This article studies the consensus problem for multiagent systems with transmission constraints. A novel model of multiagent systems is proposed where the information transmissions between agents are disturbed by irre...
详细信息
In this paper, we want to strengthen an autonomous vehicle’s lane-change ability with limited lane changes performed by the autonomous system. In other words, our task is bootstrapping the predictability of lane-chan...
详细信息
Walking with a load brings a significant burden to human shoulders, resulting in increasing metabolic energy consumption and the risk of skeleton and muscle injuries. Suspended backpack has been widely conducted for l...
详细信息
ISBN:
(纸本)9798350366907;9789887581581
Walking with a load brings a significant burden to human shoulders, resulting in increasing metabolic energy consumption and the risk of skeleton and muscle injuries. Suspended backpack has been widely conducted for load-bearing walking, but exiting time-dependent control methods and event-based control methods are unable to exploit the characteristics of human gait cycle. In this case, a time-independent control (TIC) method capable of eliminating the time dependence and adapting to variable speed is proposed. Based on the dynamical model of human-backpack system, an assistance profile along with the parameter optimization method are introduced which allows the backpack to reduce the burden on human shoulders during load-bearing walking. In the simulation evaluation, the proposed TIC method is compared with an impedance controller based time-dependent method and a locked backpack, under both constant speed and variable speed conditions. The results demonstrates that the TIC case achieves an 89.1% reduction in dynamic load on shoulder under the condition of constant speed and a 78.2% reduction under the condition of variable speed, compared with the LOCKED case.
The memristor's inherent memristive and nonlinear properties make it particularly well-suited for simulating synaptic connections in neural networks, inducing rich dynamical behaviors that are essential for unders...
详细信息
The memristor's inherent memristive and nonlinear properties make it particularly well-suited for simulating synaptic connections in neural networks, inducing rich dynamical behaviors that are essential for understanding brain mechanisms and brain-like learning. In this paper, a new locally active non-volatile trigonometric memristor is constructed and coupled into the Hopfield neural network. The motion state of the memristive Hopfield neural network (MHNN) is influenced by the coupling strength, allowing it to exhibit periodic initial offset boosting behavior. Furthermore, the MHNN demonstrates unique multi-scroll attractor extension behaviors. The number of attractor scrolls increases continuously with parameters variations at fixed time intervals, although there is an upper limit. However, as simulation time extends, the number of attractor scrolls can grow indefinitely, with newly formed scrolls extending monotonically in both directions under different conditions. The MHNN is implemented using both analog circuits and the DSP platform. Eventually, a real-time image encryption scheme aimed at protecting medical image privacy is designed, supported by practical test. In particular, the scheme can be further applied to remote video medical protection, which can encrypt the treatment content.
This article addresses the problem of event-based fully distributed state estimation for an unperturbed linear time-invariant system in the presence of communication link faults. In a networked system, each agent is c...
详细信息
This article addresses the problem of event-based fully distributed state estimation for an unperturbed linear time-invariant system in the presence of communication link faults. In a networked system, each agent is capable of constructing its local observer adaptively and transmitting its estimation to neighbors through discrete communication, thereby achieving accurate estimation of the system state while saving communication resources effectively. Specifically, first, the target system state can be decomposed into detectable and undetectable parts through detectability decomposition. Based on this, an adaptive event-triggered distributed observer is proposed, employing event-based adaptive coupling gains without the necessity for any global information. Additionally, a dynamic event-triggered mechanism with a mixed event-triggered threshold is introduced to generate the event-triggered sequence. Subsequently, the effectiveness of the proposed observer is verified through the analysis of estimation error and the assessment of Zeno behavior. Finally, the theoretical results of this article are validated through some simulation examples.
Multivariate time series anomaly detection with missing data is one of the most pending issues for industrial monitoring. Due to scarcity of labeled anomalies, most advanced data-driven anomaly detection approaches fa...
详细信息
Multivariate time series anomaly detection with missing data is one of the most pending issues for industrial monitoring. Due to scarcity of labeled anomalies, most advanced data-driven anomaly detection approaches fall in the unsupervised learning paradigm. As a premise in the presence of missing data, one needs to improve the data quality through data imputation with a separate model. Our concern lies in the consistency between data imputation and unsupervised learning for robust anomaly detection, regarding accurately discovering the spatiotemporal dependence among multiple variables over time. However, the existing practice tends to overlook this consistency and decouple the training process for these two closely linked tasks. This article novelly proposes a probabilistic multivariate time series anomaly detection framework that unifies data imputation and unsupervised learning. A deep probabilistic graphical model abbreviated SCNF is first devised for unsupervised density estimation. A tailored expectation maximization-based optimization scheme is then developed to achieve the joint training of data imputation and unsupervised learning with missing data. The efficacy is experimentally corroborated in several industrial applications, including chemical process, water treatment and network traffic. Briefly, the joint training framework enhances the AUROC of SCNF by averagely 6.34% for three applications under 50% data missing rate.
Self-supervised contrastive learning can help alleviating the meet of large numbers of annotated samples and learning high-level representations from unlabeled data. However, the high diversities in ground objects mak...
详细信息
Self-supervised contrastive learning can help alleviating the meet of large numbers of annotated samples and learning high-level representations from unlabeled data. However, the high diversities in ground objects make it difficult to learn the features at more robust and refined level in synthetic aperture radar (SAR) image analysis. To alleviate this issue, we propose a self-supervised weighted contrastive learning method with context-augmented transformer for change detection in multiresolution SAR images. First, a weighted contrastive learning framework is built by introducing a weighted contrastive loss, which can reduce the influence of changed pixels in the process of self-supervised feature learning and align feature representations of image pairs. Then, to model complex and rich context information, a context-augmented swin transformer is proposed to aggregate contextual information and compute hierarchical representations, which are beneficial for dense prediction. Specially, global channel-wise aggregation module and multiscale fusion structure are designed to enhance global features and capture fine-scale features, respectively. Thus, rich local, global and multiscale context information can be modeled jointly to achieve fine and robust feature expression. Compared with other network, our network gives full play to the advantages of CL and transformer to extract representations with rich context information in unsupervised scenes, with good generalization. Experiments on real SAR images with different resolutions demonstrate the effectiveness and superiority of the proposed method.
Transfer learning utilizes data or knowledge in one problem to help solve a related problem. It is particularly useful in electroencephalogram (EEG)-based motor imagery (MI) classification, to handle high intrasubject...
详细信息
Transfer learning utilizes data or knowledge in one problem to help solve a related problem. It is particularly useful in electroencephalogram (EEG)-based motor imagery (MI) classification, to handle high intrasubject and/or cross-subject variations. This article considers offline unsupervised cross-subject MI classification, i.e., we have labeled EEG trials from several source subjects, but only unlabeled EEG trials from the target subject. Existing transfer learning approaches usually make use of the source-domain data directly in target model learning. To protect the privacy of the source subjects, we propose lightweight source-free transfer (LSFT), which first generates source models locally and encapsulates them as model application programming interfaces (APIs), then constructs a virtual intermediate domain to transfer the knowledge in the source domains to the target domain, and finally performs feature adaptation learning. Compared with the existing deep transfer learning approaches, LSFT does not need to transfer from massive source data or models, is computationally efficient, and has a small number of parameters. Experiments on four benchmark MI data sets demonstrated that LSFT outperformed 13 different approaches, including several state-of-the-art transfer learning approaches that make use of the source-domain samples or model parameters directly.
Electroencephalogram (EEG)-based seizure sub-type classification enhances clinical diagnosis efficiency. Source-free semi-supervised domain adaptation (SF-SSDA), which transfers a pre-trained model to a new dataset wi...
详细信息
This article proposes an adaptive tracking control scheme for a class of switched stochastic non-linear systems subject to full state constraints (FSCs). A unified framework is established by integrating the adaptive ...
详细信息
This article proposes an adaptive tracking control scheme for a class of switched stochastic non-linear systems subject to full state constraints (FSCs). A unified framework is established by integrating the adaptive backstepping technique with barrier Lyapunov functions (BLFs) to address the time-varying full state constraints (TFSCs). Accordingly, utilizing the theorem of stochastic non-linear systems, a new adaptive state feedback control scheme is developed for a class of switching signals with the mode-dependent average dwell time (MDADT) property. The proposed adaptive controller is mode-dependent while the adaptive laws are mode-independent so as to facilitate an easy deployment of the controller. It is rigorously proven that all signals in the closed-loop system are bounded in probability, the tracking error converges to a bounded compact set, and the TFSCs are not violated. Finally, simulation examples are conducted to validate the effectiveness of the controller.
暂无评论