检索结果-内蒙古大学图书馆

Conference of the North American Fuzzy Information Processing Society - NAFIPS

作者： M. Makrehchi M. Kamel Pattern Analysis and Machine Intelligence Lab Department of Systems Design Engineering University of Waterloo Waterloo ONT Canada Department of Systems Design Engineering University of Waterloo Waterloo Ontario Canada

An unsupervised keyword extraction method based on corpora is proposed. After representing each document in the collection by a fuzzy set of candidate keywords, the problem is translated into finding appropriate fuzzy membership degree for each candidate. In order to determine the membership degrees, first, all terms of the vocabulary are mapped into a two-dimensional space called class-collection map by obtaining two newly proposed fuzzy measures called fuzzy significance and fuzzy relevance for each term. At the second step, the mapped terms are grouped into three categories, namely, features, keywords and stopwords that are discriminated by their contribution to the meaning of the documents. Instead of a clustering approach for grouping purpose, a fuzzy rule base is provided. The method is independent of the language and data dimensionality. It does not require the use of dictionary, thesaurus nor natural language processing.

关键词： Fuzzy sets Vocabulary Web pages Abstracts Text mining Fuzzy systems Pattern analysis Machine intelligence System analysis and design design engineering

来源：评论

学校读者我要写书评

暂无评论

Modeling of Dielectrophoretic Forces and Electrorotational Torque towards Nonlinear Control of Micromanipulation System 35

Modeling of Dielectrophoretic Forces and Electrorotational T...

引用

第35届中国控制会议

作者： Luo Hua Sun Zhendong Sun Weijie Yeow John T W College of Automation Science and Engineering South China University of Technology Key Lab of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Systems Design Engineering University of Waterloo 200 University Avenue West

ISBN: (纸本)9781509009107

This paper presents a modeling methodology able to determine the analytical representations of conventional dielectrophoretic force, travelling-wave dielectrophoretic force and electroratation torque generated by quadrupole polynomial electrodes on a sphere microparticle. Firstly, theoretical analysis is performed to illustrate the linear-dependence of the electric potential distribution on the applied electrode voltages. Then finite element method and mathematical preprocessing are conducted to obtain the analytical expression of the electric potential. Consequently, the corresponding analytical representations for conventional dielectrophoretic force, travelling-wave dielectrophoretic force and electroratation torque with respect to the applied electrode voltages are obtained and the developed analytical models lead to a nonlinear nonaffine micromanipulation system. Numerical simulations are conducted by finite element method solver to demonstrate the effectiveness of the proposed modeling method. Finally, A dynamic feedback control is proposed for stable motion control of a microparticle in such a *** results illustrate the performance of the proposed control.

关键词： Micromanipulation AC electrokinetic Analytical model Nonaffine nonlinear system Dynamic feedback control

来源：评论

学校读者我要写书评

暂无评论

Weighted combination of neural network ensembles

Weighted combination of neural network ensembles

引用

2002 International Joint Conference on Neural Networks (IJCNN '02)

作者： Wanas, Nayer M. Kamel, Mohamed S. Pattern Analysis Mach. Intell. Lab. Dept. of Systems Design Engineering University of Waterloo Waterloo Ont. N2L-3G1 Canada

There exist numerous schemes and methods to determine the output of an ensemble of classifiers. The most common approach being the majority vote. Furthermore, we might expect that an improvement can be achieved if there is a method by which we may weigh the members of the ensemble according to their individual performance. The feature based approach presented an architecture that tries to approach this target. However, if there is a way that the final classification may influence these weights we should expect an increased performance in the overall classification task. In this paper we present a new training algorithm that utilizes a feedback mechanism to iteratively improve the classification capability of the feature based approach. This approach is compared with the standard training method as well as standard aggregation schemes for combining classifier ensembles. Empirical results show that this architecture improved on classification accuracy.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Effect of brightness of assisted target detection cues in a simulated search and rescue task

Effect of brightness of assisted target detection cues in a ...

引用

54th Human Factors and Ergonomics Society Annual Meeting 2010, HFES 2010

作者： Giang, Wayne Keefe, Allan Keillor, Jocelyn Department of Systems Design Engineering University of Waterloo Waterloo Canada Defence Research and Development Canada - Toronto Toronto Canada Institute for Aerospace Research Flight Research Lab. National Research Council of Canada Ottawa Canada

ISBN: (纸本)9781617820885

Assisted target detection (ATD) systems are designed to direct the user's attention to relevant areas of the display, but the majority of the research into the use of such systems does not consider the design of the cue itself. Within a search and rescue (SAR) context, there is a possibility that cues designed to facilitate effective search could in fact distract a SAR operator's search of the terrain, reducing the probability of locating a crashed aircraft. In order to determine if salience matters in the design of an ATD system for video-based sensor systems, it is important to study the impact of highly salient cues on visual search. In a previous experiment where the saliency of a cue was varied using different levels of cue brightness in a search task with static imagery, it was found that the more salient cues produced faster response times without any detrimental effects on accuracy. In the present experiment we used dynamic imagery from a SAR simulator. We found that cues of different brightness improved the sensitivity (d') of participants when compared to conditions in which no cues were available, but there was no evidence of any differences between the different levels of cue brightness. These findings suggest that cue brightness may not influence the salience of cues as much as one might expect in the context of a full-motion simulation. Other visual dimensions such as visual onsets or colour may potentially play a larger role in determining the saliency of ATD system cues when used in a task involving motion such as SAR.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

Optimization of a neural dynamics based controller for a nonholonomic mobile robot using genetic algorithms

Optimization of a neural dynamics based controller for a non...

引用

Fourth International Conference on Control and Automation

作者： Li, Hao Yang, Simon X. Karray, Fakhri Lab. Systems Design Engineering University of Waterloo Waterloo Ont. N2L 3G1 Canada Lab. School of Engineering University of Guelph Guelph Ont. NIG 2W1 Canada

ISBN: (纸本)078037777X

In this paper, a neural dynamics based controller for a nonholonomic mobile robot is proposed. The turn angle of the robot in the proposed model is characterized by a biologically inspired shunting equation derived from Hodgkin and Huxley's membrane equation. This model is capable of generating smooth steering velocity command that drives the robot to track desired paths. Some parameters in the proposed neural dynamics based controller need to be selected. A genetic algorithm is designed to optimize the model parameters that can guarantee the convergence of tracking error of the mobile robot. Simulation studies of a four-degree-of-freedom mobile robot are conducted, which demonstrate the effectiveness of the proposed motion controller. © 2003 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Errors in Searching for Abstraction Hierarchy Information

引用

Proceedings of the Human Factors and Ergonomics Society Annual Meeting 2000年第1期44卷 270 - 273页

作者： Catherine M. Burns Cognitive Engineering Laboratory Department of Mechanical and Industrial Engineering University of Toronto Toronto CanadaNow at the Advanced Interface Design Laboratory Department of Systems Design Engineering University of Waterloo Waterloo Ontario Canada N2L 3G1

The abstraction hierarchy (Rasmussen, 1985) is a modelling framework proposed for the design of displays to aid problem-solving. The model links information along two dimensions — means-end links of abstraction, and part-whole links of decomposition. While these links connect the model, little research has directly explored the perceptual support of these links. Based on one abstraction hierarchy for a simulated power plant, we designed three graphical displays that provided differential perceptual support for means-end links. The displays provided space-time, only spatial, or only temporal integration of means-end links. Subjects performed a link-spanning information search task using one of the displays. Significant differences were found in search accuracy and in the types of errors that occurred when using the three displays. This research sheds light on the integration of means-end information in ecological displays and demonstrates a novel information search task for evaluating large ecological displays.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solar scramble: An educational children's game for collaborative multi-touch digital tabletops 10

Solar scramble: An educational children's game for collabora...

引用

Proceedings of the 28th ACM International Conference on design of Communication

作者： Kelly, Ashley R. Wallace, James R. Cerar, Katie Randall, Neil McClelland, Phillip Seto, Amanda Mindy Department of English Language and Literature Canada Department of Systems Design Engineering Canada University of Waterloo 200 University Avenue Waterloo ON N2L 3G1 Canada Critical Media Lab. Canada

ISBN: (纸本)9781450304030

Our experience report describes the design and development of an educational game for interactive, multi-touch tabletop displays. The game has been designed for children aged 5-10 on the SMART Tabletop platform. This experience report describes the process, design and development of our application and the implications we have drawn from this work in the design of educational technologies for interactive multi-touch tabletops. To investigate the effectiveness of our design, and to identify potential issues in deploying our software, we conducted participant interviews. Based on our design and development process, as well as our participant feedback, we have identified several key issues regarding the development of educational software for K-5 aged (5-10 years old) children on digital tabletops. This research was conducted at the university of waterloo jointly by the Collaborative systems laboratory and the Critical Media lab. Copyright 2010 ACM.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Performance optimization of surface electromyography (sEMG) based biometric sensing system for both verification and identification

arXiv

引用

arXiv 2021年

作者： Pradhan, Ashirbad He, Jiayuan Jiang, Ning Engineering Bionics Lab Department of Systems Design Engineering Faculty of Engineering University of Waterloo Waterloo Canada

Recently, surface electromyography (sEMG) emerged as a novel biometric authentication method. Since EMG system parameters, such as the feature extraction methods and the number of channels, have been known to affect system performances, it is important to investigate these effects on the performance of the sEMG-based biometric system to determine optimal system parameters. In this study, three robust feature extraction methods, Time-domain (TD) feature, Frequency Division Technique (FDT), and Autoregressive (AR) feature, and their combinations were investigated while the number of channels varying from one to eight. For these system parameters, the performance of sixteen static wrist and hand gestures was systematically investigated in two authentication modes: verification and identification. The results from 24 participants showed that the TD features significantly (p © 2021, CC BY-NC-SA.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Open access dataset for electromyography-based multi-code biometric authentication

arXiv

引用

arXiv 2022年

作者： Pradhan, Ashirbad He, Jiayuan Jiang, Ning Engineering Bionics Lab Department of Systems Design Engineering Faculty of Engineering University of Waterloo Waterloo Canada

Recently, electromyogram (EMG) has been proposed as a novel biometrics for addressing some key limitations of current biometrics. EMG signals are inherently different for individuals (biometrics), and they can realize multi-length codes or passwords (for example, by performing different gestures). However, current EMG-based biometric research has two critical limitations: 1) a small subject pool, compared to other more established biometric traits, and 2) limited to single-session data sets. In this study, forearm and wrist EMG data were collected from 43 participants over three different days with long separation (Day 1, 8, and 29) while they performed static hand/wrist gestures. The multi-day biometric authentication resulted in a median EER of 0.017 and 0.025 for the forearm and wrist setup, respectively. These results demonstrated the potential of EMG-based biometrics in practical applications. The large-sample multi-day data set would facilitate further research on EMG-based biometrics and other EMG gesture recognition-based applications. © 2022, CC BY.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A novel computational intelligence approach for multiple-point routing in communication networks

A novel computational intelligence approach for multiple-poi...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： S. Al-Sharhan F. Karray W. Gueaieb Department of Systems Design Engineering University of Waterloo Ontario Canada Pattern Analysis and Machine Intelligence (PAMI) Lab Department of Systems Design Engineering University of Waterloo Waterloo ONT Canada

A new evolutionary algorithm for the constrained multiple destination routing problem is presented. The constrained multicast problem is characterized by a minimum cost multicast tree and a bounded end-to-end delay. It has been proven that this problem is NP-complete. The proposed algorithm is based on a soft computing technique that integrates in an efficient manner the merits of genetic algorithms and concepts of the competitive learning in the artificial neural networks literature. A population based learning algorithm is utilized, among other techniques, to construct a delay bounded multicast tree. A salient feature of the algorithm is the adaptive learning concept that achieves an efficient trade-off between the exploration and exploitation of the search space.

关键词： Computational intelligence Routing Communication networks Multicast algorithms Delay Evolutionary computation Costs Computer networks Genetic algorithms Artificial neural networks

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：