To counteract small sample size,severe class imbalance and high feature redundancy in 90-day mRS prediction after stroke,this study proposes a four-stage pipeline-“ADASYN re-sampling→clinical+statistical feature scr...To counteract small sample size,severe class imbalance and high feature redundancy in 90-day mRS prediction after stroke,this study proposes a four-stage pipeline-“ADASYN re-sampling→clinical+statistical feature screening→dimensionality reduction→5-fold cross-validation”-and benchmark composite deep-learning architectures.ADASYN first balances the minority classes in the original feature space.Next,a tri-level filter(clinical domain knowledge,variance threshold,mutual information)removes clinically meaningless or redundant variables,after which PCA compresses the remaining features while preserving critical neurological signatures(e.g.,brain-herniation history).Four hybrid CNN-RNN models are trained and compared under strict 5-fold cross-validation;the optimal ensemble yields stable,clinically interpretable probabilities that can support individualized rehabilitation planning.展开更多
As an essential function of encrypted Internet traffic analysis,encrypted traffic service classification can support both coarse-grained network service traffic management and security supervision.However,the traditio...As an essential function of encrypted Internet traffic analysis,encrypted traffic service classification can support both coarse-grained network service traffic management and security supervision.However,the traditional plaintext-based Deep Packet Inspection(DPI)method cannot be applied to such a classification.Moreover,machine learning-based existing methods encounter two problems during feature selection:complex feature overcost processing and Transport Layer Security(TLS)version discrepancy.In this paper,we consider differences between encryption network protocol stacks and propose a composite deep learning-based method in multiprotocol environments using a sliding multiple Protocol Data Unit(multiPDU)length sequence as features by fully utilizing the Markov property in a multiPDU length sequence and maintaining suitability with a TLS-1.3 environment.Control experiments show that both Length-Sensitive(LS)composite deep learning model using a capsule neural network and LS-long short time memory achieve satisfactory effectiveness in F1-score and performance.Owing to faster feature extraction,our method is suitable for actual network environments and superior to state-of-the-art methods.展开更多
This paper presents a hierarchical formation control strategy to address the challenges of multiple Unmanned Aerial Vehicles(UAVs)formation control within a cooperative consensus framework.The proposed strategy incorp...This paper presents a hierarchical formation control strategy to address the challenges of multiple Unmanned Aerial Vehicles(UAVs)formation control within a cooperative consensus framework.The proposed strategy incorporates a reference command generation layer,which derives UAV attitude commands based on formation requirements,and a tracking control layer to ensure accurate execution.Collaborative variables,including trajectory position and flight speed,are defined using a three-dimensional track particle and autopilot model,enabling the development of a consensus-based formation control law.Desired attitude angles are computed through altitudehold and coordinated-turn strategies.A sliding surface is designed based on reference models derived from flight quality metrics,while an adaptive controller compensates for aerodynamic model uncertainties.To enhance learning capabilities,a prediction error mechanism based on a series-parallel estimation model is introduced,enabling collaborative learning and the sharing of network weight estimation parameters within the multi-agent system.This facilitates the design of a distributed composite learning law.Lyapunov stability analysis confirms the local exponential stability of the tracking error.The simulations of a twelve-UAV formation,along with comparative analysis of two algorithms,demonstrate the system’s capability for formation maintenance and high-precision tracking control.展开更多
This paper introduces a fault-tolerant control(FTC)design for a faulty fixed-wing unmanned aerial vehicle(UAV).To constrain tracking errors against actuator faults,error constraint inequalities are first transformed t...This paper introduces a fault-tolerant control(FTC)design for a faulty fixed-wing unmanned aerial vehicle(UAV).To constrain tracking errors against actuator faults,error constraint inequalities are first transformed to a new set of variables based on prescribed performance functions.Then,the commonly used and powerful proportional-integral-derivative(PID)control concept is employed to filter the transformed error variables.To handle the fault-induced nonlinear terms,a composite learning algorithm consisting of neural network and disturbance observer is incorporated for increasing flight safety.It is shown by Lyapunov stability analysis that the tracking errors are strictly constrained within the specified error bounds.Experimental results are presented to verify the feasibility of the developed FTC scheme.展开更多
This work investigates the implementation of distributed prescribed-time neural network(NN)control for nonlinear multiagent systems(MASs)using a dynamic memory event-triggered mechanism(DMETM).First,it introduces a co...This work investigates the implementation of distributed prescribed-time neural network(NN)control for nonlinear multiagent systems(MASs)using a dynamic memory event-triggered mechanism(DMETM).First,it introduces a composite learning technique in NN control.This method leverages the prediction error within the NN update law to enhance the accuracy of the unknown nonlinearity estimation.Subsequently,by introducing a time-varying transformation,the study establishes a distributed prescribed-time control algorithm.The notable feature of this algorithm is its ability to predetermine the convergence time independently of initial conditions or control parameters.Moreover,the DMETM is established to reduce the actuation frequency of the controller.Unlike the conventional memoryless dynamic event-triggered mechanism,the DMETM incorporates a memory term to further increase triggering intervals.Utilizing a distributed estimator for the leader,the DMETM-based NN prescribed-time controller is designed in a fully distributed manner,which guarantees that all signals in the closed-loop system remain bounded within the prescribed time.Finally,simulation results are presented to validate the effectiveness of the proposed algorithm.展开更多
基金Shanghai University of Engineering Science Undergraduate Innovation Training Program(Project No.:cx2521005)。
文摘To counteract small sample size,severe class imbalance and high feature redundancy in 90-day mRS prediction after stroke,this study proposes a four-stage pipeline-“ADASYN re-sampling→clinical+statistical feature screening→dimensionality reduction→5-fold cross-validation”-and benchmark composite deep-learning architectures.ADASYN first balances the minority classes in the original feature space.Next,a tri-level filter(clinical domain knowledge,variance threshold,mutual information)removes clinically meaningless or redundant variables,after which PCA compresses the remaining features while preserving critical neurological signatures(e.g.,brain-herniation history).Four hybrid CNN-RNN models are trained and compared under strict 5-fold cross-validation;the optimal ensemble yields stable,clinically interpretable probabilities that can support individualized rehabilitation planning.
基金supported by the General Program of the National Natural Science Foundation of China under Grant No.62172093the National Key R&D Program of China under Grant No.2018YFB1800602+1 种基金2019 Industrial Internet Innovation and Development Project,Ministry of Industry and Information Technology(MIIT)under Grant No.6709010003Ministry of Education-China Mobile Research Fund under Grant No.MCM20180506。
文摘As an essential function of encrypted Internet traffic analysis,encrypted traffic service classification can support both coarse-grained network service traffic management and security supervision.However,the traditional plaintext-based Deep Packet Inspection(DPI)method cannot be applied to such a classification.Moreover,machine learning-based existing methods encounter two problems during feature selection:complex feature overcost processing and Transport Layer Security(TLS)version discrepancy.In this paper,we consider differences between encryption network protocol stacks and propose a composite deep learning-based method in multiprotocol environments using a sliding multiple Protocol Data Unit(multiPDU)length sequence as features by fully utilizing the Markov property in a multiPDU length sequence and maintaining suitability with a TLS-1.3 environment.Control experiments show that both Length-Sensitive(LS)composite deep learning model using a capsule neural network and LS-long short time memory achieve satisfactory effectiveness in F1-score and performance.Owing to faster feature extraction,our method is suitable for actual network environments and superior to state-of-the-art methods.
基金co-supported in part by the National Natural Science Foundation of China(No.62403131)in part by Jiangsu Funding Program for Excellent Postdoctoral Talent,China(No.2024ZB267)in part by the Shenzhen Science and Technology Program,China(No.JCYJ20230807145500002)。
文摘This paper presents a hierarchical formation control strategy to address the challenges of multiple Unmanned Aerial Vehicles(UAVs)formation control within a cooperative consensus framework.The proposed strategy incorporates a reference command generation layer,which derives UAV attitude commands based on formation requirements,and a tracking control layer to ensure accurate execution.Collaborative variables,including trajectory position and flight speed,are defined using a three-dimensional track particle and autopilot model,enabling the development of a consensus-based formation control law.Desired attitude angles are computed through altitudehold and coordinated-turn strategies.A sliding surface is designed based on reference models derived from flight quality metrics,while an adaptive controller compensates for aerodynamic model uncertainties.To enhance learning capabilities,a prediction error mechanism based on a series-parallel estimation model is introduced,enabling collaborative learning and the sharing of network weight estimation parameters within the multi-agent system.This facilitates the design of a distributed composite learning law.Lyapunov stability analysis confirms the local exponential stability of the tracking error.The simulations of a twelve-UAV formation,along with comparative analysis of two algorithms,demonstrate the system’s capability for formation maintenance and high-precision tracking control.
基金This work was supported by the National Natural Science Foundation of China(62003162,61833013,62020106003)the Natural Science Foundation of Jiangsu Province of China(BK20200416)+3 种基金the China Postdoctoral Science Foundation(2020TQ0151,2020M681590)the State Key Laboratory of Synthetical Automation for Process Industries,Northeastern University(2019-KF-23-05)the 111 Project(B20007)the Natural Sciences and Engineering Research Council of Canada.
文摘This paper introduces a fault-tolerant control(FTC)design for a faulty fixed-wing unmanned aerial vehicle(UAV).To constrain tracking errors against actuator faults,error constraint inequalities are first transformed to a new set of variables based on prescribed performance functions.Then,the commonly used and powerful proportional-integral-derivative(PID)control concept is employed to filter the transformed error variables.To handle the fault-induced nonlinear terms,a composite learning algorithm consisting of neural network and disturbance observer is incorporated for increasing flight safety.It is shown by Lyapunov stability analysis that the tracking errors are strictly constrained within the specified error bounds.Experimental results are presented to verify the feasibility of the developed FTC scheme.
基金partially supported by the National Natural Science Foundation of China(Grant Nos.62033003,62373113,62203119)the Guangdong Basic and Applied Basic Research Foundation(Grant Nos.2023A1515011527,2023B1515120010)。
文摘This work investigates the implementation of distributed prescribed-time neural network(NN)control for nonlinear multiagent systems(MASs)using a dynamic memory event-triggered mechanism(DMETM).First,it introduces a composite learning technique in NN control.This method leverages the prediction error within the NN update law to enhance the accuracy of the unknown nonlinearity estimation.Subsequently,by introducing a time-varying transformation,the study establishes a distributed prescribed-time control algorithm.The notable feature of this algorithm is its ability to predetermine the convergence time independently of initial conditions or control parameters.Moreover,the DMETM is established to reduce the actuation frequency of the controller.Unlike the conventional memoryless dynamic event-triggered mechanism,the DMETM incorporates a memory term to further increase triggering intervals.Utilizing a distributed estimator for the leader,the DMETM-based NN prescribed-time controller is designed in a fully distributed manner,which guarantees that all signals in the closed-loop system remain bounded within the prescribed time.Finally,simulation results are presented to validate the effectiveness of the proposed algorithm.
