检索结果-内蒙古大学图书馆

第40届中国控制会议

作者： Fei Wang Zhibo Fan Chengpeng Li Jian Lu Faculty of Robot Science and Engineering Northeastern University Shenyang SIASUN Robot and Automation Co. ltd

Aiming at the poor prediction of lower limb joint angle using surface electromyography（sEMG）,a continuous motion estimation method based on binary cuckoo search algorithm（BCS） and random forest（RF） regression is *** sEMG signals of human lower limbs are collected during normal walking and the corresponding features are extracted as the initial feature ***,with the minimum estimation error as the goal,the BCS algorithm is used for the second feature selection to obtain the optimized feature ***,the trained RF regression model is used to predict the joint angle of human lower *** experiment results show that,compared with the traditional principal component analysis（PCA）,the proposed feature selection method improves the prediction performance of the RF regression model for joint *** effectiveness of the proposed algorithm is verified by analyzing the predicted results of hip joint angles and knee joint angles of different experimenters.

关键词： surface electromyography（sEMG） binary cuckoo search（BCS） random forest（RF）

来源：评论

学校读者我要写书评

暂无评论

Thickness Separation and Impurity Removal of Graphene Via Eddy Current Separation

SSRN

引用

SSRN 2024年

作者： Bin, Cao Yi, Yuan Zhicheng, Shan Lixue, Yang Kamali, Ali Reza Qiang, Wang Montalvão, Diogo Abdelkader, Amor School of Metallurgy Northeastern University Shenyang110819 China Northeastern University Shenyang110819 China Department of Design and Engineering Faculty of Science & Technology Bournemouth University Dorset PooleBH12 5BB United Kingdom Northeastern University Shenyang110819 China

The exceptional properties of graphene depend sensitively on thickness and the impurities which limit its applications. Almost all large-scale production techniques lack sufficient control over the materials and suffer from impurities introduced during manufacturing. Considering the substantial differences in electrical conductivity between graphene of varying number of layers and non-graphene impurities, we developed a process that adapts the eddy current separation concepts of thickness separation of graphene and its purification from other less conductive impurities. Through numerical simulations, the research investigates the eddy current forces, torques, and motion dynamics experienced by graphene flakes of different layers when subjected to an alternating magnetic field. The results highlight the capacity of eddy current forces to overcome the liquid-phase resistance, driving the controlled directional motion of graphene flakes. At a magnetic field frequency of 45 kHz, graphene flakes with fewer layers exhibit enhanced settling velocities and quicker response times, implying the potential for statistically significant separation of graphene flakes with varying number of layers under the influence of the alternating magnetic field. This preliminary exploration suggests the feasibility of integrating eddy current separation technology into the graphene purification process, offering insights to guide future experimental research in this field. © 2024, The Authors. All rights reserved.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on 3-DoF Motion Control of Unmanned Water-powered Aerial Vehicle Using Nozzle Rotation Mechanism

Experimental Study on 3-DoF Motion Control of Unmanned Water...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Cao-Tri Dinh Thien-Dinh Nguyen Thinh Huynh Dong-Hun Lee Yong-Woon Choi Young-Bok Kim Department of Intelligent Robot Engineering Pukyong National University Busan Korea Department of Smart Mobility Engineering Pukyong National University Busan Korea Department of Information System Science Faculty of Engineering Soka University Tokyo Japan

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

Specialized missions around water bodies, such as firefighting, rescue, and exploration, always pose a challenge to operators with low visibility, dense smoke, and extreme temperatures. To minimize the potential risks that may affect the operator, this paper proposed an unmanned water-powered aerial vehicle using a nozzle rotation mechanism. This mechanism allows the vehicle to have a wide range of forces and torques in multiple directions under constant mass flowrate condition. In the control system design, a robust controller is designed to regulate the altitude, roll, and pitch motions of the vehicle. In detail, to come up with the control law, the following steps are taken. Firstly, a mathematical model is derived to reflect the vehicle dynamics. Secondly, an integral sliding mode controller is applied to control the three-degree-of-freedom motion of the vehicle. Thirdly, experiments are conducted to confirm the effectiveness and feasibility of the controller and vehicle, respectively. Moreover, a well-known proportional-derivative-integral controller is applied to compare with the proposed control system. The results demonstrate that the vehicle could fly following the desired altitude in the presence of external disturbances.

关键词： Automation 3-DOF Control systems Mathematical models Trajectory Vehicle dynamics Motion control

来源：评论

学校读者我要写书评

暂无评论

The Network of Attention-Aware Multimodal fusion for RGB-D Indoor Semantic Segmentation Method

The Network of Attention-Aware Multimodal fusion for RGB-D I...

引用

Chinese Control and Decision Conference, CCDC

作者： Qiankun Zhao Yingcai Wan Lijin Fang Huaizhen Wang Faculty of Robot Science and Engineering Northeastern University Shenyang China Inspur Group Institute of Shandong New Generation Information Industry Technology Jinan China

ISBN: (纸本)9781665478977

In recent years, convolutional neural networks have effectively improved the accuracy of semantic segmentation tasks. However, semantic segmentation of indoor scenes is still a challenging problem due to the complexity of indoor environments. With the advent of depth sensors, the use of depth information to improve semantic segmentation has been considered. Most of the previous studies simply use equal-weight stitching or summation operations to fuse RGB features and depth features, failing to make full use of the complementary information between RGB features and depth features. In this paper, we propose the network of attention-aware multimodal fusion for RGB-D indoor semantic segmentation method. By designing an attention-aware multimodal fusion module, the multilevel RGB features and depth features are effectively fused. The cross-modal attention mechanism is also introduced in the multimodal fusion module, and the features are fused at different scales so that RGB features and depth features can guide and optimize each other using complementary information, thus extracting feature representations rich in spatial location information. The method can effectively promote the synergistic interaction of multimodal features and further improve the effect of semantic segmentation. Experimental results on publicly available datasets SUN RGB-D, NYU Depth v2 and ScanNet show that our designed algorithm outperforms other RGB-D image semantic segmentation algorithms.

关键词： Training Semantic segmentation Feature extraction Multitasking Sensors Indoor environment Data mining

来源：评论

学校读者我要写书评

暂无评论

Advancements in cheating detection algorithms in FPS games

Advancements in cheating detection algorithms in FPS games

引用

2024 International Conference on Computer Application and Information Security, ICCAIS 2024

作者： Xu, Ziwen Yu, Ruotong Liang, Yan Chen, Zihan Wan, Ye School of Computer Science and Technology Tongji University Shanghai201804 China Faculty of Science and Technology Beijing Normal University-Hong Kong Baptist University United International College Guangdong Zhuhai519087 China Luddy School of Informatics Computing and Engineering Indiana University of Bloomington Indiana BloomingtonIN47405 United States Guangdong Guangya High School Guangdong Guangzhou510000 China School of Computer Science and Technology Northeastern University Hebei Qinhuangdao066000 China

ISBN: (纸本)9781510689312

Over the past two decades, the increasing variety of cheating techniques in FPS games has led to the development of cheating detection algorithms. This literature review provides a chronological review of advancements in cheating detection techniques. Early methods, such as avatar trajectory-based detection, focused on behavioral analysis and identified bots by analyzing movement patterns. A remote anomaly-based system called Fides was presented to detect client-side manipulations with client-server architectures. With the emergence of machine learning, a variety of supervised learning methods have been introduced into the field of game detection to achieve real-time detection. More recent studies have been more innovative. Traps like the "bait-target" technique were introduced to detect cheating mechanisms that mimic human behavior. Methods combining deep learning and computer vision were proposed to detect complex cheating based on visual images. Overall, this review shows the diversity of cheat detection algorithms that have evolved to maintain the fairness of competitive gaming environments. © The Authors.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Linear Active Disturbance Rejection Anti-Backlash Control for Dual-Motor Coaxial Driving robotic Joint

Linear Active Disturbance Rejection Anti-Backlash Control fo...

引用

Chinese Control and Decision Conference, CCDC

作者： Jiqian Xu Lijin Fang Qiankun Zhao Huaizhen Wang Faculty of Robot Science and Engineering Northeastern University Shenyang China Inspur Group Institute of Shandong New Generation Information Industry Technology Jinan China

ISBN: (纸本)9781665478977

This paper describes a linear active disturbance rejection anti-backlash controller for a dual-motor coaxial driving robotic joint. This type of robotic joint is an over-actuated system that dual motors collaboratively drive load each axis. Firstly, a dual-motor driving model is built considering backlash and then a simplified control-orient model is proposed based on the principle of dual-motor anti-backlash strategy. Secondly, a linear active disturbance rejection control-based dual-motor position tracking framework is developed in accordance with the control-orient model. Finally, in order to deal with backlash coupling with unknown external torque, an admittance control-based adaptive position compensator is proposed. Unlike other control strategies, it practically achieves high tracking performance without requiring any backlash and external torque information. The effectiveness and simplicity of proposed control strategy is verified through comparative experiments.

关键词： Robust control Couplings Adaptation models Torque Admittance Transient analysis robots

来源：评论

学校读者我要写书评

暂无评论

Two-stage Cascaded Network With Deep Supervision And Residual Attention For Brain Tumor Segmentation

Two-stage Cascaded Network With Deep Supervision And Residua...

引用

第33届中国控制与决策会议

作者： Bingbing Li Jianning Chi Chengdong Wu Xiaosheng Yu College of Information Science and Engineering Northeastern University College of Robot Science and Engineering Northeastern University

Accurate segmentation of brain tumor has important research value and significance for tumor growth evaluation and *** this paper,we propose a novel two-stage cascaded network based on ResUNet,which is used to segment brain tumors and their substructures to solve the class imbalance problem in brain tumor *** tumor segmentation includes the following two *** the first stage,we use a variant of U-Net with deep supervision to segment the whole tumor structure and construct a tumor mask for more tumor boundary *** the second stage,we design a deep residual network which combines context extractor and attention mechanism to segment tumor substructure,aiming to focus on small target *** them,the tumor mask of the first network is multiplied with the multimodal images as the input of the second *** whole network is trained in an end-to-end *** proposed method is evaluated on the BraTS 2018 training dataset and achieve competitive performance compared with the state-of-the-art *** results of mean dice are 0.8813,0.8056 and 0.7366 for the whole tumor,tumor core and enhancing tumor respectively.

关键词： Brain tumor segmentation Cascaded network Deep supervision Residual attention

来源：评论

学校读者我要写书评

暂无评论

Multi-Receptive-Fields Convolutional Network for Remote Sensing Images Super-Resolution

Multi-Receptive-Fields Convolutional Network for Remote Sens...

引用

第33届中国控制与决策会议

作者： Huan Wang Qian Hu Jianning Chi Chengdong Wu Xiaosheng Yu College of Robot Science and Engineering Northeastern University College of Information Science and Engineering Northeastern University

Recently,single image super-resolution(SISR) has been widely applied in the field of remote sensing image processing and obtained remarkable performance,focusing on restoring the high-resolution(HR) image from a lowresolution(LR) ***,we observe that the existing CNN-based SISR methods mainly focus on wider or deeper architecture design,neglecting to exploit features at global receptive ***,the LR inputs and features contain abundant low-frequency information,which are perceived equally in the same receptive field,hence limiting the representational ability of *** solve these problems,we propose a Multi-Receptive-Fields Super Resolution Network(MRFSR) for remote sensing image *** proposed network employs non-local neural network to enhance low-level complex features by expanding the receptive field of the shallow convolution ***,we propose the multi-branch up-and down-sampling modules to deal with LR features in multiple receptive fields,which can enhance the high-frequency components and learn abstract feature representations in multiple scales,*** experiments on NPU-RESISC45 dataset shows that the proposed MRFSR can provide state-of-the-art or even better performance in both quantitative and qualitative measurements.

关键词： Deep Learning Convolutional Neural Network Super Resolution Remote Sensing Image

来源：评论

学校读者我要写书评

暂无评论

Human Pose Estimation Based Pre-training Model and Efficient High-Resolution Representation

Human Pose Estimation Based Pre-training Model and Efficient...

引用

第40届中国控制会议

作者： Jinchen Wen Jianning Chi Chengdong Wu Xiaosheng Yu College of Information Science and Engineering Northeastern University College of Robot Science and Engineering Northeastern University

With the continuous development of computer vision technology,deep learning technology has been well applied in human pose ***,the latest human pose estimation algorithms can not solve the problem of interdependence and occlusion between joints,so the key point detection in human pose estimation is still a challenging *** this paper,a method based on masked pre-training model and lightweight SHNet combined method,random occlusion is performed on the key points of the human body in the picture,and the pre-training model is used to predict them,so that the problems of mutual occlusion and interdependence can be *** show that the algorithm is effective in key point detection of MPII and COCO 2017 datasets.

关键词： Pose Estimation High-Resolution Representation Pre-training Model

来源：评论

学校读者我要写书评

暂无评论

Enhanced Class-weighted CNN features for CBIR

Enhanced Class-weighted CNN features for CBIR

引用

第33届中国控制与决策会议

作者： Dongliang Ma Chendong Wu Jianning Chi Xiaosheng Yu College of Information Science and Engineering Northeastern University College of Robot Science and Engineering Northeastern University

Content-based Image Retrieval in realistic senarios aims to rank in large dynamic datasets,which has great significance in computer *** extracted from convolutional neural network(CNN) are often affected by the background and noise in image when using class activation map *** order to solve this problem,we propose enhanced class-weighted CNN features based on saliency map and classification results *** saliency map with largest component area algorithm,ROI of an image can be cropped,which would make the classification more *** evaluated our proposed method on Oxford5 k and Paris6 k dataset,and get 0.809 and 0.861 mAP *** results show that our algorithm can effectively improve the mAP of image retrieval.

关键词： CBIR Deep learning Convolutional neural network Saliency map

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：