检索结果-内蒙古大学图书馆

4th International Conference on Artificial Intelligence and Computational Intelligence, AICI 2012

作者： Guo, LiTing Yi, JianBing Yang, Xuan School of Computer and Software Engineering Shenzhen Key Laboratory of Service Computing and Appliction Shenzhen University Shenzhen 518060 China

ISBN: (纸本)9783642334771

This paper proposed a novel progressive image registration method based on landmarks. At first, identification of corresponding control points is implemented by classifying of image features. We constructed a Probability Boosting Tree (PBT) to calculate the matching probability of each pair of corresponding control points and selected the highly matched ones as control points. Next, a progressive image registration is performed by inserting new landmarks selected by PBT one by one, which estimates the deformation model more and more accurate. Experimental results indicate that the proposed algorithm in this paper is feasible and can improve the precision of image registration significantly. © 2012 Springer-Verlag.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection via adaptive embedding and sparse learning for Parkinson’s disease diagnosis 1

引用

3rd International Workshop on Connectomics in NeuroImaging, CNI 2019 held in conjunction with the 22nd International Conference on Medical Image computing and Computer Assisted Intervention, MICCAI 2019

作者： Huang, Zhongwei Lei, Haijun Chen, Guoliang Li, Shiqi Li, Hancong Elazab, Ahmed Lei, Baiying Key Laboratory of Service Computing and Applications Guangdong Province Key Laboratory of Popular High Performance Computers College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen518060 China

ISBN: (数字)9783030323912

ISBN: (纸本)9783030323905

Parkinson’s disease (PD) is known as a progressive neurodegenerative disease in elderly people. Apart from decelerating the disease exacerbation, early and accurate diagnosis also alleviates mental and physical sufferings and provides timely and appropriate medication. In this paper, we propose an unsupervised feature selection method via adaptive manifold embedding and sparse learning exploiting longitudinal multimodal neuroimaging data for classification and regression prediction. Specifically, the proposed method simultaneously carries out feature selection and dynamic local structure learning to obtain the structural information inherent in the neuroimaging data. We conduct extensive experiments on the publicly available Parkinson’s progression markers initiative (PPMI) dataset to validate the proposed method. Our proposed method outperforms other state-of-the-art methods in terms of classification and regression prediction performance. © Springer Nature Switzerland AG 2019.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Robust laser self-mixing displacement demodulation viacontinuous wavelet–Hilbert transform for high-precision accelerometercalibration

引用

Applied Optics 2025年第16期64卷 4559-4567页

作者： Zhikun Chang Song Song Dongbai Xue Chunling He Zhoumiao Shi Jing Yu Ming Kong Yuying Xie Xiao Deng Tongbao Li Xinbin Cheng Institute of Precision Optical Engineering Tongji University Shanghai 200092 China National Metrology and Testing Center for Integrated Circuit Measurement and Inspection Equipment Industry (Shanghai) Tongji University Shanghai 200092 China MOE Key Laboratory of Advanced Micro-Structured Materials Tongji University Shanghai 200092 China Shanghai Frontiers Science Center of Digital Optics Tongji University Shanghai 200092 China Shanghai Professional Technical Service Platform for Full-Spectrum and High-Performance Optical Thin Film Devices and Applications Tongji University Shanghai 200092 China School of Physics Science and Engineering Tongji University Shanghai 200092 China School of Computer Science and Technology Zhejiang University of Water Resources and Electric Power Hangzhou 310018 China Shenzhen Institute of Technology Innovation NIM Shenzhen 518107 China College of Metrology and Testing Engineering China Jiliang University Hangzhou 310018 China

The laser self-mixing grating interferometer based on Cr atomlithography gratings hasbeen applied to the primarycalibration of accelerometers due to its compact structure, low cost,high accuracy, and directon-site traceability. However, the high line density of Cr gratings(4700 l/mm) introduces dense outliers in interferometricsignals, complicating displacement demodulation via conventionalderivative-based methods and causing frequent phase jumps. To addressthis challenge, we propose a hybrid algorithm integrating thecontinuous wavelet transform and the Hilbert transform, which enablesrobust displacement demodulation under high-noise *** validation on a commercial MEMS accelerometerdemonstrated exceptional accuracy: 100 consecutive data segments weresuccessfully demodulated with a displacement fitting goodness of $R^2 = 0.9964$ ( $\sigma_{R_2} =0.0027$ ), and the derived sensitivitydeviated by only 0.1% from the nominal value. This algorithmestablishes a paradigm for the high-accuracy dynamic calibration ofinertial sensors in field applications.

关键词： Laser interferometry Lithography Phase shift Refractive index Systems design Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

VMScan: an out-of-VM malware scanner

引用

The Journal of China Universities of Posts and Telecommunications 2020年第4期27卷 59-68页

作者： Lin Jie Liu Chuanyi Fang Binxing School of Computer Science and Technology Harbin Institute of TechnologyShenzhenShenzhen 518055China Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and TelecommunicationsBeijing 100876China Department of Information and Electronic Engineering Chinese Academy of EngineeringBeijing 100088China

The harm caused by malware in cloud computing environment is more and more serious. Traditional anti-virus software is in danger of being attacked when it is deployed in virtual machine on a large scale, and it tends not to be accepted by tenants in terms of performance. In this paper, a method of scanning malicious programs outside the virtual machine is proposed, and the prototype is implemented. This method transforms the memory of the virtual machine to the host machine so that the latter can access it. The user space and kernel space of virtual machine memory are analyzed via semantics, and suspicious processes are scanned by signature database. Experimental results show that malicious programs can be effectively scanned outside the virtual machine, and the performance impact on the virtual machine is low, meeting the needs of tenants.

关键词： security virtualization cloud malware virus detection signature scanning

来源：评论

学校读者我要写书评

暂无评论

Incorporating language patterns and domain knowledge into feature-opinion extraction

Incorporating language patterns and domain knowledge into fe...

引用

17th International Conference on Text, Speech, and Dialogue, TSD 2014

作者： Zhou, Erqiang Luo, Xi Qin, Zhiguang School of Computer Science and Engineering University of Electronic Science and Technology of China No.2006 Xiyuan Ave Chengdu 611731 Sichuan China Guangdong Key Laboratory of Popular High Performance Computers Shenzhen Key Laboratory of Service Computing and Applications No. 3688 Nanhai Ave Shenzhen 518060 Guangdong China

ISBN: (纸本)9783319108155

We present a hybrid method for aspect-based sentiment analysis of Chinese restaurant reviews. Two main components are employed so as to extract feature-opinion pairs in the proposed method: domain independent language patterns found in Chinese and a lexical base built for restaurant reviews. The language patterns focus on the general knowledge which is implicit contained in Chinese, thus can be used directly by other domains without any modification. The lexical base, on the other hand, targets for particular characteristics of a given domain and acts as a plug-in part in our prototype system, thus does not affect the portability when applying the proposed approach in practice. Empirical evaluation shows that our method performs well and it can gain a progressive result when each component takes into effective. © 2014 Springer International Publishing.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An interface-fitted/fictitious domain-finite element method for the simulation of particles falling in viscous fluid with contact

引用

Computers & Fluids 2025年 299卷

作者： Yi Liang Cheng Wang Pengtao Sun Yan Chen Jiarui Han School of Mathematical Sciences Tongji University 1239 Siping Road Shanghai 200092 China School of Mathematical Sciences Key Laboratory of Intelligent Computing and Applications (Ministry of Education) Tongji University 1239 Siping Road Shanghai 200092 China Department of Mathematical Sciences University of Nevada Las Vegas 4505 Maryland Parkway Las Vegas NV 89154 USA Shenzhen Raymind Biotechnology Co. Ltd 4018 Jintian Road Shenzhen China

In this paper, an interface-fitted/fictitious domain-finite element method (IF/FD-FEM) is developed to simulate the settling and rebounding processes of rigid particles in viscous fluids. Through local movements of mesh vertices near the moving interface of fluid and rigid particle, a locally moving mesh that fits the interface is obtained at each time step, which allows for large displacements of rigid particle/structure without the need of interpolation, in comparison with the classical (interface-unfitted) fictitious domain method where the interpolation from the fixed fluid mesh to the moving structural mesh is always needed for the unified-field velocity that is defined in the entire domain. On the other hand, in order to capture the dynamics inside the boundary layer near the surface of rigid particle, thereby to improve the solution accuracy near the interface of fluid and rigid particle, the mesh redistribution technique is also crucial to be performed in the region where the interactional/contacting phenomena occur between the rigid particle and fluid/fluid channel wall. Numerical experiments are carried out to validate the effectiveness and accuracy of the proposed numerical methods for the case of rigid particles falling through the fluid channel, where once the rigid particle touches down the bottom of fluid channel, collisions occur by explicitly applying the rebounding forces. Numerical results illustrate that the redistribution of mesh vertices inside the boundary layer exhibits a higher solution accuracy, furthermore, better agreements with physical experimental data in comparison with the existing literature results are also shown in simulating the settling and rebounding process of rigid particles within viscous fluids.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parallel Identifying Motifs in Biological Network on Multicore System

Parallel Identifying Motifs in Biological Network on Multico...

引用

2015全国理论计算机科学学术年会

作者： Cheng ZHONG Jing ZHAO Feng YANG Mengxiao YIN School of Computer and Electronics and Information Guangxi UniversityNanningChinaGuangdong Key Laboratory of Popular High Performance ComputersShenzhen Key Laboratory of Service Computing and ApplicationsShenzhenChina

The required time to indentify the motifs in biological networks will be sharply increased with increase of the scale of the original network or the size of motifs in the *** is very necessary to develop the fast algorithms to indentify larger motifs in large-scale biological networks.A thread-level parallel indentifying motifs algorithm is proposed on multicore machine, in which the local hash tables are used to store the subgraph SIKs mined by parallel threads and a task queue is used to dlistribute the data blocks to parallel threads to balance their loads.A dynamic task scheduling strategy is used to balance the loads among nodes on multi-core cluster, and an efficient parallel algorithn is designed to identify the motifs in biological *** experiment results in undirected network YeastPPI and directed network yeast show that compared with the existing parallel indentifying motifs algorithm, the presented parallel algorithms are faster and obtain good speedup, and it can identify larger motifs in the biological networks.

关键词： biological network motif identification multicore architecture parallel algorithms subgraph enumeration subgraph isomorphism task scheduling

来源：评论

学校读者我要写书评

暂无评论

Color transfer based on multiscale gradient-aware decomposition and color distribution mapping

Color transfer based on multiscale gradient-aware decomposit...

引用

20th ACM International Conference on Multimedia, MM 2012

作者： Su, Zhuo Deng, Daiguo Yang, Xue Luo, Xiaonan National Engineering Research Center of Digital Life State-Province Joint Laboratory of Digital Home Interactive Applications School of Information Science & Technology Sun Yat-sen University Shenzhen China Digital Home Key Technology Engineering Laboratory Shenzhen Key Laboratory of Digital Living Network and Content Service Research Institute of Sun Yat-sen University in Shenzhen China

ISBN: (纸本)9781450310895

Automatic global color transfer is a challenging problem in image editing. In this paper, we propose a novel color transfer method, which is based on the gradient-aware decomposition and the color distribution mapping. Firstly, a gradient-aware decomposition model is established to separate the target image into the base and detail layers. Then, the colors of each separated base layer are enforced to match those of a given reference image by Pitie's multi-dimensional probability density function transfer method. After that, all mapped base layers are combined with corresponding boosted detail layers to produce the final output. The experiments demonstrate that our method can achieve a visual satisfied result without post-processing gradient correction. © 2012 ACM.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Design model execution engine based on web services for distributed geography modeling environment

Design model execution engine based on web services for dist...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xiaolin Wang Hongqiang Mao Yingwei Luo The Shenzhen Key Laboratory for Cloud Computing Technology and Applications Peking University Shenzhen Graduate School Guangdong China

The design of execution engine based on web services for distributed geography modeling environment relies on model contract, model management environment, execution node, data center and control node. The execution procedure of geography model execution engine would be like this: first, geographers construct model contract according to the rule of model contract, and then submit the model contract into control node; Second, the control node parsers the model contract, queries the geography model deployment information, entry point and model input/output information from model management environment, keeps them in memory; Third, control node prepares model data and calls the models which distributed on each execution node for simulation; Finally, the environment returns the result to geographers. The model execution engine adopts multi-thread technology, and could handle multi-job submitted by geographers.

关键词： Computational modeling Biological system modeling Data models Geography Contracts Engines Web services

来源：评论

学校读者我要写书评

暂无评论

Reply to Comments on 'Direct-Splitting-Based CN-FDTD for Modeling 2D Material Nanostructure Problems'

IEEE Open Journal of Antennas and Propagation

引用

IEEE Open Journal of Antennas and Propagation 2021年 2卷 676-678页

作者： Feng, Naixing Zhang, Yuxian Zeng, Qingsheng Tong, Mei Song Joines, William T. Wang, Guo Ping Institute of Microscale Optoelectronics Shenzhen University Shenzhen China College of Astronautics Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of Embedded System and Service Computing of the Ministry of Education College of Electronics and Information Engineering Tongji University Shanghai China Department of Electrical and Computer Engineering Duke University DurhamNC United States

In this response letter, we focus on addressing Yu Hang Yang's comments so that the correctness and validity of the proposed auxiliary-differential-equation-based (ADE) Crank-Nicolson finite-difference time-domain method with direct-splitting technique (CNDS-FDTD) are demonstrated. Moreover, related applications in modeling 2D material nanostructure problems are shown. © 2020 IEEE.

关键词： Finite difference time domain method

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：