Search

Achieving robust cross contexts speech emotion recognition (SER) has become a critical next direction of research for wide adoption of SER technology. The core challenge is in the large variability of affective speech that is highly contextualized. Prior works have worked on this as a transfer learning problem that mostly focuses on developing domain adaptation strategy. However, many of the existing speech emotion corpora, even those considered as large scale, are still limited in size resulting in an unsatisfactory transfer result. On the other hand, directly collecting context-specific corpus often results in an even smaller data size leading to an inevitably non-robust accuracy. In order to mitigate this issue, we propose the concept of enhancing the affect-related variability when learning the in-context acoustic latent representation by integrating out-of-context emotion data. Specifically, we utilize adversarial autoencoder network as our backbone with multiple out-of-context emotion labels derived for each in-context samples that serve as an auxiliary constraint in learning the latent representation. We extensively evaluate our framework using three in-context databases with three out-of-context databases. In this work, we demonstrate not only an improved recognition accuracy but also a comprehensive analysis on the effectiveness of this representation learning strategy.

In many domains of empirical sciences, discovering the causal structure within variables remains an indispensable task. Recently, to tackle unoriented edges or latent assumptions violation suffered by conventional methods, researchers formulated a reinforcement learning (RL) procedure for causal discovery and equipped a REINFORCE algorithm to search for the best rewarded directed acyclic graph. The two keys to the overall performance of the procedure are the robustness of RL methods and the efficient encoding of variables. However, on the one hand, REINFORCE is prone to local convergence and unstable performance during training. Neither trust region policy optimization, being computationally expensive, nor proximal policy optimization (PPO), suffering from aggregate constraint deviation, is a decent alternative for combinatory optimization problems with considerable individual subactions. We propose a trust region-navigated clipping policy optimization method for causal discovery that guarantees both better search efficiency and steadiness in policy optimization, in comparison with REINFORCE, PPO, and our prioritized sampling-guided REINFORCE implementation. On the other hand, to boost the efficient encoding of variables, we propose a refined graph attention encoder called SDGAT that can grasp more feature information without priori neighborhood information. With these improvements, the proposed method outperforms the former RL method in both synthetic and benchmark datasets in terms of output results and optimization robustness.

Heterogeneous information network (HIN) embedding, aiming to map the structure and semantic information in a HIN to distributed representations, has drawn considerable research attention. Graph neural networks for HIN embeddings typically adopt a hierarchical attention (including node-level and meta-path-level attentions) to capture the information from meta-path-based neighbors. However, this complicated attention structure often cannot achieve the function of selecting meta-paths due to severe overfitting. Moreover, when propagating information, these methods do not distinguish direct (one-hop) meta-paths from indirect (multi-hop) ones. But from the perspective of network science, direct relationships are often believed to be more essential, which can only be used to model direct information propagation. To address these limitations, we propose a novel neural network method via implicitly utilizing attention and meta-paths, which can relieve the severe overfitting brought by the current over-parameterized attention mechanisms on HIN. We first use the multi-layer graph convolutional network (GCN) framework, which performs a discriminative aggregation at each layer, along with stacking the information propagation of direct linked meta-paths layer-by-layer, realizing the function of attentions for selecting meta-paths in an indirect way. We then give an effective relaxation and improvement via introducing a new propagation operation which can be separated from aggregation. That is, we first model the whole propagation process with well-defined probabilistic diffusion dynamics, and then introduce a random graph-based constraint which allows it to reduce noise with the increase of layers. Extensive experiments demonstrate the superiority of the new approach over state-of-the-art methods.

Partial multilabel learning (PML) aims to learn from training data, where each instance is associated with a set of candidate labels, among which only a part is correct. The common strategy to deal with such a problem is disambiguation, that is, identifying the ground-truth labels from the given candidate labels. However, the existing PML approaches always focus on leveraging the instance relationship to disambiguate the given noisy label space, while the potentially useful information in label space is not effectively explored. Meanwhile, the existence of noise and outliers in training data also makes the disambiguation operation less reliable, which inevitably decreases the robustness of the learned model. In this article, we propose a prior label knowledge regularized self-representation PML approach, called PAKS, where the self-representation scheme and prior label knowledge are jointly incorporated into a unified framework. Specifically, we introduce a self-representation model with a low-rank constraint, which aims to learn the subspace representations of distinct instances and explore the high-order underlying correlation among different instances. Meanwhile, we incorporate prior label knowledge into the above self-representation model, where the prior label knowledge is regarded as the complement of features to obtain an accurate self-representation matrix. The core of PAKS is to take advantage of the data membership preference, which is derived from the prior label knowledge, to purify the discovered membership of the data and accordingly obtain more representative feature subspace for model induction. Enormous experiments on both synthetic and real-world datasets show that our proposed approach can achieve superior or comparable performance to state-of-the-art approaches.

We study the problem of Resilient Service Provisioning for Edge computing (RSPE), i.e., how to determine a service placement strategy to maximize the expected overall utility by service provisioning, in the presence of uncertain service failures. RSPE is extremely challenging to tackle, because the explicit expression of its objective function is difficult to obtain, and it is a resilient max-min problem subject to knapsack constraints, which is unexplored so far and cannot be addressed by existing resilient optimization techniques. We first explore the potential properties of the implicit objective function, and reveal that it is monotone submodular under certain conditions. We further prove that the knapsack constraints form a q-independence system constraint, where q>0 is a constant related to the constraints. We propose two novel solutions for the general RSPE and homogeneous case, respectively. Firstly, for the general problem, we propose a “two-step greedy” algorithm achieving constant approximation ratio within polynomial time. Secondly, for the homogeneous case where one of the knapsack constraints reduces to a matroid constraint, we propose an improved “first-greedy-then-local search” polynomial time algorithm achieving better approximation ratio than the previous one. Both extensive simulations and field experiments validate the effectiveness of our proposed algorithms.

Nonoccurring behavior (NOB) studies have attracted the growing attention of scholars as a crucial part of behavioral science. As an effective method to discover both NOB and occurring behaviors (OB), negative sequential pattern (NSP) mining is successfully used in analyzing medical treatment and abnormal behavior patterns. At this time, NSP mining is still an active and challenging research domain. Most of the algorithms are inefficient in practice. Briefly, the key weaknesses of NSP mining are: 1) an inefficient positive sequential pattern (PSP) mining process, 2) a strict constraint of negative containment, and 3) the lack of an effective Negative Sequential Candidate (NSC) generation method. To address these weaknesses, we propose a highly efficient algorithm with improved techniques, named sc-NSP, to mine NSP efficiently. We first propose an improved PrefixSpan algorithm in the PSP mining process, which connects to a bitmap storage structure instead of the original structure. Second, sc-NSP loosens the frequency constraint and exploits the NSC generation method of positive and negative sequential patterns mining (PNSP) (a classic NSP mining method). Furthermore, a novel pruning strategy is designed to reduce the computational complexity of sc-NSP. Finally, sc-NSP obtains the support of NSC by using the most efficient bitwise-based calculation operation. Theoretical analyses show that sc-NSP performs particularly well on data sets with a large number of elements and items in sequence. Comparison and extensive experiments along with case studies on health data show that sc-NSP is 10 times more efficient than other state-of-the-art methods, and the number of NSPs obtained is 5 times greater than other methods.

Image and sentence matching is a critical task to bridge the visual and textual discrepancy due to the heterogeneous modalities. Great progress has been made by exploring the coarse-grained relationships between images and sentences or fine-grained relationships between regions and words. However, how to fully excavate and exploit corresponding relations between these two modalities is still challenging. In this work, we propose a novel Multi-scale Fine-grained Alignments Network (MFA), which can effectively explore multi-scale visual-textual correspondences to facilitate bridging cross-modal discrepancy. Specifically, word-scale matching module is firstly utilized to mine the basic but fundamental correspondences between single word and independent region. Then, we propose a phrase-scale matching module to explore the relations between object with the constraint of attribute and corresponding region, which can further reserve more associated information. To cope with the complex interactions among multiple phrases and images, we design the relation-scale matching module to capture high-order semantics between two modalities. Moreover, each matching module includes visual aggregation and textual aggregation, which can ensure the bi-directional coupling of multi-scale semantics. Extensive qualitative and quantitative experiments on two challenging datasets including Flickr30K and MSCOCO, show that the proposed method achieves superior performance compared with the existing methods.

Emotion recognition from EEG signals has attracted much attention in affective computing. Recently, a novel dynamic graph convolutional neural network (DGCNN) model was proposed, which simultaneously optimized the network parameters and a weighted graph G characterizing the strength of functional relation between each pair of two electrodes in the EEG recording equipment. In this paper, we propose a sparse DGCNN model which improves the DGCNN by imposing a sparseness constraint on G. Our work is based on an important observation: the tomography study reveals that different brain regions sampled by EEG electrodes may be related to different functions of the brain and then the functional relations among electrodes are possibly highly localized and sparse. However, introducing sparseness constraint into the graph G makes the loss function of sparse DGCNN non-differentiable at some singular points. To ensure that the training process of sparse DGCNN converges, we apply the forward-backward splitting method. To evaluate the performance of sparse DGCNN, we compare it with four representative recognition methods as well as different features and spectral bands. The results show that (1) sparse DGCNN has consistently better accuracy than representative methods and has a good scalability, and (2) DE, PSD and ASM features on γ bands convey most discriminative emotional information, and fusion of separate features and frequency bands can improve recognition performance.

Despite that convolutional neural networks (CNNs) have shown high-quality reconstruction for single image dehazing, recovering natural and realistic dehazed results remains a challenging problem due to semantic confusion in the hazy scene. In this article, we show that it is possible to recover textures faithfully by incorporating semantic prior into dehazing network since objects in haze-free images tend to show certain shapes, textures, and colors. We propose a semantic-aware dehazing network (SDNet) in which the semantic prior is taken as a color constraint for dehazing, benefiting the acquisition of a reasonable scene configuration. In addition, we design a densely connected block to capture global and local information for dehazing and semantic prior estimation. To eliminate the unnatural appearance of some objects, we propose to fuse the features from shallow and deep layers adaptively. Experimental results demonstrate that our proposed model performs favorably against the state-of-the-art single image dehazing approaches.

This article mainly explores the local input-to-state stability (LISS) property of a class of nonlinear systems via a saturated control strategy, where both the external disturbance and impulsive disturbance being fully considered. In terms of the Lyapunov method and inequality techniques, some sufficient conditions under which the system can be made LISS are proposed, and the elastic constraint relationship among saturated control gain, rate coefficients, external disturbance, and domain of initial value is revealed. Moreover, the optimization design procedures are provided with the hope of obtaining the estimates of admissible external disturbance and domain of initial value as large as possible, where the corresponding saturated control law can be designed by solving LMI-based conditions. In the absence of an external disturbance, the locally exponential stability (LES) property can also be presented with a set of more relaxed conditions. Finally, two examples are presented to reveal the validity of the obtained results.

Constrained operations for autonomous vehicles have been extensively studied in the literature over the recent years. However, to the best of the authors knowledge, all of the existing works address only constant or time-varying constraint functions. In this work, we study path-dependent constraint requirements, which explicitly depend on the path parameter, instead of depending on the time variable directly. This approach is more practical in reality, where the constraint requirements are often shaped by the environment boundaries. From the system users perspectives, it is also much easier to define constraint functions based on the path parameter. A modified version of the universal barrier function is used in the analysis of pathdependent constraint requirements. We show that under the proposed novel control scheme, the vehicles line-of-sight distance and angle error terms can converge into small sets near the equilibrium with a fixed-time convergence rate, while the pathdependent constraint requirements are satisfied at all time. A simulation and an experiment study further demonstrate the efficacy of the proposed scheme.

Stitching images with parallax for naturalness remains a challenging problem. This paper proposes an image stitching method which preserves the flatness of planes in the scene for a natural look. Our method formulates the alignment of images as the camera parameters and the normal vectors of planes. Given a set of feature point matches, a process of grouping points into different layers and rejecting outliers is introduced. According to the epipolar constraint of corresponding points in two images, the focal length and the pose change of the camera are recovered simultaneously. Then, the normal vectors are estimated from the point pairs. To achieve good alignment and guide the warping of images, the model is combined with the mesh deformation as a global similarity constraint. In addition, bundle adjustment is adopted to maintain the consistency for stitching multiple images. Experiment shows that the proposed approach outperforms some state-of-the-art warps on real-world scenes.

Constrained multiobjective optimization problems widely exist in real-world applications. To handle them, the balance between constraints and objectives is crucial, but remains challenging due to non-negligible impacts of problem types. In our context, the problem types refer particularly to those determined by the relationship between the constrained Pareto-optimal front (PF) and the unconstrained PF. Unfortunately, there has been little awareness on how to achieve this balance when faced with different types of problems. In this article, we propose a new constraint handling technique (CHT) by taking into account potential problem types. Specifically, inspired by the prior work, problems are classified into three primary types: 1) I; 2) II; and 3) III, with the constrained PF being made up of the entire, part and none of the unconstrained counterpart, respectively. Clearly, any problem must be one of the three types. For each possible type, there exists a tailored mechanism being used to handle the relationships between constraints and objectives (i.e., constraint priority, objective priority, or the switch between them). It is worth mentioning that exact problem types are not required because we just consider their possibilities in the new CHT. Conceptually, we show that the new CHT can make a tradeoff among different types of problems. This argument is confirmed by experimental studies performed on 38 benchmark problems, whose types are known, and a real-world problem (with unknown types) in search-based software engineering. Results demonstrate that within both decomposition-based and nondecomposition-based frameworks, the new CHT can indeed achieve a good tradeoff among different problem types, being better than several state-of-the-art CHTs.

In this article, the adaptive neural backstepping control approaches are designed for uncertain stochastic nonlinear systems with full-state constraints. According to the symmetry of constraint boundary, two cases of controlled systems subject to symmetric and asymmetric constraints are studied, respectively. Then, corresponding adaptive neural controllers are developed by virtue of backstepping design procedure and the learning ability of radial basis function neural network (RBFNN). It is worth mentioning that the integral Barrier Lyapunov function (IBLF), as an effective tool, is first applied to solve the above constraint problems. As a result, the state constraints are avoided from being transformed into error constraints via the proposed schemes. In addition, based on Lyapunov stability analysis, it is demonstrated that the errors can converge to a small neighborhood of zero, the full states do not exceed the given constraint bounds, and all signals in the closed-loop systems are semiglobally uniformly ultimately bounded (SGUUB) in probability. Finally, the numerical simulation results are provided to exhibit the effectiveness of the proposed control approaches.

Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) aims at searching corresponding natural images with the given free-hand sketches, under the more realistic and challenging scenario of Zero-Shot Learning (ZSL). Prior works concentrate much on aligning the sketch and image feature representations while ignoring the explicit learning of heterogeneous feature extractors to make themselves capable of aligning multi-modal features, with the expense of deteriorating the transferability from seen categories to unseen ones. To address this issue, we propose a novel Transferable Coupled Network (TCN) to effectively improve network transferability, with the constraint of soft weight-sharing among heterogeneous convolutional layers to capture similar geometric patterns, e.g., contours of sketches and images. Based on this, we further introduce and validate a general criterion to deal with multi-modal zero-shot learning, i.e., utilizing coupled modules for mining modality-common knowledge while independent modules for learning modality-specific information. Moreover, we elaborate a simple but effective semantic metric to integrate local metric learning and global semantic constraint into a unified formula to significantly boost the performance. Extensive experiments on three popular large-scale datasets show that our proposed approach outperforms state-of-the-art methods to a remarkable extent: by more than 12% on Sketchy, 2% on TU-Berlin and 6% on QuickDraw datasets in terms of retrieval accuracy. The project page is available at: https://haowang1992.github.io/publication/TCN.

We establish the undecidability of conditional affine information inequalities, the undecidability of the conditional independence implication problem with a constraint that one random variable is binary, and the undecidability of the problem of deciding whether the intersection of the entropic region and a given affine subspace is empty. This is a step towards the conjecture on the undecidability of conditional independence implication. The undecidability is proved via a reduction from the periodic tiling problem (a variant of the domino problem). Hence, one can construct examples of the aforementioned problems that are independent of ZFC (assuming ZFC is consistent)., 19 pages, 7 figures, presented in part at the 2021 IEEE Information Theory Workshop

In the robust secure aggregation problem, a server wishes to learn and only learn the sum of the inputs of a number of users while some users may drop out (i.e., may not respond). The identity of the dropped users is not known a priori and the server needs to securely recover the sum of the remaining surviving users. We consider the following minimal two-round model of secure aggregation. Over the first round, any set of no fewer than $U$ users out of $K$ users respond to the server and the server wants to learn the sum of the inputs of all responding users. The remaining users are viewed as dropped. Over the second round, any set of no fewer than $U$ users of the surviving users respond (i.e., dropouts are still possible over the second round) and from the information obtained from the surviving users over the two rounds, the server can decode the desired sum. The security constraint is that even if the server colludes with any $T$ users and the messages from the dropped users are received by the server (e.g., delayed packets), the server is not able to infer any additional information beyond the sum in the information theoretic sense. For this information theoretic secure aggregation problem, we characterize the optimal communication cost. When $U\leq T$ , secure aggregation is not feasible, and when $U > T$ , to securely compute one symbol of the sum, the minimum number of symbols sent from each user to the server is 1 over the first round, and $1/(U-T)$ over the second round.

This paper aims to solve the problem of decentralized event-based finite-time control for a class of high-order interconnected nonlinear systems with an asymmetric output constraint. In order to achieve finite-time stability and reduce the update frequency of the controller, a novel controller and its event-trigger mechanism is proposed by adding a power integral technique and utilizing sign function. To fulfill the requirement of asymmetric output constraints, an asymmetric barrier Lyapunov function (BLF) is constructed, which is different from tantype and log-type BLFs. Based on the contradictory idea and finite-time stability theroy, it is proved that there is no Zeno phenomenon under this event-trigger mechanism and all state variables of the closed-loop system attenuate to the origin in the finite-time while the output signals never violate the constraint. Furthermore, the result in this paper is expanded to fixed-time control. Finally, a simulation example is given to demonstrate the effectiveness of the presented strategy

This article studies an event-triggered asynchronous output regulation problem (EAORP) for networked switched systems (NSSs) with unstable switching dynamics (USDs) including all modes unstable and partial switching instants destabilization, which means that the Lyapunov function increases both on the activation intervals of all subsystems and at some switching instants. First, a memory-based mode-compared event-triggered mechanism for switched systems is proposed to effectively shorten asynchronous intervals, which employs historical sampled outputs and compares the mode of the current sampled instant and the adjacent sampled instant. Then, the maximum average dwell time for a novel switching signal is derived with a constraint on the ratio of total destabilizing switchings to total stabilizing switchings, which relaxes the requirement of the regular arrangement of destabilizing and stabilizing switchings. Moreover, with the help of different coordinate transformations in the EAORP, the discretized Lyapunov functions are no longer needed when synthesizing the NSSs with USDs, and the asynchronous switching situation is also discussed. Afterward, by designing a dynamic output feedback controller, sufficient conditions are given to solve the EAORP for NSSs with USDs subject to network-induced delays, packet disorders, and packet losses. Finally, the effectiveness of the proposed methods is verified via a switched RLC circuit.

We propose decentralized primal-dual methods for cooperative multi-agent consensus optimization problems over both static and time-varying communication networks, where only local communications are allowed. The objective is to minimize the sum of agent-specific convex functions over conic constraint sets defined by agent-specific nonlinear functions; hence, the optimal consensus decision should lie in the intersection of these private sets. Under the strong convexity assumption, we provide convergence rates for sub-optimality, infeasibility, and consensus violation in terms of the number of communications required; examine the effect of underlying network topology on the convergence rates., A preliminary result of this paper was presented in arXiv:1706.07907 by Hamedani and Aybat. In this paper, we generalize our results to the setting where agent-specific constraints are defined by nonlinear functions rather than linear ones which greatly improves the modeling capability. This generalization requires a more complicated analysis which is studied in this separate arXiv submission

Weakly supervised semantic segmentation is receiving great attention due to its low human annotation cost. In this paper, we aim to tackle bounding box supervised semantic segmentation, i.e., training accurate semantic segmentation models using bounding box annotations as supervision. To this end, we propose Affinity Attention Graph Neural Network ($A^2$GNN). Following previous practices, we first generate pseudo semantic-aware seeds, which are then formed into semantic graphs based on our newly proposed affinity Convolutional Neural Network (CNN). Then the built graphs are input to our $A^2$GNN, in which an affinity attention layer is designed to acquire the short- and long- distance information from soft graph edges to accurately propagate semantic labels from the confident seeds to the unlabeled pixels. However, to guarantee the precision of the seeds, we only adopt a limited number of confident pixel seed labels for $A^2$GNN, which may lead to insufficient supervision for training. To alleviate this issue, we further introduce a new loss function and a consistency-checking mechanism to leverage the bounding box constraint, so that more reliable guidance can be included for the model optimization. Experiments show that our approach achieves new state-of-the-art performances on Pascal VOC 2012 datasets (val: 76.5\%, test: 75.2\%). More importantly, our approach can be readily applied to bounding box supervised instance segmentation task or other weakly supervised semantic segmentation tasks, with state-of-the-art or comparable performance among almot all weakly supervised tasks on PASCAL VOC or COCO dataset. Our source code will be available at https://github.com/zbf1991/A2GNN., Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TAPMI 2021)

This article develops a dynamic version of event-triggered model predictive control (MPC) without utilizing any terminal constraint. Such a dynamic event-triggering mechanism takes the advantages of both event- and self-triggering approaches by dealing explicitly with conservatism in the triggering rate and measurement frequency. The prediction horizon shrinks as the system states converge; we prove that the proposed strategy is able to stabilize the system even without any stability-related terminal constraint. Recursive feasibility of the optimization control problem (OCP) is also guaranteed. The simulation results illustrate the effectiveness of the scheme.

This article focuses on the vibration reducing and angle tracking problems of a flexible unmanned spacecraft system subject to input nonlinearity, asymmetric output constraint, and system parameter uncertainties. Using the backstepping technique, a boundary control scheme is designed to suppress the vibration and regulate the angle of the spacecraft. A modified asymmetric barrier Lyapunov function is utilized to ensure that the output constraint is never transgressed. Considering the system robustness, neural networks are used to handle the system parameter uncertainties and compensate for the effect of input nonlinearity. With the proposed adaptive neural network control law, the stability of the closed-loop system is proved based on the Lyapunov analysis, and numerical simulations are carried out to show the validity of the developed control scheme.

With the advent of the era of massive data, the increase of storage demand has far exceeded current storage capacity. DNA molecules provide a reliable solution for big data storage by virtue of their large capacity, high density, and long-term stability. To reduce errors in storing procedures, constructing a sufficient set of constraint encoding is critical for achieving DNA storage. A new version of the Marine Predator algorithm (called QRSS-MPA is proposed in this paper to increase the lower limit of the coding set while satisfying the specific combination of constraints. In order to demonstrate the effectiveness of the improvement, the classical CEC-05 test function is used to test and compare the mean, variance, scalability, and significance. In terms of storage, the lower limit of construction is compared with previous works, and the result is found to be significantly improved. In order to prevent the emergence of a secondary structure that leads to sequencing failure, we give a more stringent lower bound for the constraint coding set, which is of great significance for reducing the error rate of DNA storage amidst its rapid development.

In robust control under state constraints the set of admissible inputs is usually considered as given, under the assumption that the actuators have been already designed. However, if the input set is too small any controller will fail in stabilizing the closed-loop system while satisfying all prescribed constraints for some initial states of interest, or vice versa the chosen actuators may be over-sized. To handle this issue, in this paper we address the problem of computing the smallest input constraint set such that the closed-loop system is stabilizable from a prescribed set of initial states while respecting all constraints. We focus our attention on linear systems with additive disturbances, and develop the algorithm based on recursive feasibility of robust model predictive control. We demonstrate the results using numerical examples, in which we consider different metrics for the input constraint set selection.

A dilemma faced by classification is that the data is not collected at the same frequency in some applications. We investigate the mixed frequency data in a new way and recognize them as a special style of multi-view data, in which each view data is collected at a different sampling frequency. This paper proposes a discriminative dictionary pair learning method constrained by ordinal locality for mixed frequency data classification (shorted by DPLOL-MF). This method integrates synthesis dictionary and analysis dictionary into a dictionary pair, which not only improves computational cost caused by the ${\ell_0}$ or ${\ell_1}$ -norm constraint, but also can deal with the sampling frequency inconsistency. The DPLOL-MF utilizes a synthesis dictionary to learn class-specified reconstruction information and employs an analysis dictionary to generate coding coefficients by analyzing samples. Particularly, the ordinal locality preserving term is leveraged to constrain the atoms of dictionaries pair to further facilitate the learned dictionary pair to be more discriminative. Besides, we design a specific classification scheme for the inconsistent sample size of mixed frequency data. This paper illustrates a novel idea to solve the classification task of mixed frequency data and the experimental results demonstrate the effectiveness of the proposed method.

This article studies the vision-based tracking control problem for a nonholonomic multirobot formation system with uncertain dynamic models and visibility constraints. A fixed onboard vision sensor that provides the relative distance and bearing angle is subject to limited range and angle of view due to limited sensing capability. The constraint resulting from collision avoidance is also taken into account for safe operations of the formation system. Furthermore, the preselected specifications on transient and steady-state performance are provided by considering the time-varying and asymmetric constraint requirements on formation tracking errors for each robot. To address the constraint problems, we incorporate a novel barrier Lyapunov function into controller design and analysis. Based on the recursive adaptive backstepping procedure and neural-network approximation, we develop a vision-based formation tracking control protocol such that formation tracking errors can converge into a small neighborhood of the origin in finite time while meeting the requirements of visibility and performance constraints. The proposed protocol is decentralized in the sense that the control action on each robot only depends on the local relative information, without the need for explicit network communication. Moreover, the control protocol could extend to an unconstrained multirobot system. Both simulation and experimental results show the effectiveness of the control protocol.

In modern discrete flexible manufacturing systems, dynamic disturbances frequently occur in real time and each job may contain several special operations in partial-no-wait constraint due to technological requirements. In this regard, a hierarchical multiagent deep reinforcement learning (DRL)-based real-time scheduling method named hierarchical multi-agent proximal policy optimization (HMAPPO) is developed to address the dynamic partial-no-wait multiobjective flexible job shop scheduling problem (DMOFJSP-PNW) with new job insertions and machine breakdowns. The proposed HMAPPO contains three proximal policy optimization (PPO)-based agents operating in different spatiotemporal scales, namely, objective agent, job agent, and machine agent. The objective agent acts as a higher controller periodically determining the temporary objectives to be optimized. The job agent and machine agent are lower actuators, respectively, choosing a job selection rule and machine assignment rule to achieve the temporary objective at each rescheduling point. Five job selection rules and six machine assignment rules are designed to select an uncompleted job and assign the next operation of which together with its successors in no-wait constraint on the corresponding processing machines. A hierarchical PPO-based training algorithm is developed. Extensive numerical experiments have confirmed the effectiveness and superiority of the proposed HMAPPO compared with other well-known dynamic scheduling methods.

Traditional target detection methods assume that the background spectrum is subject to the Gaussian distribution, which may only perform well under certain conditions. In addition, traditional target detection methods suffer from the problem of the unbalanced number of target and background samples. To solve these problems, this study presents a novel target detection method based on asymmetric weighted logistic metric learning (AWLML). We first construct a logistic metric-learning approach as an objective function with a positive semidefinite constraint to learn the metric matrix from a set of labeled samples. Then, an asymmetric weighted strategy is provided to emphasize the unbalance between the number of target and background samples. Finally, an accelerated proximal gradient method is applied to identify the global minimum value. Extensive experiments on three challenging hyperspectral datasets demonstrate that the proposed AWLML algorithm improves the state-of-the-art target detection performance.

The security and economy of multienergy systems (MESs) are directly threatened by the potential cyberattacks. It is of great importance to investigate the effects of cyberattacks, e.g., denial of service (DoS) attacks, on distributed energy management algorithms. To this end, this article focuses on exploring how the frequency and the time of duration of DoS attacks influence the behavior of Newton-Raphson-based distributed energy management (NRBDEM) algorithm for MES and in which condition the optimal operations can still be obtained. First, a switched NRBDEM algorithm is presented, which is composed of the normal operation mode and the attack mode. In the attack mode, the attackers are able to change the communication structure at will and make it unconnected to destroy the convergence of the switched NRBDEM algorithm. Then, by making use of automatons to generate the hybrid time domain, the switched NRBDEM algorithm is further modeled and formulated as a hybrid dynamical system, which provides a mathematical model for the subsequent convergence analysis. Therein, the generated hybrid time domain satisfies the average dwell-time constraint and time-ratio constraint to limit the persistent attacks. Furthermore, we analyze the restrained conditions for persistent attacks, under which the optimality and convergence of the switched NRBDEM algorithm can be guaranteed still. Finally, simulation results demonstrate the effectiveness of the proposed method.

This paper considers remote state estimation in cyber-physical systems (CPSs) with multiple sensors. Each plant is modeled by a discrete-time stochastic linear system with measurements of each sensor transmitted to the corresponding remote estimator over a shared communication network when their securities are interdependent due to network induced risks. A dynamic nonzero-sum game with asymmetric information is formulated in which each sensor subject to a resource budget constraint needs to decide whether to invest in security for sending data packets, taking the behaviors of other sensors into account. To overcome the difficulty in characterizing or computing the Nash equilibria (NE), the game with asymmetric information is transformed into another game with symmetric information such that the equilibrium of the original game can be obtained by solving the equilibrium of the new game. Under certain conditions, we devise a backward induction algorithm to obtain a subclass of NE of the original game, known as common information based Markov perfect equilibria (CIBMPE). Finally, a numerical example is provided to illustrate the results obtained.

In this paper, a parallel and gradient-free strategy is presented for autonomous navigation of a quadrotor with a limited field of view (FOV). The FOV constraint is nonlinear and non-continuous in general and involves higher order dynamics of the vehicle. Planning problems with such constraints are difficult to solve, especially with the realtime requirement. The proposed method first constructs an environment map by integrating the measurement of a limited-FOV sensor in a parallel process. Based on the map, it then selects a feasible local goal from a global path and generates a constraint-free nominal control sequence. Finally, a stochastic optimal control problem is solved to satisfy the limited FOV constraint, the dynamic constraint, the dynamic constraint, and the collision-free conditions at the same time. The objective functions are non-linear and non-continuous and involves dynamic of MAV. A parallel gradient-free algorithm is used to address these problems. Both the sensing and planning problems are solved parallelly on a light-weight Graphics Processing Unit (GPU). The effectiveness of the proposed strategy is demonstrated through both simulation and real flight experiments.

This paper proposes a novel Stackelberg game-oriented optimal control approach to address the bounded constraint-following control problem for uncertain mechanical systems. First, the uncertainties (possibly fast time-varying) in the system are assumed to be bounded with an unknown boundary which lies in a specified fuzzy evidence number. In practical engineering, bounded system performance is always demanded, such as the inequality constraint. A diffeomorphism transformation approach is proposed to transform the constrained system into a restructured one satisfying the bounded constraint. Second, we propose an adaptive robust control oriented by the constraint-following control to render the restructured system to follow the specified constraints accurately with deterministic performance (guaranteeing uniform boundedness and uniform ultimate boundedness). The self-adjusting adaptive law (leakage-type) can compensate for the uncertainties and avoid overcompensation. Third, a Stackelberg game-oriented optimization approach is proposed to obtain the optimal control parameters based on the fuzzy evidence theory. In the optimization approach, the two control parameters, are considered as two players with respective cost functions related to system performance and control cost. Furthermore, the optimization problem is solved by obtaining the Stackelberg strategy, which is proved to exist in analytic form. Ultimately, the permanent magnet synchronous linear motor system simulation is presented to show the design process and the excellent performance of the proposed optimal control scheme.

Three-way decision is consistent with human cognitive processes and applied to different information systems. However, since the real world is more imprecision, hesitation and ambiguity, experts can select interval fuzzy information to represent their evaluations. In the evaluation process, experts sometimes may not guarantee the interval fuzzy information satisfy the constraint between membership and non-membership and further impact make decisions. Interval-valued q-rung Orthopair fuzzy set (IVq-ROFS) are proposed to improve the fault-tolerant ability and ensure the experts' evaluation make sense. In this case, this paper generalizes IVq-ROFS to three-way decision, which consists of the construction of three-way decision and the aggregation of interval continuity of IVq-ROFS. For considering the aggregation of interval continuity of IVq-ROFS, we firstly investigate the IVq-ROFS integral to aggregate continuous IVq-ROFSs by developing simplified interval-valued q-rung Orthopair fuzzy set (SIVq-ROFS). Particularly, in order to obtain integrable region, we design $\varepsilon$ -amendment to amend integral region of IVq-ROFS for removing unmeaning point in advance. To simplify the calculation, we further utilize Taylor series of the integral function to replace the complicated integral function. Secondly, a new equivalence class method is constructed to support three-way decision. Thirdly, with the aid of the integral of IVq-ROFS and equivalence class method, we availably fuse the loss functions of the equivalence class and obtain the classifying rules of three-way decision by comparing the expected losses. Finally, we elaborate three-way decision by using a case of medical diagnosis about nephropathy and prove the validity of the investigated model.

We describe WaveFunctionCollapse (WFC), a new family of algorithms for content generation. WFC was recently invented by independent game developer Maxim Gumin and has since been adopted and adapted by other game developers. Trends in academic research on content generation have only recently suggested the use of ideas from constraint solving and machine learning, so it is surprising to see these manifested in in-the-wild algorithms developed outside of an academic context. We illuminate the common components in this family of algorithms by way of a rational reconstruction. Through experiments with the reconstruction we probe the impact of design choices made in various adaptations of WFC (e.g. the role of backtracking, search heuristics, or pattern learning strategies). This work highlights a mode of incremental content generation that has been overlooked by past surveys of content generation methods.

In learning tasks with high order correlations, the low-rank approximation of the regression coefficient tensor has become increasingly important. Tensor ring can capture more correlation information among tensor networks. However, its optimal rank is generally unknown and needs to be tuned from multiple combinations. To address the issue, we propose a novel tensor regression framework with a group sparsity constraint on latent factors for tensor ring rank estimation. Specifically, the proposed group sparsity term constrained matrix factorization problem is first proved to be equivalent to a better approximation of matrix rank, namely Schatten- ${1/2}$ quasi-norm. Extending it into tensor, the tensor ring rank can be inferred during the learning process to balance the prediction error and the model complexity. Besides, a total variation term is introduced to enhance the local consistency of the predicted response, which is useful for reducing the adverse effects of random noise. Experiments on the simulation dataset show that the proposed method can exactly obtain the tensor ring rank, and the effectiveness and robustness of the proposed algorithm is further verified on a real dataset for human motion capture tasks.

In this short paper, relaxed observer-based state estimation of discrete-time Takagi-Sugeno fuzzy systems is proposed via developing a new augmented matrix approach. In contrast with the recent method reported in the literature, a more advanced introduction mode of additional matrices is developed without any redundant constraint under the framework of homogeneous polynomials. Then, the proposed augmented matrices can be built in order to depict the characteristic information of each possible working mode in a superior way, and thus our obtained result is less conservative than the recent one. Moreover, it is worth noting that that the recent method belongs to the special case of ours. Finally, two numerical simulations are given to test and validate the superiority and generality of the developed method.

Deep neural networks (DNNs) have been widely used in many Cyber-Physical Systems (CPS). However, it is still challenging work to deploy DNNs in real-time systems. In particular, the execution time of DNN inference must be predictable, s.t. it could be known whether the run-time inference can complete within a required timing constraint. Moreover, the timing constraints may change dynamically with the run-time environment in many embedded applications, such as autonomous cars. A possible way to meet such dynamic real-time requirements is to execute different sub-networks of a DNN at run-time. However, improper construction of sub-networks may not only introduce unpredictable inference time, s.t. the real-timing constraints could be violated unexpectedly, but also has poor compatibility with the well-optimized machine learning framework (e.g., TensorFlow). In this paper, we study the predictability when executing different sub-networks of a DNN. In particular, we present a feature-wise run-time adaptation framework for DNN inference, which is implemented and validated on NVIDIA Jetson TX2 and Nano with TensorFlow. The experimental results show that our method can achieve predictable inference time in comparison with the state-of-the-art methods.

This article studies the event-triggered finite-time stabilization problem of nonlinear switched systems in which the time derivatives of Lyapunov functions of modes are indefinite. Based on a mode-dependent average dwell time constraint and event-triggered impulsive control (ETIC) strategy, a new type of the mode-dependent event-triggered mechanism (MDETM) which can efficiently avoid Zeno behavior for switched systems is presented. Some Lyapunov-based criteria for finite-time stability (FTS) and finite-time contractive stability (FTCS) are obtained, respectively, where a relationship between the prescribed bound and event-triggered mechanism is established. Then, we apply these proposed ETIC strategies to impulsive switched systems and design a class of LMI-based MDETMs to guarantee the FTS/FTCS property. Finally, the effectiveness of presented ETIC strategies is illustrated by two examples.

Ridge regression is frequently utilized by both supervised learning and semisupervised learning. However, the results cannot obtain the closed-form solution and perform manifold structure when ridge regression is directly applied to semisupervised learning. To address this issue, we propose a novel semisupervised feature selection method under generalized uncorrelated constraint, namely SFS. The generalized uncorrelated constraint equips the framework with the elegant closed-form solution and is introduced to the ridge regression with embedding the manifold structure. The manifold structure and closed-form solution can better save data's topology information compared to the deep network with gradient descent. Furthermore, the full rank constraint of the projection matrix also avoids the occurrence of excessive row sparsity. The scale factor of the constraint that can be adaptively obtained also provides the subspace constraint more flexibility. Experimental results on data sets validate the superiority of our method to the state-of-the-art semisupervised feature selection methods.

Multi-view data effectively model and characterize the underlying complex systems, and multi-view clustering is of great significance for revealing the mechanisms of systems, which groups objects into different clusters with high intra-cluster and low inter-cluster similarity for all views. Current algorithms are criticized for undesirable performance because they solely focus on either the shared features or correlation of objects, failing to address the heterogeneity and structural constraint of various views. To overcome these problems, a novel \textbf{M}ulti-view \textbf{C}lustering with \textbf{S}elf-representation and \textbf{S}tructural \textbf{C}onstraint (MCSSC) is proposed, which is a network-based method by fusing matrix factorization and low-rank representation of various views. Specifically, to remove heterogeneity of multi-view data, a network is constructed for each view, which casts the multi-view clustering into the multi-layer networks clustering problem. To extract the shared features of multiple views, MCSSC factorizes matrices associated with networks by projecting them into a common space, and jointly learns an affinity graph for objects in multiple views with self-representation. To facilitate the clustering, the structural constraint is imposed on the affinity graph, where the clusters are identified. Extensive experiments demonstrate that MCSSC significantly outperforms the state-of-the-art in terms of accuracy, implying that the superiority of the proposed method.

This article provides a solution to tube-based output feedback robust model predictive control (RMPC) for discrete-time linear parameter varying (LPV) systems with bounded disturbances and noises. The proposed approach synthesizes an offline optimization problem to design a look-up table and an online tube-based output feedback RMPC with tightened constraints and scaled terminal constraint sets. In the offline optimization problem, a sequence of nested robust positively invariant (RPI) sets and robust control invariant (RCI) sets, respectively, for estimation errors and control errors is optimized and stored in the look-up table. In the online optimization problem, real-time control parameters are searched based on the bounds of time-varying estimation error sets. Considering the characteristics of the uncertain scheduling parameter in LPV systems, the online tube-based output feedback RMPC scheme adopts one-step nominal system prediction with scaled terminal constraint sets. The formulated simple and efficient online optimization problem with fewer decision variables and constraints has a lower online computational burden. Recursive feasibility of the optimization problem and robust stability of the controlled LPV system are guaranteed by ensuring that the nominal system converges to the terminal constraint set, and uncertain state trajectories are constrained within robust tubes with the center of the nominal system. A numerical example is given to verify the approach.

Effective constraint handling techniques are of great significance for evolutionary algorithms dealing with constrained optimization problems. To date, many constraint handling techniques, such as penalty function, superiority of feasible solutions, and -constraint, have been designed. However, different constraint handling techniques are usually suited to different problems, even the most appropriate technique changes along with the stages of the optimization process. Motivated by this phenomenon, we propose a voting-mechanism based ensemble framework, named VMCH, to integrate multiple constraint handling techniques for solving various constrained optimization problems. In this framework, each constraint handling technique acts as a voter, all voters vote for each pair of solutions, and the solution in each pair with the highest weighted votes is considered better. In addition, an adaptive strategy is developed to adjust the voter weights according to their historical voting performance. To investigate the performance of VMCH in improving existing algorithms, the proposed VMCH is embedded into the three best algorithms in the competition on constrained single objective real-parameter optimization at CEC 2018, namely MAgES, iLSHADE, and IUDE, to form three new algorithm versions, i.e., MAgES-VMCH, iLSHADE-VMCH, and IUDE-VMCH. They are compared with seven state-of-the-art peer algorithms. Extensive experiments are conducted on 57 real-world constrained optimization problems. The ranking results show that the new algorithm version MAgES-VMCH takes first place among the ten comparison algorithms. Moreover, all the new VMCH-enhanced versions of the three best algorithms are superior to their original versions. Therefore, the proposed VMCH framework can achieve competitive performance in solving constrained optimization problems.

This paper addresses the fixed-time control problem for the constrained quarter active vehicle suspension systems (AVSSs) via an event-triggered-based adaptive fuzzy fixed-time control method. The benefit of the usage of the time-varying barrier Lyapunov function (BLF) is to avoid the violation of the time-varying displacement constraint so that the stability and safety of AVSSs can be guaranteed. The relative-thresholdbased event-triggered controller is devised so as to reduce the communication burden from the controller to the actuator. In the light of fixed time theory, it is proved that both the stability and tracking performance of the closed-loop system can be obtained in fixed time. The fixed-time based eventtriggered control strategy is independent of initial states of AVSSs in comparison with the existing finite-time results. Some simulation results and comparisons on a quarter-car AVSS indicate better performance in terms of feasible fixed-time control and exact trajectory tracking.

This article studies the distributed linear minimum mean square error (LMMSE) estimation problem for large-scale systems with local information (LSLI). Large-scale systems are composed of numerous subsystems. Each subsystem only transmits information to its neighbors. Thus, only the local information is available to each subsystem. This implies that the information available to different subsystems is different. Using local information to design an LMMSE estimator, the gains of the estimator must satisfy the sparse structure constraint, which makes the estimator design challenging and complicates the boundedness analysis of the estimation error covariance (EEC). In this article, a framework of the distributed LMMSE estimation for LSLI is established. The gains of the LMMSE estimator are effectively constructed by solving linear matrix equations. A gradient descent algorithm is exploited to design the gains of the LMMSE estimator numerically. Sufficient conditions are derived to ensure the boundedness of the EEC. Also, a gradient-based search algorithm is developed to verify whether the sufficient conditions hold or not. Finally, an example is used to illustrate the effectiveness of the proposed results.

We propose a novel structured analysis-synthesis dictionary pair learning method for efficient representation and image classification, referred to as relaxed block-diagonal dictionary pair learning with a locality constraint (RBD-DPL). RBD-DPL aims to learn relaxed block-diagonal representations of the input data to enhance the discriminability of both analysis and synthesis dictionaries by dynamically optimizing the block-diagonal components of representation, while the off-block-diagonal counterparts are set to zero. In this way, the learned synthesis subdictionary is allowed to be more flexible in reconstructing the samples from the same class, and the analysis dictionary effectively transforms the original samples into a relaxed coefficient subspace, which is closely associated with the label information. Besides, we incorporate a locality-constraint term as a complement of the relaxation learning to enhance the locality of the analytical encoding so that the learned representation exhibits high intraclass similarity. A linear classifier is trained in the learned relaxed representation space for consistent classification. RBD-DPL is computationally efficient because it avoids both the use of class-specific complementary data matrices to learn discriminative analysis dictionary, as well as the time-consuming l₁/l₀-norm sparse reconstruction process. The experimental results demonstrate that our RBD-DPL achieves at least comparable or better recognition performance than the state-of-the-art algorithms. Moreover, both the training and testing time are significantly reduced, which verifies the efficiency of our method. The MATLAB code of the proposed RBD-DPL is available at https://github.com/chenzhe207/RBD-DPL.

Supervised discrete hashing (SDH) has widely attracted attention because it can directly obtain hash codes rather than relaxing the discrete constraint, which reduces information loss during the quantization process. However, SDH and its extensions tend to ignore the underlying geometry structure of data, while in many cases, data is lying on a low-dimensional manifold. Therefore, based on SDH, we propose a novel manifold learning-based supervised discrete hashing method in this paper to further improve the performance. Our goal is to learn compact hash codes by discovering latent information and using the local structure of data. To this end, we utilize the anchor graph to capture local neighborhood relationship embedding in data for manifold learning. Besides, since the previous methods use a strict binary label matrix for classification, we jointly optimize a relaxed label matrix to increase the discriminative ability of the proposed model. As such, the learned hash codes are more suitable for classification. Compared with SDH and other popular hashing methods, the experimental results on four large-scale datasets show that the proposed hashing method has better performance.

This paper presents a robust path tracking control method by utilizing the ideology of constraint-following approach for uncertain underactuated autonomous vehicles. The uncertainties are bounded with an unknown boundary. They do not all fall within the range space of the input matrix. Based on kinematic relations between the desired path and vehicle, the path tracking task is transformed into an equality constraint of the vehicle lateral dynamics states. The control goal is to make the underactuated vehicle follow the constraint, thus realizing the desired tracking performance. The constraint-following robust control (CFRC) is designed in two steps. First, a servo control design for the nominal system is devised without considering uncertainty and initial constraint deviation. Second, the uncertainty is meticulously decomposed into matched and mismatched portions based on the geometric structural characteristics of the constraint dynamics system. As a result, since the mismatched uncertainty is orthogonal to the constraint-following geometric space, it ``disappears'' in the stability analysis. The matched uncertainty is estimated by a self-adjusting leakage type adaptive law. On this basis, a robust control is designed based on the estimated matched uncertainty. Through Lyapunov minimax analysis, the proposed control method guarantees the approximate constraint-following performance. Finally, the TruckSim-Simulink co-simulations and real vehicle experiments are presented. The results show that the proposed control can robustly realize excellent tracking performance in the presence of time-vary uncertainties.

Road traffic sensing is pivotal in all the imperative services offered by Intelligent Transportation Systems (ITS). Both static and probe based traffic sensing technologies aid in the acquisition of road traffic parameters, represented as spatio-temporal traffic data matrices. These matrices suffer from inevitable data losses, urging accurate matrix reconstruction. Many Low Rank Matrix Completion (LR-MC) approaches have been formulated in the literature, with varied optimization problems and solution methods. The subsequent approaches have exploited spatio-temporal constraints to further reduce the reconstruction error. In this paper, these formulations are modified to develop two new LR-MC approaches, the Augmented Lagrangian Sparsity Regularized Matrix Factorization (AL-SRMF) and the Constrained Low Rank (C-LR). AL-SRMF replaces the Alternating Least Squares (ALS) solution method of SRMF with an AL based method. Optimization in C-LR inherits its temporal constraint from the Temporal and Adaptive Spatial constrained Low Rank (TAS-LR) approach, while adopting its spatial constraint similar to SRMF. Spatial constraint in both C-LR and AL-SRMF is deduced by computing an adjacency matrix that leverages graph notion of the geographical road traffic network. For experimental validations of the proposed approaches, traffic matrices of Californian road network are obtained from PEMS database. Investigations reveal that for a signal integrity (SI) of 0.5, C-LR demonstrated a Normalized Mean Absolute Error (NMAE) of 3.4% and a Root Mean Square Error (RMSE) of 3.2. With a slight increase in computational time, the AL-SRMF rendered least values of NMAE and RMSE, 2.4% and 2.3 respectively, demonstrating significantly better performance than the state-of-the-art approaches.

An effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are indispensable for intelligent mobile systems (e.g. autonomous vehicles and social robots) to achieve safe and high-quality planning when they navigate in highly interactive and crowded scenarios. Due to the existence of frequent interactions and uncertainty in the scene evolution, it is desired for the prediction system to enable relational reasoning on different entities and provide a distribution of future trajectories for each agent. In this paper, we propose a generic generative neural system (called STG-DAT) for multi-agent trajectory prediction involving heterogeneous agents. The system takes a step forward to explicit interaction modeling by incorporating relational inductive biases with a dynamic graph representation and leverages both trajectory and scene context information. We also employ an efficient kinematic constraint layer applied to vehicle trajectory prediction. The constraint not only ensures physical feasibility but also enhances model performance. Moreover, the proposed prediction model can be easily adopted by multi-target tracking frameworks. The tracking accuracy proves to be improved by empirical results. The proposed system is evaluated on three public benchmark datasets for trajectory prediction, where the agents cover pedestrians, cyclists and on-road vehicles. The experimental results demonstrate that our model achieves better performance than various baseline approaches in terms of prediction and tracking accuracy., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible