检索结果-内蒙古大学图书馆

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

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

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

Computational fluid dynamics analysis of solar radiation error of sounding temperature sensor

引用

Advances in Information sciences and Service sciences 2012年第22期4卷 573-580页

作者： Liu, Qingquan Dai, Wei Yang, Jie Li, Min Zhang, Jiahong Jiangsu Key Laboratory of Meteorological Observation and Signal Processing Nanjing University of Information Science and Technology Nanjing 210044 China School of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing 210044 China School of Atmospheric Physics Nanjing University of Information Science and Technology Nanjing 210044 China Key Laboratory of Meteorological Disaster Nanjing University of Information Science and Technology Nanjing 210044 China Key Laboratory of Atmospheric Physics and Atmospheric Environment of CMA Nanjing University of Information Science and Technology Nanjing 210044 China

Due to the increasing amount of attention that has been focused on numerical weather forecast and climate change research, it is desired that the observation error of upper air temperature using sounding temperature sensors can be reduced to 0.1°C. To achieve this goal, a computational fluid dynamics (CFD) method is proposed here to study the errors induced by solar radiation, under the condition of various solar elevation angles, solar azimuths, lead materials, and air pressures from sea level to 32 km altitude. The results show that solar elevation angle, solar azimuth and lead material are important factors that affect the errors. With the increase of elevation from sea level, the solar heating error appears to be an exponential correlation with respect to the altitude, which exhibits a growing slop rate.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Shift-invariant features with multiple factors for robust text-independent speaker identification

引用

Journal of Computational Information Systems 2012年第21期8卷 8937-8944页

作者： Wu, Qiang Liu, Ju Sun, Jiande Cichocki, Andrzej School of Information Science and Engineering Shandong University Jinan 250100 China Hisense State Key Laboratory of Digital Multi-Media Technology Co. LTD Qingdao 266061 China Laboratory for Advanced Brain Signal Processing BSI RIKEN Wakoshi Saitama Japan

In this paper, we propose a new shift-invariant feature extraction method based on tensor analysis for robust text-independent speaker Identification. Multiple factors including time, frequency, scale and phase are investigated to extract the essential features of speech signal. In order to explore the shift-invariant characteristic of spectral features, we propose a convolutive model to learn the spectral basis function in tensor structure. Nonnegative assumption is also imposed on the CANDECOMP model to ensure the sparsity and preserve robust features. Experimental results demonstrate that our proposed method can improve the recognition accuracy specifically in noise conditions. © 2012 Binary Information Press.

关键词： Loudspeakers

来源：评论

学校读者我要写书评

暂无评论

Infant cry analysis and detection

Infant cry analysis and detection

引用

IEEE Convention of the Electrical and ELectronic Engineers in Israel

作者： Rami Cohen Yizhar Lavner Signal and Image Processing Laboratory (SIPL) Department of Electrical Engineering Technion-Israel Institute of Technology Haifa Israel Department of Computer Science Tel-Hai Academic College Upper Galilee Israel

In this paper we propose an algorithm for automatic detection of an infant cry. A particular application of this algorithm is the identification of a physical danger to babies, such as situations in which parents leave their children in vehicles. The proposed algorithm is based on two main stages. The first stage involves feature extraction, in which pitch related parameters, MFC (mel-frequency cepstrum) coefficients and short-time energy parameters are extracted from the signal. In the second stage, the signal is classified using the k-NN algorithm and is later verified as a cry signal, based on the pitch and harmonics information. In order to evaluate the performance of the algorithm in real world scenarios, we checked the robustness of the algorithm in the presence of several types of noise, and especially noises such as car horns and car engines that are likely to be present in vehicles. In addition, we addressed real time and low complexity demands during the development of the algorithm. In particular, we used a voice activity detector, which disabled the operation of the algorithm when voice activity was not present. A database of baby cry signals was used for performance evaluation. The results showed good performance of the proposed algorithm, even at low SNR.

关键词： Pediatrics Harmonic analysis Noise Feature extraction Mel frequency cepstral coefficient Detection algorithms Cepstrum

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

Moving shadow detection by nonlinear Tone-Mapping

Moving shadow detection by nonlinear Tone-Mapping

引用

International Conference on Systems, signals and Image processing, IWSSIP

作者： Elad Bullkich Idan Ilan Yair Moshe Yacov Hel-Or Hagit Hel-Or Signal and Image Processing Laboratory (SIPL) Department of Electrical Engineering Technion-Israel Institute of Technology Haifa Israel Google Inc. Mountain View USA Department of Computer Science University of Haifa Haifa Israel

Shadow detection is a well-known problem in image and video processing. Detecting moving shadows is useful in numerous applications such as object detection and tracking. Most works in this area are not suitable for shadow detection using a low-cost outdoor surveillance camera. In this work we suggest a fast shadow detection approach for video surveillance, by comparing each video frame to a continuously updated background image. We differentiate shadow areas from foreground areas by assuming the shadow pixels are associated with background pixels through a nonlinear tone mapping. This assumption is general and applies to various systems and scene conditions. A distance measure between patch images that account for nonlinear tone mapping is calculated by adapting a recently suggested approach for pattern matching termed Matching by Tone Mapping (MTM). We show that the proposed technique is computationally efficient and outperforms state-of-the-art shadow detection techniques in typical surveillance scenarios.

关键词： Surveillance Measurement Image color analysis Cameras Robustness Lighting

来源：评论

学校读者我要写书评

暂无评论

Analysis of ongoing EEG elicited by natural music stimuli using nonnegative tensor factorization

Analysis of ongoing EEG elicited by natural music stimuli us...

引用

20th European signal processing Conference, EUSIPCO 2012

作者： Cong, Fengyu Phan, Anh Huy Zhao, Qibin Nandi, Asoke K. Alluri, Vinoo Toiviainen, Petri Poikonen, Hanna Huotilainen, Minna Cichocki, Andrzej Ristaniemi, Tapani Department of Mathematical Information Technology University of Jyväskylä Finland Laboratory of Advanced Brain Signal Processing RIKEN Brain Science Institute Japan Department of Electrical Engineering and Electronics University of Liverpool United Kingdom Finnish Centre of Excellence in Interdisciplinary Music Research University of Jyväskylä Finland Cognitive Brain Research Unit Institute of Behavioral Sciences University of Helsinki Finland Finnish Institute of Occupational Health Helsinki Finland

ISBN: (纸本)9781467310680

This study proposes a six-step approach to analyze ongoing EEG elicited by 512-second long natural music (modern tango). The spectrogram of the ongoing EEG was first produced, and then a fourth-order tensor including the spectrograms of multiple channels of multiple participants was decomposed via nonnegative tensor factorization (NTF) into four factors, including temporal, spectral and spatial components, and multi-domain features of all participants. We found one extracted temporal component by NTF significantly (p

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Generalized geometry-based optimal power control in wireless networks

Generalized geometry-based optimal power control in wireless...

引用

IEEE Communications Society Conference on Sensor and Ad Hoc Communications and Networks (SECON)

作者： Wei Wang Kang G. Shin Zhaoyang Zhang Wenbo Wang Tao Peng Department of Information Science and Electronic Engineering Zhejiang Provincial Key Laboratory of Information Network Technology University of Zhejiang Hangzhou China Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA Wireless Signal Processing and Networking Laboratory Beijing University of Posts and Telecommunications Beijing China

Geometry-based optimal power control was proposed in [14] to transform the power-control problem to a new geometrical problem on the position relationship between a line and some points. This scheme provides a novel visual perspective and lowers the complexity of optimization. We generalize this scheme to a larger class of power-control optimization problems so as to maximize the network utility with multiple average and peak power constraints in wireless networks. To facilitate the handling of the geometrical model, we define a subset of geometrical models with specified characteristics, called a regular geometrical model, and derive the type of power-control problems eligible for the regular geometrical model. For such a type of problems, two strategies are proposed for the construction of the regular geometrical model. Utilizing geometrical properties, we propose a novel geometry-based optimization scheme for the general power-control problem. Its computational complexity is significantly lower than the conventional algorithms. We also provide a further discussion on irregular geometrical model cases. Finally, we provide two examples of deploying the proposed geometry-based power-control scheme.

关键词： Optimization Silicon Computational modeling Interference Complexity theory Power control Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Weighted Constrained Total Least-Square Algorithm for Source Localization Using TDOA Measurements

Weighted Constrained Total Least-Square Algorithm for Source...

引用

2011 International Conference on Future Wireless Networks and Information Systems(ICFWI 2011)

作者： Cao Jing-min Wei He-wen Yu Jian Science and Technology On Blind Signal Processing Laboratory

A weight constrained total least-square(WCTLS) is developed for source localization by using time difference of arrival(TDOA) *** WCTLS algorithm not only exploits the structure information of the measurement matrix,but also utilizes the prior knowledge of the TDOA *** bias and covariance of the proposed WCTLS algorithm are also *** results show that the proposed estimator achieves better performance than that of the constrained total least square,and it attains the Cramer-Rao lower bound at a sufficiently low noise level.

关键词： Weight constrained total least square(WCTLS),time difference of arrival(TDOA),source localization

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：