检索结果-内蒙古大学图书馆

Beyond Point Annotation: A Weakly Supervised Network Guided by Multi-Level Labels Generated from Four-Point Annotation for Thyroid Nodule Segmentation in Ultrasound Image

arXiv

引用

arXiv 2024年

作者： Chi, Jianning Li, Zelan Wu, Huixuan Zhang, Wenjun Huang, Ying Faculty of Robot Science and Engineering Northeastern University Shenyang China Division of Biomedical Engineering University of Saskatchewan Saskatoon Canada Department of Ultrasound Shengjing Hospital of China Medical University Shenyang China

Weakly-supervised methods typically guided the pixel-wise training by comparing the predictions to single-level labels containing diverse segmentation-related information at once, but struggled to represent delicate feature differences between nodule and background regions and confused incorrect information, resulting in underfitting or overfitting in the segmentation predictions. In this work, we propose a weaklysupervised network that generates multi-level labels from fourpoint annotation to refine diverse constraints for delicate nodule segmentation. The Distance-Similarity Fusion Prior referring to the points annotations filters out information irrelevant to nodules. The bounding box and pure foreground/background labels, generated from the point annotation, guarantee the rationality of the prediction in the arrangement of target localization and the spatial distribution of target/background regions, respectively. Our proposed network outperforms existing weakly-supervised methods on two public datasets with respect to the accuracy and robustness, improving the applicability of deep-learning based segmentation in the clinical practice of thyroid nodule diagnosis. Index Terms-Medical image processing, ultrasound nodule segmentation, weakly supervision segmentation, deep learning. © 2024, CC BY-NC-SA.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Multi-object Grasping Detection in Cluttered Scenes Based on Deep Learning 11

Multi-object Grasping Detection in Cluttered Scenes Based on...

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2021

作者： Wu, Xiangrui Xu, Fang Du, Zhenjun Song, Jilai Liu, Mingmin Liu, Hongyan Du, Kun Guo, Mingce Northeastern University Faculty of Robot Science and Engineering Shenyang110169 China SIASUN Robot Automation Co. Ltd Shenyang110168 China

ISBN: (纸本)9781665425278

In this paper, we mainly improved the grasp detection network based on the grasp pose detection (GPD) algorithm. Three Network in Network (NIN) structure blocks are used as feature extraction modules, and a fully connected layer is used for classification. And trained the network on our own dataset which these 3D models are all from GraspNetAPI, and the accuracy rate on the test set is 2% higher than the original network. And the amount of its parameters has dropped by 38%. In addition, we combine the Mask R-CNN semantic segmentation network to perform target detection and pixel-level instance segmentation on target objects, which can grasp objects of interest. Finally, we carried out grasping experiments on real robots, and the total grasping success rate was over 70%. © 2021 IEEE.

关键词： Semantics

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

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

引用

Service robotics (ICoSR), International Conference on

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

ISBN: (数字)9798350367119

ISBN: (纸本)9798350367126

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.

关键词： Mechanical sensors Limbs robot kinematics Exoskeletons Collaboration robot sensing systems Sensor systems Pattern recognition Complexity theory Biosensors

来源：评论

学校读者我要写书评

暂无评论

PARE: A Plane-Assisted Autonomous robot Exploration Framework in Unknown and Uneven Terrain

PARE: A Plane-Assisted Autonomous Robot Exploration Framewor...

引用

IEEE/RSJ International Conference on Intelligent robots and Systems (IROS)

作者： Pu Xu Zhaoqiang Bai Haoming Liu Zheng Fang Faculty of Robot Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Northeastern University Shenyang China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Identifying traversable areas is a critical task for unmanned vehicles exploring safely through unstructured environments. In practice, the ambiguity in perceiving terrain traversability usually brings great challenges for autonomous exploration in unknown and uneven terrain, which often leads to conservative strategies or potential risk of vehicle damage, resulting in many unexplored areas in the environment. To that end, this paper proposes a plane-assisted autonomous robot exploration framework (PARE) to achieve maximum volume and safe autonomous exploration. The process is carried out by a three-step dual-layer framework: constructing a local tree using Plane-Assisted RRT* (PA-RRT*), calculating exploration gain based on terrain information, and maintaining a global search graph. Firstly, the planar feature metrics (flatness, sparsity, elevation variation, slope and slope variation) are introduced to determine the terrain traversability. Secondly, to completely explore the rugged environment, we propose a dual-layer exploration framework comprising local and global strategies. A local planner based on PA-RRT* is proposed to find the best path by evaluating the planar information and the volumetric gain within the local exploration tree. Meanwhile, a global planner constructed by graph is proposed to record unexplored nodes with high exploration gain from the local tree to ensure a high level of exploration volume. Extensive simulation and real-world experiments demonstrate that our method significantly outperforms existing frameworks, with an average improvement of more than 12% in exploration volume.

关键词： Measurement Intelligent robots Autonomous vehicles Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

A method of relay UAV deployment for emergency communication scenarios in disaster areas

A method of relay UAV deployment for emergency communication...

引用

2024 China Automation Congress, CAC 2024

作者： Tao, Cancan Liu, Bowen Han, Yi Chen, Qiangqiang Ye, Jun Zhong, Ronglin School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Parallel Robot and Mechatronic System Laboratory of Hebei Province Yanshan University Qinhuangdao066004 China Faculty of Science Kunming University of Science and Technology Kunming650500 China School of Biological Science and Medical Engineering Beihang University Beijing100191 China School of Information Science and Technology University of Science and Technology of China Hefei230026 China

ISBN: (纸本)9798350368604

This article proposes a relay deployment method that uses UAVs to provide communication services to ground users, especially for emergency communication scenarios in disaster ***, a two-layer network communication model is constructed for emergency communication scenarios in disaster areas, and the relay deployment problem is transformed into a multi-objective optimization problem. On this basis, a detailed analysis of the problem is conducted, and a UAV relay deployment method based on the K-means++ algorithm is proposed. The two indicators of the number of UAVs used and the network communication performance are considered in solving the problem. Simulation results show that the proposed method can achieve a balance between the number of relay UAVs used and the achieved network performance. © 2024 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Research on the Adaptive Control Method of Quadrotor Based on Neural Network

Research on the Adaptive Control Method of Quadrotor Based o...

引用

Smart City Challenges & Outcomes for Urban Transformation (SCOUT)

作者： Xiangzhongyu Ji Haiyan Zhang Boyang Zhang Jingyu Ru Department of Mechanical and Aerospace Engineering The Hong Kong University of Science and Technology Hong Kong SAR China Faculty of Robot Science and Engineering Northeastern University Shenyang China

At present, the more widely used and mature neural network is Back Propagation (BP) neural network, which is a typical feed-forward network in artificial neural network, especially suitable for dealing with system nonlinearity, uncertainty and the identification function of approximating system or structural characteristics. Neural network-based control methods are widely used in various intelligent control systems and have a very broad development prospect. The application of neural networks in aerospace vehicles can effectively control their stability, anti-interference and convergence speed. The system performance is better adapted to different scenarios and the control accuracy is continuously improved. Therefore, this paper proposes a neural network-based adaptive control method for quadcopter, and the design of neural network-based adaptive control system is carried out based on the elaboration of neural network related theories. After simulation experiments, it is confirmed that the design in this paper has good tracking performance and small tracking error. And the application effect is good.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Operational Optimization Method for robotic Mobile Fulfillment Systems with Inventory Discrepancy Events

A Dynamic Operational Optimization Method for Robotic Mobile...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Huai Ma Ziyan Zhao Jiaqi Liang Xingyang Li Shixin Liu Department of Information Science and Engineering Northeastern University Shenyang China College of Information Science and Engineering Northeastern University Shenyang China Foshan Graduate School of Innovation Northeastern University Foshan China Département de mathématiques et génie industriel Polytechnique Montréal Montréal Canada Faculty of Robot Science and Engineering Northeastern University Shenyang China School of Control Engineering Northeastern University at Qinhuangdao Qinhuang-dao Hebei China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

A robotic Mobile Fulfillment System (RMFS) is an emerging “cargos-to-person” picking system that relies on the broom of Internet of Things (IoT) technology. It aims to offer significant enhancements in order picking efficiency. However, dynamic disturbances, such as inventory discrepancies arising from errors in receiving, shipping, and handling of goods, often disrupt its operations, leading to degraded service and increased operational costs, thereby affecting overall system performance. Traditional optimization solutions may necessitate adaptations or overhauls in response to such disturbances. This paper introduces a proactive multi-pathway response algorithm tailored to mitigating dynamic disturbances in RMFS, particularly concerning inventory discrepancies. We extend an open-source simulation framework to evaluate the performance of the proposed algorithm and conduct a comparative analysis of dynamic systems. Experimental results indicate that our proposed algorithm can effectively improve the processing efficiency of abnormal orders with the minimal system-wide impact, highlighting its potential to well address dynamic and abnormal events in smart warehouses.

关键词： Costs Heuristic algorithms System performance Optimization methods Dynamic scheduling Internet of Things Dynamical systems robots Cybernetics

来源：评论

学校读者我要写书评

暂无评论

An Asynchronous SSVEP-BCI for Intelligent Rehabilitation Exoskeleton Based on Alpha Rhythm-Detected CCA

An Asynchronous SSVEP-BCI for Intelligent Rehabilitation Exo...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Jintao Sun Shiguang Wen Yongzhao Wen Jing Liu Qi Wu Lu Han Fei Wang College of Information Science and Engineering Northeastern University Shenyang Liaoning China Faculty of Robot Science and Engineering Northeastern University Shenyang Liaoning China LiaoNing Disabled Persons' Service Center Shenyang Liaoning China

Although great progress has been made in the research on rehabilitation exoskeletons based on steady-state visually evoked potential (SSVEP)-based brain-computer interface (BCI), some factors that limit the practical applications of rehabilitation exoskeletons based on BCIs still exist. On the one hand, traditional SSVEP-BCI uses the computer screen (CS) to generate visual stimuli, which leads to poor portability, on the other hand, most BCIs are in a synchronous mode, which prevents users from autonomously controlling the system. To overcome these two problems, augmented reality (AR) technology is introduced to generate the visual stimuli, and an asynchronous control method based on the blocking phenomenon of alpha waves is proposed in this study. The offline experiment is designed to determine the classification threshold of the idle state and control state and compare the different performances of SSVEP-BCI with and without an AR environment. Finally, an intelligent rehabilitation exoskeleton platform is used for online validation. Results of the online experiment indicate that all subjects could control the rehabilitation exoskeleton to complete the rehabilitation tasks, which indicates the applicability of the intelligent rehabilitation exoskeleton system and improves the potential for application of the rehabilitation exoskeleton based on BCI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Recognising Physical Activity Intensity in Adults: Gravity-Based Acceleration Imaging with Vision Transformer 22

A Novel Approach to Recognising Physical Activity Intensity ...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Wang, Lin Zhang, Tianle Wang, Miaomin Wang, Gang Chen, Guohao Li, Zhuhui University of Exeter Faculty of Health and Life Sciences Exeter United Kingdom University of Liverpool Liverpool United Kingdom University of Exeter Faculty of Environment Science and Economy Exeter United Kingdom School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9798331520526

Research on physical activity intensity (PAI) recognition often relies on tabular data, limiting the capture of global patterns compared to image-based data, while traditional models struggle with long-sequence dependencies. This study introduces a novel method that uses a gravity-based acceleration algorithm to generate images of different intensity levels, followed by classification with a Vision Transformer (ViT) model, aiming to enhance model performance and experimental efficiency. The method uses the Euclidean Norm Minus One to calculate gravity-based acceleration per second. Gramian Angular Field images are generated based on adult intensity thresholds and are subsequently classified using the ViT model. The results showed the ViT model's high performance in recognising different PAIs. Specifically, it demonstrated that using gravity-based images for recognising PAI improves accuracy compared to METs-based images (etabolic equivalents), achieving an overall accuracy of 98.77% compared to 97.52%. Additionally, this novel approach maintains high accuracy across different time windows, with accuracy ranging from 98.59% to 99.05%, further indicating the model's stability and robust performance across varying temporal windows. © 2025 IEEE.

关键词： Acceleration Activity intensity Free-living Sensor Transformer recognising

来源：评论

学校读者我要写书评

暂无评论

Twin-Motor Servo Drive Control Based on RL and Perturbation Observer

Twin-Motor Servo Drive Control Based on RL and Perturbation ...

引用

Asian Control Conference

作者： Peng Xu Yaoming Zhuang Chengdong Wu Fengkui Cao Faculty of Robot Science and Engineering Northeastern University Shenyang China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

To perform a desired control task in the absence of system dynamics or with relatively limited knowledge of the system dynamics, we design a controller for uncertain nonlinear two-motor servo systems based on reinforcement learning (RL) and linear matrix inequality (LMI). The controller is an RL optimal coordination controller, which is capable of tracking the target well by generating the control strategy Using output regulation theory and evaluating the cost of execution using a Critique Neural Network. The controller employs an improved composite control of non-singular fast terminal sliding mode control and perturbation observer compensation techniques. Based on the modeling of the system tracking target, a disturbance observer is designed using LMI theory and embedded into the radial basis function neural network controller. This control strategy achieves optimal tracking by recording state information. Finally, the simulation outcomes, along with experimental validation, affirm the efficacy of the suggested control approach in enhancing the tracking capabilities of the dual-motor system.

关键词： Target tracking Uncertainty System dynamics Perturbation methods Reinforcement learning Drives Disturbance observers

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：