检索结果-内蒙古大学图书馆

8th International Conference on Image and Graphics, ICIG 2015

作者： Zhou, Baoliang Zheng, Aihua Jiang, Bo Li, Chenglong Tang, Jin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology AnHui University Hefei China Key Laboratory of Industry Image Processing and Analysis in Anhui Province Hefei China

ISBN: (纸本)9783319219684

Human salience of pedestrians images is distinctive and has been shown importantly in person re-identification (or pedestrians identification) problem. Thus, how to obtain the salient area of pedestrian images is important for this salience based pedestrians identification problem. In this paper, we first show that this kind of salient area detection can be formulated as a kind of outlier detection problem, and then propose a novel unsupervised salience learning method using a local outlier-detection technique for person re-identification task. The main feature of the proposed salience computation method is that it exploits both distance and density information simultaneously. Experimental results on several datasets show the effectiveness of the proposed salience based person re-identification method. © Springer International Publishing Switzerland 2015.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Coherent motion of chaotic attractors

引用

Physical Review E 2017年第4期96卷 042210-042210页

作者： Patrick Louodop Suman Saha Robert Tchitnga Paulsamy Muruganandam Syamal K. Dana Hilda A. Cerdeira São Paulo State University (UNESP) Instituto de Física Teórica Rua Dr. Bento Teobaldo Ferraz 271 Bloco II Barra Funda 01140-070 São Paulo Brazil Laboratory of Electronics and Signal Processing Faculty of Science Department of Physics University of Dschang P.O. Box 67 Dschang Cameroon Dumkal Institute of Engineering and Technology Murshidabad 742406 India Department of Instrumentation and Electronics Engineering Jadavpur University Kolkata 700090 India Institute of Surface Chemistry and Catalysis University of Ulm Albert-Einstein-Allee 47 89081 Ulm Germany Department of Physics Bharathidasan University Tiruchirapalli 620024 Tamil Nadu India Department of Mathematics Jadavpur University Kolkata 700032 India Centre for Complex System Research Kolkata Kolkata 700094 India

We report a simple model of two drive-response-type coupled chaotic oscillators, where the response system copies the nonlinearity of the driver system. It leads to a coherent motion of the trajectories of the coupled systems that establishes a constant separating distance in time between the driver and the response attractors, and their distance depends upon the initial state. The coupled system responds to external obstacles, modeled by short-duration pulses acting either on the driver or the response system, by a coherent shifting of the distance, and it is able to readjust their distance as and when necessary via mutual exchange of feedback information. We confirm these behaviors with examples of a jerk system, the paradigmatic Rössler system, a tunnel diode system and a Josephson junction–based jerk system, analytically, to an extent, and mostly numerically.

关键词： Coupled oscillators Synchronization

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Brain clocks capture diversity and disparities in aging and dementia across geographically diverse populations

引用

Nature medicine 2024年第12期30卷 3779页

作者： Sebastian Moguilner Sandra Baez Hernan Hernandez Joaquín Migeot Agustina Legaz Raul Gonzalez-Gomez Francesca R Farina Pavel Prado Jhosmary Cuadros Enzo Tagliazucchi Florencia Altschuler Marcelo Adrián Maito María E Godoy Josephine Cruzat Pedro A Valdes-Sosa Francisco Lopera John Fredy Ochoa-Gómez Alfredis Gonzalez Hernandez Jasmin Bonilla-Santos Rodrigo A Gonzalez-Montealegre Renato Anghinah Luís E d'Almeida Manfrinati Sol Fittipaldi Vicente Medel Daniela Olivares Görsev G Yener Javier Escudero Claudio Babiloni Robert Whelan Bahar Güntekin Harun Yırıkoğulları Hernando Santamaria-Garcia Alberto Fernández Lucas David Huepe Gaetano Di Caterina Marcio Soto-Añari Agustina Birba Agustin Sainz-Ballesteros Carlos Coronel-Oliveros Amanuel Yigezu Eduar Herrera Daniel Abasolo Kerry Kilborn Nicolás Rubido Ruaridh A Clark Ruben Herzog Deniz Yerlikaya Kun Hu Mario A Parra Pablo Reyes Adolfo M García Diana L Matallana José Alberto Avila-Funes Andrea Slachevsky María I Behrens Nilton Custodio Juan F Cardona Pablo Barttfeld Ignacio L Brusco Martín A Bruno Ana L Sosa Ortiz Stefanie D Pina-Escudero Leonel T Takada Elisa Resende Katherine L Possin Maira Okada de Oliveira Alejandro Lopez-Valdes Brian Lawlor Ian H Robertson Kenneth S Kosik Claudia Duran-Aniotz Victor Valcour Jennifer S Yokoyama Bruce Miller Agustin Ibanez Latin American Brain Health Institute Universidad Adolfo Ibañez Santiago de Chile Chile. Cognitive Neuroscience Center Universidad de San Andrés Buenos Aires Argentina. Department of Neurology Massachusetts General Hospital and Harvard Medical School Boston MA USA. Universidad de los Andes Bogota Colombia. Global Brain Health Institute (GBHI) University of California San Francisco CA USA. Global Brain Health Institute (GBHI) Trinity College Dublin Dublin Ireland. The University of California Santa Barbara (UCSB) Santa Barbara CA USA. Escuela de Fonoaudiología Universidad San Sebastián Santiago de Chile Chile. Grupo de Bioingeniería Decanato de Investigación Universidad Nacional Experimental del Táchira San Cristóbal Venezuela. Advanced Center for Electrical and Electronic Engineering Universidad Técnica Federico Santa María Valparaíso Chile. University of Buenos Aires Buenos Aires Argentina. The Clinical Hospital of Chengdu Brain Sciences Institute University of Electronic Sciences and Technology of China Chengdu China. Technology of China Chengdu China. Cuban Neuroscience Center La Habana Cuba. Grupo de Neurociencias de Antioquia (GNA) University of Antioquia Medellín Colombia. Department of Psychology Master Program of Clinical Neuropsychology Universidad Surcolombiana Neiva Neiva Colombia. Department of Psychology Universidad Cooperativa de Colombia Arauca Colombia. Neurocognition and Psychophysiology Laboratory Universidad Surcolombiana Neiva Colombia. Reference Center of Behavioural Disturbances and Dementia School of Medicine University of Sao Paulo Sao Paulo Brazil. Traumatic Brain Injury Cognitive Rehabilitation Out-Patient Center University of Sao Paulo Sao Paulo Brazil. Center for Social and Cognitive Neuroscience School of Psychology Universidad Adolfo Ibáñez Santiago Chile. Neuropsychology and Clinical Neuroscience Laboratory (LANNEC) Physiopathology Program-Institute of Biomedical Sciences (ICBM) Neuroscience and East Neuroscience Dep

来源：评论

学校读者我要写书评

暂无评论

Phoneme Recognition Based on Deep Belief Network

Phoneme Recognition Based on Deep Belief Network

引用

International Conference on Information System and Artificial Intelligence (ISAI)

作者： Yue Xie Cai-Rong Zou Rui-Yu Liang Hua-Wei Tao Laboratory of Underwater Acoustic Signal Processing Southeast University Nanjing China College of Electrical Engineering Guangzhou University Guangzhou China College of Communication Engineering Nanjing Institute of Technology Nanjing China School of Information Science and Engineering Southeast University Nanjing China

ISBN: (纸本)9781509015863

To improve the accuracy of phoneme recognition in continuous speech recognition, a new method based on the deep belief network which can extract the posterior probability of phonemeis proposed. Firstly, a deep belief network is pre-trained layer by layer with Restricted Boltzmann Machine, then by adding an output layer called "softmax" to the network, a deep neural network detecting the posterior probability of phoneme can be created. Subsequently, Backward Propagation algorithm is applied to fine-tune the weights discriminatively and make them better at predicting the probability distribution over the states of hidden Markov models. Finally the sequence of the predicted probability distribution is fed into a standard Viterbi decoder. The experiments show that the proposed method has a better performance on the TIMIT dataset than traditional ways.

关键词： Speech recognition Hidden Markov models Training Speech Data models Speech processing Acoustics

来源：评论

学校读者我要写书评

暂无评论

An iterative algorithm for multiple-source detection using an array

An iterative algorithm for multiple-source detection using a...

引用

International Conference on Wireless Communications and signal processing (WCSP)

作者： Jirong Xin Shilian Wang Luxi Lu Laiyuan Luo College of Electronic Science and Engineering National University of Defense Technology Changsha China National Key Laboratory of Science and Technology On Blind Signal Processing Chengdu China

ISBN: (纸本)9781467376884

In multiple source detection of using an array, the threshold of the generalized likelihood ratio test (GLRT) is only related with the noise power. And the false alarm probability will increase when one signal is present in the sidelobe of beamformer's pattern because of energy leakage. A constant false alarm ratio (CFAR) based multiple-source detection algorithm was proposed in this paper. The detection probability and false alarm probability were analyzed theoretically and by simulations, and the threshold setting method was given out. The simulation showed the algorithm proposed can detect out the multiple signals effectively and the false alarm probability keeps constant.

关键词： Arrays Detectors Direction-of-arrival estimation signal to noise ratio Interference Array signal processing

来源：评论

学校读者我要写书评

暂无评论

Proportional integral sliding mode observer for uncertain Takagi Sugeno systems with unknown inputs 7

Proportional integral sliding mode observer for uncertain Ta...

引用

7th International Conference on Modelling, Identification and Control, ICMIC 2015

作者： Elleuch, Ilyes Khedher, Atef Othmen, Kamel Ben Research Laboratory in Automatic Signal Processing and Imaging NationalSchool of Engineers Monastir Tunisia Research Laboratory: LARA Automatic ENIT Higher Institute of Applied Science and Technology Gafsa Tunisia

ISBN: (纸本)9780956715753

This paper deals with the problem of state and faults estimation for nonlinear uncertain systems described by Takagi Sugeno structures (named multiple models). In this work, only actuator are considered, they are considered as unknown inputs. The state and faults estimation is made using a structure of sliding mode observer where an integral term is added. This structure of observer is named proportional integral sliding mode observer. The integral term permits the fault estimation. The observer convergence conditions are formulated in LMI form allowing to compute the observer gains. The proposed proportional integral sliding mode observer is applied in the case of a numerical example showing the efficiency of the fault and state estimation. © 2015 University of Al Qayrawan, Tunisia.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Image authentication and self-recovery scheme based on the rehashing model

引用

Journal of Information Hiding and Multimedia signal processing 2016年第3期7卷 460-474页

作者： Lyu, Wan-Li Chang, Chin-Chen Wang, Feng Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230039 China Department of Information Engineering and Computer Science Feng Chia University 100 Wenhwa Rd. Seatwen Taichung40724 Taiwan Department of Computer Science and Information Engineering Asia University Taichung41354 Taiwan Department of Mathematics and Physics Fujian University of Technology FuzhouFujian350108 China

An effective image tamper localization and self-recovery scheme that uses the rehashing model is proposed in this paper. The aim of the proposed scheme was to reduce the failure rate in detecting image tamper areas and achieve high rates of successful detection. To achieve this aim, the proposed scheme uses a set of hash functions which are called the rehashing model, gained an optimal decreasing collision method to detect tamper areas With an improved and accurate tamper detection rate, the tampered image can be recovered more accurately. The quality of the proposed scheme was tested with gray and color images. The experimental results indicated that the proposed scheme has good performance in locating tamper locations and allows image recovery with an acceptable visual quality up to 50% of the image content tampered. © 2016.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Track Before Detect of Weak Trajectory Using Hidden Markov Model

Track Before Detect of Weak Trajectory Using Hidden Markov M...

引用

International Conference on Computer science and Network technology

作者： Jirong Xin Bo Le Liankun Bo Laiyuan Luo College of Electronic Science and Engineering National University of Defense Technology Changsha China National Key Laboratory of Science and Technology On Blind Signal Processing Chengdu China

ISBN: (纸本)9781467381741

The detect and track of the weak target in Bearing-Time Record (BTR) was studied in this paper. The distribution of the measurements of the BTR was derived. And a method of track before detect algorithm based on Hidden Markov Model was given. The simulation and the experiment with real acoustic data showed the effectiveness of this method. The performance of the two classic algorithms Viterbi and Forward-Backward to solve this problem was also compared.

关键词： track before detector Viterbi algorithm hidden Markov model track initialization Hidden Markov models Viterbi algorithm Track

来源：评论

学校读者我要写书评

暂无评论

Speech Recognition and Synthesis Algorithm for Digital Hearing Aids under Background Noise

Speech Recognition and Synthesis Algorithm for Digital Heari...

引用

International Conference on Information System and Artificial Intelligence (ISAI)

作者： Ming-Yang Zhang Cai-Rong Zou Rui-Yu Liang Li Zhao Laboratory of Under water Acoustic Signal Processing Southeast University Nanjing China College of Electrical Engineering Guangzhou University Guangzhou China College of Communication Engineering Nanjing Institute of Technology Nanjing China School of Information Science and Engineering Southeast University Nanjing China

ISBN: (纸本)9781509015863

The difficulty of speech comprehension under background noise greatly influenced the use of hearing aids. To address this problem, this paper proposes a new hearing aids algorithm based on speech recognition and synthesis. This method is based on the pure speech to build a parameters database. Under the real noisy scene, implement speech recognition for the input speech, and then extract the corresponding parameters according to the results of the recognition and synthesize the pure speech. To improve the noise robustness of speech recognition system, we use a newly proposed kernel power flow orientation coefficients (KPOCs) as the characteristic parameters for training and testing. Because the speech synthesis is based on the parameters of pure speech, the output speech almost does not contain noise, and the difficulty of speech comprehension has great improvement.

关键词： Speech Speech recognition Hidden Markov models Feature extraction Speech processing Kernel Hearing aids

来源：评论

学校读者我要写书评

暂无评论

Multidimensional scaling algorithm of localization with hybrid TOA and AOA measurements

Multidimensional scaling algorithm of localization with hybr...

引用

International Conference on Information, Communications and signal processing

作者： Cao Jing-min He Sham Gao Yu-fei Wan Qun Xu Qiang Department of Electronic Engineering University of Electronic Science and Technology of China Chengdu China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (纸本)9781467372190

Recently, multidimensional scaling (MDS) algorithms have been verified to be robust for the emitter localization. However, the traditional MDS algorithms are based on single one kind of measurement. In this paper, a novel hybrid MDS localization algorithm based on both angle-of-arrival (AOA) and time-of-arrival (TOA) measurements is proposed. In the condition that one of the sensors can obtain the AOA of the emitter, this algorithm utilizes AOA measurement to improve the traditional MDS localization based on TOA measurements. The simulation results demonstrated the improvement of this algorithm.

关键词： Sensors Measurement errors signal processing Mobile communication Wireless sensor networks signal processing algorithms

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：