检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Fuquan Wu, Yu Xu, Xinxin Wang, Chuansheng Ma, Minjia Grau, Antoni Huang, Jiayan School of Computer and Big Data Minjiang University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of New Engineering Industry Putian University Putian China Department of Automatic Control Polytechnic University of Catalonia Barcelona Spain School of Robotics Xi'an Jiaotong-Liverpool University Suzhou China College of New Engineering Industry Putian University Fujian Ruituo Information Technology Limited Company Putian China

ISBN: (纸本)9798350386226

Fatigue driving is a common potential traffic safety hazard. To detect and analysis the driver Fatigue degree in real-time, more attention have been increasing paid to application research of EEG fatigue detection device. However, existing methods suffer from complex model structure or large-scale model parameters. In the other words, they requires high computational consumption and large memory footprint, which creates a contradiction between model and portable EEG machine with limited hardware resources. In this work, we take both time and frequency domains of EEG signal into account and design an lightweight and efficient driver fatigue detection network based on GCN (EEG-GNet), which is available edge-end device application. Experiments on 4th Raspberry Pi on a public baseline dataset show that our EEG-GNet outperforms the state-of-the-art methods and takes good tradeoff between detection accuracy and resource consumption. Our EEG-GNet provides a new potential opportunity for future applications in practical portable/wearable (P/W) devices. © 2024 IEEE.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Quality Prediction of Injection Molding Process Using CNN and Parallel-Cascade LSTMs 43

Quality Prediction of Injection Molding Process Using CNN an...

引用

43rd Chinese control Conference, CCC 2024

作者： Zhang, Yibo Li, Dewei Zhou, Yuanqiang Gao, Furong Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai201100 China Tongji University College of Electronic and Information Engineering Shanghai201804 China Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong The Guangzhou Hkust Fok Ying Tung Research Institute Department of Chemical and Biological Engineering Guangzhou511458 China

ISBN: (纸本)9789887581581

Quality prediction of plastic products has always been an important research topic in the injection molding production process. However, existing quality prediction methods struggle to handle both high-frequency data and statistical data generated during the injection molding production process. This paper introduces a novel quality prediction model for injection molding production, utilizing a combination of Convolutional Neural Networks (CNN) and Parallel-Cascade Long Short-Term Memory (PCLSTM) networks. The PCLSTM network is designed to handle the complexities of high-frequency data in injection molding, overcoming the limitations of traditional LSTM methods in processing long sequence data. By segmenting data into stages and utilizing a cascade mechanism, the PCLSTM architecture efficiently captures important temporal dynamics. Additionally, the CNN network is designed to extract statistical data features. The quality prediction results are obtained by fusing two types of data features and then passing them through a fully connected network. Experimental results on real production datasets show that the CNN-PCLSTM model outperforms existing models in prediction accuracy and training convergence speed. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Contact-Aided Model for Soft Continuum Robots Moving in Unstructured Environment

A Contact-Aided Model for Soft Continuum Robots Moving in Un...

引用

Chinese Automation Congress (CAC)

作者： Zhang Jingyu Fang Qin Sun Mingjian Xiong Rong Yue Wang Lu Haojian School of Information Science and Engineering Harbin Institute of Technology Weihai China Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Department of Control Science and Engineering Harbin Institute of Technology Heilongjiang China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Due to their inherent flexibility and high human-computer interaction potential, soft continuum robots have been developed and popularized in industrial and medical scenarios. However, when moving in an unstructured environment, the contact with environment will change the configuration parameters of the robot, which brings problems to the control. Aiming at improving the control performance of soft continuum robots in an unstructured environment, a contact-aided model is proposed to estimate the varying configurations of the robot. Besides, a model-based controller is proposed to control the robot in an unstructured environment. To verify the performance of the proposed method, a small-scale soft continuum robot is designed and fabricated. Through the characterization experiment, the robot shows a large workspace by changing the contact position, and the kinematic model is verified. Through the trajectory tracking experiment, the robot showed good accuracy, with an average error of 1.2mm. Through an exploration experiment in the unstructured environment, the robot showed good control effect, with an average error of 1.9mm. This work enhances the application capability of the soft continuum robots in unstructured environments.

关键词： Human computer interaction Automation Accuracy Trajectory tracking Service robots Kinematics Continuum robots Robots

来源：评论

学校读者我要写书评

暂无评论

A third-party platoon coordination service: Pricing under government subsidies

A third-party platoon coordination service: Pricing under go...

引用

作者： Bai, Ting Johansson, Alexander Li, Shaoyuan Johansson, Karl Henrik Mårtensson, Jonas School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden KTH Royal Institute of Technology Stockholm Sweden Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Digital Futures Stockholm Sweden

This paper models a platooning system consisting of trucks and a third-party service provider (TPSP), which performs platoon coordination, distributes the platooning profit in platoons, and charges trucks in exchange for the services. Government subsidies used to incentivize platooning are also considered. We propose a pricing rule for the TPSP, which keeps part of the platooning profit including the subsidy each time a platoon is formed. In addition, a platoon coordination solution based on the distributed model predictive control (MPC) is proposed, in which the pricing rule under government subsidies is integrated. We perform a realistic simulation over the Swedish road network to evaluate the impact of the pricing rule and subsidies on the achieved profits and fuel savings. Our results show that subsidies are an effective mean to boost fuel savings from platooning. Moreover, the simulation study indicates that high pricing corresponds to a low platooning rate of the system, as trucks' incentives for platooning decrease. © 2023 The Authors. Asian Journal of control published by John Wiley & Sons Australia, Ltd on behalf of Chinese Automatic control Society.

关键词： Trucks

来源：评论

学校读者我要写书评

暂无评论

Privacy-protected object detection through trustworthy image fusion

Privacy-protected object detection through trustworthy image...

引用

作者： Zhang, Chao Zhang, Jinmei Yun, Lijun Zhang, Jun Su, Junbo Yunnan Key Laboratory of Optoelectronic Information Technology Yunnan Normal University Kunming China School of Physics and Electronic Information Yunnan Normal University Kunming China Engineering Research Center of Computer Vision and Intelligent Control Technology Department of Education of Yunnan Province Yunnan Normal University Kunming China Kunming Institute of Physics Ordnance Science and Research Academy of China Kunming China

The neural network-based technologies have emerged as a potent method for image fusion, object detection, and other computer vision tasks as the rapid development of deep learning. Multi-band infrared images, in particular, capture a more extensive range of radiation details and information compared to conventional single-band infrared images. Consequently, the fusion of multi-band infrared images can provide more features for object detection. However, it is crucial to consider that infrared images may contain sensitive information, potentially leading to privacy concerns. Ensuring datasets privacy protection plays a crucial role in the fusion and tracking process. To address both the need for improved detection performance and the necessity for privacy protection in the infrared environment, we proposed a procedure for object detection based on multi-band infrared image datasets and utilized the transfer learning technique to migrate knowledge learned from external infrared data to internal infrared data, thereby training the infrared image fusion model and detection model. The procedure consists of several steps: (1) data preprocessing of multi-band infrared images, (2) multi-band infrared image fusion, and (3) object detection. Standard evaluation metrics for image fusion and object detection ensure the authenticity of the experiments. The comprehensive validation experiments demonstrate the effectiveness of the proposed procedure in object detection tasks. Furthermore, the transfer learning can train our datasets and update the model without exposing the original data. This aspect of transfer learning is particularly beneficial for maintaining the privacy of multi-band infrared images during the fusion and detection processes. © 2024 John Wiley & Sons Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Bias Considerations When Identifying Systems from Noisy Input-Output Data — Extensions to General Model Structures

Bias Considerations When Identifying Systems from Noisy Inpu...

引用

European control Conference (ECC)

作者： Torsten Söderström Umberto Soverini Department of Information Technology Division of Systems and Control Uppsala University Uppsala Sweden Dept of Electrical Electronic and Information Engineering University of Bologna Bologna Italy

Standard identification methods give biased parameter estimates when recorded signals are corrupted by noise on both input and output sides. In previous papers it has been shown that the bias is significant in case th... 详细信息

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

关键词： Noise Transfer functions Europe control systems Data models Noise shaping Error correction codes

来源：评论

学校读者我要写书评

暂无评论

Multi-View 2D/3D Image Registration via Differentiable X-ray Rendering

Multi-View 2D/3D Image Registration via Differentiable X-ray...

引用

International Conference on Biomimetic Intelligence and Robotics & Medical Robotics Forum, ICBIR+MRF 2024

作者： Cui, Yuxin Song, Rui Li, Yibin Meng, Max Q.-H. Min, Zhe Department of Information Science and Engineering Shandong University Qingdao China Department of Control Science and Engineering Shandong University Jinan China Department of Electronic and Electrical Engineering Chinese University of Hong Kong Hong Kong Hong Kong Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Shenzhen Research Institute Chinese University of Hong Kong Shenzhen China Wellcome/EPSRC Centre for Surgical and Interventional Sciences University College London London United Kingdom

Accurate 2D/3D rigid registration between X-ray and CT images is crucial for orthopedic surgical navigation. However, existing learning-based methods often result in suboptimal registration performance due to local optima. Considering the limitations of single-view approaches, particularly the limited field of view that can omit critical information, we propose a dual-view learning-based pose regression registration framework. Our method leverages preoperative CT scans of the patient to generate multiple pairs of dual-view digitally reconstructed radiographs (DRRs). By integrating pose and pixel information from dual views during training, and utilizing dual-image information fusion for six-degree-of-freedom pose gradient optimization intraoperatively, we achieve both coarse and fine registration. The DiffDRR and PoseNet methods yield average projection distance registration errors on X-rays of 25.94 ± 23.94 mm and 7.30 ± 3.53 mm, respectively, with GFRs of 67% and 18%. In contrast, our method achieved an average registration error of 0.76 ± 1.91 mm and a GFR of 0% on the same datasets. © 2024 The Authors.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Teeth Segmentation from Bite-Wing X-Ray Images by Integrating Nested Dual UNet with Swin Transformers

Teeth Segmentation from Bite-Wing X-Ray Images by Integratin...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Li, Yubo Tian, Yibin Zhang, Zhiyuan Zhang, Xueyang Du, Bingran Zeng, Zhi School of Computer and Information Science Chongqing Normal University Chongqing401331 China College of Mechatronics and Control Engineering Shenzhen University Shenzhen518060 China Litemaze Technology Shenzhen518000 China School of Computing and Information Systems Singapore Management University Singapore487372 Singapore Shunde Hospital Department of Stomatology Foshan528000 China

ISBN: (纸本)9781665410205

In medical practice, the precision of image segmentation is crucial for diagnosis and treatment evaluations. Specifically, in dentistry, accurate teeth segmentation from bite-wing images is important for automatic and objective evaluations of root canal treatments. This study introduces Swin-U2 Net, a model merging the nested dual UNet with residual U-block and Swin Transformers. It combines the local feature extraction capability of the former and the global attention and context understanding of the latter. It has been evaluated for tooth root segmentation using 500 bite-wing dental x-ray images obtained from a root canal treatment clinic. It achieved the best segmentation outcome in terms of Intersection over Union (IOU) and the third best result in terms of Dice Similarity Coefficient (DSC) with the second least amount of network parameters among six UNet-like models, thus it is effective and efficient. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Magnetic Levitation Remote control Laboratory Based on Matlab and Websockets ⁎

引用

IFAC-PapersOnLine 2024年第9期58卷 235-240页

作者： Pavol Bistak Mikulas Huba Peter Drahos Igor Belai Damir Vrancic Institute of Automotive Mechatronics Faculty of Electrical Engineering and Information Technology Slovak University of Technology in Bratislava Slovakia Department of Systems and Control J. Stefan Institute Ljubljana Slovenia Faculty of Industrial Engineering Novo mesto Slovenia

This work proposes a novel architecture for constructing remote laboratories, employing modular building blocks: Matlab/Simulink software for control system design and simulation, WebSocket communication technology for continuous data exchange, and a front-end application developed using the Angular framework. To facilitate WebSocket communication on the Matlab server side, the MatlabWebSocket library is implemented. Beyond the Angular framework, interactivity within the remote laboratory is further enhanced through 3D visualization of the controlled system using a *** based library. These combined technologies are applied in the development of a remote laboratory for a fast, unstable, and nonlinear magnetic levitation system. The laboratory allows users to remotely set desired values and control parameters for experiments, while also providing continuous data visualization in various forms, including numerical readouts, graphs, and 3D animations. This approach demonstrates the effectiveness of the proposed architecture for building remote laboratories for complex systems.

关键词： magnetic levitation system remote laboratory Matlab/Simulink WebSocket 3D visualization unstable nonlinear dynamic system

来源：评论

学校读者我要写书评

暂无评论

A data-driven control method for vehicle lateral stability in snow and ice-rutted conditions under aperiodic sampling 7

A data-driven control method for vehicle lateral stability i...

引用

7th CAA International Conference on Vehicular control and Intelligence, CVCI 2023

作者： Zhao, Xu Guo, Jingzheng Wang, Lianbing Guo, Hongyan Liu, Zhenze Zhang, Yiming College of Communication Engineering Jilin University The Department of Aircraft Control and Information Engineering Jilin Institute of Chemical Technology Changchun China College of Communication Engineering Jilin University Changchun China State Key Laboratory of Automotive Simulation and Control The College of Communication Engineering Jilin University Changchun China SAIC Motor R&D Innovation Headquarter Jilin University Shanghai China

ISBN: (纸本)9798350340488

Designing a controller to ensure vehicle stability under snow and ice-rutted road conditions, in the absence of accurate model knowledge and with potential sampling data delay, poses a significant challenge. To address this, this paper presents a novel data-driven parametric approach that integrates linear matrix inequalities (LMIs) methods. This approach allows for the determination of an appropriate sampling time interval. By iteratively solving LMIs, a state-feedback controller is derived, which guarantees both system stability and robustness. The effectiveness of the proposed approach is demonstrated through numerical simulations conducted on the MATLAB/CarSim platform. The results highlight the good control performance and robustness achieved by the proposed method. © 2023 IEEE.

关键词： data-driven control linear matrix inequality sampling time interval vehicle stability control

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：