Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to est...
详细信息
Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://***/yahuiliu99/PointC onT.
This paper proposes a data-driven learning-based approach to predictive control for switched nonlinear systems subject to state and control constraints and external stochastic disturbances. A switched Koopman modeling...
详细信息
This paper proposes a data-driven learning-based approach to predictive control for switched nonlinear systems subject to state and control constraints and external stochastic disturbances. A switched Koopman modeling framework is developed, where a multi-mode neural network for state lifting is trained simultaneously with Koopman operators and state reconstruction matrices for all *** framework facilitates the construction of the switched linear Koopman model in a transformed space and effectively captures the dynamics of the original nonlinear system. A switched predictive control strategy is then designed to regulate the switched Koopman model with constrained states and control inputs against both the stochastic disturbances and the uncertainties introduced by the lifting neural network. The proposed control scheme ensures mean-square stability and guarantees boundedness during the online phase. Furthermore, boundedness analysis is performed to determine the bounded set of the original system state across all admissible switching sequences. The effectiveness of the proposed methodology is demonstrated through a case study of a gene regulatory network.
When the aircraft is moving at high speed in the atmosphere,aero-optical imaging deviation will appear due to the influence of aero-optical *** order to achieve real-time compensation during the flight of the aircraft...
详细信息
When the aircraft is moving at high speed in the atmosphere,aero-optical imaging deviation will appear due to the influence of aero-optical *** order to achieve real-time compensation during the flight of the aircraft,it is necessary to analyze and predict the obtained imaging deviation *** order to improve the search speed and accuracy of the prediction algorithm and the ability to jump out of local optimum,in this paper,an improved sparrow search algorithm optimized extreme learning machine(ISSA-ELM) neural network model is proposed to predict the aero-optical imagine ***,the performance of ISSA-ELM,ELM neural network and SSA-ELM neural network was *** results showed that compared with ELM and SSA-ELM algorithms,the convergence speed of ISSA-ELM was significantly enhanced,and the accuracy of data prediction was also significantly improved.
On state estimation problems of switched neural networks,most existing results with an event-triggered scheme(ETS)not only ignore the estimator information,but also just employ a fixed triggering threshold,and the est...
详细信息
On state estimation problems of switched neural networks,most existing results with an event-triggered scheme(ETS)not only ignore the estimator information,but also just employ a fixed triggering threshold,and the estimation error cannot be guaranteed to converge to *** addition,the state estimator of non-switched neural networks with integral and exponentially convergent terms cannot be used to improve the estimation performance of switched neural networks due to the difficulties caused by the nonsmoothness of the considered Lyapunov function at the switching *** this paper,we aim at overcoming such difficulties and filling in the gaps,by proposing a novel adaptive ETS(AETS)to design an event-based H_(∞)switched proportional-integral(PI)state estimator.A triggering-dependent exponential convergence term and an integral term are introduced into the switched PI state *** relationship among the average dwell time,the AETS and the PI state estimator are established by the triggering-dependent exponential convergence term such that estimation error asymptotically converges to zero with H_(∞)performance *** is shown that the convergence rate of the resultant error system can be adaptively adjusted according to triggering ***,the validity of the proposed theoretical results is verified through two illustrative examples.
Regularized system identification has become the research frontier of system identification in the past *** related core subject is to study the convergence properties of various hyper-parameter estimators as the samp...
详细信息
Regularized system identification has become the research frontier of system identification in the past *** related core subject is to study the convergence properties of various hyper-parameter estimators as the sample size goes to *** this paper,we consider one commonly used hyper-parameter estimator,the empirical Bayes(EB).Its convergence in distribution has been studied,and the explicit expression of the covariance matrix of its limiting distribution has been ***,what we are truly interested in are factors contained in the covariance matrix of the EB hyper-parameter estimator,and then,the convergence of its covariance matrix to that of its limiting distribution is *** general,the convergence in distribution of a sequence of random variables does not necessarily guarantee the convergence of its covariance ***,the derivation of such convergence is a necessary complement to our theoretical analysis about factors that influence the convergence properties of the EB hyper-parameter *** this paper,we consider the regularized finite impulse response(FIR)model estimation with deterministic inputs,and show that the covariance matrix of the EB hyper-parameter estimator converges to that of its limiting ***,we run numerical simulations to demonstrate the efficacy of ourtheoretical results.
Cardiovascular diseases (CVDs), a leading cause of global mortality, are intricately linked to arterial stiffness, a key factor in cardiovascular health. Non-invasive assessment of arterial stiffness, particularly thr...
详细信息
Semi-supervised learning (SSL) is a successful paradigm that can use unlabelled data to alleviate the labelling cost problem in supervised learning. However, the excellent performance brought by SSL does not transfer ...
详细信息
This paper investigates the optimal tracking performance (OTP) of multiple-input multiple-output (MIMO) discrete networked controlsystems (NCSs) under the influence of Denial of Service (DoS) attack, channel noise, a...
详细信息
Power systems are moving toward a low-carbon or carbon-neutral future where high penetration of renewables is *** conventional fossil-fueled synchronous generators in the transmission network being replaced by renewab...
详细信息
Power systems are moving toward a low-carbon or carbon-neutral future where high penetration of renewables is *** conventional fossil-fueled synchronous generators in the transmission network being replaced by renewable energy generation which is highly distributed across the entire grid,new challenges are emerging to the control and stability of large-scale power *** analysis and control methods are needed for power systems to cope with the ongoing *** the CSEE JPES forum,six leading experts were invited to deliver keynote speeches,and the participating researchers and professionals had extensive exchanges and discussions on the control and stability of power ***,potential changes and challenges of power systems with high penetration of renewable energy generation were introduced and explained,and advanced control methods were proposed and analyzed for the transient stability enhancement of power grids.
This study addresses the problem of guaranteed cost fault-tolerant fuzzy control for multiline re-entrant manufacturing systems (RMSs) against stochastic disturbances and workstation faults. Initially, a nonlinear hyp...
详细信息
暂无评论