检索结果-内蒙古大学图书馆

Subspace Semi-supervised Fisher Discriminant Analysis

自动化学报 2009年第12期35卷 1513-1519页

作者： YANG Wu-Yi LIANG Wei XIN Le ZHANG Shu-Wu Hi-tech Innovation Center Institute of Automation Chinese Academy of Sciences Beijing 100190 P.R. China Key Laboratory of Underwater Acoustic Communication and Marine Information Technology of the Minister of Education Xiamen University Xiamen 361005 P. R. China College of Oceanography and Environmental Science Xiamen University Xiamen 361005 P. R. China School of Electronics Information and Control Engineering Beijing University of Technology Beijing 100124 P. R. China

Fisher discriminant analysis (FDA) is a popular method for supervised dimensionality reduction. FDA seeks for an embedding transformation such that the ratio of the between-class scatter to the within-class scatter is maximized. Labeled data, however, often consume much time and are expensive to obtain, as they require the efforts of human annotators. In order to cope with the problem of effectively combining unlabeled data with labeled data to find the embedding transformation, we propose a novel method, called subspace semi-supervised Fisher discriminant analysis (SSFDA), for semi-supervised dimensionality reduction. SSFDA aims to find an embedding transformation that respects the discriminant structure inferred from the labeled data and the intrinsic geometrical structure inferred from both the labeled and unlabeled data. We also show that SSFDA can be extended to nonlinear dimensionality reduction scenarios by applying the kernel trick. The experimental results on face recognition demonstrate the effectiveness of our proposed algorithm.

关键词：费希尔判别分析法鉴别分析离散度降维方法

来源：评论

学校读者我要写书评

暂无评论

A novel load variation compensation algorithm in a sensor-less brushless DC motor drive for a reciprocating compressor

A novel load variation compensation algorithm in a sensor-le...

引用

International Conference on Telecommunications Energy (INTELEC)

作者： Sang-Taek Lee Hee-Jun Kim Dae-Kyong Kim Kwang-Woon Lee Dept. of Electronics Electrical Control and Instrumentation Engineering Hanyang Univ. Korea Digital Convergence Center Korea Electronics Technology Institute Korea School of Electrical Engineering and Computer Science Hanyang Univ. Korea Division of Maritime Electronics and Communication Engineering Mokpo National Maritime Univ. Korea

ISBN: (纸本)9781424424900

This paper presents a novel load variation compensation algorithm in a sensor-less BLDC motor drive for a reciprocating compressor. Periodic load variation of a reciprocating compressor leads to commutation position error and instantaneous speed variation and causes large peak currents. The major concept of this study includes tracking the pattern of load torque and controlling the motor input voltage by the commutation point and PWM depending on the tracked load torque. The suggested method can reduce the cost because this method does not require additional current sensing or voltage comparison circuit. The utility of the suggested algorithm was confirmed by simulation and experimental results of a sensor-less BLDC motor drive.

关键词： Load management Brushless DC motors Torque Commutation Pistons Voltage control Refrigeration Rotors Home appliances Force control

来源：评论

学校读者我要写书评

暂无评论

New technologies demonstrated at Formula Electric and Hybrid Italy 2008

引用

World Electric Vehicle Journal 2009年第1期3卷 160-171页

作者： Brusaglino, Giampiero Buja, Giuseppe Carello, Massimiliana Carlucci, Antonio Paolo Onder, Christopher H. Razzetti, Monica Italy Università di Padova Department of Electrical Engineering Padova Italy Politecnico di Torino Dipartimento di Meccanica Torino Italy Università del Salento Facoltà di Ingegneria CREA-Centrro Ricerca Energia e Ambiente Italy Swiss Federal Institute of Technology Zurich Measurement and Control Laboratory Switzerland Italy

From 1 to 3 October 2008 the Formula Electric and Hybrid Italy took place in the Safety Testing Center of Fiat Group Automobiles in Orbassano (TO), Italy. This fourth edition of Formula EHI, an international competitive demonstration of research outcomes from university student teams, has brought to the attention of the public and of the industry new technologies and innovative applications in the area of the systems addressing the ecological mobility. Teams from five European countries were the protagonists of the event. Several projects, components, systems and concept have been presented, related to advanced technologies for battery electric, hybrid and fuel cell vehicles. New technology hybrid, fuel cell and electric vehicles took part to the dynamic test on track for the evaluation of energy efficiency performance and dynamic behaviour. The 2008 event was a further step of the editions of Formula TECH held in the previous years and offered a benchmarking overview of the progress of the technology in the field of electrically propelled vehicles. © 2009 AVERE.

关键词： Fuel cells

来源：评论

学校读者我要写书评

暂无评论

Improved frame-layer bit allocation scheme for H.264/AVC rate control

引用

Journal of Shanghai Jiaotong University (Science) 2009年第2期14 E卷 143-148页

作者： Lin, Gui-Xu Zheng, Shi-Bao Zhu, Liang-Jia Institute of Image Communication and Information Processing Department of Electronic Engineering Shanghai Jiaotong University Shanghai 200240 China Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiaotong University Shanghai 200240 China Department of Automatic Control National University of Defense Technology Changsha 410073 China

In this paper, we aim at improving the video quality degradation due to high motions or scene changes. An improved frame-layer bit allocation scheme for H.264/AVC rate control is proposed. First, current frame is pre-encoded in 16 × 16 modes with a fixed quantization parameter (QP). The frame coding complexity is then measured based on the resulting bits and peak signal-to-ratio (PSNR) in the pre-coding stage. Finally, a bit budget is calculated for current frame according to its coding complexity and inter-frame PSNR fluctuation, combined with the buffer status. Simulation results show that, in comparison with the H.264 adopted rate control scheme, our method is more efficient to suppress the sharp PSNR drops caused by high motions and scene changes. The visual quality variations in a sequence are also relieved. Copyright.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Distribution of combustible gas alarm based on embedded Ethernet technology

引用

Journal of Harbin institute of technology(New Series) 2008年第2期15卷 220-223页

作者：丁喜波张俊杰王洋 Space Optics Research Center School of AstronauticsHarbin Institute of Technology College of Measure-control Technology & Communication Engineering Harbin University Science and Technology Heilongjiang Provincial Institute of Measurement and Verification

One kind of combustible gas alarms based on industrial Ethernet was designed to prevent the gas leakage in industrial production sites, The alarm adopted the high performance microprocessor LPC2214 as the main chip. The embedded operating system μC/OS-Ⅱand TCP/IP protocol stack uIP running on LPC2214 constitute a development platform of application of the combustible gas alarm, The test shows that it can automatically and continuously detect combustible gas in industrial production sites in several positions;it can give out sound-light alarm and take protective measures immediately against the gas leakage; and it can send the detected data to PC through the Ethernet interface to realize the remote detection. The designed project provides a reference to design industrial devices based on industrial Ethernet

关键词： industrial Ethernet combustible gas alarm embedded system

来源：评论

学校读者我要写书评

暂无评论

Feature extraction of electroencephalogram of photic evoked spikes with slow burst and its automatic detection

Feature extraction of electroencephalogram of photic evoked ...

引用

SICE Annual Conference

作者： Shigeto Nishida Takenao Sugi Akio Ikeda Takashi Nagamine Hiroshi Shibasaki Masatoshi Nakamura Department of Computer and Communication Engineering Fukuoka Institute of Technology Fukuoka Japan Department of Electrical and Electronic Engineering Saga University Saga Japan Department of Neurology School of Medicine Kyoto University Kyoto Japan Department of System Neuroscience Sapporo Medical University Sapporo Japan Takeda General Hospital Kyoto Japan Department of Advanced Systems Control Engineering Saga University Saga Japan

A method for detecting spikes and slow burst in photic evoked electroencephalogram (EEG) was proposed. The spikes were detected by combining methods of the morphological filter and the similarity coefficient in the time domain. The slow burst was detected by using pole of AR model in the frequency domain. The proposed method was applied for the photic evoked EEG data containing spikes and slow burst, and brought satisfactory coincidence with the results interpreted by a qualified electroencephalographer.

关键词： Feature extraction Electroencephalography Filters Frequency Biomedical engineering Medical diagnostic imaging Epilepsy Nervous system Neuroscience Hospitals

来源：评论

学校读者我要写书评

暂无评论

6-DOF MOTION AND CENTER OF ROTATION ESTIMATION BASED ON STEREO VISION

引用

Chinese Journal of Mechanical engineering 2008年第2期21卷 87-92页

作者： CAO Wanpeng BI Wei CHE Rensheng GUO Wenbo YE Dong Department of Automatic Measurement and Control Harbin Institute of Technology Harbin 150001 China China Academy of Machinery Science and Technology Beijing 100044 China Department of Electrical Engineering and Automation Harbin Institute of Technology Harbin 150001 China

A new motion model and estimation algorithm is proposed to compute the general rigid motion object＇s 6-DOF motion parameters and center of rotation based on stereo vision. The object＇s 6-DOF motion model is designed from the rigid object＇s motion character under the two defined reference frames. According to the rigid object＇s motion model and motion dynamics knowledge, the corresponding motion algorithm to compute the 6-DOF motion parameters is worked out. By the rigid object pure rotation motion model and space sphere geometry knowledge, the center of rotation may be calculated after eliminating the translation motion out of the 6-DOF motion. The motion equations are educed based on the motion model and the closed-form solutions are figured out. To heighten the motion estimation algorithm＇s robust, RANSAC algorithm is applied to delete the outliers. Simulation and real experiments are conducted and the experiment results are analyzed. The results prove the motion model＇s correction and algorithm＇s validity.

关键词： Motion estimation Center of rotation 6-DOF motion Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Gene expression data classification based on non-negative matrix factorization

Gene expression data classification based on non-negative ma...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Chun-Hou Zheng Ping Zhang Lei Zhang Xin-Xin Liu Ju Han College of Information and Communication Technology Qufu Normal University Rizhao Shandong China Intelligent Computing Laboratory Institute of Intelligent Machines Chinese Academy and Sciences Hefei Anhui China Institute of automation Qufu Normal University Rizhao Shandong China Biometric Research Center Department of Computing Hong Kong Polytechnic University Hong Kong China Department of Control Engineering Academy of Armored Forces Engineering Beijing China

With the advent of DNA microarrays, it is now possible to use the microarrays data for tumor classification. Yet previous works have not use the nonnegative information of gene expression data. In this paper, we propose a new method for tumor classification using gene expression data. In this method, we first select genes using nonnegative matrix factorization (NMF) and sparse NMF (SNMF). Then we extract features of the selected gene data by virtue of NMF and SNMF. At last, support vector machines (SVM) was applied to classify the tumor samples based on the extracted features. To better fit for classification aim, a modified SNMF algorithm is also proposed. The experimental results on three microarray datasets show that the method is efficient and feasible.

关键词： Gene expression Principal component analysis Independent component analysis Neoplasms Data mining Feature extraction Data analysis Humans Bioinformatics DNA

来源：评论

学校读者我要写书评

暂无评论

Efficiency-aware and fairness-aware joint-layer optimization for downlink data scheduling in OFDM

引用

Science in China(Series F) 2008年第2期51卷 171-182页

作者： GUO KunQi SUN LiXin WANG Ping JIA ShiLou Shanghai Research Center for Wireless Communications Shanghai Institute of Microsystem and Infor- mation Technology Chinese Academy of Sciences Shanghai 200050 China School of Measurement & Control Technology and Communication Engineering Harbin University of Science and Technology Harbin 150080 China Communication Research Center Harbin Institute of Technology Harbin 150001 China

Efficiency and fairness are two crucial issues to be considered for resource alloca- tion in multi-user wireless networks. Based on the joint optimization of physical layer and data link layer, an optimization model is derived to achieve efficient and fair downlink data scheduling in multi-user OFDM wireless networks by maximizing the total utility function with respect to the average waiting time of user queue. A dynamic sub-carrier allocation algorithm （DSAA） based on the optimization model is proposed in order to obtain the maximization of the total scheduling utility. Effi- ciency is improved by combining DSAA with time scale interference predictor （TSIP） which at large time scales predict ON/OFF period of user data with temporal corre- lation structure across multiple time scales in multi-user interference environment. Simulation results verify the efficiency and fairness of the scheme.

关键词： OFDM efficiency and fairness joint-layer scheduling utility function

来源：评论

学校读者我要写书评

暂无评论

Decomposition of VEP and dominant rhythm components during photic stimulation by use of EEG model

Decomposition of VEP and dominant rhythm components during p...

引用

IEEE/ICME International Conference on Complex Medical engineering, CME

作者： T. Sugi S. Tsuchiya S. Nishida Y. Goto S. Tobimatsu M. Nakamura Department of Electrical and Electronic Engineering Saga University Saga Japan Department of Advanced Systems Saga University Saga Japan Department of Information and Communication Fukuoka Institute of Technology Fukuoka Japan Department of Occupational Therapy Department of Clinical Neurophysiology Kyushu University Fukuoka Japan Department of Clinical Neurophysiology Kyushu University Fukuoka Japan Department of Advanced Systems Control Engineering Saga University Saga Japan

Dominant rhythm in electroencephalographic (EEG) records is seen at the posterior to occipital region as a primary component of background activity during waking state with closed eyes and is decreased or disappeared by the exogenous factors such as visual stimuli to eyes and so on. Visual evoked potential (VEP) can also be seen in EEG at the posterior to occipital regions during photic stimulation (PS). Frequency components of VEP are depended upon the frequency of stimuli and that of dominant rhythm in case of healthy adult is around 10 Hz. Therefore, components of VEP and dominant rhythm are almost overlapped when the frequency of photo stimuli is near around 10 Hz. VEP component can be extracted from the background activity by using the averaging method, but the accurate estimation of dominant rhythm component in such condition has difficulties due to the overlapping of both components in frequency domain. Some of the authors have proposed the EEG model with Markov process amplitude (MPA EEG model) in the past. The MPA EEG model has possibilities to separate the components that construct the original EEG into each one in the frequency domain. In this study, component decomposition of VEP and dominant rhythm of recorded EEG was done by using the MPA EEG model. EEGs with PS were recorded from three healthy young adults. Five seconds continuous EEG time series with PS and without PS were selected from the original data, and were transferred to the periodogram information by the FFT method. Then, the model parameters were calculated. The initial values of model parameters were determined from the periodogram of raw EEG during PS, and were optimized by Fletcher-Powell method. In the original data under PS with 10 Hz, VEP component and dominant rhythm component were overlapped each other. Proposed method decomposed the original data into five components; first harmonic VEP, second harmonic VEP, dominant rhythm, slower noise and others. Characteristics for the depressi

关键词： Rhythm Electroencephalography Brain modeling Frequency estimation Frequency domain analysis Eyes Markov processes Power harmonic filters control engineering Neurophysiology

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：