检索结果-内蒙古大学图书馆

21st IEEE International Workshop on Machine Learning for signal processing, MLSP 2011

作者： Watanabe, Shinji Nakamura, Atsushi Juang, Biing-Hwang NTT Communication Science Laboratories NTT Corporation Japan Center for Signal and Image Processing Georgia Institute of Technology United States

ISBN: (纸本)9781457716232

Linear regression for Hidden Markov Model (HMM) parameters is widely used for the adaptive training of time series pattern analysis especially for speech processing. This paper realizes a fully Bayesian treatment of linear regression for HMMs by using variational techniques. This paper analytically derives the variational lower bound of the marginalized log-likelihood of the linear regression. By using the variational lower bound as an objective function, we can optimize the model topology and hyper-parameters of the linear regression without controlling them as tuning parameters;thus, we realize linear regression for HMM parameters in a non-parametric Bayes manner. Experiments on large vocabulary continuous speech recognition confirm the generalizability of the proposed approach, especially for small quantities of adaptation data. © 2011 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Phase-Based Brain Consciousness Analysis

Phase-Based Brain Consciousness Analysis

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： Ling Li David Looney Cheolsoo Park3 Toshihisa Tanaka Jianting Cao Danilo P. Mandic L. Li is with the School of Computing University of Kent Kent U.K. Department of Electrical and Electronic Engineering Imperial College London London SW7 2AZ U.K. Department of Bioengineering University of California San Diego 9500 Gilman Drive La Jolla CA 92093-0412 USA Department of Electrical and Electronic Engineering Tokyo University of Agriculture and Technology Tokyo 184-8588 Japan and also with the Laboratory for Advanced Brain Signal Processing RIKEN Brain Science Institute Saitama 351-0198 Japan Department of Electronic Engineering Saitama Institute of Technology Japan and also with the Laboratory for Advanced Brain Signal Processing RIKEN Brain Science Institute Saitama 351-0198 Japan

ISBN: (纸本)9781424441198

This work provides a novel framework for identifying coma and brain death consciousness states by analysing frequency power and phase synchrony features from electroencephalogram (EEG). The proposed analysis of pairs of EEG electrodes using complex extensions of Empirical Mode Decomposition (EMD) permits the extraction of information related to the state of the brain function. Analysis on 34 subjects in the coma and quasi-brain-death states suggests that phase synchrony constitutes a feasible feature to discriminate quasibrain- death from coma state. Thus, illustrate the effectiveness of the proposed methods for brain consciousness identification. The predictive power of the features extracted is evaluated by building classification models using support vector machine (SVM) and evaluation the models through receiver operating characteristic (ROC) analysis.

关键词： Phase-Based Consciousness Analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamic modeling and simulation test of a 60 kW PEMFC generation system

引用

Journal of Zhejiang University-science A(Applied Physics & Engineering) 2011年第6期12卷 475-482页

作者： Ying-ying ZHANG Ji-chang SUN Ying ZHANG Xi LI Ouang-yi CAO Shandong Provincial Key Laboratory of Ocean Environment Monitoring Technology Shandong Academy of Sciences Institute of Oceanographic Instrumentation Qingdao 266001 China Control Science and Engineering Department Key Laboratory of Education Ministry for Image Processing and lntelligent Control Huazhong University of Science & Technology Wuhan 430074 China Fuel Cell Institute Department of Automation Shanghai Jiao Tong University Shanghai 200030 China

In this paper,a 60 kW proton exchange membrane fuel cell(PEMFC) generation system is modeled in order to design the system parameters and investigate the static and dynamic characteristics for control *** achieve an overall system model,the system is divided into five modules:the PEMFC stack(anode and cathode flows,membrane hydration,and stack voltage and power),cathode air supply(air compressor,supply manifold,cooler,and humidifier),anode fuel supply(hydrogen valve and humidifier),cathode exhaust exit(exit manifold and water return),and power conditioning(DC/DC and DC/AC) *** a combination of empirical and physical modeling techniques,the model is developed to set the operation conditions of current,temperature,and cathode and anode gas flows and pressures,which have major impacts on system *** current model is based on a 60 kW PEMFC power plant designed for residential applications and takes account of the electrochemical and thermal aspects of chemical reactions within the stack as well as flows of reactants across the *** simulation tests show that the system model can represent the static and dynamic characteristics of a 60 kW PEMFC generation system,which is mathematically simple for system parameters and control designs.

关键词： Proton exchange membrane fuel cell(PEMFC) Generation system Dynamic simulation model Reactant flow

来源：评论

学校读者我要写书评

暂无评论

Spiking neural P systems for arithmetic operations

Spiking neural P systems for arithmetic operations

引用

6th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2011

作者： Zeng, Xiangxiang Song, Tao Pan, Linqiang Zhang, Xingyi Key Laboratory on Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China Key Lab of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei 230039 China

ISBN: (纸本)9780769545141

Recently, Gutiérrez-Naranjo and Leporati considered performing basic arithmetic operations on a new class of bioinspired computing devices - spiking neural P systems (for short, SN P systems). However, the binary encoding mechanism used in their research looks like the encoding approach in electronic circuits, instead of the style of spiking neurons (in usual SN P systems, information are encoded as the time interval between spikes). In this work, three SN P systems are constructed as adder, subtracter and multiplier, respectively. In these devices, a number is inputted to the system as the interval of time elapsed between two spikes received by input neuron, the result of a computation is the time between the moments when the output neuron spikes. © 2011 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Synchronization and combination techniques for audio-video based handwritten mathematical content recognition in classroom videos

Synchronization and combination techniques for audio-video b...

引用

2011 11th International Conference on Intelligent Systems Design and Applications, ISDA'11

作者： Vemulapalli, Smita Hayes, Monson Center for Signal and Image Processing Georgia Institute of Technology Atlanta GA United States Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea Republic of

ISBN: (纸本)9781457716751

Recognizing handwritten mathematical content is a challenging problem, and more so when such content appears in classroom videos. However, given the fact that in such videos the handwritten text and the accompanying audio refer to the same content, a combination of a video and an audio based recognizer has the potential to significantly improve the content recognition accuracy. In this paper, using a combination of video and audio based recognizers, we focus on improving the character recognition accuracy in such videos and propose: (1) synchronization techniques for establishing a correspondence between the handwritten and the spoken content, and (2) combination techniques for combining the outputs of the video and audio based recognizers. The current implementation of the system makes use of a modified open source text recognizer and a commercially available phonetic word-spotter. For evaluation purposes, we use videos recorded in a classroom-like environment and our experiments demonstrate the significant improvements (≈ 24% relative increase as compared to the baseline video based recognizer) in character recognition accuracy that can be achieved using our techniques. © 2011 IEEE.

关键词： Character recognition

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

4th Biomedical Engineering International Conference, BMEiCON-2011

作者： Jaruwongrangsee, Kata Maturos, Thitima Bunthawin, Sakshin Wisitsoraat, Anurat Sangworasil, Manas Tuantranont, Adisorn Nanoelectronics and MEMS Laboratory National Electronics and Computer Technology Center Pathumthani Thailand Biotechnology of Electromechanics Research Unit Prince of Songkla University Phuket Thailand Biomedical Signal and Image Processing Laboratory King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand

ISBN: (纸本)9781457721908

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 7V (30 kHz-1MHz) 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. © 2011 IEEE.

关键词： Microspheres

来源：评论

学校读者我要写书评

暂无评论

A Space Target Recognition Method based on Compressive Sensing

A Space Target Recognition Method based on Compressive Sensi...

引用

International Conference on image and Graphics

作者： Ren, Yuemei Zhang, Yangning Li, Ying Huang, Jianyu Hui, Jianjiang Shaanxi Provincial Key Laboratory of Speech and Image Information Processing School of Computer Science Northwestern Polytechnical Univeristy Xi'an China Beijing Institute of Tracking and Telecommunication Technology Beijing China

ISBN: (纸本)9780769545417

Small sample space target recognition is a difficult problem in applications because the limited training samples cannot lead to satisfactory recognition accuracy. Combined with novel compression perception theory, we propose a new space target recognition method based on compressive sensing. This method avoids the sophisticated image preprocessing and feature extraction process. Firstly, a sparse representation dictionary is constructed according to the training samples. Secondly, the linear measurements of test samples are obtained by measurement matrix. Finally, the classification and recognition are done through solving an optimization problem. Simulation experiment results show that the proposed method has good recognition performance and stability. © 2011 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Noise power estimation based on the probability of speech presence

Noise power estimation based on the probability of speech pr...

引用

IEEE Workshop on Applications of signal processing to Audio and Acoustics

作者： Timo Gerkmann Richard C. Hendriks Sound and Image Processing Laboratory KTH Royal Institute of Technology Stockholm Sweden Signal and Information Processing Laboratory Delft University of Technology Delft Netherlands

In this paper, we analyze the minimum mean square error (MMSE) based spectral noise power estimator [1] and present an improvement. We will show that the MMSE based spectral noise power estimate is only updated when the a posteriori signal-to-noise ratio (SNR) is lower than one. This threshold on the a posteriori SNR can be interpreted as a voice activity detector (VAD). We propose in this work to replace the hard decision of the VAD by a soft speech presence probability (SPP). We show that by doing so, the proposed estimator does not require a bias correction and safety-net as is required by the MMSE estimator presented in [1]. At the same time, the proposed estimator maintains the quick noise tracking capability which is characteristic for the MMSE noise tracker, results in less noise power overestimation and is computationally less expensive.

关键词： Speech signal to noise ratio Estimation Speech enhancement Noise measurement Optimized production technology

来源：评论

学校读者我要写书评

暂无评论

Noise can speed convergence in Markov chains

引用

Physical Review E 2011年第4期84卷 041112-041112页

作者： Brandon Franzke Bart Kosko []Center for Quantum Information Science and Technology Signal and Image Processing Institute Department of Electrical Engineering University of Southern California Los Angeles California 90089 USA

A new theorem shows that noise can speed convergence to equilibrium in discrete finite-state Markov chains. The noise applies to the state density and helps the Markov chain explore improbable regions of the state space. The theorem ensures that a stochastic-resonance noise benefit exists for states that obey a vector-norm inequality. Such noise leads to faster convergence because the noise reduces the norm components. A corollary shows that a noise benefit still occurs if the system states obey an alternate norm inequality. This leads to a noise-benefit algorithm that requires knowledge of the steady state. An alternative blind algorithm uses only past state information to achieve a weaker noise benefit. Simulations illustrate the predicted noise benefits in three well-known Markov models. The first model is a two-parameter Ehrenfest diffusion model that shows how noise benefits can occur in the class of birth-death processes. The second model is a Wright-Fisher model of genotype drift in population genetics. The third model is a chemical reaction network of zeolite crystallization. A fourth simulation shows a convergence rate increase of 64% for states that satisfy the theorem and an increase of 53% for states that satisfy the corollary. A final simulation shows that even suboptimal noise can speed convergence if the noise applies over successive time cycles. Noise benefits tend to be sharpest in Markov models that do not converge quickly and that do not have strong absorbing states.

关键词： NOISE MARKOV processes RESONANCE EQUILIBRIUM STOCHASTIC convergence

来源：评论

学校读者我要写书评

暂无评论

Multi-regularization parameters estimation for Gaussian mixture classifier based on MDL principle

Multi-regularization parameters estimation for Gaussian mixt...

引用

International Conference on Neural Computation Theory and Applications, NCTA 2011

作者： Zhou, Xiuling Guo, Ping Philip Chen, C.L. Laboratory of Image Processing and Pattern Recognition Beijing Normal University Beijing 100875 China Artificial Intelligence Institute Beijing City University Beijing China Faculty of Science and Technology University of Macau Macau China

ISBN: (纸本)9789898425843

Regularization is a solution to solve the problem of unstable estimation of covariance matrix with a small sample set in Gaussian classifier. And multi-regularization parameters estimation is more difficult than single parameter estimation. In this paper, KLIM-L covariance matrix estimation is derived theoretically based on MDL (minimum description length) principle for the small sample problem with high dimension. KLIM-L is a generalization of KLIM (Kullback-Leibler information measure) which considers the local difference in each dimension. Under the framework of MDL principle, multi-regularization parameters are selected by the criterion of minimization the KL divergence and estimated simply and directly by point estimation which is approximated by two-order Taylor expansion. It costs less computation time to estimate the multi-regularization parameters in KLIM-L than in RDA (regularized discriminant analysis) and in LOOC (leave-one-out covariance matrix estimate) where cross validation technique is adopted. And higher classification accuracy is achieved by the proposed KLIM-L estimator in experiment.

关键词： Parameter estimation

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：