检索结果-内蒙古大学图书馆

Extending CSP to detect motor imagery in a four-class BCI

Journal of Information and Computational Science 2012年第1期9卷 143-151页

作者： Fang, Yonghui Chen, Minyou Zheng, Xufei Harrison, R.F. State Key Laboratory of Power Transmission Equipment and System Security New Technology Chongqing University Chongqing 400044 China School of Electronic and Information Engineering Southwest University Chongqing 400715 China College of Computer Science Sichuan University Chengdu 610065 China Department of Automatic Control and Systems Engineering University of Sheffield United Kingdom

Brain computer Interface (BCI) provides a direct communication channel from brain to peripheral equipment. Common Spatial Patterns (CSP) is wildly used to extract features for electroencephalogram (EEG). However, basic CSP only suits two-class discrimination and is unable to solve multi-class discrimination problems. This paper proposes a modified CSP method termed Bisearch Common Spatial Patterns (BCSP) to solve a four-class BCI problem. In BCSP, the Fisher's Linear Discriminant Analysis (LDA) is used to discriminate among the four motor imagery tasks. The BCSP can effectively reduce the number of the basic CSP, and thus makes the overall classification procedure more efficient. The Graz BCI data set from the BCI 2008 competition be used to verify the effectiveness of the BCSP. Simulation results show that BCSP has better performance than other extension schemes. © 2012 Binary Information Press January 2012.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Optimized fuzzy PDC controller for nonlinear systems with T-S model mismatch

Optimized fuzzy PDC controller for nonlinear systems with T-...

引用

2011 International Conference on Advanced Mechatronic systems, ICAMechS 2011

作者： Zeiaee, A. Kharrati, H. Khanmohammadi, S. Electrical and Computer Engineering Department Tabriz University Iran Control Engineering Japan Department of System and Control Engineering Japan

ISBN: (纸本)9780955529375

In this paper, a heuristic method based on Genetic Algorithms (GA) is proposed to improve the performance of Fuzzy Logic controllers (FLCs) designed for Takagi-Sugeno (T-S) model of nonlinear plants by Parallel Distributed Compensation (PDC) technique. Generally, T-S models might not represent the dynamics of nonlinear plants accurately. Due to this mismatch, sometimes the response of the controlled nonlinear plant is not as desirable as the response of the corresponding T-S model controlled by the same FLC. Despite the fact that there is a flurry of research on the stability of FLCs applied to T-S model of nonlinear systems, the stability matters of FLCs applied to nonlinear systems is still a challenge. It is obvious that the performance of FLCs is entirely affected by the characteristics of membership functions. Thus, by tuning the type or parameters of fuzzy controller's membership functions using GA, the drawbacks caused by model mismatch can be decreased. In fact, the proposed method concerns the applicability of fuzzy PDC controllers to nonlinear plants and does not confide itself to dealing with T-S models. Thus, the improved fuzzy PDC controller is a fine-tuned PDC controller that can compensate the nonlinear plant as well as the corresponding T-S model. In order to verify the introduced strategy, the problem of balancing and swing up of an inverted pendulum on a cart is considered as a nonlinear case study. The simulation results demonstrate the effectiveness of the improved PDC. © 2011 Intl Journal of Adv Mechatr.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Ride Comfort Performance of Electric Vehicle Conversion with Active Suspension system

Ride Comfort Performance of Electric Vehicle Conversion with...

引用

SICE Annual Conference

作者： Saiful Anuar ABU BAKAR Ryosuke MASUDA Hiromu HASHIMOTO Takeshi INABA Hishamuddin JAMALUDDIN Roslan ABD. RAHMAN Pakharuddin MOHD. SAMIN Department of Applied Computer Engineering Department of Mechanical Engineering Tokai University Department of System Dynamics and Control Universiti Teknologi Malaysia Department of Automotive Engineering Universiti Teknologi Malaysia

ISBN: (纸本)9781467322591

This paper presents the investigation on the performance of active suspension system in the electric vehicle (EV) conversion, controlled by the stability augmentation system algorithm [9] and a newly proposed SAS-Skyhook algorithm. The evaluations were done using a validated 7-degrees-freedom (7DOF) of vehicle's ride model. The mathematical modelling of the vehicle model is described. A worst case scenario of random road profiles was considered to evaluate the performance of the active suspension system. The method of subjecting the random road profiles input is also described. It was found that in general, the active suspension improved the EV conversion's ride comfort performance significantly, compared to the passive suspension system. In terms of the comparison between the active suspension system controlled by the SAS and SAS-Skyhook algorithms, the ride comfort performance provided by the SAS-Skyhook algorithm is the most significant.

关键词： Electric Vehicle Conversion Ride Comfort Active Suspension system

来源：评论

学校读者我要写书评

暂无评论

Feature extraction of motor imagery in BCI with approximate entropy

引用

Journal of Computational Information systems 2012年第6期8卷 2485-2491页

作者： Fang, Yonghui Chen, Minyou Zheng, Xufei Harrison, Robert F State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing University Chongqing 400044 China School of Electronic and Information Engineering Southwest University Chongqing 400715 China College of Computer Science Sichuan University Chengdu 610065 China Department of Automatic Control and Systems Engineering University of Sheffield Sheffield United Kingdom

Approximate Entropy (ApEn) is a regularity statistic that quantifies the unpredictability of fluctuations in a time series and can classify complex systems. This study, ApEn is used to extract features from motor imagery Electroencephalogram (EEC) that containing two motor imagery tasks. This method is different from the traditional way to get the character from EEC. Appropriate parameters must been chosen for different dataset. Two datasets are used in this paper. One comes from BCI Competion2003, the other from the lab of Electromagnetic theory and artincal intelligence, Chongqing University. The results show that ApEn can extract different features in left-hand and right-hand motor imagery EEC efficiently. Comparison between ApEn and Fast Fourier Transform (FFT) shows that ApEn has good capability to the two imagery tasks Brain computer Interface. © 2012 Binary Information Press.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Interpolation of Orientation Distribution Functions (ODFs) in Q-ball Imaging

Interpolation of Orientation Distribution Functions (ODFs) i...

引用

Iranian Conference of Biomedical engineering

作者： Maryam Afzali Emad Fatemizadeh Hamid Soltanian-Zadeh Department of Electrical Engineering Biomedical Signal and Image Processing Laboratory(BiSIPL) Sharif University of Technology Tehran Iran Control and Intelligent Processing Center of Excellence(CIPCE) School of Electrical and Computer Engineering University of Tehran Tehran Iran & Image Analysis Laboratory Radiology Department Henry Ford Health System Detroit Michigan USA

ISBN: (纸本)9781467331289

Diffusion tensor magnetic resonance imaging (DTMRI) is a non-invasive method for investigating the brain white matter structure. It can be used to evaluate fiber bundles in the brain but in the regions with crossing fibers, it fails. To resolve this problem, high angular resolution diffusion imaging (HARDI) with a large number of diffusion encoding directions is used and for reconstruction, the Q-ball method is applied. In this method, orientation distribution function (ODF) of fibers can be calculated. Mathematical models play a crucial role in the field of ODF. For instance, in registering Q-ball images for applications like group analysis or atlas construction, one needs to interpolate ODFs. To this end, principal diffusion directions (PDDs) of each ODF are needed. In this paper, PDDs are defined as vectors that connect the corresponding local maxima of ODF values. Then, ODFs are interpolated using PDDs. The proposed method is evaluated and compared with previous protocols. Experimental results show that the proposed interpolation algorithm preserves the principal direction of fiber tracts without producing any deviations in the tracts. It is shown that changes in the entropy of the interpolated ODFs are almost linear and the bloating effect (blurring of the principal directions) can be removed.

关键词： High angular resolution diffusion imaging (HARDI) Q-ball imaging Orientation distribution function (ODF) Interpolation Principal diffusion direction (PDD)

来源：评论

学校读者我要写书评

暂无评论

Unconstrained Measurement system for Scratching by Limb and Estimation of Scratching Area

Unconstrained Measurement System for Scratching by Limb and ...

引用

International Conference on Intelligent Computational systems(ICICS’2012);International Conference on Mechanical,Automotive and Materials engineering(ICMAME’2012);International Conference on Electronics,Biomedical engineering and its Applications(ICEBEA’2012);International Conference on Ecological,Environmental and Biological Sciences(ICEEBS’2012);International Conference on Business,Economics,Management and Behavioral Sciences (ICBEMBS’2012);International Conference on Applied Mathematics and Pharmaceutical Sciences(ICAMPS’2012)

作者： Toshihiro.Shino Yosuke.Kurihara Syoko.Nukaya Kajiro.Watanabe Hiroshi.Tanaka the Graduate School of Hosei University the Dept. of Computer and Information Science Faculty of Science and Technology Seikei University the Division of Advanced Therapeutical Sciences Tokyo Medical and Dental University the System Control Engineering Department Faculty of Engineering Hosei University the University Center for Information Medicine Tokyo Medical and Dental University

This paper describes an unconstrained measurement system for scratching motion. We have proposed an unconstrained bed monitoring system by piezoceramic sensors that could detect heartbeat respiration and body movement. The system could measure the bed vibrations due to the motion of the person on the bed. In this paper, we apply this unconstrained bed sensing method to the system for detecting scratching motion. The proposed sensors are placed under the bed feet. When the subject is lying on the bed, the output signals from the sensors are proportional to the magnitude of the vibration due to the body movement of the subject. Hence, it is possible to detect the subject's scratching motion from the output signals. Furthermore, also with output signals from the three ceramic sensors, the proposed system can detect the direction of the body movement, which enables us to estimate the scratched area. We evaluated three scratching motions using the proposed system in the validity experiment as follows: Case 1 is the subject's scratching the right cheek with right hand;Case 2 is the subject's scratching the back after turning over, and;Case 3 is the subject's scratching the shin with another foot. As the results of the experiment, we identified the scratching signals that enable the determination when the scratching occurred. Furthermore, the difference among the amplitudes of the output signals enabled us to estimate where the subject scratched.

关键词： body movement, itchy, piezoceramics, scratching unconstrained bed monitoring.

来源：评论

学校读者我要写书评

暂无评论

Impaired Resting State Networks in Temporal Lobe Epilepsy: A Resting State fMRI Study

Impaired Resting State Networks in Temporal Lobe Epilepsy: A...

引用

Iranian Conference of Biomedical engineering

作者： Marzie Fereidouni Hamid Soltanian-Zadeh Quan Jiang Kost V. Elisevich Control and Intelligent Processing Center of Excellence (CIPCE) School of Electrical and Computer Engineering University of Tehran Tehran Iran NMR Laboratory Department of Neurology Henry Ford Hospital Detroit Michigan USA epartment of Clinical Neurosciences Spectrum Health System Grand Rapids Michigan USA

ISBN: (纸本)9781467331289

Temporal lobe epilepsy (TLE) is the most common type of human refractory epilepsy and can cause widespread impairments in brain functionality. Previous studies show functional and structural abnormalities in different regions of TLE patients' brain in comparison with normal subjects. However, limited studies have been done on connectivity abnormalities of resting state networks (RSN) in TLE patients and most of them studied default mode network (DMN) only. In this paper, nine independent spatial maps of the brain were identified by applying independent component analysis (ICA) on functional magnetic resonance images (fMRI) of the subjects. These maps were classified into four resting state networks: visual network, auditory network, default mode network, and attention network (including right and left fronto-parietal networks and core network). Functional connectivity between time courses of the nine components were computed and then compared between TLE patients and healthy subjects. Results show that there are significant between-group differences in functional connectivity among different brain networks including decrease in functional connections of visual cortex with two other networks, DMN and attention network, and decrease in functional connectivity between DMN and left fronto-parietal network. An increase in functional connectivity between DMN and core network and also between right fronto-parietal network and auditory network is observed.

关键词： Temporal lobe epilepsy Functional connectivity Resting state networks

来源：评论

学校读者我要写书评

暂无评论

Voxel-based treatment prediction of glioblastoma multiform tumor using diffusion tensor imaging

Voxel-based treatment prediction of glioblastoma multiform t...

引用

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Hadi Sabahi Hamid Soltanian-Zadeh Lisa Scarpace Tom Mikkelsen Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran Image Analysis Laboratory Radiology Department Henry Ford Hospital Detroit MI USA Hermelin Brain Tumor Research Center Neurosurgery Department Henry Ford Health System Detroit MI USA

This paper proposes a method to predict the effect of Bevacizumab therapy on Glioblastoma Multiform (GBM) tumors. The prediction is critical for effective treatment planning. The proposed method is developed and evaluated using Diffusion Tensor Imaging (DTI) and post-contrast T1-weighted Magnetic Resonance Images (pc-T1-MRI) of 14 patients with GBM tumors gathered before and after the treatment. First, the proposed method calculates diffusion anisotropy indices (DAI) of all voxels in the brain. These diffusion anisotropy indices are Fractional Anisotropy (FA), Mean Diffusivity (MD), Relative Anisotropy (RA), and Volume Ratio (VR). Then, it registers post-treatment pc-T1-MRI and pre-treatment DAI maps to pre-treatment pc-T1-MRI. Next, it uses a thresholding method to segment the tumor from pc-T1-MRI studies. Comparing Gd-enhanced voxels of the pre- and post-treatment pc-T1-MRI, the DAIs of the tumor are labeled based on their response to the treatment. The voxels of 7 patients are randomly selected to train 4 classifiers (ANN, SVM, KNN, and ANFIS) and then all voxels of the other 7 patients are used to test them. For each classifier, four performance measures (sensitivity, specificity, positive predictive value, and accuracy) are calculated. Experimental results show that the ANFIS is more accurate than the other classifiers in predicting the treatment response.

关键词： Support vector machines Noise Magnetic resonance imaging Sensitivity Tumors Biomedical imaging Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Cross-application user modeling based on Linked Data

引用

ICIC Express Letters 2012年第10期6卷 2471-2480页

作者： Ye, Na Zhao, Yinliang Zhao, Xia Liu, Enjie Clapworthy, Gordon School of Electronic and Information Engineering Xi'an Jiaotong University No. 28 Xianning West Road Xi'an 710049 China School of Information and Control Engineering Xi'an University of Architecture and Technology No. 13 Yanta Road Xi'an 710055 China Department of Computer Science and Technology University of Bedfordshire Luton Bedfordshire LU1 3JU United Kingdom

Nowadays, there is an increasing tendency for business applications to collect knowledge and information about their users in order to provide the customers with personalized information. Cross-application user modeling provides a more complete user model view and more value-added user information to all relevant applications. In this paper, a Linked Data-driven user modeling approach is proposed to create links among the user model fragments of the same user who registers for different applications and, from these, construct a virtually global user model. A framework is presented to support the modeling and its application. From experiments, the proposed solution appears to be more feasible and to offer increased flexibility and better personalization. © 2012 ISSN.

关键词： Linked data

来源：评论

学校读者我要写书评

暂无评论

Using Data-Level Parallelism to Accelerate Instruction -Level Redundancy

Using Data-Level Parallelism to Accelerate Instruction -Leve...

引用

World Automation Congress

作者： Yu Hu Zhong liang Chen Xiaowei Li Key Laboratory of Computer System and Architecture Institute of Computing Technology CAS Beijing 100190 China Department of Electrical and Computer Engineering Northeastern University Boston MA 02115 USA

ISBN: (纸本)9781467344975

Instruction-level redundancy is an effective scheme to reduce the susceptibility of microprocessors to soft errors, offering high error detection and recovery capability;however, it usually incurs significant performance degradation due to resource racing. Motivated by the fact that narrow-width operands are commonly seen in applications, we exploit data-level parallelism to accelerate instruction-level redundancy. For the instructions within sphere of replication (SoR) of data-level redundancy, normal and redundant versions of the narrow-width operand of the instruction are folded into one register to share the same functional unit during execution hence alleviating resource racing. The other instructions are all protected by instructionlevel redundancy. We run SPECint2000 benchmarks on a modified version of SimpleScalar simulator, and synthesize the extra hardware to evaluate area overhead of the proposed pipeline. Experimental results show that our acceleration scheme outperforms conventional instruction-level redundancy by 13% in IPC. Besides, the extra area overhead is negligible.

关键词： Keywords Data-level redundancy Instruction-level redundancy Narrow-width value Sphere of replication

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：