检索结果-内蒙古大学图书馆

2024 International Conference on Intelligent Systems and robotics, CISR 2024

作者： Dong, Zhixin Wu, Chengdong Zhang, Xiangyue Yu, Xiaosheng Li, Junlin Faculty of Robotics Science and Engineering Northeastern University Shenyang110167 China

In the field of computer vision, recognizing expressions in 2D static facial images is a crucial aspect of facial emotion recognition (FER), with broad applications in real-world scenarios such as mental health diagnosis and security monitoring. Despite the various convolutional neural network (CNN) architectures proposed for FER, there is still a lack of systematic comparative studies on the classification capabilities of different CNN architectures. In this paper, we systematically compare the classification performance of four commonly used CNN architectures in FER research for 2D static facial expression recognition on the classic FER2013 dataset. Through experiments, we evaluate the classification accuracy of these architectures and analyze the recognition results for different emotion categories. © Published under licence by IOP Publishing Ltd.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Functional ternary salt construction enabling an in-situ Li3N/LiF-enriched interface for ultra-stable all-solid-state lithium metal batteries

引用

Journal of Energy Chemistry 2025年第2期101卷 68-75,I0003页

作者： Hong-Yan Liu Xin-Yu Liu Nan Zhang Peng-Fei Wang Zong-Lin Liu Jie Shu Ting-Feng Yi School of Materials Science and Engineering Northeastern UniversityShenyang 110819LiaoningChina Key Laboratory of Dielectric and Electrolyte Functional Material Hebei Province School of Resources and MaterialsNortheastern University at QinhuangdaoQinhuangdao 066004HebeiChina Faculty of Materials Science and Chemical Engineering and Key Laboratory of Photoelectric Detection Materials and Devices of Zhejiang Province Ningbo UniversityNingbo 315211ZhejiangChina

Poly(ethylene oxide)-based polymer all-solid-state lithium metal batteries(ASSLBs)have received widespread attention due to their low cost,good process ability,and high energy ***,the growth of Li dendrites within polymer solid-state electrolytes damages the reversibility of Li anodes and still impedes their widespread *** efficient strategy is to construct a superior solid electrolyte ***,a stable interface enriched with Li3N and LiF is in-situ formed between Li anode and a terna ry salt *** terna ry salt electrolyte is innovatively designed by introducing lithium bis(trifluoromethane sulfonyl)imide(LiTFSI),lithium bis(fluorosulfonyl)imide(LiFSI),and LiNO_(3)to poly(ethylene oxide)*** characterization indicates that LiNO3and LiFSI contribute to forming a Li3N-LiF-enriched interface and meanwhile LiTFSI ensures excellent ***,among various Li compound components,Li3N has high ionic conductivity,which is beneficial for reducing overpotential,while LiF has high interfacial energy which can enhance nucleation energy and suppress the formation of Li *** experimental results show that ASSLBs coupled with LiFePO4cathode display extremely excellent cycle stability approximately 2200 cycles at 2 C,with a final and corresponding discharge specific capacity of 96.7 mA h g^(-1).Additionally,a schematic illustration of the working mechanism for the Li_(3)N-LiF interface is proposed.

关键词： Solid electrolyte All-solid-state lithium metal batteries PEO(LiTFSI) In-situ SEI Lithium dendrite

来源：评论

学校读者我要写书评

暂无评论

EEG Emotion Recognition of Different Brain Regions Based on 2DCNN-DGRU 13

EEG Emotion Recognition of Different Brain Regions Based on ...

引用

13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023

作者： Qu, Gangguo Wen, Shiguang Bi, Jinying Liu, Jing Wu, Qi Han, Lu Wang, Fei College of Information Science and Engineering Northeastern University Shenyang110169 China Northeastern University Faculty of Robot Science and Engineering Shenyang110169 China LiaoNing Disabled Persons' Service Center Shenyang China

ISBN: (纸本)9798350315196

In order to explore the differences in the activation of brain regions under emotional stimuli, and the best effect of emotion recognition under the combination of different brain regions, this paper divides the electrode channels into four different regions: Frontal lobe (Fron), Temporal lobe (Temp), Parietal lobe (Pari) and Occipital lobe (Occi), and Combine them into 9 schemes for further exploration. The differential entropy feature (DE) extracted on the emotion datasets SEED and DEAP is used as the input of the model, and the emotion categories are defined as positive, neutral, and negative. Secondly, in order to evaluate the effect of emotion recognition in brain regions, we propose a hybrid deep model - 2DCNN-DGRU. In the end, an average accuracy rate of 97.74% and 92.18% was obtained for the Whole brain region, respectively. In terms of single brain region, the Temp was the most critical, with an average accuracy rate of 94.99% and 80.16%. In the combination of the three brain regions Fron-Temp-Occi, the highest accuracy rate of 98.40% was achieved, surpassing that of the Whole brain region. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

H∞ Output Anti-Bump Control for Switched Linear Systems

H∞ Output Anti-Bump Control for Switched Linear Systems

引用

2023 International Annual Conference on Complex Systems and Intelligent science, CSIS-IAC 2023

作者： Li, Jinghan Liu, Yan Ma, Ruicheng Northeastern University College of Information Science and Engineering Shenyang110819 China Northeastern University Faculty of Robot Science and Engineering Shenyang110819 China Liaoning University School of Mathematics and Statistics Shenyang110036 China

ISBN: (纸本)9798350309003

This paper focuses on the H∞ output anti-bump control problem for a class of switched linear systems. There exist bumps of the output signal for the switched systems at the switching instants. A novel description of the output anti-bump performance for the system is provided, which can suppress the bumps of the output. The developed strategy ensures the H∞ control of the switched system while possesses output anti-bump performance. Moreover, the switching controller and a switching law are designed to solve the H∞ output anti-bump control problem. An example is provided to show the validation of the proposed method. © 2023 IEEE.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

State-of-the-art Research in Perception and Control of Lower Limb Exoskeletons: A Systematic Review 3

State-of-the-art Research in Perception and Control of Lower...

引用

3rd International Conference on Service robotics, ICoSR 2024

作者： Luo, Xiaofeng Ma, Yang Cai, Zhibin Zhou, Tianqi Liu, Xiaoyu Long, Yi Weapon Equipment Research Institute China Ordnance Industries Group Beijing China School of Mechanical Engineering and Automation Northeastern University Shenyang China Northeastern University Faculty of Robot Science and Engineering Shenyang China Foshan Graduate School of Innovation Northeastern University Foshan China

ISBN: (纸本)9798350367119

The lower limb exoskeleton is an intelligent robot worn by the human body and moves in coordination with the human limbs. It can enhance the human body's weight-bearing capacity, maneuverability and operation capabilities. Perception and control, as the brain of the exoskeleton robot, directly determine its collaborative performance and auxiliary effect with the main body. However, the current lower limb exoskeleton has not been widely adopted. One of the reasons is that the 'brain' of the exoskeleton robot is not intelligent enough. Therefore, this article reviewed relevant literature on lower limb exoskeleton sensing and control technology in the past five years, and studied the impact of different sensing methods and control strategies on exoskeleton performance. In addition, this article discusses the current challenges of lower limb exoskeletons and provides some innovative insights into future research directions to promote the further development of lower limb exoskeleton technology. © 2024 IEEE.

关键词： Exoskeleton (robotics)

来源：评论

学校读者我要写书评

暂无评论

SGT-Net: A Transformer-Based Stratified Graph Convolutional Network for 3D Point Cloud Semantic Segmentation

引用

Computers, Materials & Continua 2024年第6期79卷 4471-4489页

作者： Suyi Liu Jianning Chi Chengdong Wu Fang Xu Xiaosheng Yu Faculty of Robot Science and Engineering Northeastern UniversityShenyang110167China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang110169China SIASUN Robot&Automation Co. Ltd.Shenyang110169China

In recent years,semantic segmentation on 3D point cloud data has attracted much *** 2D images where pixels distribute regularly in the image domain,3D point clouds in non-Euclidean space are irregular and inherently ***,it is very difficult to extract long-range contexts and effectively aggregate local features for semantic segmentation in 3D point cloud *** current methods either focus on local feature aggregation or long-range context dependency,but fail to directly establish a global-local feature extractor to complete the point cloud semantic segmentation *** this paper,we propose a Transformer-based stratified graph convolutional network(SGT-Net),which enlarges the effective receptive field and builds direct long-range ***,we first propose a novel dense-sparse sampling strategy that provides dense local vertices and sparse long-distance vertices for subsequent graph convolutional network(GCN).Secondly,we propose a multi-key self-attention mechanism based on the Transformer to further weight augmentation for crucial neighboring relationships and enlarge the effective receptive *** addition,to further improve the efficiency of the network,we propose a similarity measurement module to determine whether the neighborhood near the center point is *** demonstrate the validity and superiority of our method on the S3DIS and ShapeNet *** ablation experiments and segmentation visualization,we verify that the SGT model can improve the performance of the point cloud semantic segmentation.

关键词： 3D point cloud semantic segmentation long-range contexts global-local feature graph convolutional network dense-sparse sampling strategy

来源：评论

学校读者我要写书评

暂无评论

Semantic Range Image for Loop Closure of 3D Lidar SLAM 13

Semantic Range Image for Loop Closure of 3D Lidar SLAM

引用

13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023

作者： Li, Fang Shen, Yehui Zou, Fengshan Du, Zhenjun Liu, Mingmin Northeastern University Faculty of Robot Science and Engineering Liaoning Shenyang110169 China SIASUN Robot & Automation Co. Ltd Liaoning Shenyang110168 China

ISBN: (纸本)9798350315196

The purpose of SLAM loop closure detection is to reduce the cumulative error in the system by identifying the same scene that the robot passed through. Traditional loop detection methods detect loops based on physical information. These methods use basic physical features to identify loop closures and pay less attention to the role of semantic information as high-level information in loop closure detection. This paper regards semantic information as one of the criteria for confirming loop closure, so that semantic information can be deeply involved in the process of loop closure detection. We construct a global descriptor based on range image and semantic information, which is called SeRI. The descriptor encodes the semantic and geometric features of the surrounding environment. Loop closure candidates are determined by matching between pairs of semantic range images. We evaluate our method on the KITTI dataset. Experiments have shown that the proposed method can effectively identify loop closure candidates correctly with high precision and recall rate. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning of robot End-Effector Position and Orientation Based on Cubic Spline 5

Trajectory Planning of Robot End-Effector Position and Orien...

引用

5th World robot Conference Symposium on Advanced robotics and Automation, WRC SARA 2023

作者： Liu, Yang Du, Zhenjun Liu, Mingmin Tao, Yongliang Li, Chenpeng Northeastern University Faculty of Robot Science and Engineering Liaoning Shenyang110169 China Siasun Robot & Automation Co. Ltd Liaoning Shenyang110168 China

ISBN: (纸本)9798350307320

Trajectory planning for the end effector of industrial robots has been a hot topic in the field of robotics. A continuous and smooth trajectory of the end effector's pose is beneficial for avoiding unnecessary impacts and vibrations, thereby improving the performance and lifespan of industrial robots. In recent years, researchers have predominantly focused on the trajectory planning of multi-directional variations in orientation using quaternions, while giving less attention to the coordinated planning of position and orientation. To address this issue, this paper proposes an efficient trajectory planning method based on improved spline curve interpolation. The orientation of key pose points, characterized by multi-directional variations, is represented using quaternions. By employing a quaternion dimension reduction algorithm, these quaternions are transformed into vector forms in three-dimensional space, allowing for unified representation of position and orientation within the same dimension. Taking the chord length between key pose points as a parameter, the position and orientation components are subjected to cubic spline curve interpolation with chord length as the independent variable. The proposed method is applicable for coordinated planning of position and orientation trajectories, ensuring high-order continuity of the pose trajectory. The effectiveness and rationality of the proposed method are validated through a set of key pose points featuring multi-directional variations. Finally, a comparative analysis is conducted between this set of key pose points and existing trajectory planning algorithms. Experimental results demonstrate that the proposed method not only guarantees high-order continuity of the trajectory but also exhibits higher smoothness. © 2023 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

CAO-RONet: A Robust 4D Radar Odometry with Exploring More Information from Low-Quality Points

arXiv

引用

arXiv 2025年

作者： Li, Zhiheng Cui, Yubo Huang, Ningyuan Pang, Chenglin Fang, Zheng Faculty of Robot Science and Engineering Northeastern University Shenyang China

Recently, 4D millimetre-wave radar exhibits more stable perception ability than LiDAR and camera under adverse conditions (e.g. rain and fog). However, low-quality radar points hinder its application, especially the odometry task that requires a dense and accurate matching. To fully explore the potential of 4D radar, we introduce a learning-based odometry framework, enabling robust ego-motion estimation from finite and uncertain geometry information. First, for sparse radar points, we propose a local completion to supplement missing structures and provide denser guideline for aligning two frames. Then, a context-aware association with a hierarchical structure flexibly matches points of different scales aided by feature similarity, and improves local matching consistency through correlation balancing. Finally, we present a window-based optimizer that uses historical priors to establish a coupling state estimation and correct errors of inter-frame matching. The superiority of our algorithm is confirmed on View-of-Delft dataset, achieving around a 50% performance improvement over previous approaches and delivering accuracy on par with LiDAR odometry. Our code will be available. Copyright © 2025, The Authors. All rights reserved.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Improving 3D Human Pose Estimation with Enhanced Body Feature Representation

Improving 3D Human Pose Estimation with Enhanced Body Featur...

引用

Advanced Algorithms and Control engineering (ICAACE), International Conference on

作者： Shidong Zhao Chengdong Wu Xiangyue Zhang Faculty of Robot Science and Engineering Northeastern University Liaoning China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

Transformer-based methods have shown promising performance in 2D-to-3D human pose estimation. However, existing approaches often ignore the relationships between specific joints of the human body and the varying motion patterns across different body parts. This paper first introduces the Spatial Transformer Based on Human Anatomy module to enhance the spatial features of the human body. Additionally, a Cross-Joint Split and Recombination training strategy is designed within the temporal attention module to learn the motion patterns across different body parts. Finally, a Residual Gated Channel Transformation is introduced to foster collaboration and interaction between features. Experimental results on two benchmark datasets show that our algorithm effectively improves model performance with only a slight increase in computational cost.

关键词： Training Limbs Three-dimensional displays Human anatomy Control engineering Computational modeling Pose estimation Logic gates Transformers Skeleton

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：