检索结果-内蒙古大学图书馆

Cyber-Physical Social intelligence (ICCSI), International Conference on

作者： Jialiang Luo Shichao Chen Yisheng Lv Wenqiao Sun Fan Yang Ruijie Xu The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Information Engineering China University of Geosciences Beijing China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited Beijing China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Transportation and Economics Research Institute and the Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited China The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences College of Rail Transit Shan Dong JiaoTong University Jinan China Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University Hong Kong China

With the rapid development and widespread application of Inertial Measurement Units (IMUs), IMU-based human localization has become critically important in environments lacking Global Navigation Satellite systems (GNSS) signals. Methods such as UWB/WIFI and other anchor-based localization have been employed to enhance the positioning accuracy. However, these methods are susceptible to the environmental interference and increased costs. In contrast, SINS-based localization methods eliminate reliance on the external data. However, this method can suffer from drift errors due to cumulative integration errors. Inertial navigation error correction techniques like Zero Detection Update Technology (ZUPT) provide potential solutions to address drift errors. This paper proposes an error correction method based on the multithreshold zero-velocity detection and Square Root Cubature Kalman Filter (SRCKF) updates. Compared to the single fixed threshold detection, the multi-threshold zero-velocity detection reduces the likelihood of missed zero velocity detection and false alarms, providing accurate time intervals for error correction. Experimental results demonstrate that the SRCKF-based algorithm reduces position deviation to approximately 0.3146 meters, corresponding to an error ratio of1.14%. The proposed method enables cost-effective and accurate pedestrian localization, driving advancements in the field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Performance Evaluation of SSVEP-BCI Actuated Wheelchair with Parameter Setting of Time-Window Length and Stimulation Layout

The Performance Evaluation of SSVEP-BCI Actuated Wheelchair ...

引用

Workshop on Metrology for Industry 4.0 and IoT

作者： Jun Xie Xiaojun Wu Peng Fang Guanglin Li Guozhi Cao Tao Xue Science and Technology on Electrooptic Control Laboratory Luoyang China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology & Shenzhen Engineering Laboratory of Neural Rehabilitation Shenzhen China School of Mechanical Engineering Xi'an Jiaotong University Xi'an China

ISBN: (数字)9781728148922

ISBN: (纸本)9781728148939

Due to the advantages of prominent brain responses, less training duration, and robustness to artifacts, steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) has been recently applied to intelligent wheelchair navigation. Recent researches mainly focused on the implementation of a specific recognition method to analyze the wheelchair navigation performance under fixed stimulation target number. The navigation performance evaluation under different recognition methods and different BCI target numbers is rarely compared. In this paper, the navigation performance comparison between different numbers of stimulation targets and different recognition methods was carried out. The multichannel integrated GT 2 circ and canonical correlation analysis (CCA) recognition methods were used to compare the wheelchair navigation performance under different time-window (TW) lengths. And the 3-target and 4-target arrangement layouts were adopted to compare the navigation performance between the “No feedback” and the “Feedback” conditions. Experimental results showed that the GT 2 circ recognition method with TW length of 2 s would promote the navigation efficiency and different stimulation target number could be tailored for different wheelchair application purposes, which would bring tutorial instructions to the applicable navigation of the BCI-actuated wheelchair.

关键词： brain-computer interface (BCI) steady-state visual evoked potential (SSVEP) wheelchair navigation time-window (TW) length stimulation layout Performance Evaluation Wheelchair parameter setting navigation Navigation efficiency Brain-Computer Interfaces Recognition (Psychology) Stimuli layouts

来源：评论

学校读者我要写书评

暂无评论

A Computationally Efficient and Refined Signal control Method for Isolated Intersections in a Connected Vehicle Environment

SSRN

引用

SSRN 2023年

作者： Dai, Rongjian Ding, Chuan Cai, Pinlong Wang, Xu Yu, Bin Zhang, Ruhua School of Qilu Transportation Shandong University Jinan China School of Transportation Science and Engineering Beijing Key Laboratory for Cooperative Vehicle Infrastructure System and Safety Control Beihang University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China

With the advent of connected vehicles (CVs), much richer and more accurate data become available for more flexible and sophisticated traffic signal control. Existing CV-based signal control methods were hard to solve owing to the complex optimization models especially when individual vehicles’ trajectories are considered. This paper presents a computationally efficient and refined signal control method for isolated intersections in a CV environment. First, we establish a mixed integer nonlinear program model to minimize the total vehicle travel time by applying a simplified car-following model to predict individual vehicles’ trajectories. Then, we cluster incoming vehicles into platoons and analyzed the platoon features by considering the interactions between vehicles and between vehicles and traffic signals. Based on this, we reformulate the signal optimization model to address the computational concerns. To further improve the utilization efficiency of intersection resources, we determine the minimum required clearance time for each pair of two conflicting signals. Finally, simulation experiments are conducted at a typical four-leg intersection to validate the proposed control method. Simulation results show that the proposed control method can significantly reduce vehicle travel time and fuel consumption compared to the classical adaptive signal control method and the vehicle-actuated control methods under different demand levels. Moreover, the proposed control method has high computational efficiency, validating its potential for practical applications. © 2023, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Efficient 3D Deep LiDAR Odometry

arXiv

引用

arXiv 2021年

作者： Wang, Guangming Wu, Xinrui Jiang, Shuyang Liu, Zhe Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of 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 Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Key Laboratory of Artificial Intelligence of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China

An efficient 3D point cloud learning architecture, named EfficientLO-Net, for LiDAR odometry is first proposed in this paper. In this architecture, the projection-aware representation of the 3D point cloud is proposed to organize the raw 3D point cloud into an ordered data form to achieve efficiency. The Pyramid, Warping, and Cost volume (PWC) structure for the LiDAR odometry task is built to estimate and refine the pose in a coarse-to-fine approach. A projection-aware attentive cost volume is built to directly associate two discrete point clouds and obtain embedding motion patterns. Then, a trainable embedding mask is proposed to weigh the local motion patterns to regress the overall pose and filter outlier points. The trainable pose warp-refinement module is iteratively used with embedding mask optimized hierarchically to make the pose estimation more robust for outliers. The entire architecture is holistically optimized end-to-end to achieve adaptive learning of cost volume and mask, and all operations involving point cloud sampling and grouping are accelerated by projection-aware 3D feature learning methods. The superior performance and effectiveness of our LiDAR odometry architecture are demonstrated on KITTI, M2DGR, and Argoverse datasets. Our method outperforms all recent learning-based methods and even the geometry-based approach, LOAM with mapping optimization, on most sequences of KITTI odometry dataset. We open sourced our codes at: https://***/IRMVLab/EfficientLO-Net. Copyright © 2021, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Research on Event-B based formal modeling and verification of automatic production line

Research on Event-B based formal modeling and verification o...

引用

第28届中国控制与决策会议

作者： Kaiming-FU Bin Fang Yafen-LI Huijie-LI College of Electronic and Control Engineering Beijing University of Technology The Ministry of Education P.R.C.Engineering Research Center of Digital Community Beijing Laboratory for Urban Mass Transit Beijing Key Laboratory of Computational Intelligence and Intelligent System

ISBN: (纸本)9781467397155

Before the automatic production line put into practical use in industrial domain,it must go through a large number of long-term rigorous test to detect errors in the design *** in the actual test process,the same mistake leads to different results due to the different test methods and there are some special conditions resulting from the limitation of field test environment what can't be used to be *** formal method,by using the method of discrete mathematics to practical system mathematical modeling and validation,can replace the methods what can not been tested under the conditions of system *** formal method is also suitable for developing large reactive and distributed *** this paper,the specific formal method which is called Event-B improves the high security and reliability of *** the related tools such as Rodin are used for modeling,refinement and verification in the PLC(Programmable Logic controller) automatic production *** result in this paper shows that our approach contributes to reducing system details during the early development stage and leads to simpler proofs and more automated *** it provides a new method for reference for higher requirements in the reliability in engineering projects,so as to ensure the correctness of the designed software.

关键词： automatic production line PLC model verify Event-B Formal method

来源：评论

学校读者我要写书评

暂无评论

An active fault-tolerant control strategy of aircraft engines based on multi-model predictive control

引用

International Journal of Turbo and Jet Engines 2020年第0期

作者： Du, Xian Ma, Yan-Hua School of Control Science and Engineering Dalian University of Technology Dalian China Jiangsu Province Key Laboratory of Aerospace Power System Nanjing China School of Microelectronics Dalian University of Technology Dalian China DUT Artificial Intelligence Institute Dalian China

In order to mitigate or even eliminate the adverse effects caused by typical components faults of aircraft engines, an active fault-tolerant strategy based on multi-model predictive control is proposed, which consists of a pre-established multi-model library, a judgement module, and corresponding predictive controllers with smooth transition switching logic. Multiple dynamic nonlinear or linear models are firstly established by means of system identification methods, based on the component-level nonlinear engine model or historical data in faults cases. The judgement module is utilized to online compare the engine measured outputs with that of all models in the pattern library and select the best matched dynamic model on the basis of outputs error quadratic performance index, thus determining the most appropriate predictive controller for the next control sample period. When a certain fault occurs, the fault model in the library could be identified and fault-model based predictive controller is activated. Finally, two kinds of pre-considered high-pressure compressor and high-pressure turbine component-level faults are taken as an example to design the active fault-tolerant controller. Simulation results show that the judgement module owns the ability to sense the fault and gives smooth switching signal to the suitable predictive controller, verifying the effectiveness of the proposed technique. © 2020 Walter de Gruyter GmbH, Berlin/Boston 2020.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Strike a Balance in Continual Panoptic Segmentation

arXiv

引用

arXiv 2024年

作者： Chen, Jinpeng Cong, Runmin Luo, Yuxuan Ip, Horace Ho Shing Kwong, Sam Department of Computer Science City University of Hong Kong Hong Kong School of Control Science and Engineering Shandong University Shandong Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Shandong Jinan China Centre for Innovative Applications of Internet and Multimedia Technologies City University of Hong Kong Hong Kong Lingnan University Hong Kong

This study explores the emerging area of continual panoptic segmentation, highlighting three key balances. First, we introduce past-class backtrace distillation to balance the stability of existing knowledge with the adaptability to new information. This technique retraces the features associated with past classes based on the final label assignment results, performing knowledge distillation targeting these specific features from the previous model while allowing other features to flexibly adapt to new information. Additionally, we introduce a class-proportional memory strategy, which aligns the class distribution in the replay sample set with that of the historical training data. This strategy maintains a balanced class representation during replay, enhancing the utility of the limited-capacity replay sample set in recalling prior classes. Moreover, recognizing that replay samples are annotated only for the classes of their original step, we devise balanced anti-misguidance losses, which combat the impact of incomplete annotations without incurring classification bias. Building upon these innovations, we present a new method named Balanced Continual Panoptic Segmentation (BalConpas). Our evaluation on the challenging ADE20K dataset demonstrates its superior performance compared to existing state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Traffic Flow Prediction via Weighted Combination of ARIMA and WASDNN Models

Traffic Flow Prediction via Weighted Combination of ARIMA an...

引用

第33届中国控制与决策会议

作者： Xiao Liu Yunong Zhang Min Yang Zhongxian Xue Chengxu Ye School of Electronics and Information Technology Sun Yat-sen University Guangdong Key Laboratory of Modern Control Technology Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education School of Data and Computer Science Sun Yat-sen University School of Computer Science Qinghai Normal University

The modeling and prediction of traffic flow are important in transportation study and traffic network *** from individual models,a hybrid model which is a combination of autoregressive integrated moving average(ARIMA) and weights and structure determination neural network(WASDNN) models,is proposed for modeling and prediction of traffic *** with individual models like ARIMA and WASDNN,the proposed ARIMAWASDNN model has better performance in modeling and prediction of traffic flow of Shenzhen city as an *** addition,prediction results of different activation functions of hidden layer neurons are *** is more,the proposed ARIMA-WASDNN model also performs better than the popular long short-term memory(LSTM) model in predicting traffic flow of Shenzhen *** effectiveness and superiority of ARIMA-WASDNN model are substantiated by results of numerical experiments.

关键词： Time series traffic flow prediction autoregressive integrated moving average(ARIMA) model weights and structure determination(WASD) algorithm

来源：评论

学校读者我要写书评

暂无评论

Distributed Air-Assisted Coverage control for Sensing-Limited Multi-Robot systems in Time-Varying Environment

Distributed Air-Assisted Coverage Control for Sensing-Limite...

引用

Fully Actuated system Theory and Applications (CFASTA), Conference on

作者： Hang Zhang Ronghao Zheng Lingxia Lu Senlin Zhang Meiqin Liu College of Electrical Engineering Zhejiang University Hangzhou China National Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Jinhua Institute of Zhejiang University Jinhua China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Xi’an Jiaotong University Xi’an China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

In the multi-robot coverage control application, a group of ground robots tries to optimize the environment coverage performance. However, most of the existing works consider that the environment is static and the ground robots have large sensing ranges. In this paper, we present a fully distributed, air-assisted coverage control scheme to address the challenge of a time-varying environment and limited sensing range. Firstly, we use aerial robots equipped with low-resolution but high-sensing-range sensors to achieve a weighted Voronoi coverage of the environment. Then the aerial robots utilize their local information to guide the ground robots, equipped with low-sensing-range but high-resolution sensors, to explore the environment to optimize a high-resolution coverage performance. The ground robots adopt a new controller to promptly adapt to environmental changes. Simultaneously, each aerial robot dynamically adjusts its domain to optimize the coverage performance of the ground robots. The convergence of the control scheme is proved and its performance is evaluated through simulations.

关键词： Manifolds Adaptation models Atmospheric modeling Robot sensing systems Autonomous aerial vehicles Sensors Multi-robot systems

来源：评论

学校读者我要写书评

暂无评论

Self-Organized Criticality in C. Elegans Neural Network

Self-Organized Criticality in C. Elegans Neural Network

引用

Chinese control Conference (CCC)

作者： Xiao Gu Jian Liu Ye Yuan Peng Zhao Kuankuan Xin Tao Fang Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China Shanghai Engineering Research Centre of Intelligent Control and Management Shanghai China Institute of Machine Intelligence University of Shanghai for Science and Technology Shanghai China Queensland Brain Institute The University of Queensland Brisbane QLD Australia

The self-organized criticality is a fundamental property for organisms to perform normal functional activities. Extensive large-scale biological neural network researches have found the existence of self-organized criticality through avalanche phenomenon, which is typical characteristic of self-organized criticality. However, such research method is not suitable for small-scale biological neural network, because number of neurons in small-scale biological neural network is not large enough to support the emergence of avalanche phenomenon. It has been demonstrated that branching parameter can also be used to describe the propagation of activity in the neural network. Here, in this paper, the C. elegans neural network composed of 302 neurons is selected to investigate the existence of self-organized criticality using branching parameter. Based on the obtained connectome of C. elegans, a directed graph model is constructed to simulate the gradient potential of neurons and the activity of C. elegans, then, the existence of self-organized criticality in the neural network of C. elegans is proved by using branching parameter method. Meanwhile, the result is further confirmed by analyzing the calcium activity data of C. elegans obtained from biological experiments.

关键词：

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：