检索结果-内蒙古大学图书馆

3rd International symposium on Communications, control, and Signal Processing (ISCCSP 2008), vol.2

作者： Arash Mohammadi Farshad Almasganj Nima Sadrieh Alireza Zandi Biomedical Engineering Department Amirkabir University of Technology슠 Tehran Iran Communication Department Yazd University Iran Communication Department Isfahan University of Technology Iran

Speech recognition accuracy degrades in presence of additive noise especially when recognizer's training data are clean. Several methods have been proposed to compensate effects of noise on recognition accuracy among these methods Feature-Based Missing Feature Techniques, have shown promising results in making speech recognition systems robust. In these methods first corrupted parts of speech spectrogram are identified then prior to recognition these parts are reconstructed. In this paper Kalman-Based incomplete spectrogram reconstruction is proposed. By kalman-Based reconstruction, correlations between successive frames are used to infer missed parts of spectrogram. Kalman-Based reconstruction, improves recognition accuracy in comparison to previous most efficient reconstruction algorithm, Cluster-based reconstruction, in low SNR values. Average of 10% improvements in -5 dB in presence of different noises is achieved with noisy cluster membership identification and 4.3% in -10 dB and 3.2% in -5 dB in presence of white noise in comparison to Cluster-Based method with weighted average cluster membership identification.

关键词： Noise Robust Speech Recognition Missing Feature Techniques Feature-Based Methods Kalman Filter

来源：评论

学校读者我要写书评

暂无评论

Logical modelling and analysis of the budding yeast cell cycle

引用

BMC BIOINFORMATICS 2007年第8-Sup期8卷 1-2页

作者： Faure, Adrien Chaouiya, Claudine Ciliberto, Andrea Thieffry, Denis Univ Mediterrranee Marseille France INSERM ERM206 F-13258 Marseille France IFOM Milan Italy

Biological background The budding yeast cell cycle core engine has been modelled in great detail, most notably by the groups of B33;la Novak and John Tyson, using a differential formalism. Several models focusing o... 详细信息

Biological background The budding yeast cell cycle core engine has been modelled in great detail, most notably by the groups of Béla Novak and John Tyson, using a differential formalism. Several models focusing on different regulatory modules have been developed. In this respect, the use of a logical formalism facilitates the development of more integrated models, through the articulation of control modules to the core engine. Such integrated models are difficult to build with the differential formalism due to the lack of quantitative data, as well as to numerical instabilities inherent to large non linear systems. Logical modelling of cell cycle regulatory modules Relying on the logical framework defined by Thomas and Kaufman, we use GINsim, the modelling software developed in our team to integrate the morphogenesis checkpoint module to the core model of the yeast cell cycle published by Chen et al.(see also for an application on the Mammalian cell cycle). Our current logical model recapitulates the wild type succession of events as presently characterised. We are now adjusting the model parameters to account for all mutant phenotypes described together with the original differential model. At this point we focus on Knock Out (KO) mutants and on strong gene over-expressions. Our logical simulations provide consistent results for two thirds of the 90 mutants already tested. The remaining problematic cases involve regulatory genes such as Sic1 and Cdh1, whose parameterisation is very complex. We are currently implementing in GINsim the possibility to define the parameters in the form of logical formulas to overcome this problem. In parallel with our model of the budding yeast cycling core, we are developing a logical model of the morphogenesis checkpoint, inspired by the work of Ciliberto et al. This module is expected to produce a stable state with active Clb2 when the checkpoint is off, and when the checkpoint is on, Clb2 activation should be delayed, to prevent th

关键词： Differential Formalism Mutant Phenotype Core Model Logical Formula Yeast Cell Cycle

来源：评论

学校读者我要写书评

暂无评论

Rule-based decision-making framework for knowledge-based anatomical landmark localization (K-BALL)

Rule-based decision-making framework for knowledge-based ana...

引用

3rd IEEE International symposium on biomedical Imaging

作者： Siadat, Mohammad-Reza Soltanian-Zadeh, Hamid Elisevich, Kost Henry Ford Hlth Syst Radiol Image Anal Lab Detroit MI 48202 USA Univ Tehran Control & Intelligent Proc Ctr Excellence Dept Elect & Comp Engn Tehran 14395515 Iran Henry Ford Hlth Syst Dept Neurosurg Detroit MI 48202 USA

ISBN: (纸本)9780780395763

K-BALL is a general method for localization of anatomical phenomena of the same origin with natural discrepancies distributed over a reference space, e.g., human brain anatomical structures. In this paper, we focus on information analysis step (2(nd) step) of K-BALL during which landmarks extracted in its first step are evaluated. We provide a framework in which rules are automatically generated based on estimated and derived models. We show that the rules based on the derived models can improve the overall success rate of K-BALL. Each rule evaluates the extracted points by producing an intermediate confidence factor (ICNF). A total confidence factor is calculated using ICNF's to facilitate the acceptance or rejection of a set of points as landmarks of interest. Using the rules merely based on the estimated models, simulation study produced an overall success rate of 91.8%. Using the rules based on both of the estimated and derived models, this rate increased to 92.5%.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

An optimal iterative learning scheme for dynamic neural network modelling

An optimal iterative learning scheme for dynamic neural netw...

引用

3rd International symposium on Neural Networks, ISNN 2006 - Advances in Neural Networks

作者： Guo, Lei Wang, Hong Research Institute of Automation Southeast University Nanjing 210096 China Control Systems Centre University of Manchester Manchester M60 1QD United Kingdom

ISBN: (纸本)354034439X

In this paper, iterative learning control is presented to a dynamic neural network modelling process for nonlinear (stochastic) dynamical systems. When (B-spline) neural networks are used to model a nonlinear dynamical functional such as the output stochastic distributions in the repetitive processes or the batch processes, the parameters in the basis functions will be tuned using the generalized iterative learning control (GILC) scheme. The GILC scheme differs from the classical model-based ILC laws, with no dynamical input-output differential or difference equations given a prior. For the "model free" GILC problem, we propose an optimal design algorithm for the learning operators by introducing an augmented difference model in state space. A sufficient and necessary solvable condition can be given where a robust optimization solution with an LMI-based design algorithm can be provided. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Statistic tracking control: A multi-objective optimization algorithm

引用

3rd International symposium on Neural Networks, ISNN 2006 - Advances in Neural Networks

作者： Guo, Lei Research Institute of Automation Southeast University Nanjing 210096 China

ISBN: (纸本)3540344373

This paper addresses a new type of control framework for dynamical stochastic systems, which is called statistic tracking control here. General non-Gaussian systems are considered and the tracked objective is the statistic information (including the moments and the entropy) of a given target probability density function (PDF), rather than a deterministic signal. The control is aiming at making the statistic information of the output PDFs to follow those of a target PDF. The B-spline neural network with modelling error is applied to approximate the corresponding dynamic functional. For the nonlinear weighting system with time delays in the presence of exogenous disturbances, the generalized H2 and H∞ optimization technique is then used to guarantee the tracking, robustness and transient performance simultaneously in terms of LMI formulations. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Algorithmic languages

来源：评论

学校读者我要写书评

暂无评论

Face recognition using a neural network simulating olfactory systems

引用

3rd International symposium on Neural Networks, ISNN 2006 - Advances in Neural Networks

作者： Li, Guang Zhang, Jin Wang, You Freeman, Walter J. National Laboratory of Industrial Control Technology Zhejiang University Hangzhou 310027 China Department of Biomedical Engineering Zhejiang University Hangzhou 310027 China Software College Human University Changsha 410082 China Division of Neurobiology University of California at Berkeley Donner 101 Berkeley CA 94720-3206 United States

ISBN: (纸本)3540344373

A novel chaotic neural network K-set has been constructed based in research on biological olfactory systems. This non-convergent neural network simulates the capacities of biological brains for signal processing in pattern recognition. Its accuracy and efficiency are demonstrated in this report on an application to human face recognition, with comparisons of performance with conventional pattern recognition algorithms. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Incremental learning for segmentation in medical images

Incremental learning for segmentation in medical images

引用

IEEE International symposium on biomedical Imaging

作者： A. Misra A. Sowmya P. Compton School of Computer Science and Engineering University of New South Wales Australia

Hand-coded vision systems are problematic in complex medical domains and are hard to change as new information emerges. Knowledge-engineering and machine learning approaches to intelligent vision systems also face learning bottlenecks. We have developed an approach to engineering vision systems, which allowed the user to make incremental changes to refine the performance of the system and address these limitations. A medical image segmentation system was built using this approach. In only a few hours of training, the system was able to exceed the performance of a similar hand-coded system built over a period of three months

关键词： Image segmentation biomedical imaging Machine vision Machine learning Intelligent systems Learning systems Knowledge acquisition biomedical engineering Medical control systems Lungs

来源：评论

学校读者我要写书评

暂无评论

Sketch initialized Snakes for rapid, accurate and repeatable interactive medical image segmentation

Sketch initialized Snakes for rapid, accurate and repeatable...

引用

IEEE International symposium on biomedical Imaging

作者： T. McInerney M.R. Akhavan Sharif Department of Computer Science Ryerson University Toronto ONT Canada

We combine a pen and pressure-sensitive tablet input device, and a sketch-based user initialization process, with a general subdivision-curve Snake to create an intuitive, fast, accurate, interactive model-based segmentation method. Using the pen input device, the Snake is quickly and precisely initialized with a series of sketch lines such that it is extremely close to the position and shape of the target object boundary, making the Snake's task much simpler and hence more likely to succeed in noisy images with minimal user editing. The user may also use pen pressure levels to easily impart knowledge of object edge strength to the model, and the low degree-of-freedom subdivision curve Snake provides powerful control and editing capabilities. We apply our Snake to the segmentation of several 2D medical images

关键词： biomedical imaging Image segmentation Shape control Noise shaping Deformable models Computer science Power system modeling Automatic control Pressure control Medical control systems

来源：评论

学校读者我要写书评

暂无评论

MRI brain image segmentation by adaptive spatial deterministic annealing clustering

MRI brain image segmentation by adaptive spatial determinist...

引用

IEEE International symposium on biomedical Imaging

作者： Zhi Min Wang Qing Song Yeng Chai Soh Centre for Modeling and Control of Complex Systems School of Electrical and Electronic Engineering Nanyang Technological University Singapore

ISBN: (纸本)078039576x

This paper describes a novel image segmentation algorithm suitable for MRI image segmentation. We introduce a new dissimilarity measure which incorporates the spatial connectivity. A fully automatic technique is developed to obtain the segmentation result and the new clustering objective function incorporates the spatial information. The weighting factor for neighborhood effect is adaptive to the image content. It enhances the smoothness towards piecewise-homogeneous region and reduces the edge-blurring effect. The experimental results with synthetic and MRI brain images demonstrate that the proposed method is effective in improving the segmentation and it outperforms the popular Markov random field algorithm

关键词： Magnetic resonance imaging Brain Image segmentation Annealing Clustering algorithms Electrical resistance measurement Pixel control system synthesis Automatic control Markov random fields

来源：评论

学校读者我要写书评

暂无评论

Effect of random structured backgrounds on Hotelling SNR fluorescence imaging systems

Effect of random structured backgrounds on Hotelling SNR flu...

引用

IEEE International symposium on biomedical Imaging

作者： A.K. Sahu A. Joshi E.M. Sevick-Muraca Division of Molecular Imaging Department of Radiology Baylor University College of Medicine Houston TX USA

We study the effect of anatomical backgrounds on the detection capability as quantified by the Hotelling observer. The imaging system is modeled by the diffusion approximation of the time-dependent radiative transfer equation, which typically describes NIR light propagation through clinically relevant tissue volumes. We introduce random structures in the background using lumpy object model. Varying intensities of the lumpy objects are introduced in order to evaluate their effect on the Hotelling signal-to-noise ratio (SNR). Large samples of image data sets are considered to generate sufficient statistical data in order to perform Hotelling observer studies. We find that the value of Hotelling SNR decreases as we increase the strength of the lumpy objects

关键词： Fluorescence Optical imaging Equations Optical propagation Optical scattering Tomography Optical coupling Absorption Optical refraction Optical variables control

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：