检索结果-内蒙古大学图书馆

IEEE International Conference on Computational Science and Engineering, CSE

作者： Yanqi Li Jianzhou Liu Shaoming Zhi State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Hangzhou Innovation Institute of Beihang University Beihang University Hangzhou China Hamden Hall Country Day School Hamden CT USA

With the improvement of the spatial resolution of Unmanned Aerial Vehicle (UAV) imagery, the texture information of the surface structures becomes richer and more complex, which Making high-resolution image classification bring new opportunities and great challenges. Therefore, this paper proposes a novel imagery classification method based on U-Net fully convolution neural network combine with a conditional random field model to process this kind of images. First, deep and abstract visual features are extracted by convolution and pooling operations, and then feature map is reconstructed by deconvolution and upsampling operations. Then, a softmax classifier generates the initial classification results. Finally, conditional random field is used to optimize the classification results. The effectiveness and robustness of the proposed method is verified on the UAV imagery data collected from Guangdong Province. Experimental results indicate that the method proposed in this paper can effectively classify different objects with an overall accuracy larger than 91.09% and obtained an average 4.18% improvement over UAV imagery data.

关键词： Computational modeling Feature extraction Decoding Object oriented modeling Convolution Image resolution Semantics

来源：评论

学校读者我要写书评

暂无评论

Novel metaballs-driven approach with dynamic constraints for character articulation

引用

Science China(Information Sciences) 2018年第9期61卷 256-258页

作者： Junxuan BAI Junjun PAN Yuhan YANG Hong QIN State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beihang University Qingdao Research Institute Department of Computer Science Stony Brook University

Skinning techniques are essential for character articulation in 3D computer ***,skeleton-based methods are widely used in the animation industry for its simplicity and efficiency,especially in linear blend skinning(LB...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust and efficient SPH simulation for high-speed fluids with the dynamic particle partitioning method 26

Robust and efficient SPH simulation for high-speed fluids wi...

引用

26th Pacific Conference on Computer Graphics and Applications, Pacific Graphics 2018

作者： Zheng, Zhong Gao, Yang Li, Shuai Qin, Hong Hao, Aimin State Key Laboratory of Virtual Reality Technology and Systems Beihang University China Beihang University Qingdao Research Institute Beihang University China Department of Computer Science Stony Brook University United States

ISBN: (纸本)9783038680734

In this paper, our research efforts are devoted to the efficiency issue of the SPH simulation when the ratio of velocities among fluid particles is large. Specifically, we introduce a k-means clustering method into the SPH framework to dynamically partition fluid particles into two disjoint groups based on their velocities, we then use a two-scale time step scheme for these two types of particles. The smaller time steps are for particles with higher speed in order to preserve temporal details and guarantee the numerical stability. In contrast, the larger time steps are used for particles with smaller speeds to reduce the computational expense, and both types of particles are tightly coupled in the simulation. We conduct various experiments which have manifested the advantages of our methods over the conventional SPH technique and its new variants in terms of efficiency and stability. © 2018 The Author(s).

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Chinese guidelines for the application of colon cancer staging recognition systems based on artificial intelligence platforms (2021)

引用

Intelligent Medicine 2021年第1期1卷 37-42页

作者： Yun Lu Shuai Li Yuan Gao Yong Dai Bo Feng Fanghai Han Jiagang Han Jingjing He Xinxiang Li Guole Lin Qian Liu Guiying Wang Quan Wang Zhenning Wang Zheng Wang Aiwen Wu Bin Wu Yingchi Yang Hongwei Yao Wei Zhang Jianping Zhou Aimin Hao Zhongtao Zhang 无 Department of General Surgery The Affiliated Hospital of Qingdao UniversityQingdaoShandong 266003China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing 100191China Department of General Surgery Qilu Hospital of Shandong UniversityJinanShandong 250012China Department of General Surgery Ruijin HospitalShanghai Jiao Tong University School of MedicineShanghai 200020China Shanghai Minimally Invasive Surgery Center Ruijin HospitalShanghai Jiao Tong University School of MedicineShanghai 200020China Department of Gastrointestinal Surgery Sun Yat-sen Memorial HospitalSun Yat-sen UniversityGuangzhouGuangdong 510120China Department of General Surgery Beijing Chaoyang HospitalCapital Medical UniversityBeijing 100027China Institute of International Law Chinese Academy of Social SciencesBeijing 102442China Department of Colorectal Surgery Fudan University Shanghai Cancer CenterShanghai 200032China Department of Oncology Shanghai Medical CollegeFudan UniversityShanghai 200032China Department of General Surgery Peking Union Medical College HospitalChinese Academy of Medical Sciences&Peking Union Medical CollegeBeijing 100730China National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences&Peking Union Medical CollegeBeijing 100730China Third Hospital of Hebei Medical University ShijiazhuangHebei 50051China Department of Colon and Rectum Surgery The First Hospital of Jilin UniversityChangchunJilin 130031China Department of Surgical Oncology and General Surgery Key Laboratory of Precision Diagnosis and Treatment of Gastrointestinal TumorsMinistry of EducationThe First Affiliated Hospital of China Medical UniversityShenyangLiaoning 110001China Department of Gastrointestinal Surgery Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhanHubei 430030China Key Laboratory of Carcinogenesis and Translational Research(Ministry of Education) Department of Unit II

The incidence and mortality of colon cancer in China are increasing each *** present,treatment selection for colon cancer patients mainly depends on imaging results,which require a large number of radiologists to *** China,there is a shortage and uneven distribution of experienced radiologists,which leads to delays and bias in the evaluation of imaging *** on these considerations,the Colorectal Surgery Group of the Surgery Branch of the Chinese Medical Association in collaboration with experts at Beihang University has independently developed an artificial intelligence(AI)-based recognition system for the preoperative determination of colon cancer stage to partially replace the work of and relieve the pressure on *** guidelines aim to standardize the use of AI-based recognition systems in the preoperative staging of colon cancer and guide their clinical application.

关键词： Artificial intelligence Colon cancer Deep learning Preoperative staging

来源：评论

学校读者我要写书评

暂无评论

Design of Gesture Recognition System Based on Multi-Channel Myoelectricity Correlation

Design of Gesture Recognition System Based on Multi-Channel ...

引用

2019 IEEE Global Communications Conference (GLOBECOM)

作者： Di Wu Huiyong Li Xuefeng Liu Jianwei Niu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beihang University Hangzhou Innovation Research Institute Beihang University

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

Gesture recognition systems based on myoelectric signal have raised more and more attention from researchers. Traditional gesture recognition methods are susceptible to multiple types of noise and require a large number of features, which increase overhead and decrease recognition efficiency. Fully utilizing the characteristics of the signal to recognize gestures is a big challenge. This paper proposes an improved empirical mode decomposition method (XB-EMD) based on autocorrelation function to denoise myoelectric signal. In addition, a novel deep neural network (CRNet) which combines the CNN and RNN layers together is trained for classifying the gestures based on denoised myoelectric signal. Experimental results show that the proposed gesture recognition system can improve recognition effectiveness at 97.4\% with 10 typical gestures, and 72.55\% with 16 complicated gestures.

关键词： Correlation Gesture recognition Feature extraction Empirical mode decomposition Recurrent neural networks Sensors

来源：评论

学校读者我要写书评

暂无评论

The Cutting Force Simulation of 30CrMnSiA Based on AdvantEdge 2D Broaching

引用

Journal of Physics: Conference Series 2020年第4期1601卷

作者： Zheng Hu Wanhao Zhang Xin Li Hanjun Gao Science and Technology on Vehicle Transmission Laboratory China North Vehicle Research Institute Beijing 100072 China State Key Laboratory of Virtual Reality Technology and Systems School of Mechanical Engineering and Automation Beihang University Beijing 100191 China

30CrMnSiA alloy steel is a kind of medium carbon quenched and tempered structural steel commonly used in machinery manufacturing industry, which has superior comprehensive mechanical and technological properties. In view of the great difficulty in solving the cutting process of metal by analytical method, this paper simulates the broaching process of 30CrMnSiA by using AdvantEdge software, and studies the influence of cutting parameters, tool geometry parameters, heat exchange coefficient of coolant and other factors on the cutting force. The results show that the cutting force increases with the increase of cutting width, cutting thickness, friction coefficient between tool and chip, and cutting edge radius, while decreases with the increase of relief angle. The cutting force decreases slightly with increasing of rake angle, and it almost does not change with the increase of cutting speed, coating thickness and the heat exchange coefficient of coolant.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal PI controller design for second order plus time delay processes based on gain margin and improved error integration indices

Optimal PI controller design for second order plus time dela...

引用

IEEE Conference on Industrial Electronics and Applications

作者： Huanchao Du Guofeng Zhang Xiaoguang Hu Jifang Liu Jin Xiao State Key Laboratory of Virtual Reality Technology and Systems Beihang University High-tech Institute QingZhou

In this paper, we present an optimal PI controller design method for second order plus time delay models using gain margin (GM) index and any one of the improved error integration indices: improved integral of absolute error (ISE) index, improved integral of square error (IAE) index and improved integral of time absolute error (ITAE) index. GM index has been used to guarantee system stability and determine the search region. Different error integration indices are compared, results show that the improved error integration indices are essentially the same and they give the same design results. System's unit step response curve show that the PI controllers designed by improved error integration indices have an optimal control performance.

关键词： PI controller Gain margin Improved ISE IAE and ITAE Optimal control

来源：评论

学校读者我要写书评

暂无评论

High-fidelity compression of dynamic meshes with fine details using piece-wise manifold harmonic bases 2018

High-fidelity compression of dynamic meshes with fine detail...

引用

2018 Computer Graphics International Conference, CGI 2018

作者： Chen, Chengju Xia, Qing Li, Shuai Qin, Hong Hao, Aimin State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Beihang University Qingdao Research Institute Beihang University Qingdao China Department of Computer Science Stony Brook University NY United States

ISBN: (纸本)1595930361

Mesh-based animation, usually represented as dynamic meshes with fixed connectivity, is becoming more and more prevalent in movies, games and other graphics applications nowadays, and there is a growing need to compactly store and rapidly transmit these meshes for practical use, especially for those with high-quality geometric details. In this paper, we explore a novel key-frame based dynamic mesh compression method, wherein we apply pose-similarity with spectral techniques to define piece-wise manifold harmonic bases to reduce spatial-temporal redundancy. We first partition the sequence into several clusters with similar poses, and then decompose the meshes in each cluster into primary poses and geometric details using the manifold harmonic bases derived from the extracted key-frame in that cluster. The primary poses can be characterized as linear combinations of manifold harmonic bases, and the geometric details can be recovered by deformation transfer technique. Thus, we only need a small number of key-frames and a few coefficients for compressing dynamic meshes, which saves a significant amount of storage comparing to traditional methods in which bases are stored explicitly. Furthermore, we apply a second-order linear prediction coding to the harmonic coefficients to further reduce the temporal redundancy. Our extensive experiments and evaluations on various datasets have manifested that our novel method could obtain a high compression ratio while preserving high-fidelity geometry details and guaranteeing limited human perceived distortion rate simultaneously. © 2018 ACM.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

DHA: Supervised Deep Learning to Hash with an Adaptive Loss Function

DHA: Supervised Deep Learning to Hash with an Adaptive Loss ...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Jiehao Xu Chengyu Guo Qingjie Liu Jie Qin Yunhong Wang Li Liu State Key Laboratory of Virtual Reality Technology and System Beihang University China College of System Engineering National University of Defense Technology China Inception Institute of Artificial Intelligence Center for Machine Vision and Signal Analysis University of Oulu Finland

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Hashing, which refers to the binary embedding of high-dimensional data, has been an effective solution for fast nearest neighbor retrieval in large-scale databases due to its computational and storage efficiency. Recently, deep learning to hash has been attracting increasing attention since it has shown great potential in improving retrieval quality by leveraging the strengths of deep neural networks. In this paper, we consider the problem of supervised hashing and propose an effective model (i.e., DHA), which is able to generate compact and discriminative binary codes while preserving semantic similarities of original data with an adaptive loss function. The key idea is that we scale and shift the loss function to avoid the saturation of gradients during training, and simultaneously adjust the loss to adapt to different levels of similarities of data. We evaluate the proposed DHA on three widely-used benchmarks, i.e., NUS-WIDE, CIFAR-10, and MS COCO. The state-of-the-art image retrieval performance clearly shows the effectiveness of our method in learning discriminative hash codes for nearest neighbor retrieval.

关键词： Binary codes Hamming distance Training Machine learning Semantics Data models Quantization (signal)

来源：评论

学校读者我要写书评

暂无评论

GA\SQP Optimization for Design of A Serial Robotic Arm Used As A Spatial Pointing Mechanism

GA\SQP Optimization for Design of A Serial Robotic Arm Used ...

引用

IEEE Conference on Cybernetics and Intelligent systems

作者： Xiaocong Wu Xiao Li Haowei Wang Guanyang Liu Chen Guan Chao Huang Ge Yu School of Mechanical Engineering & Automation Beihang University Beijing China Beijing Institute of Spacecraft System Engineering Beijing China School of Mechanical Engineering & Automation State Key Lab of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (数字)9781728134581

ISBN: (纸本)9781728134598

When designing a serial robotic arm based spatial pointing mechanism, a challenging problem is to identify all the design variables to satisfy all the requirements of launching, working conditions and adjustment of working state. Traditionally, engineers rely on experiences and use 3D CAD software to design it by trial and error, however, the approach is inefficient and impossible to provide the optimal solution. In this paper, we propose a genetic algorithm and sequential quadratic programming based methodology to solve the problem and develop a software for engineers to complete the dimensional design of a spatial pointing mechanism. Experimental results validate the effectiveness and efficiency of the proposed approach, and engineers use the developed software to design a spatial pointing robot conveniently and accurately.

关键词： Manipulators Optimization Robot kinematics Genetic algorithms Automation Mechanical engineering

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：