检索结果-内蒙古大学图书馆

Deep learning-based semantic segmentation of human features in bath scrubbing robots

Biomimetic Intelligence & Robotics 2024年第1期4卷 70-79页

作者： Chao Zhuang Tianyi Ma Bokai Xuan Cheng Chang Baichuan An Minghuan Yin Hao Sun School of Artificial Intelligence and Data Science Hebei University of TechnologyTianjin 300401China Engineering Research Center of Intelligent Rehabilitation Device and Detection Technology Ministry of EducationTianjin 300401China

With the rise in the aging population,an increase in the number of semidisabled elderly individuals has been noted,leading to notable challenges in medical and healthcare,exacerbated by a shortage of nursing *** study aims to enhance the human feature recognition capabilities of bath scrubbing robots operating in a water fog *** investigation focuses on semantic segmentation of human features using deep learning ***,3D point cloud data of human bodies with varying sizes are gathered through light detection and ranging to establish human ***,a hybrid filtering algorithm was employed to address the impact of the water fog environment on the modeling and extraction of human ***,the network is refined by integrating the spatial feature extraction module and the channel attention module based on *** results indicate that the algorithm adeptly identifies feature information for 3D human models of diverse body sizes,achieving an overall accuracy of 95.7%.This represents a 4.5%improvement compared with the PointNet network and a 2.5%enhancement over mean intersection over *** conclusion,this study substantially augments the human feature segmentation capabilities,facilitating effective collaboration with bath scrubbing robots for caregiving tasks,thereby possessing significant engineering application value.

关键词： 3D point cloud Human model LiDAR Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Pain Recognition Algorithm Based on Improved Xception and Attention Mechanism 8

Pain Recognition Algorithm Based on Improved Xception and At...

引用

8th International Symposium on Computer Science and intelligent Control, ISCSIC 2024

作者： Geng, Yanli Lu, Shijie Guo, Shijie Gu, Bowen Hebei University of Technology Enginneering Research Center of Intelligent Rehabilitation Device Detection Technology Ministry of Education School of Artificial Intelligence Control Engineering Technology Innovation Center of Hebei Province Tianjin China Hebei University of Technology School of Mechanical Engineering Tianjin China Hebei University of Technology Enginneering Research Center of Intelligent Rehabilitation Device Detection Technology Ministry of Education School of Mechanical Engineering Tianjin China

ISBN: (纸本)9798350380286

Efficient and accurate pain assessment is crucial for diagnosing medical conditions. To improve the accuracy of pain assessment, a pain expression recognition algorithm based on improved Xception and attention mechanism was proposed. A facial pain expression acquisition platform was built to extract video frame sequences and establish a pain expression database. Xception was used as the backbone network. Skip connections were added to enhance the extraction and utilization of shallow features. Multi-scale convolution module was designed to extract richer facial features. Relu was replaced by the Leaky Relu activation function. Attention mechanism was introduced to enhance important features. The model was verified on the pain expression database. The results illustrated the superiority of the proposed model, achieving an accuracy of 9 5. 2 %, which effectively identifies pain more than other basic deep learning models. © 2024 IEEE.

关键词： attention mechanism CBAM pain recognition algorithm Xception

来源：评论

学校读者我要写书评

暂无评论

Movement Function Assessment Based on Human Pose Estimation from Multi-View

引用

Computer Systems Science & engineering 2024年第2期48卷 321-339页

作者： Lingling Chen Tong Liu Zhuo Gong Ding Wang School of Artificial Intelligence Hebei University of TechnologyTianjin300400China Intelligent Rehabilitation Device and Detection Technology Engineering Research Centre of the Ministry of Education Tianjin300400China

Human pose estimation is a basic and critical task in the field of computer vision that involves determining the position(or spatial coordinates)of the joints of the human body in a given image or *** is widely used in motion analysis,medical evaluation,and behavior *** this paper,the authors propose a method for multi-view human pose *** image sensors were placed orthogonally with respect to each other to capture the pose of the subject as they moved,and this yielded accurate and comprehensive results of three-dimensional(3D)motion reconstruction that helped capture their multi-directional *** this,we propose a method based on 3D pose estimation to assess the similarity of the features of motion of patients with motor dysfunction by comparing differences between their range of motion and that of normal *** converted these differences into Fugl–Meyer assessment(FMA)scores in order to quantify ***,we implemented the proposed method in the Unity framework,and built a Virtual Reality platform that provides users with human–computer interaction to make the task more enjoyable for them and ensure their active participation in the assessment *** goal is to provide a suitable means of assessing movement disorders without requiring the immediate supervision of a physician.

关键词： Human pose estimation 3D pose reconstruction assessment of movement function plane of features of human motion

来源：评论

学校读者我要写书评

暂无评论

Pressure Ulcer Stage Evaluation Algorithm Based on Multi-Scale Attention Residual Network 8

Pressure Ulcer Stage Evaluation Algorithm Based on Multi-Sca...

引用

8th International Symposium on Computer Science and intelligent Control, ISCSIC 2024

作者： Geng, Yanli Sun, Hao Li, Zelei Yang, Shucai Hebei University of Technology Enginneering Research Center of Intelligent Rehabilitation Device Detection Technology Ministry of Education School of Artificial Intelligence Control Engineering Technology Innovation Center of Hebei Province Tianjin China Tianjin Magic Technology Co. Ltd. Tianjin China

ISBN: (纸本)9798350380286

Pressure ulcer, alternatively referred to as a pressure injury, mostly occurs in long-term bedridden patients. This issue has emerged as a significant global health concern. Accurate diagnosis is the key to the treatment of pressure sores in clinical application scenarios. Conventional contact-based artificial pressure ulcer detection methods can cause discomfort to patients and potentially elevate the risk of infection. In response to these problems, a pressure ulcer stage evaluation algorithm based on multi-scale attention residual network was proposed. The residual network was used as the basic framework, the stage 0 was improved to enhance the network's nonlinear expressive capacity, and the residual structure was improved to enhanced the model's generalization capability, the FPN feature pyramid was added to fuse the high-level features with the underlying features to achieve feature pyramid feature extraction. The incorporation of the attention mechanism enhanced the model's overall performance and recognition accuracy. The pressure damage stage dataset was used in an experiment to validate the model's performance. The experimental outcomes demonstrate that the proposed method could achieve the precision, recall, F1-score and accuracy of the algorithm of 82.64 %, 83.26 %, 0.83 and 82.37% respectively. Compared with other deep learning models, this proposed algorithm can improve the accuracy and identify the pressure ulcer effectively. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimization of fracture reduction robot controller based on improved sparrow algorithm

引用

Biomimetic Intelligence & Robotics 2023年第4期3卷 16-28页

作者： Baichuan An Jianwen Chen Hao Sun Minghuan Yin Zicheng Song Chao Zhuang Cheng Chang Minghe Liu School of Artificial Intelligence and Data Science Hebei University of TechnologyTianjin 300401China Limb Deformity Correction and Function Reconstruction Department Southern University of Science and Technology HospitalShenzhen 518000China Engineering Research Center of Intelligent Rehabilitation Device and Detection Technology Ministry of EducationTianjin 300401China

The accuracy of a fracture reduction robot(FRR)is critical for ensuring the safety of *** the repositioning accuracy of a FRR,reducing the error,and realizing a safer and more stable folding motion is *** achieve this,a sparrow search algorithm(SSA)based on the Levy flight operator was proposed in this study for self-tuning the robot controller *** inverse kinematic analysis of the FRR was also *** robot dynamics model was established using Simulink,and the inverse dynamics controller for the fracture reduction mechanism was designed using the computed torque control *** simulation and physical experiments were also *** actual motion trajectory of the actuator drive rod and its error with a desired trajectory was obtained through *** optimized Levy-sparrow search algorithm(Levy-SSA)crack reduction robot controller demonstrated an overall reduction of two orders of magnitude in the reduction error,with an average error reduction of 98.74%compared with the traditional unoptimized *** Levy-SSA increased the convergence of the crack reduction robot control system to the optimal solution,improved the accuracy of the motion trajectory,and exhibited important implications for robot controller optimization.

关键词： Fracture reduction robot The sparrow search algorithm Levy flight Reduction accuracy

来源：评论

学校读者我要写书评

暂无评论

Adaptive Closed-Loop Functional Electrical Stimulation System With Visual Feedback for Enhanced Grasping in Neurological Impairments

IEEE Transactions on Medical Robotics and Bionics

引用

IEEE Transactions on Medical Robotics and Bionics 2025年第2期7卷 678-686页

作者： Lin, Chengyu Cheng, Kong Hoi Pan, Wei Sun, Jinxin Gou, Guotao Fu, Junyun Leng, Yuquan Fu, Chenglong Southern University of Science and Technology Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Guangdong Provincial Key Laboratory of Human-Augmentation Rehabilitation Robotics in Universities Department of Mechanical and Energy Engineering Shenzhen518055 China Guilin University of Electronic Technology Guangxi Human Physiological Information Non Invasive Detection Engineering Technology Research Center School of Life and Environmental Sciences Guilin541004 China

Grasping is a critical motor skill essential for daily activities, but it is often compromised in individuals with neural impairments. Functional Electrical Stimulation (FES) has emerged as a promising intervention, utilizing electrical pulses to stimulate muscles and thereby restore impaired motor functions. However, existing closed-loop FES systems depend on pre-calibrated angles or forces specific to individual objects, which limits their practicality in dynamic, real-world environments with varying object properties. This paper presents a novel closed-loop FES (CLFES) system with visual feedback, designed to dynamically adjust stimulation parameters based on real-time interaction states without requiring object-specific calibration. The system employs a finite state machine to manage sequential grasp-release tasks and integrates a visual perception module for slip detection and intent recognition. The system was tested with two individuals with disabilities on five common household objects. Experimental results demonstrate significant improvements, including a 42.6% increase in success rate and a 45.9% reduction in task completion time compared to tasks performed without the system. These results underscore the system's potential to improve daily task performance for individuals with neural impairments. © 2018 IEEE.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

Configuration Synthesis of 4 DOF Knee rehabilitation Parallel Mechanism Based on Multiset Theory 16th

Configuration Synthesis of 4 DOF Knee Rehabilitation Paralle...

引用

16th International Conference on intelligent Robotics and Applications, ICIRA 2023

作者： Zhang, Zhongxin Yu, Bin Wang, Jinbao Song, Jingke Wei, Jun School of Mechanical Engineering Hebei University of Technology Tianjin300401 China Intelligent Rehabilitation Device and Detection Technology Engineering Research Center of the Ministry of Education Tianjin300130 China Key Laboratory of Robot Perception and Human–Machine Fusion Hebei Province Tianjin300130 China

ISBN: (纸本)9789819965007

The occurrence of diseases and accidental damage cause many people to have knee motion dysfunction, the synthesis design of the knee joint rehabilitation mechanism is of great significance. This paper proposes a new 4 DOF (degree-of-freedom) motion equivalent model of knee joint, and the limb synthesis and configuration synthesis of 4 DOF parallel rehabilitation mechanism of knee joint are carried out. Firstly, according to the physiological characteristics of the knee joint and the three non-negligible motion characteristics of the knee joint, a 4 DOF motion equivalent model of the knee joint that is more in line with the knee joint motion is obtained, and the motion screw system and constraint screw system of this model are obtained, Configuration synthesis conditions are proposed. Second, the type of limb constraint is obtained according to the configuration synthesis conditions, and the limb synthesis is carried out by using screw correlation and reciprocity. Finally, the constraint types of the moving platform are classified by using the constraint screw multiple set theory, and the configuration synthesis of each type is carried out, a large number of knee joint 4 DOF parallel rehabilitation mechanisms that meet the requirements are obtained. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Screws

来源：评论

学校读者我要写书评

暂无评论

Kinematics Analysis of the Wearable Waist rehabilitation Robot 1

引用

16th International Conference on intelligent Robotics and Applications, ICIRA 2023

作者： Qi, Kaicheng Fu, Kefei Wei, Jun Lui, Chenglei Song, Jingke Zhang, Jianjun School of Mechanical Engineering Hebei University of Technology Tianjin300401 China Intelligent Rehabilitation Device and Detection Technology Engineering Research Center of the Ministry of Education Tianjin300130 China Key Laboratory of Robot Perception and Human–Machine Fusion Hebei Province Tianjin300130 China

ISBN: (数字)9789819964987

ISBN: (纸本)9789819964970

Patients with lumbar injuries are becoming more common and there is a shortage of intelligent rehabilitation equipment. A wearable lumbar rehabilitation robot for the treatment of low back pain disease is designed to help patients recover their lumbar motion. Firstly, the motion characteristics of the human lumbar spine and its range of motion is determined, and based on the size and range of motion of the human lumbar spine, the configuration design of the lumbar rehabilitation robot is proposed, and a 2-PUU/2-PUS parallel mechanism with three rotations and one translation is proposed;then the degree of freedom(DoF) analysis is carried out based on the screw theory;Finally, the kinematic inverse solution analysis is performed based on the Euler transformation and the geometrical characteristics of this parallel mechanism respectively, and validated based on the established virtual prototype model, and the results show that the mechanism motion characteristics meet the requirements of lumbar rehabilitation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

Optimization of Fracture Reduction Robot Controller 8

Optimization of Fracture Reduction Robot Controller

引用

8th International Symposium on Computer Science and intelligent Control, ISCSIC 2024

作者： An, Baichuan Chen, Jianwen Liu, Minghe Yin, Minghuan Song, Zicheng Zhuang, Chao Chang, Cheng Sun, Hao Hebei University of Technology School of Artificial Intelligence and Data Science Tianjin China Southern University of Science and Technology Hospital Limb Deformity Correction and Function Reconstruction Department Shenzhen China Hebei University of Technology School of Artificial Intelligence and Data Science Engineering Research Center of Intelligent Rehabilitation Device and Detection Technology Ministry of Education Control Engineering Technology Innovation Center of Hebei Province Tianjin China

ISBN: (纸本)9798350380286

To improve the accuracy of fracture reduction, combining inverse kinematic analysis with robot dynamics modelling might lead to a more effective controller for the fracture reduction process. The trajectory of the actuator driving rod's motion and any deviations from it are calculated using Simulink simulation. The Levy-SSA-optimized fracture reduction robot's positioning inaccuracy is two orders of magnitude lower than the PID adjustment approach. Using this method also improves the reduction trajectory's accuracy and speeds up the convergence of the fracture-resetting robot control system to the ideal solution. © 2024 IEEE.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

research on DMP-based gait generation and control method for prosthetic limbs 12

Research on DMP-based gait generation and control method for...

引用

12th International Conference on CYBER technology in Automation, Control, and intelligent Systems, CYBER 2022

作者： Liu, Meiqi Xuan, Bokai Liu, Yifei Geng, Yanli School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin300400 China Engineering Research Center of Intelligent Rehabilitation Device and Detection Technology Ministry of Education Tianjin300131 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

The gait profile of the prosthetic joint and the control of the motion trajectory of the prosthesis are key factors affecting the adaptation of the prosthesis to different motion states. Prosthetic systems that are controlled based on predefined gait curves suffer from poor environmental adaptation and control effects. In this paper, a dynamic movement primitives based learning strategy is proposed to address this problem, which provides motion track information through prediction models under different load conditions and controls the prosthetic system using sliding mode variable structure control. First, the human walking lower limb motion analysis is modeled to obtain the angle and moment data of the lower limb joints;then, the DMP(dynamic movement primitives) is used to generate the joint angle and joint moment distribution curve learning trajectories of the human body under different loads;finally, the dynamics model of the prosthetic test platform is derived using the Lie group Lie algebra, and the sliding mode control is performed based on the dynamics model. The experimental results show that the gait trajectory of the DMP-based prosthetic limb has the same trend with primary curve the control of the prosthetic limb based on the sliding mode control has ideal angle and angular velocity curve tracking effect within a certain error range. © 2022 IEEE.

关键词： Sliding mode control

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：