检索结果-内蒙古大学图书馆

A hybrid rough set - Particle swarm algorithm for image pixel classification

A hybrid rough set - Particle swarm algorithm for image pixe...

6th International Conference on Hybrid Intelligent Systems and 4th Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006

作者： Das, Swagatam Abraham, Ajith Sarkar, Subir Kumar Department of Electronics and Telecommunication Engineering Jadavpur University Kolkata 700032 India IITA Professorship Program School of Computer Science Yonsei University Seoul Korea Republic of

ISBN: (纸本)0769526624

This article presents a framework to hybridize the rough set theory with a famous swarm intelligence algorithm known as Particle Swarm Optimization (PSO). The hybrid rough-PSO technique has been used for grouping the pixels of an image in its intensity space. Medical and remote sensing satellite images become corrupted with noise very often. Fast and efficient segmentation of such noisy images (which is essential for their further interpretation in many cases) has remained a challenging problem for years. In this work, we treat image segmentation as a clustering problem. Each cluster is modeled with a rough set. PSO is employed to tune the threshold and relative importance of upper and lower approximations of the rough sets. Davies-Bouldin clustering validity index is used as the fitness function, which is minimized while arriving at an optimal partitioning. © 2006 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Genetic programming with incremental learning for grammatical inference

Genetic programming with incremental learning for grammatica...

引用

6th International Conference on Hybrid Intelligent Systems and 4th Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006

作者： Rodrigues, Ernesto Lopes, Heitor Silvério Graduate Program in Electrical Engineering and Computer Science Federal University of Technology - Paraná Av. 7 de setembro 3165 80230-901 Curitiba Brazil

ISBN: (纸本)0769526624

We present an evolutionary algorithm for the inference of context-free grammars from positive and negative examples. The algorithm is based on genetic programming and uses a local optimization operator that is capable of improving the learning task. Ordinary genetic operators are modified so as to bias the search. The system was evaluated using Tomita 's language examples and results were compared with another similar approach. Results show that the proposed approach is promising and more robust than the other one. © 2006 IEEE.

关键词： Context free grammars

来源：评论

学校读者我要写书评

暂无评论

Workshop on imaging science development for cancer prevention and preemption

引用

Cancer Biomarkers 2007年第1期3卷 1-33页

作者： Kelloff, Gary J. Sullivan, Daniel C. Baker, Houston Clarke, Lawrence P. Nordstrom, Robert Tatum, James L. Dorfman, Gary S. Jacobs, Paula Berg, Christine D. Pomper, Martin G. Birrer, Michael J. Tempero, Margaret Higley, Howard R. Petty, Brenda Gumbs Sigman, Caroline C. Maley, Carlo Sharma, Prateek Wax, Adam Ginsberg, Gregory G. Dannenberg, Andrew J. Hawk, Ernest T. Messing, Edward M. Grossman, H. Barton Harisinghani, Mukesh Bigio, Irving J. Griebel, Donna Henson, Donald E. Fabian, Carol J. Ferrara, Katherine Fantini, Sergio Schnall, Mitchell D. Zujewski, Jo Anne Hayes, Wendy Klein, Eric A. DeMarzo, Angelo Ocak, Iclal Ketterling, Jeffrey A. Tempany, Clare Shtern, Faina Parnes, Howard L. Gomez, Jorge Srivastava, Sudhir Szabo, Eva Lam, Stephen Seibel, Eric J. Massion, Pierre McLennan, Geoffrey Cleary, Kevin Suh, Robert Burt, Randall W. Pfeiffer, Ruth M. Hoffman, John M. Roy, Hemant K. Wang, Thomas Limburg, Paul J. El-Deiry, Wafik S. Papadimitrakopoulou, Vali Hittelman, Walter N. MacAulay, Calum Veltri, Robert W. Solomonzz, Diane Jeronimo, Jose Richards-Kortum, Rebecca Johnson, Karen A. Viner, Jaye L. Stratton, Steven P. Rajadhyaksha, Milind Dhawan, Atam NIH/NCI/DCTD Cancer Imaging Program Bethesda MD United States NIH/NCI/DCTD Cancer Imaging Program NCI-Frederick Frederick MD United States NIH/NCI/DCP Early Detection Research Group Bethesda MD United States The Johns Hopkins University School of Medicine Departments of Radiology Pharmacology and Oncology Division of Neuroradiology Baltimore MD United States NIH/NCI/CCR Cell and Cancer Biology Branch Bethesda MD United States University of California San Francisco Department of Medicine Division of Medical Oncology San Francisco CA United States CCS Associates Inc. Mountain View CA United States Wistar Institute Molecular and Cellular Oncogenesis Program Philadelphia PA United States University of Kansas School of Medicine VA Hospital Kansas City MO United States Duke University Department of Biomedical Engineering Medical Physics Program Durham NC United States University of Pennsylvania School of Medicine Department of Gastroenterology Philadelphia PA United States New York Presbyterian Hospital Weill Medical College of Cornell University New York NY United States NIH/NCI/OD Office of Centers for Training and Resources Bethesda MD United States University of Rochester Medical Center Department of Urology Rochester NY United States University of Texas MD Anderson Cancer Center Department of Urology Houston TX United States Massachusetts General Hospital Abdominal Imaging/Interventional Radiology Boston MA United States Boston University Biomedical Engineering Electrical and Computer Engineering and Physics Boston MA United States NIH/NCI/DCP Gastrointestinal and Other Cancers Research Group Bethesda MD United States The George Washington University Cancer Institute Office of Cancer Prevention and Control Washington DC United States University of Kansas Cancer Center Clinical Oncology Kansas City KS United States University of California Davis Department of Biomedical Engineering Davis CA United States Tufts University De

The concept of intraepithelial neoplasm (IEN) as a near-obligate precursor of cancers has generated opportunities to examine drug or device intervention strategies that may reverse or retard the sometimes lengthy process of carcinogenesis. Chemopreventive agents with high therapeutic indices, well-monitored for efficacy and safety, are greatly needed, as is development of less invasive or minimally disruptive visualization and assessment methods to safely screen nominally healthy but at-risk patients, often for extended periods of time and at repeated intervals. Imaging devices, alone or in combination with anticancer drugs, may also provide novel interventions to treat or prevent precancer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Guest editorial nonlinear optimization of communication systems

引用

IEEE Journal on Selected Areas in Communications 2006年第8期24卷 1421-1423页

作者： Chiang, Mung Low, Steven H. Luo, Zhi-Quan Shroff, Ness B. Yu, Wei Steenstrup, M. Princeton University Department of Electrical Engineering Program in Applied and Computational Mathematics Princeton NJ 08544 United States California Institute of Technology Department of Computer Science Pasadena CA 91125 United States University of Minnesota Department of Electrical and Computer Engineering Minneapolis MN 55455 United States Purdue University School of Electrical and Computer Engineering West Lafayette IN 47907 United States University of Toronto Edward S. Rogers Sr. Department of Electrical and Computer Engineering Toronto Ont. M4S 3G5 Canada

No abstract available

关键词： Communication systems Design optimization Communication system control Optimization methods Protocols Distributed algorithms Power system modeling Nonlinear control systems Lagrangian functions Surges

来源：评论

学校读者我要写书评

暂无评论

A light-weight tool for teaching the development and evaluation of requirements documents

A light-weight tool for teaching the development and evaluat...

引用

113th Annual ASEE Conference and Exposition, 2006

作者： Garbers, Ben Periyasamy, Kasi University of Wisconsin La Crosse United States Master of Software Engineering Program University of Wisconsin La Crosse United States IBM Computer Science Department Program University of Wisconsin La Crosse United States

Writing correct and consistent software requirements specification (SRS) is one of the most important goals of a requirements engineering process. The SRS serves as the basis for subsequent design, testing and maintenance of the software product. The more errors and inconsistencies contained in an SRS, the more time and efforts are required to correct them at a later stage in the development process. Most SRS documents are manually typed using a word processor and hence the writer is responsible for ensuring the correctness and consistency of the document. Without adequate tool support, the manual construction and analysis of SRS documents is a tedious process and is error-prone. This paper describes an interactive tool developed at the University of Wisconsin-La Crosse that assists students preparing an SRS document based on the IEEE standard 83019981. The tool provides an easy-to-use interface and the ability to create, edit, load and save SRS documents. In addition, it evaluates the requirements document based on criteria published by the Software Metrics program at the Software Assurance Technology Center, NASA2. A function-point metrics analyzer is also built into the tool so that the efforts required to complete the project specified in the document can be evaluated. © American Society for engineering Education, 2006.

关键词： computer aided software engineering

来源：评论

学校读者我要写书评

暂无评论

Investigating the user mobility in wireless mobile networks through real measurements 06

Investigating the user mobility in wireless mobile networks ...

引用

2nd Conference on Future Networking Technologies, CoNEXT'06

作者： Campos, Carlos Alberto V. De Moraes, Luis Felipe M. Systems Engineering and Computer Science Program-COPPE HighSpeed Networks Laboratory RAVEL Federal University of Rio de Janeiro/UFRJ Rio de Janeiro RJ Brazil

In this paper is proposed a real mobility characterization study for wireless devices. For this, we use mobility metrics and statistic analysis to evaluate the behavior of device movement components.

ISBN: (纸本)1595934561

In this paper is proposed a real mobility characterization study for wireless devices. For this, we use mobility metrics and statistic analysis to evaluate the behavior of device movement components.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Identifying offline muscle strength profiles sufficient for short-duration FES-LCE exercise: A PAC learning model approach

引用

Journal of Clinical Monitoring and Computing 2006年第3期20卷 209-220页

作者： Trumbower, Randy D. Rajasekaran, Sanguthevar Faghri, Pouran D. Sensory Motor Performance Program Rehabilitation Institute of Chicago Northwestern University Storrs CT United States School of Engineering Department of Computer Science and Engineering Storrs CT United States School of Allied Health Department of Health Promotion University of Connecticut 358 Mansfield Road Storrs CT 06269-2101 United States

Functional electrical stimulation-induced leg cycle ergometry (FES-LCE) provides therapeutic exercise for persons with spinal cord injury (SCI). However, there exists no systematic approach to predict whether an individual has sufficient thigh muscle strength necessary for FES-LCE exercise. Objective. To develop and test a Probably Approximately Correct (PAC) learning model as a predictor of thigh muscle strengths sufficient for short-duration FES-LCE exercise and compare the model's performance with other well-known statistical methods. Methods. Six healthy male individuals with SCI, having age (32.0 ± 12.5 years), height (1.8 ± 0.04 m), and weight (79.12 ± 10.76 kg), participated in static and dynamic experiments. During static experiments, absolute crank torque measurements were used to estimate thigh muscle strengths in response to maximum FES intensities of 70 mA, 105 mA, and 140 mA at fixed crank positions on an FES-LCE. During dynamic experiments, changes in power output measurements were used to classify rider performance as 'Fatigue' or 'No Fatigue' during short-duration FES-LCE at maximum stimulation intensities of 70 mA, 105 mA, and 140 mA and flywheel resistance levels of 0/8th, 1/8th, and 2/8th kilopounds. A Probably Approximately Correct (PAC) learning model was developed to classify static offline muscle strength observations with online rider performances. PAC's discriminatory power was compared with logistic regression (LR), Fisher's linear discriminant analysis (LDA), and an artificial neural network (ANN) model. Results. PAC and ANN learning models correctly identified 100% of the training examples. PAC's average performance on the validation set was 93.1%. The ANN and LR performed comparable with 92.8% and 93.1% accuracy, respectively. The LDA method faired well on the validation set at 89.9%. Conclusions. PAC performed well in identifying muscle strengths associated with the online performance criterion. Although PAC did not perform best during

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

The temporal changes of arterial blood flow dynamics

The temporal changes of arterial blood flow dynamics

引用

作者： Shibeshi, Shewaferaw S. Collins, William E. Computer Science Program Lynchburg College 1501 Lakeside Drive Lynchburg VA 24501 United States Department of Chemical Engineering Howard University Washington DC 20059 United States

computer simulation of hydrodynamic models, using two dimensional T-junction geometry and experimentally determined arterial wave velocities, shows turbulent blood flow behavior of varying degrees at different critical points of the cardiac cycle. The flow disturbances get stronger when the waveform changes from systolic acceleration to diastolic deceleration. Finally, in the region of diastolic endpoints the flow demonstrates transition to stability due to subsiding blood pressure and arterial wall remodeling effect as a preparation for the start of more streamlined flow at the subsequent cycle. Such flow variations have implications on the initiation of atherosclerosis and interventional surgical procedures designed to alleviate such diseases. First, oscillating wall shear stress can induce different cell signaling pathways which can facilitate the initiation and progression of arterial diseases. Second, through advective transport of atherogenic plasma proteins, filtration to the artery wall is known to be regulated. Third, such constantly changing flows can cause early failure of arterial grafts and could also negatively affect their compatibility with the host tissue. Copyright 2006 ISA. All Rights Reserved.

关键词： Blood

来源：评论

学校读者我要写书评

暂无评论

Multimode locomotion via SuperBot reconfigurable robots

Multimode locomotion via SuperBot reconfigurable robots

引用

作者： Shen, Wei-Min Krivokon, Maks Chiu, Harris Everist, Jacob Rubenstein, Michael Venkatesh, Jagadesh Information Sciences Institute Computer Science Department University of Southern California University of Southern California Polymorphic Robotics Laboratory Information Science Institute Polymorphic Robotics Laboratory Product Development Engineering Program University of Southern California

One of the most challenging issues for a self-sustaining robotic system is how to use its limited resources to accomplish a large variety of tasks. The scope of such tasks could include transportation, exploration, construction, inspection, maintenance, in-situ resource utilization, and support for astronauts. This paper proposes a modular and reconfigurable solution for this challenge by allowing a robot to support multiple modes of locomotion and select the appropriate mode for the task at hand. This solution relies on robots that are made of reconfigurable modules. Each locomotion mode consists of a set of characteristics for the environment type, speed, turning-ability, energy-efficiency, and recoverability from failures. This paper demonstrates a solution using the SuperBot robot that combines advantages from M-TRAN, CONRO, ATRON, and other chain-based and lattice-based robots. At the present, a single real SuperBot module can move, turn, sidewind, maneuver, and travel on batteries up to 500 m on carpet in an office environment. In physics-based simulation, SuperBot modules can perform multimodal locomotions such as snake, caterpillar, insect, spider, rolling track, H-walker, etc. It can move at speeds of up to 1.0 m/s on flat terrain using less than 6 W per module, and climb slopes of no less 40 degrees.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Evolving neural networks for pharmaceutical research

Evolving neural networks for pharmaceutical research

引用

2006 International Conference on Hybrid Information Technology, ICHIT 2006

作者： Grosan, Crina Abraham, Ajith Tigan, Stefan Tae, Gyu Chang Dong, Hwan Kim Department of Computer Science Babes-Bolyai University Cluj-Napoca 3400 Romania IITA Professorship Program School of Computer Science and Engineering Chung-Ang University Seoul 156-756 Korea Republic of University Iuliu Haţieganu Faculty of Medicine Department of Biostatistics and Medical Informatics Cluj-Napoca Romania

ISBN: (纸本)0769526748

This article presents the application of Meta-Learning Evolutionary Artificial Neural Network (MLEANN) for a pharmaceutical research problem. Designing drugs is a current problem in the pharmaceutical research domain. By designing a drug we mean to choose some variables of drug formulation (inputs), for obtaining optimal characteristics of drug (outputs). To solve such a problem we propose an evolutionary artificial neural network and the performance is compared with a neuro-fuzzy system and an artificial neural network trained using scaled conjugate gradient algorithm. This research used the experimental data obtained from the Laboratory of Pharmaceutical Techniques of the Faculty of Pharmacy in Cluj-Napoca, Romania. Bootstrap techniques were used to generate more samples of data and the number of experimental data is reduced due to the costs and time durations of experimentations. We obtain in this way a better estimation of some drug parameters. Experiment results indicate that the proposed method is efficient. © 2006 IEEE.

关键词： 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：