检索结果-内蒙古大学图书馆

European signal processing Conference

作者： Sooraj K. Ambat Saikat Chatterjee K. V. S. Hari Statistical Signal Processing Laboratory Dept. of Electrical Communication Engg. Indian Institute of Science Communication Theory Laboratory School of Electrical Engineering KTH Royal Institute of Technology

ISBN: (纸本)9781467310680

Greedy Pursuits are very popular in Compressed Sensing for sparse signal recovery. Though many of the Greedy Pursuits possess elegant theoretical guarantees for performance, it is well known that their performance depends on the statistical distribution of the non-zero elements in the sparse signal. In practice, the distribution of the sparse signal may not be known a priori. It is also observed that performance of Greedy Pursuits degrades as the number of available measurements decreases from a threshold value which is method dependent. To improve the performance in these situations, we introduce a novel fusion framework for Greedy Pursuits and also propose two algorithms for sparse recovery. Through Monte Carlo simulations we show that the proposed schemes improve sparse signal recovery in clean as well as noisy measurement cases.

关键词： Compressed sensing Sparse Recovery Greedy Pursuits Fusion signal restoration greedy method signal reconstruction Compressed sensing Fusion reactions Fusion, biological Additive identity statistical distribution FUSION fusion (melting) Monte Carlo technique

来源：评论

学校读者我要写书评

暂无评论

Adaptive selection of search space in look ahead orthogonal matching pursuit

Adaptive selection of search space in look ahead orthogonal ...

引用

National Conference on Communications (NCC)

作者： Sooraj K. Ambat Saikat Chatterjee K.V.S. Hari Statistical Signal Processing Laboratory Department of Electrical Communication Engineering Indian Institute of Science Bangalore India Communication Theory Laboratory School of Electrical Engineering KTH-Royal Institute of Technology Stockholm Sweden

Compressive Sensing theory combines the signal sampling and compression for sparse signals resulting in reduction in sampling rate and computational complexity of the measurement system. In recent years, many recovery algorithms were proposed to reconstruct the signal efficiently. Look Ahead OMP (LAOMP) is a recently proposed method which uses a look ahead strategy and performs significantly better than other greedy methods. In this paper, we propose a modification to the LAOMP algorithm to choose the look ahead parameter L adaptively, thus reducing the complexity of the algorithm, without compromising on the performance. The performance of the algorithm is evaluated through Monte Carlo simulations.

关键词： Noise measurement Computational complexity Matching pursuit algorithms signal processing algorithms signal processing Atomic measurements Indexes

来源：评论

学校读者我要写书评

暂无评论

Efficient person recognition by Finger-Knuckle-Print based on 2D Discrete Cosine Transform

Efficient person recognition by Finger-Knuckle-Print based o...

引用

International Conference on Information technology and e-Services (ICITeS)

作者： Mohammed Saigaa Abdallah Meraoumia Salim Chitroub Ahmed Bouridane Signal and Image Processing Laboratory Electronics and Computer Science Faculty University of Sciences and Technology Houari Boumediene Algiers Algeria School of Computing Engineering and Information Sciences Northumbria University Newcastle-upon-Tyne UK

Biometric system has been actively emerging in various industries for the past few years, and it is continuing to roll to provide higher security features for access control system. In the recent years, hand based biometrics is extensively used for personal recognition. In this paper a new biometric system based on texture of the hand knuckles, namely Finger-Knuckle-Print (FKP), is proposed. To extract the image local texture information and represent the FKPs features, the 2D Block based Discrete Cosine Transform (2D-BDCT), is employed. Finally, performance of all finger types is determined individually and a min rule fusion is applied to develop a multimodal system. Experimental results show that 2D-DCT-mod2 yields the best performance for identifying FKPs and it is able to provide an excellent recognition rate and provide more security.

关键词： Feature extraction Biometrics Databases Vectors Thumb Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

On-chip cell separation and manipulation using traveling wave dielectrophoretic force controlled by four-phase signal generator

On-chip cell separation and manipulation using traveling wav...

引用

Biomedical Engineering International Conference (BMEiCON)

作者： Kata Jaruwongrangsee Thitima Maturos Sakshin Bunthawin Anurat Wisitsoraat Manas Sangworasil Adisorn Tuantranont Biomedical signal and image processing laboratory King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand Nanoelectronics and MEMS laboratory National electronics and computer technology center Pathumthani Thailand Biotechnology of Electromechanics Research Unit Prince of Songkla University Phuket Thailand

In this work, we present a device for cell manipulation and separation using travelling wave dielectophoretic (twDEP) force. The device consists of microchamber and 16 parallel electrode array controlled by four-phase signal. The dielectrophoretic PDMS chamber and Cr/Au parallel electrode array were fabricated by standard microfabrication techniques. The driving signals for the twDEP system are produced by a specially designed four-phase signal generator. The signal generator can be operated in a fixed or ±90° phase shift mode with varying frequency, applied voltage and shift interval. In addition, the signal conditions can be store to and retrieved from a built-in database. The twDEP system was tested with polystyrene microspheres suspension in de-ionized water and red blood cells in D-mannitol solution. Cells responded to the electric field in various mechanisms depending on the applied signals conditions. The results showed that the twDEP force occurred when the applied signals were 10 V (50 kHz-700 kHz) and 7 V (30 kHz-1 MHz) for 4.5 μm and 10 μm microspheres respectively. The mixed solution containing equal amount of 4.5 and 10 μm microspheres were used for separation test. Under the signal conditions for 10 μm microspheres, the microspheres were moved under twDEP force while the smaller microspheres were attached to the electrodes. Therefore, the twDEP device can successfully manipulate and separate the microspheres of different sizes, and it can be further applied for cells selection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tensor classification for P300-based brain computer interface

Tensor classification for P300-based brain computer interfac...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Akinari Onishi Anh Huy Phan Kiyotoshi Matsuoka Andrzej Cichocki Laboratory for Advanced Brain Signal Processing RIKEN Brain Science Institute Wako Saitama Japan Graduate School of Life Science and System Engineering Department of Brain Science and Engineering Kyushu Institute of Technology Kitakyushu Fukuoka Japan

Classification methods have been widely applied in most brain computer interfaces (BCIs) that control devices for better quality of life. Most existing classification methods for P300-based BCIs extract features based on temporal structure related to P300 components of event-related potentials (ERPs). Some others exploit the spatial distribution of ERPs optimally selected by recursive channel elimination. However, none of them employed multilinear structures which exploit hidden features in P300-based BCI data. In this paper, we propose a new feature extraction method based on tensor decomposition for ERP-based BCIs. The method seeks an optimal feature subspace simultaneously spanned by temporal and spatial bases, and additional bases which indicate a variant of ERPs obtained by different degrees of polynomial fittings. The proposed method has been evaluated by both the BCI competition III data set II and the affective face driven paradigm data set, and achieved 92% and 95% classification accuracies respectively, which were better than those of most existing P300-based BCI algorithms.

关键词： Tensile stress Feature extraction Electroencephalography Polynomials Training Brain modeling Brain computer interfaces

来源：评论

学校读者我要写书评

暂无评论

A hybrid method to segment common carotid arteries from 3D ultrasound images

A hybrid method to segment common carotid arteries from 3D u...

引用

IEEE EMBS International Conference on Information technology Applications in Biomedicine (ITAB)

作者： Xin Yang Wanji He Jiaoying Jin Xuming Zhang Ming Yuchi Mingyue Ding State Key Laboratory for Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence (IPRAI) Huazhong University of Science and Technology Wuhan Hubei China Image Processing and Intelligence Control Key Laboratory of Education Ministry of China S School of Life Science and Technology Huazhong University of Science and Technology Wuhan Hubei China

A hybrid method is used to evaluate atherosclerosis through a mathematical morphology approach and GVF-Snake method. Common carotid artery (CCA) segmentation requires outlining the intima and adventitia contours on the transverse view of B-mode ultrasound (US) images. The lumen and adventitia contours are segmented using a morphology and GVF-Snake methods, respectively. Upon analyzing ten separate patient data sets demonstrate that a comparison between the proposed method and the traditional approach (manual contouring) on 110 transverse images of the CCA showed a mean absolute distance (MAD) of 0.67±0.17mm for lumen and 0.64 ± 0.19mm for adventitia. Their Dice Similarity Coefficient (DSC) values are 92.7%±2.3% and 90.3%±3.5% for lumen and adventitia segmentation, respectively. These values are in good agreement with clinical standards.

关键词： image segmentation Three dimensional displays Measurement Biomedical imaging Ultrasonic imaging Sun

来源：评论

学校读者我要写书评

暂无评论

Whispered speech emotion recognition based on improved shuffled frog leaping algorithm neural network

引用

Journal of Convergence Information technology 2012年第19期7卷 121-130页

作者： Zhang, Xiaodan Bao, Yongqiang Xi, Ji Zhao, Li Zou, Cairong Key Laboratory of Underwater Acoustic Signal Processing Ministry of Education School of Information Science and Engineering Southeast University Nanjing 210096 China School of Communication Engineering Nanjing Institute Technology Nanjing 211167 China

An improved shuffled frog leaping algorithm (ISFLA) is originally proposed in this paper which is based on the basic ideas of molecular dynamics simulations. Propose a new intermolecular force instead of classic two-body Lennard-Jones force and use Velocity-Verlet algorithm and Gaussian mutation instead of the original SFLA update strategy, which balance the population diversity and search efficiency effectively. And combining ISFLA with RBF neural network, an ISFLA neural network algorithm is proposed in this paper. Based on the research of whispered speech characteristic parameters, the ISFLA neural network algorithm is applied to the whispered speech emotion recognition. In the recognition experiments, RBF neural network and ISFLA neural network are compared under the same testing environment. The test results indicate that the improvement mechanisms provided in this paper bring an outstanding improvement in the classification ability and provide a new method and idea for whispered speech emotion recognition.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Analytical algorithm of program quaternion in the arbitrary spacecraft attitude-adjusting control

引用

Journal of Information and Computational science 2012年第3期9卷 751-759页

作者： Ni, Shaobo Wu, Jianwu Liu, Lei Wang, Yongji Shan, Jiayuan Su, Mao School of Aerospace Engineering Beijing Institute of Technology Beijing 100081 China Beijing Aerospace Automatic Control Institute Beijing 100854 China Key Laboratory of Education Ministry for Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China

The analytical algorithm of program quaternion is studied, aiming at the problem of the arbitrary space vehicle attitude-adjusting control. The analytical constructor method of the program quaternion is provided for arbitrary given initial quaternion, initial angle velocity, terminal quaternion and terminal angle velocity. The presented method has advantages as: good adaptability, the initial and terminal conditions are both arbitrary;reduced operation, the calculation process involves the fundamental algebraic operation;direct optimization, the time consumption in the process of space vehicle attitude adjustment and the maximum angular velocity can be optimized directly by using the program quaternion model. Finally, according to the simulation results, the program quaternion tracking can be realized by a PD control law. © 2012 Binary Information Press.

关键词： Attitude control

来源：评论

学校读者我要写书评

暂无评论

Regularized CSP with Fisher's criterion to improve classification of single-trial ERPs for BCI

Regularized CSP with Fisher's criterion to improve classific...

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Yu Zhang Qibin Zhao Guoxu Zhou Xingyu Wang Andrzej Cichocki Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai China Laboratory for Advanced Brain Signal Processing Brain Science Institute RIKEN Wako Saitama Japan

A brain-computer interface (BCI) based on the combination of oddball paradigm and face perception has been introduced. Such BCI mainly exploits three event-related potential (ERP) components, namely vertex positive potential (VPP), N170 and P300 instead of only P300. With different temporal and spatial distributions of the three ERP components, a regularized common spatial pattern (CSP) with Fisher's criterion (FC), named FCCSP, is proposed to extract the most discriminative features for single trial classification of ERP components. With linear discriminant analysis (LDA) classifier, the proposed FCCSP spatial filtering method yields an average classification accuracy of 95.4% on seven healthy subjects for single-trial ERP components, which outperforms no spatial filtering, the CSP and the FC.

关键词： Feature extraction Accuracy Electroencephalography Face Eigenvalues and eigenfunctions Optimization Brain computer interfaces

来源：评论

学校读者我要写书评

暂无评论

Feature set augmentation for enhancing the performance of a non-intrusive quality predictor

Feature set augmentation for enhancing the performance of a ...

引用

International Workshop on Quality of Multimedia Experience, QoMEx

作者： Petko N. Petkov Hannes Helgason W. Bastiaan Kleijn Sound and Image Processing Laboratory School of Electrical Engineering KTH Royal Institute of Technology Stockholm Sweden School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

A non-intrusive quality predictor constitutes a mapping from signal features to a (typically one dimensional) representation of the perceived quality. Assuming that the regression model performing the mapping is suited to the data, the performance of the predictor largely depends on how well the parameters of this regression model can be inferred from the training data. In situations where the training data is scarce, model performance is degraded due to over-fitting. The effects of over-fitting can be mitigated by feature selection but the model performance remains low due to the insufficiently representative training data. The objective we pursue is to enhance the performance of a quality predictor by augmenting the feature set with the output of a pre-trained quality predictor. This approach introduces an implicit dependence of the regression model parameters on a larger amount of training data. In view of the increasing usage of speech signals with higher bandwidth, and the dearth of training data for such signals, an augmentation of particular interest is that of a wide-band feature set with a narrow-band quality prediction. Experimental results for additive noise and non-linear distortions encountered in hearing aids, using quality labels from an intrusive quality predictor, illustrate the performance enhancement capabilities of the proposed approach.

关键词： Training data Niobium Data models Uncertainty Quality assessment Training Predictive models

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：