to replace the standard convolution kernel to improve the speed of the algorithm, thereby making up for the efficiency loss caused by the feature pyramid model. In this article, the tracker is experimentally verified and analyzed on the VOT-2017, VOT-2018, OTB-2013, and OTB-2015 datasets. The results show that our tracker has achieved better results than the state-of-the-art trackers.

In high dimensional environment, the interaction among particles significantly affects their movements in searching the vast solution space and thus plays a vital role in assisting particle swarm optimization (PSO) to attain good performance. To this end, this paper designs a random contrastive interaction (RCI) strategy for PSO, resulting in RCI-PSO, to tackle large-scale optimization problems (LSOPs) effectively and efficiently. Unlike existing interaction mechanisms for low-dimensional problems, RCI randomly chooses several different peers from the current swarm to construct a random interaction topology for each particle. Then, it lets the particle interact with the selected peers based on their current evolutionary information instead of their historical evolutionary information. Within the topology, RCI only propagates the evolutionary information of two contrastive dominators with the largest difference in fitness to direct the evolution of the particle. Therefore, particles with no more than two dominators in their topologies are not updated. Furthermore, a dynamic topology size adjustment scheme is devised to gradually enlarge the interaction topology. In this way, the swarm gradually switches from exploring the immense search space dispersedly to exploiting the found optimal regions intensively as the evolution continues. With these two strategies, RCI-PSO expectedly compromises search diversity and search convergence well at the swarm level and the particle level. At last, extensive experiments executed on two public LSOP suites verify that RCI-PSO performs competitively with or even much better than totally 40 state-of-theart large-scale approaches and preserves a good capability and scalability in tackling complex LSOPs.

The rapid increase of the number of motor vehicles over the last several decades has driven a corresponding increase in the severity of traffic congestion, which has exhibited a considerable human impact. Intelligent anti-collision control via inter-vehicle communication technology can facilitate vehicles adhering to spacing speed standards and improve road utilization and traffic efficiency. In this paper, we apply a deep learning image estimation model based on joint attention mechanism. The network framework uses a deep estimation network Yolov5 and a location based VANET information fast transmission strategy to work together. This paper mainly considers vehicle distance measurement technology as a point of entry to study multi-sensor information fusion for vehicle collision prevention technology based on the self-organizing vehicular ad-hoc network (VANET). This paper also proposes a solution based on the strategy of one-way transmission of shared information and dynamic valuation of a cluster distance threshold with vehicle density. The proposed vehicle anti-collision control algorithm is designed to realize dynamic vehicle control via inter-vehicle communication. In this paper, the two-way coupling of traffic flow and network simulator is used to randomly generate vehicle nodes on the road, and the behavior of the anti-collision system is simulated. The experimental results show that the predetermined control goal is achieved, which demonstrates the effectiveness of the proposed algorithm.

Different from existing studies where low-dimensional optimizers are utilized to optimize the path of an unmanned aerial vehicle (UAV), this paper attempts to employ large-scale swarm optimizers to solve the path planning problem of UAV, such that the path can be subtler and smoother. To this end, a variation encoding scheme is devised to encode particles. Specifically, each dimension of a particle is encoded by a triad consisting of the relative movements of UAV along the three coordinate axes. With this encoding scheme, a large number of anchor points can be optimized to form the path and repetitive anchor points can be avoided. Subsequently, this paper embeds this encoding scheme into four representative and well-performed large-scale swarm optimizers, namely the stochastic dominant learning swarm optimizer (SDLSO), the level-based learning swarm optimizer (LLSO), the competitive swarm optimizer (CSO), and the social learning particle swarm optimizer (SL-PSO), to optimize the path of UAV. Experiments have been conducted on 16 scenes with 4 different numbers of peaks in the landscapes. Experimental results have demonstrated that the devised encoding scheme is effective to cooperate with the four large-scale swarm optimizers to solve the path planning problem of UAV and SDLSO achieves the best performance.

Ant Colony Optimization (ACO) has shown very promising performance in solving Traveling Salesman Problem (TSP). However, most existing ACO algorithms utilize either the absolutely best ants or all ants to update the pheromone matrix. This leads to either serious diversity loss or slow convergence. To alleviate these predicaments, this paper designs a random pairwise competition based ant selection for pheromone updating. Specifically, a number of ants are randomly selected from the ant colony and then are randomly paired together. Subsequently the better one in each pair is selected to update the pheromone matrix. In this way, a good balance between search diversity and search convergence is potentially maintained. Integrating this selection strategy along with a local search scheme into the ACO framework, a new ACO algorithm called random pairwise competition based ACO (RPCACO) is developed. Experiments conducted on 8 TSP instances from the TSPLIB benchmark set demonstrate that RPCACO is more effective and efficient than the five classical ACO algorithms in solving TSP.

Multiple traveling salesmen problem (MTSP) is an extension of traditional traveling salesman problem (TSP). It involves both the city assignment optimization and the route optimization of each salesman. Genetic algorithms (GA) have been widely used to solve MTSP thanks to its easiness in implementation and good global search ability. To help GA effectively solve MTSP, researchers have developed various encoding schemes. However, there is no systematic and comparative study on the effectiveness of these encoding strategies. To fill this gap, this paper conducts investigations to compare four popular encoding strategies for MTSP, namely the one-chromosome encoding, the two-chromosome encoding, the two-part-chromosome encoding and the multi-chromosome encoding. Experimental results on different MTSP instances with different numbers of cities and salesmen show that the multi-chromosome encoding is far better than the other encoding strategies.

Mutation plays a crucial role in assisting differential evolution (DE) to effectively solve optimization problems. The key to mutation lies in the selection of parent individuals participating in the mutation. Along this road, this paper devises a binomial distribution-assisted individual selection strategy for DE. Specifically, this paper takes advantage of the probability distribution function of the binomial distribution to assign weights to individuals based on their fitness rankings. In this way, the selection of individuals focuses more on medium better individuals instead of the top best ones. Therefore, high mutation diversity can be preserved and thus it is likely that falling into local regions can be effectively avoided. Embedding this selection strategy into DE, a novel DE variant called binomial distribution assisted DE (BDDE) is developed. Experiments conducted on the CEC2017 benchmark suite have verified the effectiveness of BDDE in solving optimization problems. Particularly, BDDE gains much better performance against the well-known and representative mutation strategies.

Expensive optimization problems (EOPs) are becoming more and more ubiquitous nowadays. To effectively solve such problems, surrogate-assisted evolutionary algorithms (SAEAs) have been developed. Specifically, a SAEA usually maintains a surrogate model to simulate the real objective function of an EOP. Such a surrogate model is trained based on real-evaluated solutions. Then, it is utilized to evaluate the fitness of individuals in the EA instead of the real expensive fitness evaluation. Though many SAEAs have been designed, they mainly concentrate on dealing with low-dimensional EOPs with fewer than 300 dimensions. Their performance on large-scale EOPs with more than 300 dimensions is unknown. To fill this gap, this paper conducts a comparative study on two types of state-of-the-art SAEAs with a total of four algorithms on four classical EOPs. To make comprehensive comparisons, we range the dimension size from 50 to 1000. As far as we know, this is the first time to assess SAEAs on EOPs with such a wide range of dimension sizes and such high dimensionality. The comparison results show that the optimization performance of the compared four SAEAs on high-dimensional EOPs with more than 500 dimensions is not as satisfactory as their performance on low-dimensional EOPs because of their slow convergence. Therefore, research on large-scale SAEAs for high-dimensional EOPs still deserves intensive attention.

Because of the robustness and sparsity performance of least absolute deviation (LAD or$l_{1}$) optimization, developing effective solution methods becomes an important topic. Recurrent neural networks (RNNs) are reported to be capable of effectively solving constrained$l_{1}$-norm optimization problems, but their convergence speed is limited. To accelerate the convergence, this article introduces two RNNs, in form of continuous- and discrete-time systems, for solving$l_{1}$-norm optimization problems with linear equality and inequality constraints. The RNNs are theoretically proven to be globally convergent to optimal solutions without any condition. With reduced model complexity, the two RNNs can significantly expedite constrained$l_{1}$-norm optimization. Numerical simulation results show that the two RNNs spend much less computational time than related RNNs and numerical optimization algorithms for linearly constrained$l_{1}$-norm optimization.

Multiple traveling salesmen problem with visiting constraints (VCMTSP) is a general version of the classical multiple traveling salesmen problem (MTSP), where each city can be only accessed by a number of salesmen. To cope with this new problem, we adapt the genetic algorithm (GA) for MTSP by using a dual-chromosome representation scheme with one chromosome denoting the visiting sequence of cities and the other representing the assignment of cities to salesmen. To further promote the effectiveness of GA in solving VCMTSP, we modify three popular crossover operators, namely the cycle crossover (CX), the order crossover (OX), and the partially mapped crossover (PMX). Similar to the execution for traditional TSP, the three crossover operators are all executed on the city sequence chromosome, while the adaption of them lies in the modification of the salesman assignment in the second chromosome. To this end, a correction mechanism according to the accessibility matrix is conducted to make the generated solutions after crossover feasible. Extensive experiments conducted on totally 16 VCMTSP instances generated from the benchmark TSPLIB set demonstrate that the adapted GA could effectively cope with VCMTSP, and the GA with the modified PMX achieves the best overall performance.

The scaling factor (F) in the mutation operation and the crossover rate (CR) in the crossover operation are considerably critical in assisting differential evolution (DE) to attain good optimization performance. As a result, DE is very sensitive to these two parameters. To address this predicament, many adaptive parameter control methods have been proposed for these two parameters. However, there are no comprehensive comparisons among these adaptive parameter methods. To make up for this defect, this paper mainly investigates the effectiveness of six widely utilized adaptive strategies, namely the ones in JADE, IDE, jDE, SinDE, FDSADE, and RDE. For fairness, this paper selects the binomial crossover and the mutation “DE/current-to-pbest/1” to accompany the six adaptive parameter strategies. Experimental results on the commonly adopted CEC2014 benchmark suite have demonstrated that the adaptive parameter control methods in IDE and JADE help DE achieve the best overall performance. With these investigations, it is envisaged that this paper provides a fundamental guideline for new learners and those looking for an appropriate adaptive parameter technique for their newly created DE algorithms.

This paper proposes a ranking weight based roulette wheel selection (RWRWS) method for a promising particle swarm optimizer, called comprehensive learning particle swarm optimizer (CLPSO), to further improve its optimization performance. Specifically, the proposed RWRWS adopts a non-linear weight function to enhance the selection probabilities of promising personal best positions during the exemplar construction. In this way, it is expected that the construction efficiency of generating a promising leading exemplar for each particle could be improved and thus the optimization performance of CLPSO is expectedly elevated. To validate the feasibility and effectiveness of RWRWS, we carry out extensive experiments on a widely acknowledged benchmark problem set by comparing it with other three selection methods, namely the fitness-based roulette wheel selection (FRWS), the ranking based roulette wheel selection (RRWS), and the tournament selection (TS). Experimental results demonstrate that RWRWS helps CLPSO attain the best overall performance among the four selection methods.

Influenced by many complex factors, it is very difficult to obtain high-performance industrial power load forecasting. The industrial power load forecasting is deeply studied by fusing some machine-learning methods for industrial enterprise power consumers. As a result, a novel power load forecasting method is proposed by taking into account the variation of load characteristics in different regions, industries, and production patterns. First, through the improved K -means clustering analysis, the historical load data are classified as the production patterns to which they belong. Then, the prediction algorithm combining reinforcement learning with particle swarm optimization and the least-squares support vector machine is proposed. Finally, the improved algorithm in this article is used for short-term load forecasting separately by the load data in different patterns after the above processing. The forecasting method in this article is based on data driven with real datasets. The results of the simulation experiment show that the improved prediction algorithm can distinguish the changes in different production patterns and identify the load characteristics of different regions and industries with high prediction accuracy, which has practical application value.

This article investigates a robust guaranteed cost finite-time control for coupled neural networks with parametric uncertainties. The parameter uncertainties are assumed to be time-varying norm bounded, which appears on the system state and input matrices. The robust guaranteed cost control laws presented in this article include both continuous feedback controllers and intermittent feedback controllers, which were rarely found in the literature. The proposed guaranteed cost finite-time control is designed in terms of a set of linear-matrix inequalities (LMIs) to steer the coupled neural networks to achieve finite-time synchronization with an upper bound of a guaranteed cost function. Furthermore, open-loop optimization problems are formulated to minimize the upper bound of the quadratic cost function and convergence time, it can obtain the optimal guaranteed cost periodically intermittent and continuous feedback control parameters. Finally, the proposed guaranteed cost periodically intermittent and continuous feedback control schemes are verified by simulations.

Time delays are unavoidable since they are ubiquitous and may have a great impact on the performance of neural networks. Resources efficiency is a common concern in many networked systems with limited resources. This article investigates quasisynchronization of the heterogeneous neural networks with time-varying delays via event-triggered impulsive controls which combine the impulsive control and the event-triggered technique. The centralized and distributed event-triggered impulsive controls are, respectively, presented. The suitable Lyapunov functions are constructed, and the triggering functions are derived, which guarantee that not only are the synchronization errors less than a non-negative bound but also the Zeno behaviors can be eliminated. It is suggested that the distributed one has great superiority in taking up fewer resources compared with the time-triggered impulsive control. Numerical examples are proposed to verify the validity of the centralized and distributed control methods.

Deep convolutional neural network (CNN) shows excellent effectiveness on hyperspectral image (HSI) classification. However, the architecture design of CNN requires abundant expert knowledge and experience, which poses great prohibition to its wide application in real-world engineering. To alleviate the issue, this article proposes an evolving block-based CNN (EB-CNN) to search the optimal architecture based on the genetic algorithm (GA) automatically. Specifically, two kinds of basic blocks with totally six different configurations are first designed to construct the search space. Then, a flexible encoding strategy is devised for the GA to allow different chromosomes to evolve with different lengths. In this manner, the width of each layer and the depth of the architecture can be simultaneously optimized. Furthermore, a novel swapping mutation operator is proposed for the GA to speed up the search efficiency and save computing resources. With the abovementioned techniques, the proposed algorithm automatically seeks the optimal CNN architecture for HSI classification, leading to its better usability than handcrafted CNNs. At last, extensive experiments conducted on five commonly used HSI datasets demonstrate that the proposed EB-CNN achieves highly competitive or even better performance, as compared with the state-of-the-art peer algorithms.

Commercialized 5G technology will provide reliable and efficient connectivity of motor vehicles that could support the dissemination of information under an intelligent transportation system. However, such service still suffers from risks or threats due to malicious content producers. The traditional public key infrastructure (PKI) cannot restrain such untrusted but legitimate publishers. Therefore, a trust-based service management mechanism is required to secure information dissemination. The issue of how to achieve a trust management model becomes a key problem in the situation. This paper proposes a novel prototype of the decentralized trust management system (DTMS) based on blockchain technologies. Compared with the conventional and centralized trust management system, DTMS adopts a decentralized consensus-based trust evaluation model and a blockchain-based trust storage system, which provide a transparent evaluation procedure and irreversible storage of trust credits. Moreover, the proposed trust model improves blockchain efficiency by only allowing trusted nodes participating in the validation and consensus process. Additionally, the designed system creatively applies a trusted execution environment (TEE) to secure the trust evaluation process together with an incentive model that is used to stimulate more participation and penalize malicious behaviours. Finally, to evaluate our new design prototype, both numerical analysis and practical experiments are implemented for performance evaluation.

This paper proposes an adaptive version of an existing promising large-scale optimizer named level-based learning swarm optimizer (LLSO). Though such an optimizer has shown promising performance in dealing with large-scale optimization, it is much sensitive to its two introduced parameters. To alleviate this dilemma, this paper devises two simple yet effective adaptive adjustment strategies for the two parameters, leading to an adaptive LLSO(ALLSO). Specifically, this paper first defines a novel aggregation indicator based on the difference between the global best fitness and the averaged fitness of the swarm, to roughly evaluate the evolution state of the swarm. Then, based on this indicator, two adaptive adjustment strategies are devised to dynamically determine the values of the two parameters during the evolution. With these two strategies, the swarm is expected to maintain a potentially good balance between intensification and diversification. Extensive experiments conducted on two widely used large- scale benchmark sets demonstrate that the two adaptive strategies effectively improve the performance of LLSO.

This paper is concerned with the finite-time synchronization (FTS) of memristor-based recurrent neural networks (MRNNs) combined with inertial items and mixed delays, where both the discrete delays and bounded distributed delays are included. First, MRNNs with inertial items are of second-order state derivatives, thereby differing from the classical first-order MRNNs and bringing difficulties to study the dynamics of such systems. By using the order-reduction method, such kind of second-order MRNNs is transferred into conventional first-order differential systems. Then, under two kinds of designed feedback controllers, several sufficient conditions are derived ensuring the FTS of MRNNs with inertial items and mixed delays. Finally, numerical simulations are provided to show the effectiveness of the results and one application is also presented in pseudorandom number generation.

Classification plays an important role in the field of hyperspectral image (HSI) remote sensing. In this letter, a novel multiscale superpixel kernel-based low-rank representation (MSKLRR) classifier is proposed for HSI classification. A multiscale superpixel segmentation method is first used to generate several homogeneous regions at different scales. Then, the multiscale superpixel spectral-spatial kernel (SSK) is generated using the radial basis function (RBF) kernel on the multiscale superpixels. Finally, the multiscale superpixel kernel is integrated into a low-rank representation (LRR) to generate the MSKLRR classifier for HSI classification. The experimental results with two widely used HSIs suggest an advantage of the proposed method over other classical classification methods.

In dynamic optimization problems (DOPs), as the environment changes through time, the optima also dynamically change. How to adapt to the dynamic environment and quickly find the optima in all environments is a challenging issue in solving DOPs. Usually, a new environment is strongly relevant to its previous environment. If we know how it changes from the previous environment to the new one, then we can transfer the information of the previous environment, e.g., past solutions, to get new promising information of the new environment, e.g., new high-quality solutions. Thus, in this paper, we propose a neural network (NN)-based information transfer method, named NNIT, to learn the transfer model of environment changes by NN and then use the learned model to reuse the past solutions. When the environment changes, NNIT first collects the solutions from both the previous environment and the new environment and then uses an NN to learn the transfer model from these solutions. After that, the NN is used to transfer the past solutions to new promising solutions for assisting the optimization in the new environment. The proposed NNIT can be incorporated into population-based evolutionary algorithms (EAs) to solve DOPs. Several typical state-of-the-art EAs for DOPs are selected for comprehensive study and evaluated using the widely used moving peaks benchmark. The experimental results show that the proposed NNIT is promising and can accelerate algorithm convergence.