检索结果-内蒙古大学图书馆

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Zhou, Guangze Luo, Zhong Zhu, Yunpeng Gao, Yi Wang, Zhiao Northeastern University School of Mechanical Engineering and Automation Shenyang110819 China Northeastern University Key Laboratory of Vibration and Control of Aero-Propulsion Systems Ministry of Education of China Shenyang110819 China Dalian University of Technology State Key Laboratory of Structural Analysis for Industrial Equipment Dalian116024 China University of Sheffield Department of Automatic Control and System Engineering SheffieldS13JD United Kingdom

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

Model based online fault detection often conducted by extracting features from models driven by system input and output data under various working conditions. The efficiency of online system modelling is therefore significant to improve the performance of online fault detections. In this study, a novel fast data-driven modelling approach, known as the OMP (Orthogonal Matching Pursuit)- ERR (Error Reduction Ratio) method is proposed to improve the efficiency of online fault detections. The new system identification method is motivated by noticing that the traditional OMP algorithm is much faster but usually less accurate than the OLS (Orthogonal least squares) algorithm in the identification of system NARX (Nonlinear Auto-Regressive with Exogenous inputs) models. The problem is first illustrated by the identification of a Single Degree of Freedom (SDoF) system. After that, the OMP-ERR algorithm is developed to improve the NARX modelling efficiency for the purpose of system model-based online fault detections. A case study on the crack detection of a cantilever beam shows that the new approach is over 10 times faster than the traditional OLS modelling process, demonstrating the promising applications of the new approach in online fault detections in engineering practice. © 2022 IEEE.

关键词： Least squares approximations

来源：评论

学校读者我要写书评

暂无评论

Influence of the Kalman Filtering Initial Setting on SINS Initial Alignment and an Improved Method for the Alignment of Large Misalignment Angles

Influence of the Kalman Filtering Initial Setting on SINS In...

引用

Saint Petersburg International Conference on Integrated Navigation systems (ICINS)

作者： Xiaoge Ning Jixun Huang Jianxun Li Department of Automation School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Beijing Aerospace Times Optical-Electronic Co. Ltd Beijing China Beijing Institute of Aerospace Control Devices Beijing China

This paper analyzes the instability of the filtering system of the initial alignment under a quasi-static base and points out the great influence of Kalman filtering initial value setting on the filtering results. This is instructive for many conditions under initial alignment and integrated navigation. Meanwhile, an improved method for the alignment of large misalignment angles is proposed by replacing the body-frame bias state with the geographic-frame bias state. Simulation experiments show that it can improve the horizontal alignment accuracy by 0.1°and vertical alignment accuracy by 1.6°.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Res2Net Based on Multi-scale Attention Mechanism for Breast Cancer Image Classification 12th

Improved Res2Net Based on Multi-scale Attention Mechanism fo...

引用

12th International Conference on Computer engineering and Networks, CENet 2022

作者： Lei, Suqin Deng, Xing Shao, Haijian Xia, Wang Department of Computer Jiangsu University of Science and Technology Jiangsu Zhenjiang212003 China College of Automation Key Laboratory of Ministry of Education of Complex Engineering System Measurement and Control Southeast University Jiangsu Nanjing210009 China School of Information Science and Technology Nantong University Nantong Jiangsu226019 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

ISBN: (纸本)9789811969003

Breast cancer is one of the most common cancers among female diseases. Since the classification accuracy of pathological images is crucial to the diagnosis of breast cancer, in order to reduce the error of manual diagnosis and improve the automatic classification accuracy of pathological images, this paper proposes a high-accuracy breast cancer classification method based on multi-scale attention mechanism enhanced Res2Net. By constructing a multi-channel residual connection in the residual block, and introducing a convolutional attention mechanism to enhance the feature extraction ability of Res2Net, and using group convolution to replace part of the ordinary convolution. In addition, since the channel information interaction across groups cannot be realized in the group convolution, which reduces the feature extraction ability. In this paper, the channel shuffling operation is used to reorganize the feature maps after the group convolution to achieve the information interaction between different groups. The evaluation results on the BreaKHis dataset show that, the accuracy and precision of the method in this paper have reached 98.5% and 98.9% respectively, in binary classification of histopathological images compared with the benchmark method, and the advantages of recall rate and F1 value are also more obvious. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Improved Auction Algorithm for Weapon Target Assignment with Firepower-Health Model

Improved Auction Algorithm for Weapon Target Assignment with...

引用

Chinese control Conference (CCC)

作者： Shuobo Wang Yong Heng Yongzhao Hua Xiwang Dong Zhang Ren Institute of Artificial Intelligence Beihang University Beijing P.R. China Beijing Institute of Electronic System Engineering Beijing PR China School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing P.R. China

This paper proposes an improved auction algorithm to optimize the efficiency of dynamic weapon target assignment (WTA) problem. Firstly, the dynamic battlefield environment of firepower-health model is analyzed and the constraints of weapon assignment problem are established. The firepower-health model is about the idea of adding constraints of weapon firepower and target health to promote the result of assignment more effectively. Secondly, in order to improve the computing speed of WTA algorithm, the penalty mechanism is introduced in the compensation auction algorithm. The main idea of improved algorithm is to reduce the extra consuming of the weapon during the assignment, from which penalty mechanism can optimize the assignment results and reduce the number of algorithm iterations by punishing the overkilled target under certain rules. Finally, the simulation results based on the dynamic firepower-health model show that the proposed algorithm can meet the requirements of firepower allocation, and can promote the effectiveness of assignment with high real-time response.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural-LAFC: A Neural Learning Adaptive Flight controller for Tailless Flapping-Wing Robots Under Uncertain Wind Disturbance Conditions

引用

IEEE Transactions on Aerospace and electronic systems 2025年

作者： Guo, Qingcheng Zhang, Yichen Mou, Jiawang Liu, Wu Wu, Xiaosheng Lu, Jun-Guo Shanghai Jiao Tong University Department of Automation China Key Laboratory of System Control and Information Processing Ministry of Education of China China National Key Laboratory of Advanced Micro and Nano Manufacture Technology Shanghai200240 China Shanghai Jiao Tong University National Key Laboratory of Advanced Micro and Nano Manufacture Technology China Shanghai Jiao Tong University Department of Micro/Nano Electronics School of Electronic Information and Electrical Engineering Shanghai200240 China Designing Institute of Hubei Space Technology Academy Wuhan China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China

Enabling bio-inspired flapping-wing robots (FWRs) to maintain stable flight in windy environments, similar to real flying creatures, is of significant importance. In this work, a neural learning-based adaptive flight controller (Neural-LAFC) is proposed for the attitude and position control of a tailless FWR under uncertain wind conditions. The key approach involves employing a deep neural network (DNN) that incorporates not only attitude information but also instantaneous flapping angles of the wings to learn the aerodynamic torques that cannot be accurately modeled. The training data are obtained from flight experiments conducted with the FWR in a wind tunnel environment. Subsequently, a composite adaptive law is presented to update a set of linear coefficients. These linear coefficients are utilized to blend the pre-trained basis functions to represent the aerodynamic torques. The tracking errors are shown to exponentially converge to a bounded region, as guaranteed by a Lyapunov function. Based on the learning-based attitude controller, we also develop an adaptive controller for position control. Notably, apart from the training phase, the FWR operates without prior knowledge of wind speed. Experimental results demonstrate that the Neural-LAFC successfully achieves the desired attitude stabilization, target point tracking, and path tracking of the FWR in windy conditions. The proposed control scheme also outperforms baseline controllers in wind disturbance suppression, reducing the root mean square position errors by more than 40% when the FWR is subjected to a horizontal wind within the speed of 180 {cm s{-1}}. © 1965-2011 IEEE.

关键词： Wind tunnels

来源：评论

学校读者我要写书评

暂无评论

Adversarially Robust Reinforcement Learning for Urban Traffic Signal control

Adversarially Robust Reinforcement Learning for Urban Traffi...

引用

International Conference on Technology, Informatics, Management, engineering, and Environment (TIME-E)

作者： Muhammad Shafly Hamzah Endra Joelianto Herman Yoseph Sutarto Adiyana Putri Instrumentation and Control Master Program Institut Teknologi Bandung Bandung Indonesia Instrumentation Control and Automation Research Group Institut Teknologi Bandung Bandung Indonesia Department of Intelligent System PT. Pusat Riset Energi Bandung Indonesia Doctoral Program of Engineering Physics Institut Teknologi Bandung Bandung Indonesia

ISBN: (数字)9798350364750

ISBN: (纸本)9798350364767

Urban traffic congestion presents critical challenges, resulting in delays, environmental pollution, and significant economic costs. While traditional traffic control methods, such as fixed-time and adaptive systems, have been widely implemented, they often fail in unpredictable conditions, particularly when confronted with noisy or inaccurate data. This research proposes a robust reinforcement learning (RL) solution for traffic signal control using the RADIAL-DQN (Robust Adversarial Loss DQN) algorithm. Integrating adversarial training enhances the system's robustness to real-world uncertainties. Evaluations conducted using a SUMO traffic simulation show that the robust agent produced an increase of only 60.71% in queue length under a projected gradient descent (PGD) adversarial attack, outperforming standard RL agents, which experienced an 89% increase. These results demonstrate the potential of robust RL to improve both the reliability and scalability of urban traffic control systems.

关键词： Training Adaptive systems Uncertainty Scalability Urban areas Traffic control Robustness Standards Traffic congestion Testing

来源：评论

学校读者我要写书评

暂无评论

Optimal Energy Management of Storage-Assisted Distribution Network for Operating Cost Reduction: Considering Effects of Different Seasons

Optimal Energy Management of Storage-Assisted Distribution N...

引用

International Conference on Electric Power and Energy Conversion systems (EPECS)

作者： Fatma Avli Firis Ali Rifat Boynuegri Aydin Yesildirek Seref Naci Engin Department of Electrical and Electronic Engineering Kahramanmaras Sutcu Imam University Kahramanmaras Türkiye Department of Electrical Engineering Clean Energy Technologies Institute Yildiz Technical University Istanbul Türkiye Department of Mechatronics Faculty of Mechanical Engineering Yildiz Technical University Istanbul Türkiye Department of Control and Automation Faculty of Electrical and Electronics Engineering Yildiz Technical University Istanbul Türkiye

ISBN: (数字)9798331516963

ISBN: (纸本)9798331516970

This paper introduces a framework to reduce operational costs in active distribution systems by utilizing battery energy storage systems. It employs a two-stage stochastic programming approach involving Here-and-Now and Wait-and-See decisions. The scheduling problem is studied as a mixed-integer linear programming model in GAMS and solved using the CPLEX solver. A feeder from an active electricity distribution network is chosen to demonstrate the effectiveness of the proposed method. Operating costs are evaluated under varying scenarios with and without energy storage across seasons. The research contributes to the literature by providing a comprehensive analysis of the strategic role of Battery Energy Storage system in optimizing operational efficiency and enhancing flexibility in active distribution networks. The findings underscore the critical value of energy storage in reducing costs and managing uncertainties in energy operations, as validated by the simulation results demonstrating the economic benefits of the proposed strategy.

关键词： Costs Uncertainty Profitability Battery energy storage system Simulation Stochastic processes Distribution networks Electrical power distribution Programming Springs

来源：评论

学校读者我要写书评

暂无评论

MA-RRT* Algorithm for Path Planning with Maximum Rotation Angle Constraint and Adaptive Crossing Threat Zone

MA-RRT* Algorithm for Path Planning with Maximum Rotation An...

引用

Chinese control Conference (CCC)

作者： Jiong Luo Yong Heng Qi Li Yongzhao Hua Xiwang Dong Zhang Ren School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing P.R. China Beijing Institute of Electronic System Engineering Beijing PR China Institute of Artificial Intelligence Beihang University Beijing P.R. China

With the gradual diversification of modern application scenes, the demand for UAV path planning is becoming more and more abundant. This paper first introduces a possible battle scenario, and the problems that must be considered in path planning in this scene are analyzed: the maximum rotation angle constraint and the demand that the UAV can cross the threat zone flexibly. Maximum rotation angle and Adaptive crossing threat zone RRT * (MA-RRT*) algorithm is proposed to solve the above problems. The algorithm improves the reconnection process of neighbor set in RRT*, and adds the maximum rotation angle constraint to the RRT * framework, so that the generated path strictly meets this constraint. In addition, the above process also reduces the time consumption of RRT*, and the speed advantage of MA-RRT* becomes more and more obvious with the increase of iteration times. Then, the obstacle information is regarded as one of the components of the node cost of the path, and the original obstacle is regarded as a soft constraint. This enables the path to adaptively cross the threat zone, which is more in line with the actual situation. We compare our algorithm with RRT * in numerical simulation, which verifies the effectiveness and time consumption advantages of the algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Domain Adaptation Variational Autoencoder for EEG-Based Emotion Recognition

引用

IEEE/CAA Journal of Automatica Sinica 2022年第9期9卷 1612-1626页

作者： Yixin Wang Shuang Qiu Dan Li Changde Du Bao-Liang Lu Huiguang He the Research Center for Brain-inspired Intelligence National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of ScienceBeijing 100190 the University of Chinese Academy of Sciences Beijing 100049 the Beijing Institute of Control and Electronic Technology Beijing 100038China the School of Mathematics and Information Sciences Yantai UniversityYantai 264003China the Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of ScienceBeijingChina the Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China

Traditional electroencephalograph(EEG)-based emotion recognition requires a large number of calibration samples to build a model for a specific subject,which restricts the application of the affective brain computer interface(BCI)in *** attempt to use the multi-modal data from the past session to realize emotion recognition in the case of a small amount of calibration *** solve this problem,we propose a multimodal domain adaptive variational autoencoder(MMDA-VAE)method,which learns shared cross-domain latent representations of the multi-modal *** method builds a multi-modal variational autoencoder(MVAE)to project the data of multiple modalities into a common *** adversarial learning and cycle-consistency regularization,our method can reduce the distribution difference of each domain on the shared latent representation layer and realize the transfer of *** experiments are conducted on two public datasets,SEED and SEED-IV,and the results show the superiority of our proposed *** work can effectively improve the performance of emotion recognition with a small amount of labelled multi-modal data.

关键词： Cycle-consistency domain adaptation electroencephalograph(EEG) multi modality variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Real-time Framework of Multi-Camera Vehicle Tracking system

A Real-time Framework of Multi-Camera Vehicle Tracking Syste...

引用

2024 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2024

作者： Zhuang, Hanyang Chen, Xingyuan Lan, Jianglin Wang, Ying Lu, Zhaoxuan Wang, Chunxiang Yang, Ming University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai200240 China University of Glasgow James Watt School of Engineering GlasgowG12 8QQ United Kingdom Shanghai Jiao Tong University School of Mechanical Engineering Shanghai200040 China Shanghai Intelligent and Connected Vehicle R and D Center Co. LTD Shanghai201400 China Shanghai Jiao Tong University Department of Automation Shanghai200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9798350372601

Multi-camera vehicle tracking (MCVT) system is a key technology to build an intelligent city and intelligent transportation system. The MCVT system utilizes roadside monitoring devices and computing platforms to achieve city-level road traffic perception at a finer scale by tracking each vehicle on the road to obtain the trajectory. The existing MCVT system mainly focuses on dealing with the algorithm modules separately, without studying the real-time performance and system architecture of the entire pipeline. However, in real-world applications, many of the tricks in improving evaluation metrics are not applicable since there is endless traffic flow running all the time. Therefore, this paper proposes a real-time framework of the MCVT system to streamline all the algorithm modules with proper data flow. Firstly, a multi-threaded multi-vehicle tracking (MVT) module is developed to detect vehicles in each camera. Re-identification is implemented during MVT to provide the feature for tracking in the same camera and across different cameras. Then, after the vehicle leaves the camera field of view, the feature of vehicle trajectory is calculated by averaging the feature at each frame. Meanwhile, a background thread runs continuously to match the incoming feature of vehicle trajectory with past features by conducting a topology searching method. In the end, the vehicle trajectories with well-matched features are considered to be the same vehicle. The entire pipeline has been validated on two different datasets, the precision is 0.64 in the CityFlow dataset which uses 6 cameras simultaneously. In the customized dataset, the same method can still reach real-time when using 16 cameras at the same time with smaller network modules. © 2024 IEEE.

关键词： Vehicle locating systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：