检索结果-内蒙古大学图书馆

A New Intrusion Detection Method Based on Adaptive Feature Extraction

学校读者我要写书评

暂无评论

A New Intrusion Detection Method Based on Adaptive Feature E...

第三十八届中国控制会议

作者： Ya-Li Wu Guo-Ting Li Yu-Long Fu Xiao-Peng Wang School of Automation and Information Engineering Xi'an University of Technology Shaanxi Province Key Laboratory of Complex System Control and Intelligent Information Processing

Compared with traditional machine learning, intrusion detection based on deep learning has the advantage of feature extraction. Auto-encoders, owing to having good feature extraction and dimensionality reduction ability, are known for the superior performance. However, the network structure selection is time-consuming and laborious. The essential features cannot be automatically extracted according to different distribution characteristics of the data set. Moreover, the existing data pre-processing method fails to adapt the model better. Based on the stack sparse auto-encoders(SSAE), we propose a new intrusion detection model named DBSO-SSAE. The algorithm is based on difference brain storm optimization(DBSO) which automatically adapts to selection network framework. Meanwhile, a new normalization strategy is introduced to further improve the accuracy of the model. The simulation results show that DBSO-SSAE greatly reduces the complexity of manual tuning and increases the adaptability of the network model.

关键词： intrusion detection feature extraction SSAE deep learning difference brain storm optimization

Transformer Winding Deformation Diagnosis Based on Signal Distance

学校读者我要写书评

暂无评论

Transformer Winding Deformation Diagnosis Based on Signal Di...

第30届中国过程控制会议（CPCC 2019）

作者： LiShengmin ZhaoDan HeYuanyuan WangXiaoafan School of Automation and Information Engineering Xi'an University of Technology Key Laboratory of Shaanxi Province for Complex System Control and Intelligent Information Processing

Aiming at the problem that the correlation coefficient method cannot judge the deformation of the transformer winding when the measured frequency response curve is the same as the reference frequency response curve(frequency response analysis,FRA) and the amplitude is different, this paper proposed a new transformer winding diagnosis method based on signal *** method can accurately determine whether the winding is deformed according to the mutual distance value [0, 1] by calculating the mutual distance between the measured frequency response curve and the reference frequency response *** the simulation experiment and the national standard judgment criterion, the criteria for judging the deformation of the winding by mutual distance were *** simulation results show that the method is sensitive, reliable and universal.

关键词： FRA Frequency response curve Winding deformation signal distance mutual distance

3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Guangming Zhong, Jiquan Zhao, Shijie Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Engineering Mechanics Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization. Copyright © 2021, The Authors. All rights reserved.

关键词： Robots

Point Cloud Preprocessing on 3D LiDAR data for Unmanned Surface Vehicle in Marine Environment

学校读者我要写书评

暂无评论

Point Cloud Preprocessing on 3D LiDAR data for Unmanned Surf...

information Technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Xianzhi Qi Wenxing Fu Pei An Bingli Wu Jie Ma National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9781728152240

ISBN: (纸本)9781728152257

Point cloud preprocessing is still a challenging task in the marine environment, for it is difficult to filter out non-obstacle points while avoiding damage to the obstacle completeness. In this paper, we propose a novel data preprocessing method on 3D LiDAR data for the unmanned surface vehicle in the marine environment. It consists of two tasks: outlier removal and wake filtering. As the spatial resolution of LiDAR changes with distance, we exploit distance normalization on statistical outlier filter for robust outlier removal. Considering the gradient difference between wave wake and obstacle surface near the water, we define and calculate the vertical state of point cloud on the range image to obtain the pre-filtering point set, and then use the RANSAC method to filter out the wake points. Experiments on real data has demonstrated the effectiveness of the proposed algorithm both in terms of feasibility and accuracy.

关键词： Three-dimensional displays Laser radar Filtering Filtering algorithms Spatial resolution Task analysis Measurement by laser beam

Distributed urban freeway traffic optimization considering congestion propagation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gao, Fengkun Yang, Bo Chen, Cailian Guan, Xinping Zhang, Yang Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Industrial Intelligent Control and Management Shanghai200240 China Shanghai Municipal Urban-Rural Construction and Transportation Development Institute China

Traffic optimization strategies are imperative for improving the performance of transportation networks. Most traffic optimization strategies only depend on traffic states of congested road segments, where congestion propagation is neglected. Therefore, we propose a distributed traffic optimization strategy for urban freeways considering the potential congested road segments caused by congestion propagation, called potential-homogeneous-area (PHA). Utilizing the historical traffic density data, we firstly quantify the effect of congestion propagation and identify PHA by applying the proposed spatio-temporal lambda-connectedness method. Meanwhile, dynamic capacity constraints of PHA are determined and are integrated with cell transmission model (CTM) in a centralized traffic optimization problem. To reduce computational complexity and improve scalability, we then propose a doubleconsensus- based alternating direction method of multipliers algorithm (DC-ADMM) to handle the neighbor coupling constraints and global coupling constraints for solving the problem in a fully distributed way. We prove that the proposed DC-ADMM algorithm converges to the optimal solution in the condition of convex objective function. Finally, simulations based on real traffic density data, collected in Inner Ring Road, Shanghai, China, reveal the effectiveness of our proposed strategy. © 2021, CC BY.

关键词： Roads and streets

Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gao, Jiaqi Huang, Zhizhong Lei, Yiming Shan, Hongming Wang, James Z. Wang, Fei-Yue Zhang, Junping The Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China The Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China The Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai201210 China The College of Information Sciences and Technology The Pennsylvania State University University ParkPA16802 United States The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The Institute of Systems Engineering Macau University of Science and Technology China Qingdao Academy of Intelligent Industries Qingdao266109 China

Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensive pixel-level annotations for training supervision. One way to mitigate the intensive labeling effort and improve counting accuracy is to leverage large amounts of unlabeled images. This is attributed to the inherent self-structural information and rank consistency within a single image, offering additional qualitative relation supervision during training. Contrary to earlier methods that utilized the rank relations at the original image level, we explore such rank-consistency relation within the latent feature spaces. This approach enables the incorporation of numerous pyramid partial orders, strengthening the model representation capability. A notable advantage is that it can also increase the utilization ratio of unlabeled samples. Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images. In addition, we have collected a new unlabeled crowd counting dataset, FUDAN-UCC, comprising 4,000 images for training purposes. Extensive experiments on four benchmark datasets, namely UCF-QNRF, ShanghaiTech PartA and PartB, and UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods. The codes are available at https://***/bridgeqiqi/DREAM. Copyright © 2022, The Authors. All rights reserved.

关键词： Image enhancement

Distributed Neighbor Selection in Multi-agent Networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shao, Haibin Pan, Lulu Mesbahi, Mehran Xi, Yugeng Li, Dewei Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China William E. Boeing Department of Aeronautics and Astronautics University of Washington SeattleWA98195-2400 United States

Achieving consensus via nearest neighbor rules is an important prerequisite for multi-agent networks to accomplish collective tasks. A common assumption in consensus setup is that each agent interacts with all its neighbors. This paper examines whether network functionality and performance can be maintained-and even enhanced-when agents interact only with a subset of their respective (available) neighbors. As shown in the paper, the answer to this inquiry is affirmative. In this direction, we show that by exploring the monotonicity property of the Laplacian eigenvectors, a neighbor selection rule with guaranteed performance enhancements, can be realized for consensus-type networks. For distributed implementation, a quantitative connection between entries of Laplacian eigenvectors and the "relative rate of change" in the state between neighboring agents is further established;this connection facilitates a distributed algorithm for each agent to identify "favorable" neighbors to interact with. Multi-agent networks with and without external influence are examined, as well as extensions to signed networks. This paper underscores the utility of Laplacian eigenvectors in the context of distributed neighbor selection, providing novel insights into distributed data-driven control of multi-agent systems. Copyright © 2021, The Authors. All rights reserved.

关键词： Multi agent systems

Local Path Planning Algorithm for UGV Based on Improved Covariance Matrix Adaptive Evolution Strategy

学校读者我要写书评

暂无评论

Local Path Planning Algorithm for UGV Based on Improved Cova...

第33届中国控制与决策会议

作者： Jiangbo Zhao Jiaquan Zhang Junzheng Wang Xin Zhang Yanlong Wang Key Laboratory of Complex System Intelligent Control and Decision School of AutomationBeijing Institute of Technology Key Laboratory of Servo Motion System Drive and Control Ministry of Industry and Information TechnologySchool of AutomationBeijing Institute of Technology Technical center Xinxing Cathay International Group Co.Ltd. Techenology Center of Special Vehicle Manufacture and Evaluation Engineering of Beijing Beijing North Vehicle Group Co.Ltd.

Local path planning algorithm is one of the key technologies for unmanned ground vehicle(UGV).In order to reduce the computational complexity of the local path planning algorithm and ensure the real-time performance of the algorithm,a non-uniform column grid lines modeling method is introduced,and on this basis,a modeling method for planning paths is *** at the path planning problem in a multi-obstacle environment,the evaluation function of the path is constructed from four aspects,and the covariance matrix adaptive evolution strategy(CMA-ES)is used to solve the nonlinear optimization *** order to further reduce the amount of calculation,the CMA-ES algorithm is improved by the dynamic adjustment strategy of population *** results show that the path planning algorithm can effectively realize the local path planning in complex environment.

关键词： Local path planning CMA-ES Unmanned ground vehicle

Path Planning and Evaluation for Obstacle Avoidance of Manipulator Based on Improved Artificial Potential Field and Danger Field

学校读者我要写书评

暂无评论

Path Planning and Evaluation for Obstacle Avoidance of Manip...

第33届中国控制与决策会议

作者： Jiangbo Zhao Qiang Zhao Junzheng Wang Xin Zhang Yanlong Wang Key Laboratory of Complex System Intelligent Control and Decision School of AutomationBeijing Institute of Technology Key Laboratory of Servo Motion System Drive and Control Ministry of Industry and Information TechnologySchool of AutomationBeijing Institute of Technology Technical center Xinxing Cathay International Group Co.Ltd. Technology Center of Special Vehicle Manufacture and Evaluation Enginneering of Beijing Beijing North Vehicle Group Co.Ltd.

This paper takes 6-DOF manipulator as the research object,proposes the improved Artificial Potential Field(APF) method to plan the obstacle avoidance path of the manipulator,and combines the Danger Field(DF) method to evaluate the safety of the path planned using *** to the characteristics of the manipulator,the kinematics model of the manipulator is analyzed,and the ball envelope algorithm is applied to simplify the physical model of the *** with the traditional APF method,the improved APF searches in the joint space and introduces the joint attraction potential to improve the search speed and *** problem of local minimum is dealt with by the combination of adding virtual obstacles and increasing joint attraction *** improved APF not only has the advantages of good real-time performance and smooth path,but also solves the problem of the traditional APF falling into a local minimum,and combines the danger field method to judge the path rationality to ensure no collision with *** simulation verification,the proposed method realizes the obstacle avoidance path planning of the manipulator and the safety evaluation of the planned path.

关键词： Artificial potential field Danger field Obstacle avoidance Path planning Collision detection