检索结果-内蒙古大学图书馆

A tuning parameter selector method for the gsvm-scad in determining significant genes and biological pathway

ICIC Express Letters 2012年第4期6卷 851-856页

作者： Misman, Muhammad Faiz Mohamad, Mohd Saberi Deris, Safaai Hashim, Siti Zaiton Mohd Leham, Nurdyana Ibrahim, Zuwairie Artificial Intelligence and Bioinformatics Research Group Faculty of Computer Science and Information Systems 81310 UTM Skudai Johor Darul Takzim Malaysia Department of Mechatronics and Robotics Center for Artificial Intelligence and Robotics Faculty of Electrical Engineering Universiti Teknologi Malaysia 81310 UTM Skudai Johor Darul Takzim Malaysia

A hybrid of support vector machines and a smoothly clipped absolute deviation with group-specific penalty terms (gSVM-SCAD) is a penalized classifier that has been used to identify and select significant pathways in pathway-based microarray analysis. Despite its advantages in identifying significant pathways, the gSVM-SCAD has some limitations, as it depends on the proper choice of tuning parameter. If the tuning parameter is too small, it can bring little sparsity and overfit to the classifier model, while if it is too large, it can make much sparsity to the classifier model and produce poor discriminating power. Therefore, it is important to choose an appropriate tuning parameter selector method for the gSVM-SCAD. The generalized cross validation (GACV) has been widely used as a tuning parameter selector method. Unfortunately, GACV has some limitations where it poorly performs when dealing with the low number of variables (in this paper referred as genes) and large sample sizes. This is because some pathways contain not more than 100 genes and even some pathways contain less than 10 genes. This scenario can lead to the poor performance of SCAD in selecting the informative genes and simultaneously identifying significant ones. In order to surmount the limitations of the gSVM-SCAD, we proposed to use the B-type generalized approximate cross validation (BGACV) as a tuning parameter selector method for gSVM-SCAD. ICIC International © 2012.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Motion detection based on simulated depth measurement

Frontiers in Artificial Intelligence and Applications

引用

Frontiers in Artificial Intelligence and Applications 2012年 243卷 335-344页

作者： Lim, Chern Hong Kadyrov, Alexander Seng Chan, Chee Liu, Honghai Centre of Image and Signal Processing Faculty of Computer Science and Information Technology University of Malaya Malaysia Intelligent Systems and Biomedical Robotics Group School of Creative Technologies University of Portsmouth United Kingdom

ISBN: (纸本)9781614991045

Depth information is a very important cue to understand human motion. In this paper, we establish that, even with no real depth camera, the concept of obtaining depth information is applicable for human motion detection. We propose a new motion detection method based on the concept of a real world video surveillance system enhanced with depth cameras. It is developed for detecting and analysing human motion. First, it imitates depth measuring process of a depth camera. Specially chosen in the image during the initialization process, view points play the role of cameras, whereas the depth is measured as a distance from these points to the human figure in the image. Initially, the body is partitioned into four segments to obtain the information about which part of the body is moving. Then, in course of the working cycle of the method, the received depth values are constantly subtracted from the previously obtained values, and the intensity of the body motion is calculated using root mean square. The method has been tested on actions taken from a standard motion dataset (IXMAS). It proved to be stable and reliable. © 2012 The authors and IOS Press. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Aerial service robotics: The AIRobots perspective

Aerial service robotics: The AIRobots perspective

引用

2012 2nd International Conference on Applied robotics for the Power Industry, CARPI 2012

作者： Marconi, L. Basile, F. Caprari, G. Carloni, R. Chiacchio, P. Hurzeler, C. Lippiello, V. Naldi, R. Nikolic, J. Siciliano, B. Stramigioli, S. Zwicker, E. CASY-DEIS University of Bologna Italy Università degli Studi di Salerno Italy Alstom Inspection Robotics Switzerland Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Netherlands Eidgenossische Technische Hochschule Zürich Switzerland PRISMA Lab Università degli Studi di Napoli Federico II Italy

ISBN: (纸本)9781467345873

This paper presents the main vision and research activities of the ongoing European project AIRobots (Innovative Aerial Service Robot for Remote Inspection by Contact, ***). The goal of AIRobots is to develop a new generation of aerial service robots capable of supporting human beings in all those activities that require the ability to interact actively and safely with environments not constrained on ground but, indeed, airborne. Besides presenting the main ideas and the research activities within the three-year project, the paper shows the first technological outcomes obtained during the first year and a half of activity. ©2012 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Biologically inspired intrinsically motivated learning for service robots based on novelty detection and habituation

Biologically inspired intrinsically motivated learning for s...

引用

IEEE International Conference on robotics and Biomimetics

作者： Yiannis Gatsoulis Chris Burbridge T. Martin McGinnity Intelligent Systems Research Centre Faculty of Computing and Engineering University of Ulster Derry UK Intelligent Robotics Laboratory School of Computer Science University of Birmingham Birmingham UK

The effective operation of service robots relies on developmental programs that allow the robot to expand its knowledge about its dynamic operating environment. Motivation theories from neuroscience and neuropsychology study the underlying mechanisms that drive the engagement of biological creatures to certain activities, such as learning. This research uses a physical Willow Garage PR2 robot, which is equipped with a cumulative learning mechanism driven by the intrinsic motivation of novelty detection based on computational models of biological habituation. It cumulatively learns the 360° appearance of novel real-world objects by picking them up. This paper discusses the theoretical motivations and background information on intrinsic motivations as novelty detection. The results and conclusions from the experimental study are presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Canonical Decomposition of Multiports Revisited: Properties and Relations to Fundamental Principles of Physics

引用

IFAC Proceedings Volumes 2012年第2期45卷 404-408页

作者： Peter C. Breedveld University of Twente Faculty of Electrical Engineering Mathematics and Computer Science Robotics and Mechatronics Laboratory (CE) P.O. Box 217 Enschede 7500 AE Netherlands (Tel: +31 53 489 2792)

Abstract Properties of decompositions of multiport models are discussed. In particular, it is shown that the congruent canonical decomposition of multiport storage elements or multiport resistors that is based on Choleski factorization of their Jacobians can be causally inverted without generating algebraic loops and that an arbitrary number of ports of such a multiport may be dualized without generating essential gyrators in its decomposition. As a result, it is argued that the congruent canonical decomposition is a preferred decomposition, in particular from a computational point of view.

关键词： port-based modeling multiport bond graphs decomposition Choleski factorization energy power entropy

来源：评论

学校读者我要写书评

暂无评论

A Further Study on Short Term Memory Improvement by Neurofeedback

A Further Study on Short Term Memory Improvement by Neurofee...

引用

International Conference on Biomedical Engineering and Biotechnology (iCBEB)

作者： Wenya Nan Joao Pedro Rodrigues Feng Wan Peng Un Mak Pui In Mak Mang I. Vai Agostinho Rosa Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macao China LaSEEB-System and Robotics Institute Instituto Superior Tecnico Technical University of Lisbon Portugal

Our previous study successfully improved short term memory by individual alpha neurofeedback training. However, short term memory and its improvement in different languages are still not clear. Therefore, the purpose of this paper was to evaluate the memory performance in alphabetic and ideographic language groups. Besides, the relationship between initial memory and its improvement was investigated. The results indicated short term memory in ideographic language was higher than those in alphabetic language and forward digit span improvement was positive related to its initial performance.

关键词： Noise measurement Training Neurofeedback Electroencephalography Correlation Educational institutions Electrodes

来源：评论

学校读者我要写书评

暂无评论

Fault Detection and Isolation for Inertial Measurement Units

Fault Detection and Isolation for Inertial Measurement Units

引用

IEEE Conference on Decision and Control

作者： S. Brás P. Rosa C. Silvestre P. Oliveira Laboratory of Robotics and Systems in Engineering and Science (LARSyS) Instituto Superior Técnico Universidade Técnica de Lisboa Lisbon Portugal Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macao China

This paper addresses the problem of Fault Detection and Isolation (FDI) for navigation systems equipped with sensors providing inertial measurements and vector observations. Two strategies are proposed. The first one takes advantage of existing hardware redundancy, providing sufficient conditions for the isolation of faults. The second approach exploits the analytical redundancy between the angular velocity measurements and the vector observations, by resorting to Set-Valued Observers (SVOs). The behavior of both strategies are illustrated in simulation.

关键词： Vectors Redundancy Noise Sensor systems Angular velocity Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Continuous Reactive-based Position-Attitude Control of Quadrotors

Continuous Reactive-based Position-Attitude Control of Quadr...

引用

American Control Conference

作者： Anand Sanchez Vicente Parra-Vega Chinpei Tang Fatima Oliva-Palomo Carlos Izaguirre-Espinosa Robotics and Advanced Manufacturing Division Research Center for Advanced Studies (Cinvestav) Saltillo Campus Mexico Faculty of Engineering The Erik Johnson School of Engineering and Computer Science University of Texas at Dallas USA

ISBN: (纸本)9781457710957

A new control scheme for position-orientation tracking of underactuated quadrotor robotic vehicle is proposed. A quaternion-based sliding surface parametrizes the open-loop error equation of orientation dynamics, then a second order sliding mode (SOSM) is synthesized for global exponential stabilization of attitude coordinates along an orientation equilibrium manifold. This SOSM for any initial condition leads to a simplified design of a torque PD controller for position dynamics, for globally uniformly ultimately bounded of position trajectories. The SOSM reacts to the effect of the PD as if it were an endogenous persistent disturbance, which vanishes until it reaches its equilibrium position manifold. In contrast to other results that consider the full model without linearization nor further simplifications, our proposal yields a controller which is smooth and does not require the dynamic model. Since the parametrization of attitude representation is global, aggressive maneuvering capabilities are exhibited. Simulations are presented for a variety of flight regimes, including carry out helixes and loops at high angular velocities. Real-time experiments provide a glimpse of the closed-loop performance for a custom made quadrotor.

关键词： Vehicle dynamics Quaternions Strontium Torque Manifolds Angular velocity Attitude control

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

Automatika 2012年第2期53卷 103-106页

作者： Martínez-Salamero, Luis Milanovič, Miro Rovira i Virgili University School of Electrical and Computer Engineering Department of Electrical Electronic and Automatic Control Engineering Spain University of Maribor Faculty of Electrical Engineering and Computer Science Institute for Robotics Slovenia

来源：评论

学校读者我要写书评

暂无评论

A landmark-based controller for global asymptotic stabilization on SE(3)

A landmark-based controller for global asymptotic stabilizat...

引用

IEEE Conference on Decision and Control

作者： Pedro Casau Ricardo G. Sanfelice Rita Cunha Carlos Silvestre Department of Electrical Engineering and Computer Science and Institute for Robotics and Systems in Engineering and Science (LARSyS) Instituto Superior Técnico Universidade Técnica de Lisboa Lisboa Portugal Department of AeroSpace and Mechanical Engineering University of Arizona AZ USA Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macao China

In this paper, we address the problem of designing a landmark-based control law that robustly globally asymptotically stabilizes a rigid body at a desired equilibrium point on the SE(3) manifold. Synergistic potential functions are combined within a hybrid systems framework to generate such a hybrid control law. The proposed control law is solely a function of vector measurements characterizing the position of some given landmarks. We provide sufficient conditions on the geometry of the landmarks to solve the given problem. Finally, the proposed solution is simulated and compared with an almost global continuous feedback control law.

关键词： Vectors Eigenvalues and eigenfunctions Noise Robustness Feedback control Manifolds Geometry

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：