This paper studies the detection and identification problem of malicious network traffic and proposes a rule extraction algorithm based on interpretable models. The algorithm utilizes interpretable greedy trees as the...
详细信息
ISBN:
(数字)9798331518493
ISBN:
(纸本)9798331518509
This paper studies the detection and identification problem of malicious network traffic and proposes a rule extraction algorithm based on interpretable models. The algorithm utilizes interpretable greedy trees as the foundational model and extends its applicability to handle multi-classification problems, thereby enhancing interpretability and detection accuracy. This methodology furnishes a more dependable and secure framework for discerning attack categories within the domain of network security. The experiment results show that the proposed algorithm achieves better balance between interpretability and identification precision.
LiDAR-based 3D object detection is essential for autonomous driving systems. However, LiDAR point clouds may appear to have sparsity, uneven distribution, and incomplete structures, significantly limiting the detectio...
详细信息
In this paper, we propose a novel event-triggered near-optimal control for nonlinear continuoustime systems. The receding horizon principle is utilized to improve the system robustness and obtain better dynamic contro...
详细信息
In this paper, we propose a novel event-triggered near-optimal control for nonlinear continuoustime systems. The receding horizon principle is utilized to improve the system robustness and obtain better dynamic control performance. In the proposed structure, we first decompose the infinite horizon optimal control into a series of finite horizon optimal problems. Then a learning strategy is adopted, in which an actor network is employed to approximate the cost function and an critic network is used to learn the optimal control law in each finite horizon. Furthermore, in order to reduce the computational cost and transmission cost, an event-triggered strategy is applied. We design an adaptive trigger condition, so that the signal transmissions and controller updates are conducted in an aperiodic way. Detailed stability analysis shows that the nonlinear system with the developed event-triggered optimal control policy is asymptotically *** results on a single-link robot arm with different noise types have demonstrated the effectiveness of the proposed method.
An optimized YOLOX+DeepSORT method is proposed to accurately detect and track container trucks and truck drivers at the working position of automated rubber tire gantries in ports, while ensuring their safety during t...
An optimized YOLOX+DeepSORT method is proposed to accurately detect and track container trucks and truck drivers at the working position of automated rubber tire gantries in ports, while ensuring their safety during the whole working process. In the proposed method, the improved YOLOX performs object detection and its output is used as the input for multi -object tracking using DeepSORT. The improved YOLOX model is developed through replacing standard convolution with depthwise separable convolution, adding the convolutional block attention module to enhance feature extraction, and using Focal Loss in the loss function to address sample imbalances. Comparative experiments were carried out on a self-built dataset, showing a 4.32% increase in mAP and improved reasoning speed for improved YOLOX compared to the original YOLOX. Furthermore, the optimized method shows a 3.57% increase in Multi-Object Tracking Accuracy and a 1.73% increase in Multi-Object Tracking Precision compared to the benchmark YOLOX+DeepSORT.
This paper presents a single-loop Model Predictive control strategy that incorporates a reduced-order Generalized Proportional Integral Observe and a Kalman filter to enhance the speed regulation of Permanent Magnet S...
This paper presents a single-loop Model Predictive control strategy that incorporates a reduced-order Generalized Proportional Integral Observe and a Kalman filter to enhance the speed regulation of Permanent Magnet Synchronous Motor systems in the presence of complex disturbances and measurement noises. The proposed controller design seamlessly integrates the predictive control, disturbance observer, and state filter components, and it was evaluated through simulation comparisons. The performance of the proposed method is evaluated using various metrics, including maximum velocity drop, recovery time, and variance of steady-state error, which demonstrate its superior response performance and anti-disturbance ability when compared to other existing methods without state filtering.
Traffic Signal control (TSC) optimization is vital for efficient traffic flow in urban intersections. Recent research has explored the application of Reinforcement Learning (RL) agents to tackle TSC challenges. Howeve...
Traffic Signal control (TSC) optimization is vital for efficient traffic flow in urban intersections. Recent research has explored the application of Reinforcement Learning (RL) agents to tackle TSC challenges. However, the selection of an appropriate reward function in RL agent training still relies on subjective judgment and experience. To address this issue, an Inverse Reinforcement Learning (IRL) integrated RL algorithm is proposed. In the IRL learning section, expert trajectory data are collected and analyzed by Relative Entropy IRL (REIRL). The latent reward of expert policy is reconstructed and utilized in RL agent training process. In the RL control section, a Double Dueling Deep Q Network is applied under a cycle control framework. As verified in simulations, the introduction of expert experience improves the performance of the RL agent to the expert level and concurrently enables robustness to expert policy noises.
In this paper, we investigate the synthesis problem of edit functions for opacity enforcement in systems modelled as partially-observed finite-state automata. For better plausible deniability for the edit functions, i...
详细信息
Dear editor,With the rapid development of network and communication technology, group systems interrelated in terms of both time and space are commonly encountered, such as sensor networks, multi-agent systems, and sm...
详细信息
Dear editor,With the rapid development of network and communication technology, group systems interrelated in terms of both time and space are commonly encountered, such as sensor networks, multi-agent systems, and smart power grids. How to save communication resources among systems has become a very important and urgent issue.
This paper investigates optimal longitudinal control problems for a vehicle platoon in presence of parameter uncertainties and external ***,a multi-constraint multi-objective optimization model is developed,where phys...
详细信息
This paper investigates optimal longitudinal control problems for a vehicle platoon in presence of parameter uncertainties and external ***,a multi-constraint multi-objective optimization model is developed,where physical limits,safety constraints,driving comfort,and fuel economy are taken into *** reduce communication burden and avoid network congestion,the preceding vehicle's acceleration is obtained by employing a finite time disturbance observer(FTDO).As for the parameter uncertainties as well as external disturbances,they are estimated as a lumped disturbance by exploiting a ***,under a predecessor following communication topology,a FTDO-based tube model predictive control method with explicit consideration of string stability is ***,numerical simulations illustrate the effectiveness and superiority of the proposed control approach.
This paper focuses on the vision-based autonomous landing mission of a quadrotor unmanned aerial vehicle (UAV). A double-layered nested Aruco landing marker is designed which can adapt to the situation that the field ...
详细信息
暂无评论