检索结果-内蒙古大学图书馆

IEEE International Conference on Cyber technology in Automation, Control, and intelligent systems

作者： Siang Xu Xiangyu Wang Yanding Qin Hongpeng Wang Ningbo Yu Jianda Han Institute of Robotics and Automatic Information System Nankai University Tianjin China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen China

ISBN: (数字)9798331506056

ISBN: (纸本)9798331506063

Limited by the complex porous structure of the bronchi, supervised segmentation of the bronchial orifice is difficult to perform. Since there is no gold standard for definition of the edges of bronchial orifices, manual labeling can lead to inconsistencies in calibration standards. This paper presents a self-supervised bronchial orifice segmentation method based on depth information and synthetic data. The method uses synthetic data and synthetic depth maps to train CNN and can be directly applied to real image data. We also propose an Attention Guidance Module that uses depth information to guide the neural network attention distribution. We manually segmented the bronchial orifice region as ground truth and counted the offset of the center point between the segmentation result and ground truth. The results show that the mIoU of the segmentation result is 79.52, the dice coefficient of the result is 0.86 which is better than 0.77 of the previous method, and the pixel deviation of the center point in a 128 × 128 image is 3.92 which is better than 4.35 of the previous method.

关键词： Bronchoscopy Image segmentation Neural networks Orifices Phantoms Manuals Respiratory system Robots Standards Synthetic data

来源：评论

学校读者我要写书评

暂无评论

High-compatibility Manipulation Method for Parallel In-situ Isolation of Microalgal Cells via Optoelectronic Tweezers

High-compatibility Manipulation Method for Parallel In-situ ...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Shilong Qin Jiaxin Liu Yuxin Chen Haotian Yang Ziyi Zhao Qing Shi Qiang Huang Huaping Wang Key Laboratory of Biomimetic Robots and Systems Beijing Institute of Technology Ministry of Education Beijing China School of Mechatronical Engineering Beijing Institute of Technology Intelligent Robotics Institute Beijing China School of Medical Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

Isolating microalgae in in-situ liquid environment based on optoelectronic tweezers (OETs) enables providing specific species of microalgae in high-purity, thus has significant potential in environmental detection, aquaculture, bioenergy, and biomedicine development. However, the conventional OET method can only separate and extract one type of microalgae in a single-step operation and is challenging to utilize the opposite dielectrophoretic force when the cross frequency of microalgae is too high /low or even absent. In this study, a novel automated microalgae isolation method based on optoelectronic tweezers is proposed, which integrates two strategies: cluster manipulation and discretized synchronous manipulation. Firstly, an optoelectronic tweezer robot platform was built, the dielectrophoretic forces on microalgae and the factors affecting the dielectrophoretic forces were analyzed. Secondly, a cluster manipulation strategy based on light patterns dynamic locomotion structure scheme was designed to simultaneously separate microalgae subject to dielectrophoretic forces of different attributes and the same attribute. Finally, a discretized synchronous manipulation strategy based on visual feedback and PID controller was designed to realize the precise isolation of microalgae subjected to the same dielectrophoretic force and different dielectrophoretic forces. Experimental results demonstrated that the aforementioned method provides a feasible microalgae isolating method based on optoelectronic tweezers within 10 minutes, which has potential applications in the in-situ water contamination detection and treatment.

关键词： Visualization Liquids Force Dynamics Water pollution Real-time systems Dielectrophoresis

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Based System Identification for Linear Time-Invariant systems

Data-Driven Based System Identification for Linear Time-Inva...

引用

2023 China Automation Congress, CAC 2023

作者： Yang, Shaobudao Fu, Anqi Qiao, Junfei Faculty of Information Technology Beijing University of Technology Beijing China Key Laboratory of Computational Intelligence and Intelligent Systems Beijing University of Technology Beijing China Beijing Laboratory of Smart Environmental Protection Beijing Artificial Intelligence Institute Beijing China

ISBN: (纸本)9798350303759

System identification is an important basis for understanding the behavior characteristics of unknown systems and for further optimization and control purposes. In this brief, we focus on the model identification for LTI systems using a finite set of sampled data and noise bounds. In order to precisely capture the dynamics of the unknown system, a 2-step approach is proposed. Imprimis, a set operation based on zonotope is applied to compute all the possible matrices that describe the system dynamics with an estimated noise set. The computed result is consistent with all data points and noise bound which is represented by matrix zonotope. Secondly, by solving a proposed optimization problem to find the fittest system dynamic matrix. The aim of the problem is to minimize the noise zonotope. The foregoing 2-step approach is capable of effectively approximating the actual systems. Numerical example demonstrates the validity of the proposed method. © 2023 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

RESIDUAL LIFE PREDICTION OF LITHIUM BATTERY BASED ON IMPROVED MULTI-OPTIMIZATION ALGORITHM AND SUPPORT VECTOR REGRESSION 14

RESIDUAL LIFE PREDICTION OF LITHIUM BATTERY BASED ON IMPROVE...

引用

14th International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, QR2MSE 2024

作者： Tao, Yulong Wang, Jun Wang, Kai School of Computer Science and Technology Shenyang University of Chemical Technology Shenyang China Key Laboratory of Intelligent Technology for Chemical Process Industry Liaoning Province Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Robotics and Artificial Intelligence Manufacturing Innovation Institute Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9781837242672

The lithium-ion battery is increasingly critical in the fields of electric vehicles and sustainable energy. Accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is essential to mitigate risks and minimize potential losses. This paper introduces a novel fusion algorithm, FPSOGWO, which combines Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) with an enhanced Circle chaos strategy and a random adaptive weighting strategy. The FPSOGWO algorithm, integrated with Support Vector Regression (FPSOGWO-SVR), was utilized to predict the RUL of health factors in lithium batteries. Compared to other optimization algorithms, FPSOGWO exhibits superior optimization speed and value, effectively overcoming issues of local optimality. Specifically, when benchmarked against the Whale Optimization Algorithm-SVR (WOA-SVR), the R-Square values of FPSOGWO-SVR showed improvements of 15.62%, 1.28%, 5.67%, and 10.65% across four different types of batteries. Experimental results demonstrate that FPSOGWO-SVR provides more accurate RUL predictions for lithium batteries, highlighting its potential for broader application in battery health management systems. © The Institution of Engineering & technology 2024.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

Using machine learning and satellite data from multiple sources to analyze mining,water management,and preservation of cultural heritage

引用

地球空间信息科学学报（英文版） 2024年第3期27卷 552-571页

作者： Joaquim J.Sousa Jiahui Lin Qun Wang Guang Liu Jinghui Fan Shibiao Bai Hongli Zhao Hongyu Pan Wenjing Wei Vanessa Rittlinger Peter Mayrhofer Ruth Sonnenschein Stefan Steger Luís Paulo Reis School of Science and Technology University of Trás-Os-Montes E Alto DouroVila RealPortugal Centre for Robotics in Industry and Intelligent Systems(CRIIS) INESC Technology and SciencePortoPortugal Aerospace Information Research Institute Chinese Academy of SciencesBeijingChina International Research Center of Big Data for Sustainable Development Goals BeijingChina College of Resources and Environment University of Chinese Academy of SciencesBeijingChina Application system Department Ⅰ China Siwei Surveying and Mapping Technology Co.LtdBeijingChina China Aero Geophysical Survey and Remote Sensing Center for Natural Resources BeijingChina College of Marine Science and Engineering Nanjing Normal UniversityNanjingChina Institute of Mountain Hazards and Environment Chinese Academy of SciencesChengduChina College of Marine Science and Engineering Nanjing Normal UniversityNanjingChina Institute for Earth Observation Eurac ResearchBolzanoItaly Faculty of Engineering University of PortoPortoPortugal

Remote sensing,particularly satellite-based,can play a valuable role in monitoring areas prone to *** high spatial and temporal coverage provided by satellite data can be used to reconstruct past events and continuously monitor sensitive areas for potential *** paper presents a range of techniques and methods that were applied for in-depth analysis and utilization of Earth observation data,with a particular emphasis on:(1)detecting mining sub-sidence,where a novel approach is proposed by combining an improved U-Net model and Interferometry Synthetic Aperture Radar(InSAR)*** results showed that the Efficient Channel Attention(ECA)U-Net model performed better than the U-Net(baseline)model in terms of Mean Intersection over Union(MIoU)and Intersection over Union(loU)indicators;(2)monitor-ing water conservancy and hydropower *** Xiaolangdi multipurpose dam complex was monitored using Small BAsline Subsets(SBAS)InSAR method on Sentinel-1 time series data and four small regions with high deformation rates were identified on the slope of the reservoir bank on the north *** dam body also showed obvious deformation with a velocity exceeding 60 mm/a;(3)the evaluation of the potential of InSAR results to integrate monitoring and warning systems for valuable heritage and architectural *** overall outcome of these methods showed that the use of Artificial Intelligence(AI)techniques in combination with InSAR data leads to more efficient analysis and interpretation,resulting in improved accuracy and prompt identification of potential hazards;and(4)finally,this study also presents a method for detecting landslides in mountainous regions,using optical *** new temporal landslide detection method is evaluated over a 7-year analysis period and unlike conventional bi-temporal change detection methods,this approach does not depend on any prior-knowledge and can potentially detect landslides over extended periods of time

关键词： Landslide detection InSAR time series analysis machine learning heritage preservation mining subsidence water conservancy infrastructures

来源：评论

学校读者我要写书评

暂无评论

Object Localization Based on a Single RGB Camera for a 4-DOF Robotic Arm

Object Localization Based on a Single RGB Camera for a 4-DOF...

引用

International Conference on Autonomous Robots and Agents, ICARA

作者： Elvira Chebotareva Adel Mukhamedshin Niyaz Imamov Evgeni Magid Institute of Information Technology and Intelligent Systems Kazan Federal University Kazan Russia Russia HSE University Moscow Russia

ISBN: (数字)9798331509231

ISBN: (纸本)9798331509248

This study presents a method for constructing metric depth maps based on relative depth maps for a 4-DOF manipulator with a single RGB camera, which is attached to an end effector. To create a relative depth map of a scene, we utilize the Depth Anything V2 model along with a system of twelve ArUco markers positioned at varying distances from one another. Unlike traditional methods for determining distances to objects using ArUco markers, the proposed approach does not require a continuous presence of markers within a camera's field of view; it only necessitates measuring a distance to a few markers in an initial frame. The proposed method enables the robot to perform object localization using a relative depth map concurrently with an object search process.

关键词： Location awareness Automation Depth measurement Robot vision systems Grasping Cameras Search problems End effectors Calibration

来源：评论

学校读者我要写书评

暂无评论

Weak Maneuvering Target Detection Using Cost-Reference Particle Filter Bank 5

Weak Maneuvering Target Detection Using Cost-Reference Parti...

引用

5th International Conference on intelligent Control, Measurement and Signal Processing, ICMSP 2023

作者： Lu, Jin Peng, Guojie Sun, Changming Zhang, Weichuang School of Electrical Information and Artificial Intelligence Shaanxi University of Science & Technology Xi'an China CSIRO Data61 NSW Australia Institute for Integrated and Intelligent Systems Griffith University QLD Australia

ISBN: (纸本)9798350336030

In this paper, a novel cost-reference particle filter bank (CRPFB) based method is proposed for detecting a low signal to noise ratio (SNR) nonlinear frequency modulated signal. The proposed method has two stages. First, the designed CRPFB is used for state estimation of a possible target. Second, a test metric (i.e., generalized likelihood ratio) based on the state estimation of the first stage is compared with an analyzable threshold for determining the presence of a target. In first stage, the CRPFB consists of many parallel cost-reference particle filters (CRPFs). The output of the CRPF with the minimum cumulated cost is considered as the estimation results of the CRPFB. In second stage, the threshold can be analytically obtained from several noisy-only measurements by using generalized extreme value distribution. Simulation results illustrate that, compared with the state-of-the-art methods, the proposed method has low computational complexity and its detection threshold can be analytically estimated. © 2023 IEEE.

关键词： Filter banks

来源：评论

学校读者我要写书评

暂无评论

ViT-based Terrain Recognition System for wearable soft exosuit

引用

Biomimetic Intelligence & robotics 2023年第1期3卷 57-64页

作者： Fangliang Yang Chunjie Chen Zhuo Wang Hui Chen Yao Liu Gang Li Xinyu Wua Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China Shenzhen College of Advanced Technology University of Chinese Academy of SciencesShenzhen 518055China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Guangdong-Hong Kong-Macao Joint Laboratory of Human–Machine Intelligence-Synergy Systems Shenzhen 518055China SIASUN Robot and Automation CO. LtdShenyang 110169China

Terrain classification and force assistance strategies in complex environments have always piqued the interest of many *** wearable soft exosuits,inaccurate terrain recognition can easily introduce undesired assist forces that can easily injure the *** of these problems,we introduced a depth camera into the exosuit system,perform classification of terrain based on a Vision Transformer(ViT),and optimized the control algorithm,which is known as a ViT-Based Terrain Recognition System(TTRS).First,we used the Transformer algorithm to achieve a considerable classification effect in terrain *** also introduced terrain recognition as prior knowledge into the force assistance strategy of the exosuit,providing different force assistance to the exosuit in different ***,we performed human experiments with seven able-bodied people(six males and one female).The promising results demonstrate that our classification accuracy can reach 99.2%under six different terrains and that it can smoothly switch the force–assist curve in different terrains to better adapt to the complex terrain and improve the walking *** aforementioned terrain recognition algorithms and force–assist strategies may positively influence the study of soft exosuit,powered prostheses,and orthotics.

关键词： Vision Transformer(ViT) Depth camera Wearable soft exosuit Force assistance strategy Terrain recognition

来源：评论

学校读者我要写书评

暂无评论

GACL-Net:Hybrid Deep Learning Framework for Accurate Motor Imagery Classification in Stroke Rehabilitation

引用

Computers, Materials & Continua 2025年第4期83卷 517-536页

作者： Chayut Bunterngchit Laith H.Baniata Mohammad H.Baniata Ashraf ALDabbas Mohannad A.Khair Thanaphon Chearanai Sangwoo Kang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of Computing Gachon UniversitySeongnam13120Republic of Korea Computer Science Department Faculty of Information TechnologyThe World Islamic Sciences and Education UniversityAmman11947Jordan Intelligent Systems Department Faculty of Artificial IntelligenceAl-Balqa Applied UniversityAl-Salt19117Jordan IT Infrastructure Department Qatrana Cement CompanyAmman11821Jordan Division of Industrial and Logistics Engineering Technology Faculty of Engineering and TechnologyKing Mongkut’s University of Technology North BangkokRayong CampusRayong21120Thailand

Stroke is a leading cause of death and disability worldwide,significantly impairing motor and cognitive *** rehabilitation is often hindered by the heterogeneity of stroke lesions,variability in recovery patterns,and the complexity of electroencephalography(EEG)signals,which are often contaminated by *** classification of motor imagery(MI)tasks,involving the mental simulation of movements,is crucial for assessing rehabilitation strategies but is challenged by overlapping neural signatures and patient-specific *** address these challenges,this study introduces a graph-attentive convolutional long short-term memory(LSTM)network(GACL-Net),a novel hybrid deep learning model designed to improve MI classification accuracy and ***-Net incorporates multi-scale convolutional blocks for spatial feature extraction,attention fusion layers for adaptive feature prioritization,graph convolutional layers to model inter-channel dependencies,and bidi-rectional LSTM layers with attention to capture temporal *** on an open-source EEG dataset of 50 acute stroke patients performing left and right MI tasks,GACL-Net achieved 99.52%classification accuracy and 97.43%generalization accuracy under leave-one-subject-out cross-validation,outperforming existing state-of-the-art ***,its real-time processing capability,with prediction times of 33–56 ms on a T4 GPU,underscores its clinical potential for real-time neurofeedback and adaptive *** findings highlight the model’s potential for clinical applications in assessing rehabilitation effectiveness and optimizing therapy plans through precise MI classification.

关键词： Motor imagery EEG stroke rehabilitation deep learning brain-computer interface

来源：评论

学校读者我要写书评

暂无评论

IVR-SSM: Industrial Vehicular Robot Safe & Smart Move Using Wheel-Encoder and Inertial-RGB-Depth Measurements 30

IVR-SSM: Industrial Vehicular Robot Safe & Smart Move Using ...

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Liu, Yuanhao Liang, Wei Wang, Chu Zhang, Xin Gao, Huanbing Zhang, Yinlong State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China School of Information and Electrical Engineering Shandong Jianzhu University Jinan China Shandong Key Laboratory of Intelligent Buildings Technology Jinan China

ISBN: (纸本)9798350391916

Safe & smart move (SSM) aims to help industrial vehicular robot (IVR), such as warehousing robots, running safely and smartly by detecting the obstacles in front and maintaining a safe distance & attitude. However, the traditional SSM methods suffer the drawbacks of limited ranges, inaccurate regression of safety distance & orientation between the robot and the forward unexpected obstacles, and the inappropriate IVR control strategies. To solve these issues, this paper designs an innovative real-time safety-aware framework using the complementary Wheel-Encoder and Inertial-RGB-Depth measurements to ensure the IVR running safely, reasonably and reliably. To estimate the robot running states, we take advantages of the complementary wheel encoder, monocular RGB images and inertial measurements to obtain the robot positions, orientations, angular and linear velocities in a tightly-coupled manner. To improve the safety relative distance & attitude estimation accuracy, we exploit the RGB and depth measurements in a task-oriented fashion. The forward obstacles with the specific contours are detected using the Mask-RCNN model, followed by the Gaussian Mixture Model to obtain the forward obstacle depth. Eventually, an IVR control strategy is designed to maintain the robot safety distance and orientation, and to keep the minimum damage to the robot mechanical system. The presented method has been evaluated on the developed industrial vehicular robot safety perception platform. The experimental results prove the competitiveness against the state-of-the-art methods. © 2024 IEEE.

关键词： Industrial robots

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：