检索结果-内蒙古大学图书馆

Semisupervised Sparse Multilinear Discriminant Analysis

Journal of Computer Science & Technology 2014年第6期29卷 1058-1071页

作者：黄锴张丽清 MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Department of Computer Science and EngineeringShanghai Jiao Tong University IEEE

Various problems are encountered when adopting ordinary vector space algorithms for high-order tensor data input. Namely, one must overcome the Small Sample Size （SSS） and overfitting problems. In addition, the structural information of the original tensor signal is lost during the vectorization process. Therefore, comparable methods using a direct tensor input are more appropriate. In the case of electrocardiograms （ECGs）, another problem must be overcome; the manual diagnosis of ECG data is expensive and time consuming, rendering it difficult to acquire data with diagnosis labels. However, when effective features for classification in the original data are very sparse, we propose a semisupervised sparse multilinear discriminant analysis （SSSMDA） method. This method uses the distribution of both the labeled and the unlabeled data together with labels discovered through a label propagation Mgorithm. In practice, we use 12-lead ECGs collected from a remote diagnosis system and apply a short-time-fourier transformation （STFT） to obtain third-order tensors. The experimental results highlight the sparsity of the ECG data and the ability of our method to extract sparse and effective features that can be used for classification.

关键词： ECG analysis semisupervised learning sparse coding dimension reduction tensor learning approach

来源：评论

学校读者我要写书评

暂无评论

An iterative method for classifying stroke subjects' motor imagery EEG data in the BCI-FES rehabilitation training system

Advances in Intelligent Systems and Computing

引用

Advances in intelligent systems and computing 2014年 215卷 363-373页

作者： Zhang, Hao Liang, Jianyi Liu, Ye Wang, Hang Zhang, Liqing MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China

Motor imagery-based BCI-FES rehabilitation system has been proved to be effective in the treatment of movement function recovery. Common Spatial Pattern (CSP) and Support Vector Machine (SVM) are commonly used in the feature extraction and classification of Two-classes motor imagery. However, motor imagery signals of stroke patients are irregular due to the damage of the specified brain area. Traditional CSP is not able to detect the optimal projection direction on such EEG data recorded from stroke patients under the interference of irregular patterns. In this paper, an adaptive CSP method is proposed to deal with these unknown irregular patterns. In the method, two models are trained and updated by using different subsets of the original data in every iteration procedure. The method is applied on the EEG datasets of several stroke subjects comparing with traditional CSP-SVM. The results also provide an evidence of the feasibility of our BCI-FES rehabilitation system. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

ECG Representation with Simulated 2D and 3D VCG using Prior Knowledge Based Weighted PCA

ECG Representation with Simulated 2D and 3D VCG using Prior ...

引用

2012 International Conference on Medical Physics and Biomedical Engineering(ICMPBE 2012)

作者： Kai Huang Liqing Zhang MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Department of Computer Science and EngineeringShanghai Jiao Tong University

It is important to use prior knowledge of signal characteristics and their distribution in time-frequency space to extract valuable information from noisy medical ***,the noise in an ECG often has a wide bandwidth which is difficult for approaches based on filters or *** adaptive filters such as Wigner filters or Kalman filters are able to remove wide-bandwidth noise,signal waveform distortion may be brought *** we propose a new noise reduction method which uses the inherent information redundancy in an *** construct 2D and 3D Vectorcardiographs from a standard 12 channel ECG signal,and then project them onto the channel axes to recreate the ECG ***,we take advantage of prior knowledge of where the valuable information is in the *** then apply a knowledge-based weighted Principle Component Analysis to reduce the noise and extract the valuable waveform with the recreated ECG signal.

关键词： Prior Knowledge based Weighted PCA,ECG denoise,information redundancy

来源：评论

学校读者我要写书评

暂无评论

How faithfully can π be interpreted in SA?

引用

Science China(Information Sciences) 2013年第3期56卷 82-96页

作者： LONG Huan FU YuXi Basic Studies in Computing Science Department of Computer ScienceMOE-MS Key Laboratory for Intelligent Computing and Intelligent SystemsShanghai Jiao Tong University

The π calculus and the safe ambient calculus are two of the widely studied variants of process calculi in the field of concurrency *** former is the most classic model for mobile processes and the latter is well known for its nested ***,the relationship between these two models deserves further *** this paper,we reinvestigate this problem *** first give the strengthened encoding *** we propose the encoding of the synchronous π-calculus into the safe ambients *** encoding scheme is a generalization and improvement of Levi and Sangiorgi’s work when moving from the asynchronous π-calculus to the synchronous π-*** show the merits of the encoding by checking the mentioned criteria.

关键词： encoding expressiveness synchronous π-calculus safe ambients

来源：评论

学校读者我要写书评

暂无评论

Process Passing Calculus,Revisited

引用

Journal of Shanghai Jiaotong university(Science) 2013年第1期18卷 29-36页

作者：尹强龙环 Laboratory of Basic Study in Computing Science MOE-MS Key Laboratory for Intelligent Computing and Intelligent SystemsDepartment of Computer Science and EngineeringShanghai Jiaotong University

In the context of process calculi, higher order π calculus （A calculus） is prominent and popular due to its ability to transfer processes. Motivated by the attempt to study the process theory in an integrated way, we give a system study of A calculus with respect to the model independent framework. We show the coincidence of the context bisimulation to the absolute equality. We also build a subbisimilarity relation from A calculus to the π calculus.

关键词： higher order π-calculus encoding expressiveness bisimulation

来源：评论

学校读者我要写书评

暂无评论

The value-passing calculus

The value-passing calculus

引用

Theories of Programming and Formal Methods: Essays Dedicated to Jifeng He on the Occasion of His 70th Birthday

作者： Fu, Yuxi BASICS Department of Computer Science Shanghai Jiaotong University China MOE-MS Key Laboratory for Intelligent Computing and Intelligent Systems China

ISBN: (纸本)9783642396977

A value-passing calculus is a process calculus in which the contents of communications are values chosen from some data domain, and the propositions appearing in the conditionals are formulas constructed from a logic. Previous studies treat the domain models, as well as the logic theories, as unspecified oracles. The open-ended approach leaves open some fundamental issues unanswered. The paper provides a more formal account of the value-passing calculi. The new treatment is self-contained in that the logic theory a value-passing calculus refers to is formally defined. A value-passing calculus consists of a complete first order theory with an operational model that makes use of the terms and the boolean expressions of the theory. A systematic investigation into the theory of the value-passing calculi is carried out. A particular value-passing calculus, double-struck Vℂ, is shown to be the least expressive among all Turing complete value-passing calculi. © 2013 Springer-Verlag.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

Motion deblurring using super-sparsity

Motion deblurring using super-sparsity

引用

20th International Conference on Neural Information Processing, ICONIP 2013

作者： Zhao, Jingxiong Zhao, Haohua Zhang, Keting Zhang, Liqing MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Department of Computer Science and Engineering Shanghai Jiao Tong University China

ISBN: (纸本)9783642420504

Motion blur is caused by the camera shake during the exposure in which the blur kernel describes the trace of shaking. Based on this generating process of the kernel , we observed that the distribution of the kernel obeys super-sparsity, as the natural images. Recent works mostly exploit various kinds of priors in their models, but focus on the the speed or a close-form formulation for convenience of mathematical calculation ignoring the intrinsic feature of the kernels and images. In this paper we propose a new model with super-sparse prior for the deblurring problem from one single image. Since the close-form formulation of this model doesn't exist, we use a look-up table trick to approximate the solution. Qualitative and quantitative evaluation demonstrate that our model with super-sparse prior can produce stable and high-quality results. © Springer-Verlag 2013.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A frequency boosting method for motor imagery EEG classification in BCI-FES rehabilitation training system

A frequency boosting method for motor imagery EEG classifica...

引用

10th International Symposium on Neural Networks, ISNN 2013

作者： Liang, Jianyi Zhang, Hao Liu, Ye Wang, Hang Li, Junhua Zhang, Liqing MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China

ISBN: (纸本)9783642390678

Common Spatial Pattern (CSP) and Support Vector Machine (SVM) are usually adopted for feature extraction and classification of two-class motor imagery. However, in a motor imagery based BCI-FES rehabilitation system, stroke patients usually are not able to conduct correct motor imagery like healthy people due to the injury of motor cortex. Therefore, motor imagery EEG of stroke patients lacks of specific discriminant features as appearances of healthy people, which significantly blocks CSP to seek the optimal projection subspace. In this paper, a method, which filters EEG into a variety of bands and improves performance through boosting principle based on a set of weak CSP-SVM classifiers, was proposed to solve the problem mentioned above and was evaluated on the EEG datasets of three stroke subjects. The proposed method outperformed the traditional CSP-SVM method in terms of classification accuracy. From data analysis, we observed that optimal spectral band for classification had been changing along with rehabilitation training, which may reveal mechanisms that dominant frequency band may be changed along with rehabilitation training and spectral power distribution may be changed in different stages of rehabilitation. In addition, this work also demonstrated the feasibility of our SJTU-BCMI BCI-FES rehabilitation training system. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Causal neurofeedback based BCI-FES rehabilitation for post-stroke patients

Causal neurofeedback based BCI-FES rehabilitation for post-s...

引用

20th International Conference on Neural Information Processing, ICONIP 2013

作者： Wang, Hang Liu, Ye Zhang, Hao Li, Junhua Zhang, Liqing MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China

ISBN: (纸本)9783642420535

BCI-FES therapy has been proved to be an effective way to help post-stroke patients restore motor function of paralyzed limbs. In the existing BCI-FES system, patients can only asynchronously receive feedback in the form of FES or robot-assisted arm movements, and such a system does not provide a positive feedback corresponding to patient's motor imagery. In this work, we propose a causal related BCI-FES rehabilitation training platform, consisting top-down and bottom-up causal chains to achieve a better rehabilitation performance. We compare our system with a popular BCI-FES system on EEG data recorded from ten patients divided in two groups. The results show that almost all patients have achieved improvements in the motor function recovery after our training. © Springer-Verlag 2013.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Optimal calculation of tensor learning approaches

Optimal calculation of tensor learning approaches

引用

10th International Symposium on Neural Networks, ISNN 2013

作者： Huang, Kai Zhang, Liqing MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China

ISBN: (纸本)9783642390647

Most algorithms have been extended to the tensor space to create algorithm versions with direct tensor inputs. However, very unfortunately basically all objective functions of algorithms in the tensor space are non-convex. However, sub-problems constructed by fixing all the modes but one are often convex and very easy to solve. However, this method may lead to difficulty converging;iterative algorithms sometimes get stuck in a local minimum and have difficulty converging to the global solution. Here, we propose a computational framework for constrained and unconstrained tensor methods. Using our methods, the algorithm convergence situation can be improved to some extent and better solutions obtained. We applied our technique to Uncorrelated Multilinear Principal Component Analysis (UMPCA), Tensor Rank one Discriminant Analysis (TR1DA) and Support Tensor Machines (STM);Experiment results show the effectiveness of our method. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Tensors

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：