检索结果-内蒙古大学图书馆

Alpha wave attention EEG analysis based on the multiscale Jensen-Shannon divergence

2nd International Conference on Materials Science and Mechanical Engineering, ICMSME 2014

作者： Zhang, Zheng Xia Xu, Si Qiu Zhou, Er Ning Huang, Xiao Lin Wang, Jun Image Processing and Image Communications Key Lab College of Geo and Bio Information Nanjing Univ of Posts and Telecomm Nanjing 210003 China Institute of Biomedical Electronic Engineering School of Electronic Science and Engineering Nanjing University Nanjing 210093 China

ISBN: (纸本)9783038351689

The article adopted the multiscale Jensen - Shannon Divergence method for EEG complexity analysis. Then the study found that the method can distinguish between three different status (eyes closed, count, in a daze) acquisition of Alpha EEG time series, which shows three different states of Alpha EEG time series having significant differences. In each state of the three different states (eyes closed, count, in a daze), we aimed at comparing and analyzing the statistical complexity of EEG time series itself and the statistical complexity of EEG time series proxy data, finding that there are large amounts of nonlinear time series in the Alpha EEG signals. This method is also fully proved that the multiscale JSD algorithm can be used to analyze EEG signals. Attention statistical complexity can be used as a measure of brain function parameter, which can be applied to the auxiliary clinical brain function evaluation in the future. © (2014) Trans Tech Publications, Switzerland.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Attention electroencephalogram analysis based on Jensen-Shannon Divergence analysis

Attention electroencephalogram analysis based on Jensen-Shan...

引用

2013 International Conference on Bio-Medical Materials and Engineering, ICBME 2013

作者： Zheng, Zheng Zhong Zhao, Jun Chang Huang, Xiao Lin Wang, Jun Image Processing and Image Communications Key Lab College of Geo and Bio Information Nanjing Univ of Posts and Telecomm Nanjing 210003 China Institute of Biomedical Electronic Engineering School of Electronic Science and Engineering Nanjing University Nanjing 210093 China

ISBN: (纸本)9783037857557

In this paper, the complexity analysis method based on Jensen-Shannon Divergence was used to calculate the complexity of the Idle states, the close eyes states and the count numbers states electroencephalogram. The study found that the JSD value of close eyes states EEG was highest, followed by that of the Idle states EEG, and that of the count numbers states EEG was minimum. The result can be used to assisted clinical diagnosis. © (2013) Trans Tech Publications, Switzerland.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Effective bandwidth based scheduling for streaming multimedia

Effective bandwidth based scheduling for streaming multimedi...

引用

Proceedings: 2003 International Conference on image processing, ICIP-2003

作者： Kang, Sang H. Zakhor, Avideh Communication Networks Research Lab. Department of ECE University of Seoul Korea Republic of Video and Image Processing Lab. Department of EECS U.C. Berkeley United States

We propose a class of packet scheduling algorithms for streaming media. The importance level of a video packet is determined by its relative position within its group of pictures, taking into account the motion-texture discrimination and temporal scalability. We generate a number of nested substreams, with more important streams embedding less important ones in a progressive manner. We model the streaming system as a queueing system, compute the run-time decoding failure probability of a frame in each substream based on effective bandwidth, and determine the optimum substream to be sent at any moment in time. The data within optimum substream is sent based on earliest-deadline-first scheduling, until the next channel report arrives, at which time the optimum substream is recomputed. From experiments with real video data, we show that our proposed scheduling scheme outperforms the conventional sequential sending scheme.

关键词： Multimedia systems

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution Reconstruction of Compressed Video Based on Adaptive Quantization Constraint Set

Super-Resolution Reconstruction of Compressed Video Based on...

引用

International Conference on Innovative Computing, Information and Control (ICICIC)

作者： Zhong-qiang Xu Xiu-chang Zhu Ministry Strategic Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China

Super-resolution (SR) technique is to estimate the high-resolution (HR) images by combining the non-redundant information that is available into a set of low-resolution (LR) images, which has been a great focus for compressed video. Based on the theory of projection onto convex set (POCS), this paper constructs quantization constraint set (QCS) using the motion between the frames and the quantization information embedded from the video bit stream. By combing the statistical properties of image and the human visual system (HVS), a novel adaptive quantization constraint set (AQCS) is proposed. The proposed algorithm and its performance analysis are also described. Simulation results show that AQCS-based SR algorithm obtains better performance in both objective and subjective quality, which is applicable for compressed video

关键词： Video compression Quantization image coding Strontium image reconstruction image resolution Focusing Constraint theory Streaming media Humans

来源：评论

学校读者我要写书评

暂无评论

Stereo matching using aggregated likelihood and multi-scale prior

Stereo matching using aggregated likelihood and multi-scale ...

引用

International Conference on Audio, Language and image processing, ICALIP

作者： Liang Wang Tianliang Liu Xiuchang Zhu Jiangsu Provincial Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781467301732

This paper proposes a novel global stereo matching method using aggregated likelihoods and multi-scale priors. The likelihoods of dense stereo correspondences as data term can be robustly expressed by aggregated matching costs based on Weber feature descriptors in an asymmetrical linear filtering model. The multi-scale priors on disparity surface are designed to capture scene smooth term from larger neighborhood besides 4-connected neighborhood. The presented stereo approach being relatively simple does not rely on image segmentation and any scene semantic analysis. Experiments demonstrate that the proposed stereo matching algorithm can produce the dense smooth disparity results comparable to those of excellent stereo matching techniques.

关键词： Stereo vision Visualization Robustness image segmentation Algorithm design and analysis Computer vision image color analysis

来源：评论

学校读者我要写书评

暂无评论

Identification of various food residuals on denim based on hyperspectral imaging system and combination optimal strategy

引用

Artificial Intelligence in Agriculture 2021年第1期5卷 125-132页

作者： Yuzhen Chen Ziyi Xu Wencheng Tang Menghan Hu Douning Tang Guangtao Zhai Qingli Li Shanghai Key Laboratory of Multidimensional Information Processing School of Communication&Electronic EngineeringEast China Normal UniversityShanghai 200062China School of Statistics East China Normal UniversityShanghai 200062China Institute of Image Communication and Information Processing Shanghai Jiao Tong UniversityShanghai 200240China McCormick School of Engineering Northwestern UniversityEvanstonILUnited States

As the science and technology develop,crime methods and scenes have become increasingly complex and *** evidence analysis has become amore and more important criminal investigation technology and liquid is the main form of trace *** can provide not only energy,but clues to solve *** this study,we build a hyperspectral imaging system to detect liquid residue traces,including apple juice,coffee,cola,milk and tea,on denims with light,middle and dark *** obtained hyperspectral images are first subjected to spectral calibration and hyperspectral data ***,Partial Least Squares(PLS)is applied to select the informative wavelengths from the preprocessed *** modeling phase,the combination optimal strategy,support vector machine(SVM)combined with random forest(RF),is developed to establish classification *** experimental results demonstrate that the combination optimal model can achieve TPR,FPR,Precision,Recall,F1,and AUC of 83.5%,2.30%,79.7%,83.5%,81.6%,and 94.7%for classifying fabrics contaminated by various food *** respect to the classification of liquid and fabric types,the combination optimalmodel also yields satisfactory classification *** future work,wewill expand the types of liquid,and make appropriate adjustment to algorithms for improving the robustness of classification *** research may play a positive role in the construction of a harmonious society.

关键词： Hyperspectral imaging Food residual on denim Combination optimal strategy Variable selection Forensic application

来源：评论

学校读者我要写书评

暂无评论

Research on attention eeg based on the multiscale jensen-shannon divergence

Research on attention eeg based on the multiscale jensen-sha...

引用

3rd International Conference on Mechanical Automation and Materials Engineering, ICMAME 2014

ISBN: (纸本)9783038350941

The article adopted the multiscale Jensen-Shannon Divergence analysis method for EEG complexity analysis. Then the study found that this method can distinguish between three different status (Eyes closed, count, in a daze) acquisition of EEG time series. It showed that three different states of EEG time series have significant differences. In each state of the three different states (Eyes closed, count, in a daze), we aimed at comparing and analyzing the statistical complexity of EEG time series itself and the statistical complexity of EEG time series shuffled data. It was found that there are large amounts of nonlinear time series in the EEG signals. This method is also fully proved that the multiscale JSD algorithm can be used to analyze attention EEG signals. The multiscale Jensen-Shannon Divergence statistical complexity can be used as a measure of brain function parameter, which can be applied to the auxiliary clinical brain function evaluation in the future. © (2014) Trans Tech Publications, Switzerland.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Robust piecewise planar stereo with modified segmentation cues in urban scenes

Robust piecewise planar stereo with modified segmentation cu...

引用

International Conference on Multimedia Technology

作者： Zengtao Jiao Tianliang Liu Xiuchang Zhu Jiangsu Provincial Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China

This paper proposes a robust piecewise planar multi view stereo (MVS) approach specifically designed for urban scenes. These architectural scenes are problematic for traditional computer vision methods. In our work, we focus on exploiting some useful constraints of artificial structures such as piecewise coplanarity and boundaries of superpixels. Firstly, we reconstruct quasi-dense 3D point clouds of urban scenes using patches-based MVS (PMVS) method. Secondly, a set of 3D candidate planes are generated by the obtained point clouds without any assumption on the normals of planes, unlike famous Manhattan-world assumption. Then, we segment multi-view images with watershed algorithm and modify the contours of superpixels by the classical Douglas-Peucker approximation algorithm to fit the contours to the boundaries of objects in urban scenes as much as possible. Finally, we use the candidate planes as labels and superpixels as nodes to formulate our Markov Random Field (MRF) optimization problem, then a piecewise planar depth map for each view is recovered by solving the optimization problem using graph-cuts. Experiments show that our method outperforms previous approaches in terms of accuracy.

关键词： Three dimensional displays image segmentation Computer vision Stereo vision Approximation methods image reconstruction Optimization

来源：评论

学校读者我要写书评

暂无评论

MR image segmentation by nonparametric model

MR image segmentation by nonparametric model

引用

2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011

作者： Lu, Yi-Su Chen, Wu-Fan Key Lab for Medical Image Processing Southern Medical University Guangzhou China Electronic Engineering Department South China Institute of Software Engineering Guangzhou China

ISBN: (纸本)9781424493524

Nonparametric Dirichlet Process Mixtures (MDP) model algorithm is applied to segment images, which can obtain the segmentation class numbers automatically without initialization. The algorithm is used to segment noisy natural images and magnetic resonance images with biasing field. Compared with classical Markov Field (MRF) segmentation, the nonparametric segmentation results show the greater performance. This method is also analyzed quantitatively on the belly magnetic resonance images. The Dice Similarity Coefficients (DSC) of all slices exceed 93%, which show that the proposed method is robust and accurate. © 2011 IEEE.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Learning distance metric for regression by semidefinite programming with application to human age estimation 09

Learning distance metric for regression by semidefinite prog...

引用

17th ACM International Conference on Multimedia, MM'09, with Co-located Workshops and Symposiums

作者： Xiao, Bo Yang, Xiaokang Xu, Yi Zha, Hongyuan Institute of Image Communication and Information Processing Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiaotong University Shanghai 200240 China College of Computing Georgia Institute of Technology Atlanta GA 30332 United States

ISBN: (纸本)9781605586083

A good distance metric for the input data is crucial in many pattern recognition and machine learning applications. Past studies have demonstrated that learning a metric from labeled samples can significantly improve the performance of classification and clustering algorithms. In this paper, we investigate the problem of learning a distance metric that measures the semantic similarity of input data for regression problems. The particular application we consider is human age estimation. Our guiding principle for learning the distance metric is to preserve the local neighborhoods based on a specially designed distance as well as to maximize the distances between data that are not in the same neighborhood in the semantic *** any assumption about the structure and the distribution of the input data, we show that this can be done by using semidefinite programming. Furthermore, the low-level feature space can be mapped to the high-level semantic space by a linear transformation with very low computational cost. Experimental results on the publicly available FG-NET database show that 1) the learned metric correctly discovers the semantic structure of the data even when the amount of training data is small and 2) significant improvement over the traditional Euclidean metric for regression can be obtained using the learned metric. Most importantly, simple regression methods such as k nearest neighbors (kNN), combined with our learned metric, become quite competitive (and sometimes even superior) in terms of accuracy when compared with the state-of-the-art human age estimation approaches. Copyright 2009 ACM.

关键词： Clustering algorithms

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：