检索结果-内蒙古大学图书馆

23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Zhou, Yan-Jie Xie, Xiao-Liang Hou, Zeng-Guang Zhou, Xiao-Hu Bian, Gui-Bin Liu, Shi-Qi State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China CAS Center for Excellence in Brain Science and Intelligence Technology Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9783030597245

In endovascular interventional therapy, the fusion of preoperative data with intraoperative X-ray fluoroscopy has demonstrated the potential to reduce radiation dose, contrast agent and processing time. Real-time intraoperative stent segmentation is an important pre-requisite for accurate fusion. Nevertheless, this task often comes with the challenge of the thin stent wires with low contrast in noisy X-ray fluoroscopy. In this paper, a novel and efficient network, termed Lightweight Double Attention-fused Network (LDA-Net), is proposed for end-to-end stent segmentation in intraoperative X-ray fluoroscopy. The proposed LDA-Net consists of three major components, namely feature attention module, relevance attention module and pre-trained MobileNetV2 encoder. Besides, a hybrid loss function of both reinforced focal loss and dice loss is designed to better address the issues of class imbalance and misclassified examples. Quantitative and qualitative evaluations on 175 intraoperative X-ray sequences demonstrate that the proposed LDA-Net significantly outperforms simpler baselines as well as the best previously-published result for this task, achieving the state-of-the-art performance. © 2020, Springer Nature Switzerland AG.

关键词： Stents

来源：评论

学校读者我要写书评

暂无评论

A Novel Two-Stream Model for Human Motor Characteristics Learning

A Novel Two-Stream Model for Human Motor Characteristics Lea...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Tian-Yu Xiang Xiao-Hu Zhou Xiao-Liang Xie Shi-Qi Liu Hong-Jun Yang Zhen-Qiu Feng Jian-Long Hao Zeng-Guang Hou The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The school of Information Shanxi University of Finance and Economics Taiyuan China The CAS Center for Excellence in Brain Science and Intelligence Technology Beijing China The Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology Taipa Macau

ISBN: (纸本)9781665481106

Electroencephalogram (EEG) is one of the most pop-ular sources for learning human motor characteristics. However, most current methods only consider its temporal features and overlook spatial information. This paper proposes a novel two-stream model based on spatial and temporal features to learn human motor characteristics from EEG signals. The spatial stream is analyzed by graph neural networks (GNN) to extract the relationship among different channels. Adjacent matrices can be learned through the training process, unlike pre-defined ones used in other GNN-based EEG analysis methods. The temporal stream is processed with mixed convolution structures, which consist ID convolution, depthwise convolution, and separable convolution. The features of two streams are fused with fully-connected neural networks for human motor characteristics learning. Experimental results show the proposed model can achieve the accuracy of 0.684/0.709 (four classes motor imagery) in subject-independent/dependent schemes, demonstrating the promising for it used in brain computer interface (BCI) scenarios.

关键词： Training Convolution Computational modeling Biological system modeling Streaming media Brain modeling Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Learning from Demonstrations for Long-Horizon Tasks

Hierarchical Learning from Demonstrations for Long-Horizon T...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Boyao Li Jiayi Li Tao Lu Yinghao Cai Shuo Wang China Academy of Launch Vehicle Technology Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China

Although reinforcement learning (RL) has achieved great success in robotic manipulation skills learning, it is still challenging for long-horizon tasks. Combining RL with demonstrations is an effective solution. In this paper, we propose a novel hierarchical learning from demonstrations method for long-horizon tasks, which leverages (i) object-centered segmentation of demonstrations to automatically segment the teaching trajectories into episodes. (ii) a bi-level hierarchical imitation learning method with a parallel training mechanism to train the two-level policies simultaneously. Experimental results on three challenging long-horizon tasks with sparse rewards show that our proposed method significantly outperforms state-of-art approaches in terms of both sample-efficiency and success rate. Moreover, our method is the only one which achieves satisfactory performance in tasks of multi-object stack and multi-object push&stack.

关键词： Deep learning Training Learning systems Automation Conferences Reinforcement learning Trajectory

来源：评论

学校读者我要写书评

暂无评论

Real-Time Marker Localization Learning for GelStereo Tactile Sensing

arXiv

引用

arXiv 2022年

作者： Liu, Shujuan Cui, Shaowei Zhang, Chaofan Cai, Yinghao Wang, Shuo The University of Science and Technology Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Institute of Automation Chinese Academy of Sciences Beijing100190 China The Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China

Visuotactile sensing technology is becoming more popular in tactile sensing, but the effectiveness of the existing marker detection/localization methods remains to be further explored. Instead of contour-based blob detection, this paper presents a learning-based marker localization network for GelStereo visuotactile sensing called Marknet. Specifically, the Marknet presents a grid regression architecture to incorporate the distribution of the GelStereo markers. Furthermore, a marker rationality evaluator (MRE) is modelled to screen suitable prediction results. The experimental results show that the Marknet combined with MRE achieves 93.90% precision for irregular markers in contact areas, which outperforms the traditional contour-based blob detection method by a large margin of 42.32%. Meanwhile, the proposed learning-based marker localization method can achieve better real-time performance beyond the blob detection interface provided by the OpenCV library through GPU acceleration, which we believe will lead to considerable perceptual sensitivity gains in various robotic manipulation tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Nearest-Better Network for Fitness Landscape Analysis of Continuous Optimization Problems

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Diao, Yiya Li, Changhe Zeng, Sanyou Yang, Shengxiang Coello, Carlos A. Coello China University of Geosciences School of Automation Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China Anhui University of Sciences and Technology School of Artificial Intelligence Hefei China China University of Geosciences School of Mechanical Engineering and Electronic Information Wuhan China De Montfort University School of Computer Science and Informatics LeicesterLE1 9BH United Kingdom Department of Computer Science CINVESTAV-IPN 07360 Mexico Tecnologico de Monterrey Faculty of Excellence The School of Engineering and Sciences N.L. Monterrey Mexico

Fitness landscape analysis (FLA) is quite important in evolutionary computation. In this paper, we propose a novel FLA method, the nearest-better network (NBN), which uses the nearest-better relationship to simplify the original fitness landscape of continuous optimization problems. We introduce an efficient algorithm to calculate NBN for continuous problems. We also propose four numerical measurements and a 3D visualization method based on NBN. Experiments show that compared to the other main FLA methods, the four numerical measurements proposed here can effectively measure the four intended features: neutrality, ruggedness, modality, and basin of attraction, respectively, and common features of the fitness landscape can be maintained in 3D NBN visualization, regardless of the scale of the problem. NBN also provides a view of how algorithms search in high-dimensional problems with the help of the 3D NBN visualization. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Novel Two-Stage Framework for 2D/3D Registration in Neurological Interventions

A Novel Two-Stage Framework for 2D/3D Registration in Neurol...

引用

IEEE International Conference on Robotics and Biomimetics

作者： De-Xing Huang Xiao-Hu Zhou Xiao-Liang Xie Shi-Qi Liu Zhen-Qiu Feng Jian-Long Hao Zeng-Guang Hou Ning Ma Long Yan The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The School of Information Shanxi University of Finance and Economics Taiyuan China The CAS Center for Excellence in Brain Science and Intelligence Technology Beijing China The Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology Taipa Macau The Department of Interventional Neuroradiology Beijing Tiantan Hospital Capital Medical University Beijing China

ISBN: (纸本)9781665481106

2D/3D medical image registration of pre-operative volumes and intra-operative images plays an important role in neurological interventions. However, vast space of transformation parameters makes this task incredibly challenging. In this paper, a novel two-stage framework for 2D/3D registration is proposed. It consists of two basic modules: CNN regression for preliminarily estimating transformation parameters, and centroid alignment for further reducing estimation errors to get refined images. Experimental results on two patients show the proposed framework can achieve superior performances to baseline methods with an inference rate of 22 FPS, satisfying real-time requirements (6~12 FPS) in clinical practice. Extensive ablation studies prove the effectiveness of centroid alignment in significantly improving registration accuracies. These promising results indicate the framework has the potential to be integrated into navigation frameworks for neurological interventions, facilitating treatments of physicians.

关键词： Image registration Estimation error Three-dimensional displays Navigation Biomimetics Medical services Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Multi-Task Framework for Guidewire Segmentation and Endpoint Localization in Endovascular Interventions

A Real-Time Multi-Task Framework for Guidewire Segmentation ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Yan-Jie Zhou Shi-Qi Liu Xiao-Liang Xie Xiao-Hu Zhou Guan-An Wang Zeng-Guang Hou Rui-Qi Li Zhen-Liang Ni Chen-Chen Fan State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology Beijing China CASIA-MUST Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology China

Real-time guidewire segmentation and endpoint localization play a pivotal role in robot-assisted minimally invasive surgery, which is helpful to reduce radiation dose and procedure time. Nevertheless, the tasks often come with the challenge of limited computational resources. For this purpose, a real-time multi-task framework with two stages is developed. In the first stage, a Fast Attention-fused Network (FAD-Net) is proposed to obtain accurate guidewire segmentation masks. In the second stage, a lightweight localization network and a post-processing algorithm are designed to robustly predict the guidewire endpoint position. Quantitative and qualitative evaluations on intraoperative X-ray sequences from 30 patients demonstrate that the developed framework outperforms the previously-published results for the tasks, achieving state-of-the-art performance. Moreover, the inference rate of the developed framework is approximately 10.6 FPS, which meets the real-time requirement of X-ray fluoroscopy. These results indicate the proposed approach has the potential to be integrated into the robotic navigation framework for endovascular interventions, enabling robotic-assisted minimally invasive surgery.

关键词： Location awareness Minimally invasive surgery Navigation Prediction algorithms Real-time systems Robustness Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Weakly Aligned Feature Fusion for Multi-modal Object Detection

arXiv

引用

arXiv 2022年

作者： Zhang, Lu Liu, Zhiyong Zhu, Xiangyu Song, Zhan Yang, Xu Lei, Zhen Qiao, Hong The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100086 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China The Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong The Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China

To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, depth, etc. However, multi-modal data often suffer from the position shift problem, i.e. the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multi-modal features and puzzles the CNN training. In this paper, we propose a general multi-modal detector named Aligned Region CNN (AR-CNN) to tackle the position shift problem. Firstly, a region feature alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal region features. Secondly, we propose a novel RoI jitter strategy to improve the robustness to unexpected shift patterns. Thirdly, we present a new multi-modal feature fusion method, which selects the more reliable feature and suppresses the less useful one via feature re-weighting. Additionally, by locating bounding boxes in both modalities and building their relationships, we provide novel multi-modal labelling named KAIST-Paired. Extensive experiments on 2D and 3D object detection, RGB-T and RGB-D datasets demonstrate the effectiveness and robustness of our method. Copyright © 2022, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Group Feature Learning and Domain Adversarial Neural Network for aMCI Diagnosis System Based on EEG

Group Feature Learning and Domain Adversarial Neural Network...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Chen-Chen Fan Haiqun Xie Liang Peng Hongjun Yang Zhen-Liang Ni Guan’an Wang Yan-Jie Zhou Sheng Chen Zhijie Fang Shuyun Huang Zeng-Guang Hou State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China First People's Hospital of Foshan Foshan China CAS Center for Excellence in Brain Science and Intelligence Technology Beijing China CASIA-MUST Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology China

Medical diagnostic robot systems have been paid more and more attention due to its objectivity and accuracy. The diagnosis of mild cognitive impairment (MCI) is considered an effective means to prevent Alzheimer's disease (AD). Doctors diagnose MCI based on various clinical examinations, which are expensive and the diagnosis results rely on the knowledge of doctors. Therefore, it is necessary to develop a robot diagnostic system to eliminate the influence of human factors and obtain a higher accuracy rate. In this paper, we propose a novel Group Feature Domain Adversarial Neural Network (GF- DANN) for amnestic MCI (aMCI) diagnosis, which involves two important modules. A Group Feature Extraction (GFE) module is proposed to reduce individual differences by learning group- level features through adversarial learning. A Dual Branch Domain Adaptation (DBDA) module is carefully designed to reduce the distribution difference between the source and target domain in a domain adaption way. On three types of data set, GF-DANN achieves the best accuracy compared with classic machine learning and deep learning methods. On the DMS data set, GF-DANN has obtained an accuracy rate of 89.47%, and the sensitivity and specificity are 90% and 89%. In addition, by comparing three EEG data collection paradigms, our results demonstrate that the DMS paradigm has the potential to build an aMCI diagnose robot system.

关键词： Deep learning Neural networks Medical services Human factors Sensitivity and specificity Feature extraction Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Group feature learning and domain adversarial neural network for aMCI diagnosis system based on EEG

arXiv

引用

arXiv 2021年

作者： Fan, Chen-Chen Xie, Haiqun Peng, Liang Yang, Hongjun Ni, Zhen-Liang Wang, Guanan Zhou, Yan-Jie Chen, Sheng Fang, Zhijie Huang, Shuyun Hou, Zeng-Guang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Beijing100190 China Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology China Department of Neurology First People’s Hospital of Foshan FoshanGuangdong528000 China

— Medical diagnostic robot systems have been paid more and more attention due to its objectivity and accuracy. The diagnosis of mild cognitive impairment (MCI) is considered an effective means to prevent Alzheimer’s disease (AD). Doctors diagnose MCI based on various clinical examinations, which are expensive and the diagnosis results rely on the knowledge of doctors. Therefore, it is necessary to develop a robot diagnostic system to eliminate the influence of human factors and obtain a higher accuracy rate. In this paper, we propose a novel Group Feature Domain Adversarial Neural Network (GF-DANN) for amnestic MCI (aMCI) diagnosis, which involves two important modules. A Group Feature Extraction (GFE) module is proposed to reduce individual differences by learning group-level features through adversarial learning. A Dual Branch Domain Adaptation (DBDA) module is carefully designed to reduce the distribution difference between the source and target domain in a domain adaption way. On three types of data set, GF-DANN achieves the best accuracy compared with classic machine learning and deep learning methods. On the DMS data set, GF-DANN has obtained an accuracy rate of 89.47%, and the sensitivity and specificity are 90% and 89%. In addition, by comparing three EEG data collection paradigms, our results demonstrate that the DMS paradigm has the potential to build an aMCI diagnose robot system. © 2021, CC BY.

关键词： Diagnosis

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：