检索结果-内蒙古大学图书馆

Accelerated algorithm to incomplete nonnegative matrix factorization

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2011年第2期39卷 291-295页

作者： Shi, Jia-Rong Jiao, Li-Cheng Shang, Fan-Hua Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an Shaanxi 710071 China

Nonnegative matrix factorization (NMF) is an increasingly popular technique for data processing and analysis. For an incomplete data matrix, the weighted nonnegative matrix factorization (WNMF) is employed to decompose it. But the searching step size in WNMF is not optimal along the given searching direction. This paper studies the incomplete nonnegative matrix factorization (INMF) and proposes an accelerated algorithm. First, INMF is transformed into solving alternatively two nonnegative least squares (NNLS) problems. For each NNLS problem, the exact step size is chosen along the searching direction. Then, the complexity of NNLS problems is analyzed. Finally, experimental results show that the proposed method outperforms WNMF.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

An Improved Non-local Means Filter for image Denoising

An Improved Non-local Means Filter for Image Denoising

引用

International Conference on intelligent Computation and Bio-Medical Instrumentation (ICBMI)

作者： Yi Zhan Mingyue Ding Feng Xiao Xuming Zhang Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

This paper proposes a improved non-local means (NLM) filter for image denoising. Due to the drawback that the similarity is computed based on the noisy image, the traditional NLM method easily generates the artifacts in case of high-level noise. The proposed method first preprocesses the noisy image by Gaussian filter. Then, a moving window at each pixel of the noisy image is chosen as the search window, and meanwhile, a improved calculation method of spatial distance based on the preprocessed image is used for computing the similarity. Finally, combining the improved distance with search window based on the noisy image, the intensity of each pixel is restored as the traditional NLM method. The standard images are used to evaluate restoration performance of the proposed method. Additionally, the application on medical image denoising also demonstrates that our method is practical.

关键词： Noise measurement Noise Noise reduction image denoising image restoration Biomedical imaging image edge detection

来源：评论

学校读者我要写书评

暂无评论

A Tube Length Measurement Device Based on Acoustic Method

A Tube Length Measurement Device Based on Acoustic Method

引用

International Conference on intelligent Computation and Bio-Medical Instrumentation (ICBMI)

作者： Yimin Chen Jian Qi Xuming Zhang Mingyue Ding Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

A low-cost device using acoustic method for measuring open-end tube length is developed. The proposed device is aimed to get the length of the tubes which are piled up together, and only one end of which is available in the warehouse or dumping areas. The device contains the emitting and receiving probes to echo the sound pulse and receive the reflection sound wave, and has been developed with discrete component circuits whose key part is the logical control circuit based on ARM. Experiments are performed in the open tubes with the lengths between 0.85 m to 6 m. The measurement error is below 0.5 cm. For the tubes blocked by the cement or earth, the device can detect the location of obstruction automatically. Based on the acoustic method, experiments are also conducted in the blocked tubes based on Matlab software, and the analysis of the reflection wave is given.

关键词： Electron tubes Length measurement Acoustics Acoustic measurements Calibration Earth Measurement uncertainty

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of the intima-media layer in ultrasound common carotid artery image based on active contour model

Automatic detection of the intima-media layer in ultrasound ...

引用

2011 IEEE International conference on intelligent Computation and Bio-Medical Instrumentation, ICBMI 2011

作者： Jin, Jiaoying Ding, Mingyue Yang, Xin Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Life School of Science and Technology Huazhong University of Science and Technology Wuhan China State Key Laboratory for Multi-spectral Information Processing Technologies Life School of Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780769546230

The analysis of the carotid artery wall is of paramount importance in clinical practice. Especially, the intima-media thickness is a risk index for some of the most severe acute cerebrovascular pathologies, hence, an accurate segmentation of the different layers of the carotid artery is needed. IMT is usually manually measured on longitudinal B-mode ultrasound images. In the past ten years, many computer-based techniques for intima-media thickness measurement have been proposed to overcome the limits of manual segmentation, but almost all of them require a certain degree of user interaction. In this paper we proposed a novel approach for the completely user-independent segmentation of the common carotid artery wall. Our algorithm is designed for the extraction of the intima and media layers of the distal carotid wall in ultrasound images. It is based on integrated approach consisting of common carotid artery region identification, contour initialization with threshold segmentation, intima-lumen segmentation with Snake, and media-adventitia segmentation with GVF-Snake that enables the automated tracing of the carotid walls. The acoustic impedance's difference is employed to locate common carotid artery region. Finally, the characterization of the algorithm in terms of segmentation error was evaluated with a set of 40 common carotid artery ultrasound images and compared to the segmentation traced by a trained operator. Experiments showed that a mean error lower than 1.3 pixel both on the intima and media layers was obtained, which is comparable to that obtained by means of operator dependent techniques. © 2011 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A programmable multi-channel stimulator for array electrodes in transcutaneous electrical stimulation

A programmable multi-channel stimulator for array electrodes...

引用

IEEE/Institute of Complex Medical Engineering International Conference on Complex Medical Engineering

作者： Xu, Qi Huang, Tao He, Jiping Wang, Yizhao Zhou, Houlun Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan China Harrington Department of Bioengineering Arizona State University Tempe AZ United States Tongji Medical College Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781424493241

Transcutaneous electrical stimulation (TES) has been applied to restore or maintain the muscle activity of paralyzed patients who suffer from spinal cord injuries and related neural impairments for several decades. In this paper, a portable and low-cost versatile stimulator for multichannel TES applications is described. The microcontroller-based programmable stimulator with four bipolar output channels send arbitrarily specified electrical pulses to the element in the electrode array for enabling the complex schemes of muscles. The amplitude and phase of each pulse in the stimulus sequence are independently variable, and the four channels are independently programmable, allowing a wide variety of stimulus patterns. We also designed an output circuit that can provide bi-phasic, voltage-regulated, charge-balanced outputs while avoiding the electrochemical erosion of electrode due to charge accumulation. The proposed stimulator has provided an opportunity for further study of a potential novel electrical stimulator with closed-loop stimulation paradigm suitable for a variety of FES applications, both for experimental and clinical studies. © 2011 IEEE.

关键词： Functional electric stimulation

来源：评论

学校读者我要写书评

暂无评论

Fabric defect detection using undecimated wavelet transform

引用

Information Technology Journal 2011年第9期10卷 1701-1708页

作者： Bi, Mingde Sun, Zhigang Department of Control Science and Engineering Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology 1037 Luoyu Road 430074 Hubei Wuhan China

In this study, a new fabric defect detection algorithm base on undecimated wavelet transform is proposed. The selection scheme of wavelet decomposition scales is investigated to set the decomposition scales adaptively to the fabric texture. The objective of the scheme is to enhance the energy of defective region and attenuate the energy of non-defective region. And the performance of detection results with different number of decomposition scales is also discussed. A simple and computationally effective data fusion scheme combined with amplitudes division of wavelet coefficients is used to fuse data from multiple scales together. And several features based on defective energy estimation are extracted from fused image. By examining the extracted features the proposed algorithm can provide not only the location of defects but also some detailed information about them which can be used for defect recognition and classification. Experimental results of real fabric defects are provided to validate the effectiveness and robustness of the defect detection algorithm. © 2011 Asian Network for Scientific Information.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Nondominated individual selection strategy based on adaptive partition for evolutionary multi-objective optimization

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2011年第4期48卷 545-557页

作者： Gong, Maoguo Cheng, Gang Jiao, Licheng Liu, Chao Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Xidian University Xi'an 710071 China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

Many real world problems involve the simultaneous optimization of various and often conflicting objectives. These optimization problems are known as multi-objective optimization problems. Evolutionary multi-objective optimization, whose main task is to deal with multi-objective optimization problems by evolutionary computation techniques, has become a hot topic in evolutionary computation community. The solution diversity of multi-objective optimization problems mainly focuses on two aspects, breadth and uniformity. After analyzing the traditional methods which were used to maintain the diversity of individual in multi-objective evolutionary algorithms, a novel nondominated individual selection strategy based on adaptive partition is proposed. The new strategy partitions the current trade-off front adaptively according to the individual's similarity. Then one representative individual will be selected in each partitioned regions for pruning nondominated individuals. For maintaining the diversity of the solutions, the adaptive partition selection strategy can be incorporated in multi-objective evolutionary algorithms without the need of any parameter setting, and can be applied in either the parameter or objective domain depending on the nature of the problem involved. In order to evaluate the validity of the new strategy, we apply it into two state-of-the-art multi-objective evolutionary algorithms. The experimental results based on thirteen benchmark problems show that the new strategy improves the performance obviously in terms of breadth and uniformity of nondominated solutions.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

control of Upper-Limb Power-Assist Exoskeleton Based on Motion Intention Recognition

Control of Upper-Limb Power-Assist Exoskeleton Based on Moti...

引用

2011 IEEE International Conference on Robotics and Automation(2011年IEEE世界机器人与自动化大会 ICRA 2011)

作者： Yongji Wang Jian Huang Weiguang Huo Jun Wu Lei Cheng Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Technol Engineering Research Center of Metallurgical Automation and Measurement Technology Ministry of Educa

Recognizing the user motion intention plays an important role in the study of power-assist robots. An intention-guided control strategy is proposed for the upper-limb power-assist exoskeleton. A force sensor system comprised of force sensing resistors (FSRs) is designed to online estimate the motion intention of user upper limb. A new concept called “intentional reaching direction (IRD)” is proposed to quantitatively describe this intention. Both the state model and the observation model of IRD are obtained by enumerating the upper limb behavior modes and analyzing the relationship between the measured force signals and the motion intention. Based on these two models, the IRD can be online inferred by applying filtering technology. Guided by the estimated IRD, an admittance control strategy is assumed to control the motions of three DC motors in the joints of the robotic arm. The effectiveness of the proposed approaches is finally confirmed by the experiments on a 3-DOF robotic exoskeleton.

关键词： Joints Exoskeletons Force Humans Robot sensing systems Jacobian matrices

来源：评论

学校读者我要写书评

暂无评论

Echo State Networks Based Method for Harmonic Extraction in Shunt Active Power Filters

Echo State Networks Based Method for Harmonic Extraction in ...

引用

International Conference on Bio-Inspired Computing: Theories and Applications, BICTA

作者： Jinbang Xu Jun Yang Feng Liu Zhixiong Zhang Anwen Shen Department of Control Science & Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science & Technology Wuhan China

With the wide use of power conversion devices, harmonic currents are being injected into the power grid. Shunt Active Power Filters (SAPF) is a power electronic device to compensate the harmonic currents caused by nonlinear loads. As the foundation of the harmonics recognition and compensation, harmonic extraction techniques are becoming more and more important. This paper proposes a new harmonic extraction method based on the Echo State Networks (ESN). ESN is a new type of Recurrent Neural Networks (RNN), which has much faster training speed than other types of RNN. To evaluate the dynamic system modeling capability of the ESN, the ESN with different dynamic reservoir size are discussed. The performance of the ESN based harmonic extraction method is compared with traditional methods and method based on multilayer perceptron networks (MLP). The ESN algorithm is trained and tested in MATLAB.

关键词： Harmonic analysis Power harmonic filters Training Training data Reservoirs Neurons

来源：评论

学校读者我要写书评

暂无评论

Effective supervised classification of fMRI activation maps between populations by spatial descriptors

Effective supervised classification of fMRI activation maps ...

引用

2011 7th Iranian Conference on Machine Vision and image processing, MVIP 2011

作者： Eshaghian, Shaghayegh Hossein-Zadeh, Gholam-Ali Soltanian-Zadeh, Hamid Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran 14395-515 Iran Image Analysis Laboratory Radiology Department Henry Ford Hospital Detroit MI 48202 United States

ISBN: (纸本)9781457715358

The major obstacle in discrimination between different groups of subjects in a common cognitive state, by functional Magnetic Resonance Imaging (fMRI), has been the high intersubject functional and anatomical variability in the spatial patterns of brain activity. To overcome this, we have used two types of spatial descriptors that characterize the brain regions of interest (ROIs) involved in the cognitive tasks. They include, firstly three-dimensional invariant moment descriptors (3-DMIs), and secondly k-dimensional feature vectors based on concentric spheres. Both types of descriptors are applied to analyze the spatial patterns of cognitive activity of a challenging task and then to classify them across two different subject groups. SVM classifiers along with sequential floating forward feature selection technique are applied to the extracted descriptors of each ROI across the subjects. Our method is applied to experimental fMRI data with the aim of discriminating mental status of heroin IV (Intravenous) abusers and from of those in control subjects in a visual cue task which can induce drug craving. Our results demonstrate that 3-D texture of activation maps provide a good discrimination (with high accuracy) between healthy and addict group. © 2011 IEEE.

关键词： Brain

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：