检索结果-内蒙古大学图书馆

第41届中国控制会议

作者： Ming Zeng Zhijing Wang Yu Ma Jiazhe Liu Baofeng Zhang Yunke Nie Institute of Robotics and Automation Systems School of Electrical and Information EngineeringTianjin University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

When multi-legged robots work in dangerous and complex environments,their legs are easily damaged,resulting in a sharp decline in their movement ability,or even completely out of *** this paper,the gait generation method combined deep reinforcement learning with bionic gait restrictions is presented for multi-legged robots with injured *** this study,we first built an ant gait video acquisition platform using the Camponotus Japonicus as the research object,and on this basis established a gait dataset of injured ***,the gait characteristics of ants in the injured state were ***,our proposed gait generation method combining bionic gait constraints with deep reinforcement learning was compared with the reinforcement-learning-based method in the MATLAB simulation *** test results show that the training reward values of our proposed algorithm are 1-2 times higher than those of the reinforcement learning method alone,and at the same time,the moving speed of the injured robot is also nearly twice as fast.

关键词： Injured multi-legged robot,Ant gait,Gait generation,Reinforcement learning Bionic constraints

来源：评论

学校读者我要写书评

暂无评论

An Improved Object Detection Algorithm for Assembly Line Garbage Sorting 41

An Improved Object Detection Algorithm for Assembly Line Gar...

引用

第41届中国控制会议

作者： Ming Zeng Jiazhe Liu Xiangzhe Lu Zhijing Wang Yuanhao Li Siying Li Institute of Robotics and Automation Systems School of Electrical and Information EngineeringTianjin University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Garbage object detection is of central importance to achieve accurate garbage *** this work,we propose an improved object detection algorithm for sorting complex garbage objects on the assembly *** algorithm utilizes the Faster RCNN as the baseline and improves its performance with several tips,including deformable convolution,PAFPN,mixup,cutout,color jitter,multi-scale training and ImageNet transfer *** the lack of public datasets for the garbage object detection task,we synthesize a highly realistic multi-object garbage detection dataset,M-GarbageNet,with 20000 training images,5000 validation images and 5000 test ***,we evaluate our algorithm than Faster RCNN,and obtain a 8.2%relative improvement on the M-GarbageNet dataset.

关键词： Garbage object detection Improved Faster RCNN M-GarbageNet Image augmentation

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Torque Control of Six-Phase Switched Reluctance Motors Based on Improved Voltage Vector Strategy

引用

IEEE Transactions on Transportation Electrification 2025年第3期11卷 7650-7661页

作者： Yang, Yifei Sun, Xiaodong Dianov, Anton Demidova, Galina Prakht, Vladimir Wang, Yong Han, Shouyi Suzhou Vocational University School of Mechanical and Electrical Engineering Suzhou215104 China Jiangsu University Automotive Engineering Research Institute Zhenjiang212013 China Wenzhou University Pingyang Institute of Intelligent Manufacturing Wenzhou325035 China ITMO University Faculty of Control Systems and Robotics Saint Petersburg197101 Russia Ural Federal University Department of Electrical Engineering Yekaterinburg620062 Russia Jiangsu University School of Electrical and Information Engineering Zhenjiang212013 China

To rapidly and accurately establish the model of switched reluctance motors (SRMs) and enhance torque control performance, this article proposes a model predictive torque control (MPTC) strategy based on the optimized voltage vector. First, a fourth-order Fourier series is used to calculate the flux and torque models, and a complete nonlinear model of the SRM is constructed using the Kriging model. Second, the torque characteristics are used to divide the sectors, thereby reducing the number of candidate voltage vectors (CVVs) and effectively decreasing the computational burden of predictive control. Finally, an adaptive adjustment algorithm for the sector boundary angle is proposed, where the position of the sectors is determined based on variations in speed and load. The proposed method reduces torque ripple and enhances dynamic response capability. The effectiveness of this approach is validated through experiments on a 12/10 pole six-phase SRM prototype. © 2015 IEEE.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Retina Vessels in 2D OCT-Reconstructed Fundus Images with 3D UNet 26

Segmentation of Retina Vessels in 2D OCT-Reconstructed Fundu...

引用

26th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2023

作者： Marciniak, Tomasz Stankiewicz, Agnieszka Zaradzki, Przemyslaw Poznan University of Technology Division of Electronic Systems and Signal Processing Institute of Automatic Control and Robotics Department of Control Robotics and Electrical Engineering Poznan Poland

ISBN: (纸本)9798350304985

This paper presents an analysis of the effectiveness of blood vessel segmentation in human retinal images. The segmentation process was carried out for three-dimensional optical coherence tomography (OCT) scans using the author's publicly available CAVRI-C database. A 3D version of the U-Net artificial neural network was used. Various dimensions of the input blocks were investigated to determine their influence on the segmentation process. The effectiveness of the proposed solutions was evaluated using various metrics and the results obtained were compared with the 2D solution, also based on neural networks. The use of the proposed solutions allowed us to improve the segmentation even by 15% (in the case of the F1-score). © 2023 Division of Signal Processing and Electronic systems, Poznan University of Technology (DSPES PUT).

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Multispectral Image Segmentation in Agriculture: Evaluating Deep Learning Models with Train-Test Split and Cross-Validation Strategies

Multispectral Image Segmentation in Agriculture: Evaluating ...

引用

Iberian robotics Conference (ROBOT)

作者： Wilgo Cardoso Tiago Barros Gil Gonçalves Cristiano Premebida Urbano J. Nunes Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Portugal Dept. of Mathematics Institute for Systems Engineering and Computers at Coimbra University of Coimbra Portugal

ISBN: (数字)9798350376364

ISBN: (纸本)9798350376371

In agricultural robotics, the integration of multi-spectral image processing and deep learning (DL) has become the state-of-the-art (SOTA) in crop monitoring, yield estimation, and efficient land management. This work addresses the impact of different DL-segmentation models and evaluation protocols on multispectral imagery datasets collected by a UAV over vineyards. In terms of evaluation protocols, we have considered train-test split, standard k-fold cross-validation, and group k-fold cross-validation. While the first two assume that the training and test data are drawn from the same underlying distribution, the group k-fold cross-validation protocol assumes that each fold represents distinct distributions. Most works either adopt train-test split or k-fold cross-validation under the assumption that both the training and test sets are drawn from the same distribution. However, this assumption is rarely met in real-world applications. Therefore, the objective of this study is to evaluate and compare different evaluation protocols within the context of a real-world agricultural task, highlighting their limitations and weaknesses. Two SOTA DL-based segmentation models, SegNet and DeepLabV3, are employed to perform semantic segmentation on datasets of three Vineyards. The models have been trained and tested considering single-modality representations. In addition to the RGB modality, models trained on NDVI, GNDVI and early fusion are also evaluated. The performance of the models are evaluated using the IoU metric across different dataset configurations. The results indicate that the early fusion representation achieves the highest performance across the various splitting protocols, compared to the single-input representations. The results also show that the train-test and random k-fold splitting approaches report similar results. However, when employing group k-fold the performance drops consistently across both models and the modalities. This indicates that the models

关键词： Deep learning Training Precision agriculture Measurement Protocols Data models Yield estimation Robots Monitoring Standards

来源：评论

学校读者我要写书评

暂无评论

A Multi-Gas Detection System Based on Convolutional Neural Network 43

A Multi-Gas Detection System Based on Convolutional Neural N...

引用

43rd Chinese Control Conference, CCC 2024

作者： Chen, Si-Wen Li, Hong-Yue Hou, Hui-Rang Meng, Qing-Hao Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China

ISBN: (纸本)9789887581581

The emission of carbon oxides (COx), nitrogen oxides (NOx), sulfur compounds, and volatile organic compounds (VOCs) from vehicles has significantly impacted the air quality, thus posing threats to the environmental resources and human health. This work presents the development of a non-dispersive infrared (NDIR) multi-gas detection system featuring three broadband light sources, a sealed gas chamber, and three multi-channel pyroelectric detectors with a response time shorter than 32 ms. The proposed system is used for constructing an odor dataset comprising five target gases, including carbon dioxide (CO2), carbon monoxide (CO), nitric oxide (NO), sulfur dioxide (SO2), and propane (C3 H8). We perform odor recognition experiments using the traditional machine learning methods, as well as one-dimensional convolutional neural network (1D-CNN) and depthwise separable convolutional neural network (DS-CNN). The results show that the proposed DS-CNN model achieves an accuracy of 94.75% in recognizing different odors, thus outperforming other classification algorithms. This work demonstrates that the proposed detection system exhibits rapid response and precise recognition, thus establishing it as an effective approach for analyzing the primary components of automobile exhaust. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

E-Nose-Based Domain-Generalization Recognition of Ignitable Liquids 43

E-Nose-Based Domain-Generalization Recognition of Ignitable ...

引用

43rd Chinese Control Conference, CCC 2024

作者： Song, Tian-Shu Chen, Zhen-Peng Hou, Hui-Rang Li, Hong-Yue Meng, Qing-Hao Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China

ISBN: (纸本)9789887581581

Detecting ignitable liquids (ILs) at the scene of a fire is crucial for fire investigation. The electronic nose (e-nose) is crucial for detecting ILs due to its affordability and rapid response time. Process limitations and changes in environmental conditions can cause variations in the reactions of multiple e-noses with the same sensor array to the same input gas. This can significantly reduce the accuracy of identifying ILs when deploying a model trained on one e-nose to other e-noses. In order to tackle the issue of cross-platform identification of ILs using e-noses, we developed a feature mute gated network (FMG-Net). This network is capable of maintaining consistency in the shared components of different e-noses at the low-level feature level while effectively muting the distinct low-level features. FMG-Net is comprised of a main network and multiple branch networks that are specific to different domains. Initially, a subsidiary domain-specific convolutional neural network (SDS-CNN) is trained to learn the network parameters on various e-nose platforms with known labels. Additionally, the backbone network generates low-level features of the e-nose responses. Furthermore, the SDS-CNN incorporates random input of low-level features and generates a mask using the gradient. This mask is then used to explicitly remove the non-overlapping parts of the low-level features. At last, the low-level features are sent back to the backbone network for further training once the non-overlapping parts have been removed. Experiments were conducted to identify four types of ILs (diesel, gasoline, ethanol, and thinner) using five self-made e-nose platforms with identical sensor arrays. The results indicated that the proposed FMG-Net consistently outperforms other domain-generalization algorithms in terms of recognition accuracy and parameter sizes. FMG-Net has the ability to detect volatile gases in ILs using an e-nose, even without the need for a dataset. © 2024 Technical Committ

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Basis change, projection, and relative linear algebra tricks in signal and image processing 27

Basis change, projection, and relative linear algebra tricks...

引用

27th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2024

作者： Dabrowski, Adam Poznań University of Technology Faculty of Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Division of Signal Processing and Electronic Systems Jana Pawla II 24 Poznań60-965 Poland

ISBN: (纸本)9788362065486

In this tutorial some basic linear algebra problems: basis change and projection, are discussed together with examples of their applications in signal and image processing. In typical linear algebra university courses perpendicular projections are only discussed. However, in image processing, for defining various color spaces, we need non-perpendicular projections. That is why this is the key problem in this tutorial. © 2024 Division of Signal Processing and Electronic systems, Poznan University of Technology (DSPES PUT).

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

A Depression Level Classification Model Based on EEG and GCN Network with Domain Generalization 43

A Depression Level Classification Model Based on EEG and GCN...

引用

43rd Chinese Control Conference, CCC 2024

作者： Zhang, Zhongyi Xu, Chenyang Jin, Licheng Hou, Huirang Meng, Qinghao Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin Key Laboratory of Process Measurement and Control Tianjin300072 China

ISBN: (纸本)9789887581581

Electroencephalography (EEG) contains a wealth of information, including neuron activity, allowing for a partial understanding of the brain's state. As a reliable tool, EEG, combined with deep neural networks, has been increasingly utilized to assist in the detection of depression and has achieved satisfactory results. However, there are still some limitations in the current models. Firstly, it is worth noting that many existing models are binary classification models. These models can determine whether a subject is depressed or not, but they lack the capability to differentiate the severity of depression. Besides, the variations in EEG signals among various individuals have not been thoroughly taken into account, leading to subpar performance when applying the trained model to new subjects. To address the aforementioned issues, we suggest implementing a multi-classification model that utilizes a graph convolutional neural network (GCN) to identify levels of depression. Additionally, to mitigate the problem of imbalanced samples in multi-classification tasks, we introduce a penalty coefficient for the smaller categories. At the same time, the issue of signal discrepancies among subjects was taken into account, leading to the introduction of the domain generalization module. Finally, the depression level identification task on the MODMA and PRED+CT dataset achieved an accuracy of 75.47% and 77.97% respectively, surpassing the performance of the state-of-the-art (SOTA) model. In addition, numerous ablation experiments were conducted to validate the efficacy of each module. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

Computational Intelligence 2023年第4期39卷 530-531页

作者： Er, Meng Joo Ju, Zhaojie Ferrein, Alexander Changjiang Scholar Distinguished Director of Institute of Artificial Intelligence and Marine Robotics College of Marine Electrical Engineering Dalian Maritime University Dalian China Reader in Machine Learning and Robotics School of Computing University of Portsmouth Portsmouth United Kingdom Department of Electrical Engineering and Information Technology Mobile Autonomous Systems & Cognitive Robotics Institute Robotics and Foundations of Computer Science FH Aachen - University of Applied Sciences Aachen Germany

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：