检索结果-内蒙古大学图书馆

Configuration Design and Kinematic Performance Analysis of a Novel 4-DOF Parallel Ankle Rehabilitation Mechanism with Two Virtual Motion Centers

引用

Chinese Journal of Mechanical Engineering 2023年第6期36卷 87-104页

作者： Jingke Song Jun Wei Bin Yu Chenglei Liu Cunjin Ai Jianjun Zhang School of Mechanical Engineering Hebei University of TechnologyTianjin 300401China Hebei Provincial Key Laboratory of Robot Perception and Human-Machine Fusion Tianjin 300130China Intelligent Rehabilitation Device and Detection Technology Engineering Research Center of the Ministry of Education Tianjin 300130China

Aiming at the problem that the existing ankle rehabilitation robot is difficult to fully fit the complex motion of human ankle joint and has poor human-machine motion compatibility,an equivalent series mechanism model that is highly matched with the actual bone structure of the human ankle joint is proposed and mapped into a parallel rehabilita-tion *** parallel rehabilitation mechanism has two virtual motion centers(VMCs),which can simulate the complex motion of the ankle joint,adapt to the individual differences of various patients,and can meet the reha-bilitation needs of both left and right feet of ***,based on the motion properties and physiological structure of the human ankle joint,the mapping relationship between the rehabilitation mechanism and ankle joint is determined,and the series equivalent model of the ankle joint is *** to the kinematic and con-straint properties of the ankle equivalent model,the configuration design of the parallel ankle rehabilitation robot is carried ***,according to the intersecting motion planes theory,the full-cycle mobility of the mechanism is proved,and the continuous axis of the mechanism is judged based on the constraint power and its ***,the kinematics of the parallel ankle rehabilitation robot is ***,based on the OpenSim biomechanical soft-ware,a human-machine coupling rehabilitation simulation model is established to evaluate the rehabilitation effect,which lays the foundation for the formulation of a rehabilitation strategy for the later prototype.

关键词： Ankle rehabilitation robot Double-VMCs mechanism Kinematic performance Human-machine rehabilitation simulation

来源：评论

学校读者我要写书评

暂无评论

Predicting Prostate Cancer Risk Stratification Based on PSA and Functional Subsets of Peripheral Lymphocyte

Predicting Prostate Cancer Risk Stratification Based on PSA ...

引用

International Conference on Control and robots (ICCR)

作者： Yin Fang Yan Jiang Xinyu Cao Hanshuo Xing Peiyan Wu Wenbo Song Xinglong Wu Hubei Key Laboratory of Intelligent Robot School of Computer Science & Engineering Wuhan Institute of Technology Wuhan Hubei China

Prostate cancer (PCa) is the second most common cancer among men worldwide, but its diagnosis has long grappled with issues of over-and under-treatment. To address this challenge, novel screening tools and liquid biopsy techniques have emerged in recent years. These methods not only enhance risk stratification for prostate cancer but also reduce patient discomfort and risk. Notably, Prostate-specifc antigen (PSA) screening is no longer the sole choice. In this study, we selected functional subsets of peripheral lymphocyte along with PSA levels to predict the three risk stratifications of PCa. We collected clinical data from 197 prostate cancer patients, subjected it to data cleaning, and used lasso feature selection to choose the optimal feature subset. A decision tree model was employed with ten-fold cross-validation to predict low, intermediate, and high-risk stratifications for PCa. The study yielded an AUC of 0.8688, F1 score of 0.7950, sensitivity of 0.7944, and specificity of 0.9093.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TOWARDS ROBUST AND EFFICIENT CLOUD-EDGE ELASTIC MODEL ADAPTATION VIA SELECTIVE ENTROPY DISTILLATION

arXiv

引用

arXiv 2024年

作者： Chen, Yaofo Niu, Shuaicheng Wang, Yaowei Xu, Shoukai Song, Hengjie Tan, Mingkui South China University of Technology China Pengcheng Laboratory China Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Pazhou Laboratory China

The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for some period) due to the potential high cost of model adaptation for both the server and edge sides. However, in many real-world scenarios, the test environments may change dynamically (known as distribution shifts), which often results in degraded performance. Thus, one has to adapt the edge models promptly to attain promising performance. Moreover, with the increasing data collected at the edge, this paradigm also fails to further adapt the cloud model for better performance. To address these, we encounter two primary challenges: 1) the edge model has limited computation power and may only support forward propagation;2) the data transmission budget between cloud and edge devices is limited in latency-sensitive scenarios. In this paper, we establish a Cloud-Edge Elastic Model Adaptation (CEMA) paradigm in which the edge models only need to perform forward propagation and the edge models can be adapted online. In our CEMA, to reduce the communication burden, we devise two criteria to exclude unnecessary samples from uploading to the cloud, i.e., dynamic unreliable and low-informative sample exclusion. Based on the uploaded samples, we update and distribute the affine parameters of normalization layers by distilling from the stronger foundation model to the edge model with a sample replay strategy. Extensive experimental results on ImageNet-C and ImageNet-R verify the effectiveness of our CEMA. Copyright © 2024, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Medical Image Generation based on Latent Diffusion Models

Medical Image Generation based on Latent Diffusion Models

引用

Artificial Intelligence Innovation (ICAII), International Conference on

作者： Wenbo Song Yan Jiang Yin Fang Xinyu Cao Peiyan Wu Hanshuo Xing Xinglong Wu Hubei Key Laboratory of Intelligent Robot School of Computer Science & Engineering Wuhan Institute of Technology Wuhan Hubei China

The application of deep learning networks in med-ical image analysis has become increasingly mature. However, the availability of a large amount of medical image data for training deep learning networks is hindered by various factors such as workload of doctors, different devices, and ethical privacy policies. These factors can limit the full potential of deep learning network models. In recent years, generative models, particularly diffusion models, have made significant progress in synthesizing realistic images in various domains. Nevertheless, there is currently limited research on the application of Latent Diffusion Models (LDMs) in medical image generation, especially when generating different types of medical images using a unified process. In our research, we explore the use of LDMs to generate synthetic images from various medical image datasets. We train the LDMs on the BreastMRI, Hand, HeadCT, and CXR images extracted from the MedNIST dataset. By employing a consistent LDMs architecture, we aim to generate images from different medical device sources. Additionally, we assess the similarity between the generated images and the real images to evaluate the performance of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PFSC:Pyramid R-CNN for Point-Voxels with Focal Sparse Convolutional Networks for 3D Object Detection

PFSC:Pyramid R-CNN for Point-Voxels with Focal Sparse Convol...

引用

IEEE International Conference on Mechatronics and Automation

作者： Zhao Su Xuehui Liang Jigang Tong Sen Yang Shengzhi Du Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of Technology Tianjin China Department of Electrical Engineering Tshwane University of Technology Pretoria South Africa

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

In the point cloud 3D object detection task, the point cloud data is unevenly distributed in 3D space. Therefore, whether it is regular sparse convolution or submanifold sparse convolution, there is a significant difference in the detection performance when dealing with objects at different positions using sparse convolutional networks. Therefore, this paper proposes an improvement using focal sparse convolution to break the limitations of traditional convolution methods and enhance the representation ability of sparse convolution. Focal sparse convolution is utilized to replace the currently better-performing two-stage object detection network based on the combination of points and voxels, enhancing the end-to-end training effectiveness and achieving better detection results. And an optional detachable auxiliary network is added, which, during the training stage, combines point features to guide the backbone network in learning the structural information of the 3D point cloud, enhancing the localization accuracy of the backbone network. Extensive experiments have been conducted on the KITTI dataset to validate the proposed method, yielding promising detection results and demonstrating the effectiveness of the approach.

关键词： Point cloud compression Training Location awareness Three-dimensional displays Accuracy Mechatronics Convolution

来源：评论

学校读者我要写书评

暂无评论

Research on Semantic Sentiment Analysis Based on BiLSTM 4

Research on Semantic Sentiment Analysis Based on BiLSTM

引用

4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021

作者： Zhang, Chenyue Liu, Lizhi Hubei Key Laboratory of Intelligent Robot School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9780738131702

This paper proposes an emotion classification model based on attention mechanism and Bi-LSTM. Firstly, the texts were trained into word vectors by word2vec model. Secondly, Bi-LSTM network was used to learn the semantic information of context. Then attention mechanism was added to extract the relatively important part of the texts for emotion classification. Finally, the activation function was used to classify the texts. This paper made an experiment of emotion classification based on IMDB data sets. The experimental results show that the proposed model is better than the traditional machine learning method and recurrent neural network in accuracy, recall and F1value. This proves that the AT-BiLSTM model proposed in this paper can effectively improve the effect of emotion classification, and has certain practicability. © 2021 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

LGNet:Local and global representation learning for fast biomedical image segmentation

引用

Journal of Innovative Optical Health Sciences 2023年第4期16卷 29-39页

作者： Guoping Xu Xuan Zhang Wentao Liao Shangbin Chen Xinglong Wu School of Computer Science&Engineering Hubei Key Laboratory of Intelligent RobotWuhan Institute of TechnologyWuhanHubei 430205P.R.China Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and TechnologyWuhanHubei 430074P.R.China

Medical image segmentation plays a crucial role in clinical diagnosis and therapy systems,yet still faces many *** on convolutional neural networks(CNNs),medical image segmentation has achieved tremendous ***,owing to the locality of convolution operations,CNNs have the inherent limitation in learning global *** address the limitation in building global context relationship from CNNs,we propose LGNet,a semantic segmentation network aiming to learn local and global features for fast and accurate medical image segmentation in this ***,we employ a two-branch architecture consisting of convolution layers in one branch to learn local features and transformer layers in the other branch to learn global *** has two key insights:(1)We bridge two-branch to learn local and global features in an interactive way;(2)we present a novel multi-feature fusion model(MSFFM)to leverage the global contexture information from transformer and the local representational features from *** method achieves state-of-the-art trade-off in terms of accuracy and efficiency on several medical image segmentation benchmarks including Synapse,ACDC and ***,LGNet achieves the state-of-the-art performance with Dice's indexes of 80.15%on Synapse,of 91.70%on ACDC,and of 95.56%on ***,the inference speed attains at 172 frames per second with 224-224 input *** extensive experiments demonstrate the effectiveness of the proposed LGNet for fast and accurate for medical image segmentation.

关键词： CNNs transformers segmentation medical image contextual information

来源：评论

学校读者我要写书评

暂无评论

FAM: Fully Attention Module for Medical Image Segmentation

FAM: Fully Attention Module for Medical Image Segmentation

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Xu, Guoping Wu, Xinglong Wuhan Institute of Technology School of Computer Science Engineering Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (纸本)9781665401265

Semantic segmentation plays crucial role in image analysis, which needs rich spatial information and contextual representations. Recently, deep convolution neural networks have achieved much progress in semantic segmentation. However, it still faces many challenges due to the complexity of images, like the blur, noise, and similarity, which imped the progress of the image segmentation. In this paper, we rethink the feature fusion attention methods, such as spatial attention and channel attention, and propose a novel Fully Attention Module (named FAM) based on every pixel of feature map without reducing the size of the input feature maps. We integrate the proposed FAM into U-Net and Fast-SCNN to assess its effectiveness on Synapse dataset. The extensive experiments show that FAM could improve the performance of both two architectures with acceptable cost in terms of speed and total number of parameters. Specifically, we improve the average Dice Similarity Coefficient (DSC) 4.31% / 1.07% and average Hausdorff Distance (HD) 17.62mm / 8.21mm comparing to U-Net and FastSCNN, respectively. In summary, our proposed FAM could boost the segmentation performance by extracting the fully attention of each pixel in the feature maps. The code will be made publicly available at https://***/apple1986/FAM. © 2021 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

The Multi-Strategy based Ant Colony Algorithm for the Path Planning of Mobile robots 8

The Multi-Strategy based Ant Colony Algorithm for the Path P...

引用

8th IEEE International Conference on Advanced robotics and Mechatronics, ICARM 2023

作者： Sun, Xiyue Xu, Wenxia Zheng, Yanlie Huang, Jian Du, Bing Yu, Baocheng Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Hubei Wuhan430205 China Fiberhome Telecommunication Technologies Co. Ltd Hubei Wuhan430074 China School of Automation Huazhang University of Science and Technology Hubei Wuhan430074 China Fiberview Technology Co. Ltd Hubei Wuhan430074 China

ISBN: (纸本)9798350300178

To address the issues of slow convergence speed in the early stage, rapid decrease of diversity, and a tendency to get stuck in local optima in traditional Ant Colony Optimization algorithms for mobile robot path planning, a composite Multi-strategy improved Ant Colony Optimization algorithm is proposed. In a two-dimensional plane, the mobile robot working environment is created using a grid method. The L-M trust region strategy is used to plan the initial information weight of the path map to reduce the blindness of ant colony path search in the early stage. Next, a new heuristic function is constructed based on multi-factor induction strategy to reduce the probability of the ant colony getting stuck in local optima. Finally, the 'lion king rule' strategy is used to improve the updating method of information weight. Experimental results show that the improved Ant Colony Optimization algorithm effectively improves the early stage convergence speed, has good global optimization performance, and verifies the feasibility and superiority of the improved Ant Colony Optimization algorithm in two-dimensional space path planning. © 2023 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

A Fault Diagnosis Method for High-Speed Train Wheelset Bearings Based on Deep Learning 5

A Fault Diagnosis Method for High-Speed Train Wheelset Beari...

引用

5th World Conference on Mechanical Engineering and intelligent Manufacturing, WCMEIM 2022

作者： Zheng, Hu Tan, Libin Yu, Xiaoliu Anhui University of Technology AnHui Province Key Laboratory of Special Heavy Load Robot Ma'anshan China Beijing Advanced Innovation Center for Intelligent China Robots and Systems Beijing Institute of Technology Beijing China

ISBN: (纸本)9781665473699

Aiming at the problem that the traditional fault diagnosis method is difficult to effectively extract the fault features of the high-speed train wheelset bearing signal, this paper proposes a fault diagnosis method based on the two-dimensional image method. First, the one-dimensional vibration signal is converted into a Two-dimensional grayscale image, eliminating the influence of expert experience on the feature extraction process. Then an improved network model is proposed, which can automate the process of feature extraction and fault diagnosis. Finally, this paper simulates the complex driving environment of high-speed trains by adding noise with different SNRs to the vibration signal and analyzes the influence of noise on the diagnostic ability of the method. The results show that the method is effective. © 2022 IEEE.

关键词： Failure analysis

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：