检索结果-内蒙古大学图书馆

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

Optimizing Wireless Communication using Adaptive Packet Sizing and Turbo Codes

Optimizing Wireless Communication using Adaptive Packet Sizi...

引用

Wireless Telecommunications Symposium, WTS

作者： Manish S. Mittal Jill Gemmill Helmuth F. Orthner Department of Electrical and Computer Engineering University of Alabama Birmingham UK Department of Academic Computing University of Alabama Birmingham UK Department of HSA-Health Informatics Program University of Alabama Birmingham UK

Unlike wired networks, wireless networks have very dynamic channel properties and the data communication suffers from interference, multi-path fading and noise. Since wireless devices are mobile, factors such as energy consumption, effective coverage area and most of all reliability and quality of service are of key importance. The 802.11a/b/g wireless protocols employ static link layer control and transmit packets/frames with pre-determined sizes. This paper focuses on benefits derived from combining adaptive packet/frame sizing with forward error correcting (FEC) turbo codes. Protecting the data frames on the channel, using FEC enhances efficiency of dynamic packet sizing and is shown to increase energy efficiency and communication range. Adaptive packet sizing software from SmartPackets Inc. and turbo code simulations are used to discover parameters that are common to both and affect communication efficiency. A multi-fold improvement in throughput is found when these technologies are used simultaneously

关键词： Wireless communication Turbo codes Forward error correction Wireless networks Data communication Interference Fading Energy consumption Telecommunication network reliability Quality of service

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

International Conference on Hybrid Information Technology, ICHIT

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

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

关键词： Neural networks Pharmaceuticals Drugs Artificial neural networks Computer science Costs Biomedical engineering Biomedical informatics Application software Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Biological network epitomes via topological compression

Biological network epitomes via topological compression

引用

IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS)

作者： Gil Alterovitz Marco F. Ramon Health Science and Technology/Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge USA Children's Hospital Informatics Program at the Harvard-MIT Division of Health Sciences and Technology / Harvard Medical School- Partners Center for Genetics and Genomics Boston 02115 USA.

High-throughput generation of new types of relational biological datasets is creating a demand for network-based signal processing and pattern recognition to provide new insights. Such networks are often too large to interpret visually and too complicated to be explained solely based on local topological properties. Just as signal processing and statistical techniques have been used in traditional, sequential-based biological datasets, so too are methodologies needed to automatically discern patterns in the huge, emerging networks. One way to do this is by transforming these very large networks into discernable epitomes, or abstracts, of the original networks. This work presents an approach for doing this via topological compression. Through capturing nodes' global topologies and subsequent compression, a new network epitome can be derived. Here, this is done with an E. Coli gene regulation network, resulting in biological findings that could not be derived from the local topology of the original network.

关键词： Biological information theory Network topology Genomics Bioinformatics Biomedical signal processing Compression algorithms Visualization Biology Gas insulated transmission lines Computer science

来源：评论

学校读者我要写书评

暂无评论

Gene lethality detection across biological network domains: Hubs versus stochastic global topological analysis

Gene lethality detection across biological network domains: ...

引用

IEEE International Workshop on Genomic Signal Processing and Statistics (GENSIPS)

作者： Gil Alterovitz Vinayak Muralidhar Marco F. Ramoni Health Science and Technology/Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge USA Harvard Medical School-Partners Center for Genetics and Genomics Boston USA Harvard-MIT Division of Health Sciences and Technology Children's Hospital Informatics Program Boston USA

In this paper, we investigate the properties of lethal genes in E. coli, our model organism. Topological analysis of networks of functional interactions among genes has shown that lethal genes share common local connectivity properties. In this paper, we analyze cellular networks across three domains. We show that a stochastic global topological analysis, via random walks, is more effective at predicting gene lethality than simply looking at local topology using the standard hub-based method. We also introduce the possibility of using metabolic pathways to understand lethal genes, as regulating these pathways is among one of the most important functions of the gene-encoded proteins. Additionally, we analyze lethal genes in terms of the Gene Ontology (GO) and find that the graph forms two highly connected clusters that are each GO enriched for specific terms. We also find that lethal metabolic regulators are extremely enriched. Finally, we provide applications of the work and avenues for future research.

关键词： Stochastic processes Proteins Organisms Humans Genomics Bioinformatics Databases Genetics Network topology Production

来源：评论

学校读者我要写书评

暂无评论

Parameter Stability of the Structural-Functional Model GREENLAB-Tomato as Affected by Plant Density and Biomass Data Acquisition

Parameter Stability of the Structural-Functional Model GREEN...

引用

International Symposium on Plant Growth Modeling and Applications (PMA)

作者： G. Louarn Q.X. Dong Y.M. Wang J.F. Barczi P. de Reffye Sino-French Laboratory of Informatics Automation and Applied Mathematics (LIAMA) Chinese Academy and Sciences Beijing China Department of Electronic Information College of Information and Electrical Engineering China Agricultural University Beijing China CIRAD UMR AMAP Montpellier France Digiplant Program INRIA Rocquencourt Le Chesnay France

In this study, we assessed the possibility of using the GREENLAB model to quantitatively simulate adaptive responses of tomato plants competing for light. The model was able to reproduce modifications induced by a reduction of plant spacing in dry matter production and in the allocation pattern. However, the analysis of parameter stability showed that some parameters were environment dependent and that an adjustment of model formalisms was required to explicitly represent the plant response. Model parameters also proved to be sensitive to the data acquisition procedure. We confirmed that target files composed of dry matter records lead to parameters that were better indicators of the carbohydrates metabolism at all densities.

关键词： Stability Bioinformatics Biomass Crops Predictive models Irrigation Production Data visualization Educational institutions Laboratories

来源：评论

学校读者我要写书评

暂无评论

A genetic algorithm for the optimization of cable routing

引用

Systems and Computers in Japan 2006年第7期37卷 61-71页

作者： Ma, Xuan Iida, Kazuhiro Xie, Mengchun Nishino, Junji Odaka, Tomohiro Ogura, Hisakazu Graduate School of Engineering University of Fukui Fukui City 910-8507 Japan Wakayama National College of Technology Gobo City 644-0023 Japan Faculty of Automation and Information Engineering Xi an University of Technology B Techno College Department of Electrical and Computer Engineering Wakayama National College of Technology Information Processing Society of Japan China Mechanical Design Society Department of Systems Engineering University of Electro-Communications Japan Society for Fuzzy Theory and Intelligent Informatics Japanese Academy of Facial Studies Japan Society of Kansei Engineering Graduate Program of Nuclear Power and Energy Safety Engineering Graduate School of Engineering Fukui University IEEE CS ACM IPSJ IEICE JSMBET Department of Human and Artificial Intelligent Systems JSAI Japan SOFT IEEE

In this paper the authors propose a structural method for a genetic algorithm (GA) for the optimization problem of cable routing in which cables have to be laid optimally. When there are no limits on the layout routes, the optimal routes for the individual cables can be found using the Dijkstra method in a finite discrete graph. However, when there are limits on the capacity in the layout routes, optimization cannot be performed using the Dijkstra method. The proposed GA is a two-level hierarchical GA that uses chromosome coding involving two levels. The routes for each cable and the combinations of cable routes are defined respectively, and layout route selection is optimized overall through genetic operations involving these levels. Block crossover and block mutation are used as genetic operations in the first level. In addition, a method to take advantage of lethal genes, which do not satisfy the constraints and are generated in the second level is used. Computer simulations confirm that the two-level hierarchical GA with these genetic operations functions effectively for the optimization problem of cable routing. © 2006 Wiley Periodicals, Inc.

关键词： Electric cable laying

来源：评论

学校读者我要写书评

暂无评论

Conduction heat transfer problem solution using the method of fundamental solutions with the dual reciprocity method

Conduction heat transfer problem solution using the method o...

引用

2005 ASME Summer Heat Transfer Conference, HT 2005

作者： Erdönmez, Cengiz Saygin, Hasan Institute of Informatics Computational Science and Engineering Program Istanbul Technical University Maslak Istanbul 34469 Turkey Institute of Energy Istabul Technical University Maslak Istanbul 34469 Turkey

ISBN: (纸本)0791847314

The method of fundamental solutions (MFS) is first proposed in 1964 by Kupradze and theoretical basis of this method is constructed at the end of 1980's. As a meshless method, no domain meshing is required for MFS. Fundamental solutions are used to solve problems without coping with the singularity on the boundary because of the fictitious boundary defined containing the domain of the problem. In this paper effectiveness of the MFS will be introduced by two test problem for the homogeneous and inhomogeneous modified helmholtz equations. Inhomogeneous terms are approximated by using the method of particular solutions through the dual reciprocity method. The conduction heat transfer problem is defined and transformed to the corresponding elliptic partial differential equation by using finite difference and the method of lines method which gives an inhomogeneous helmholtz equation. Then the problem is solved iteratively by using the MFS. Two test problem are solved by both the finite element method (FEM) and MFS and compared in the figures. It can be seen that as a meshless method, MFS gives very good results for the test problems. The thermal shock problem presented here also gives accurate solutions by using MFS and agrees well with the FEM solution. Copyright © 2005 by ASME.

关键词： Heat conduction

来源：评论

学校读者我要写书评

暂无评论

A comparative evaluation of competitive learning algorithms for edge detection enhancement

A comparative evaluation of competitive learning algorithms ...

引用

13th European Signal Processing Conference, EUSIPCO 2005

作者： Sirin, Tuba Saglam, Mehmet Izzet Erer, Isin Gokmen, Muhittin Ersoy, Okan Informatics Institute Advanced Technologies in Engineering Computer Science and Engineering Maslak Istanbul 34469 Turkey Informatics Institute Advanced Technologies in Engineering Satellite Communication and Remote Sensing Program Maslak Istanbul 34469 Turkey Faculty of Electrical and Electronic Engineering Electronics and Communication Department Maslak Istanbul 34469 Turkey Faculty of Electrical and Electronic Engineering Computer Engineering Department Istanbul Technical University Maslak Istanbul 34469 Turkey Purdue University School of Electrical and Computer Engineering West Lafayette IN United States

ISBN: (纸本)1604238216

Most edge detection algorithms include three main stages: smoothing, differentiation, and labeling. In this paper, we evaluate the performance of algorithms in which competitive learning is applied first to enhance edges, followed by an edge detector to locate the edges. In this way, more detailed and relatively more unbroken edges can be found as compared to the results when an edge detector is applied alone. The algorithms compared are K-Means, SOM and SOGR for clustering, and Canny and GED for edge detection. Perceptionally, best results were obtained with the GED-SOGR algorithm. The SOGR is also considerably simpler and faster than the SOM algorithm.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Edge detection in multispectral remote sensing images

Edge detection in multispectral remote sensing images

引用

RAST 2005 - 2nd International Conference on Recent Advances in Space Technologies

作者： Sirin, Tuba Saglam, Mehmet Izzet Erer, Isin Gökmen, Muhittin Ersoy, Okan Istanbul Technical University Informatics Institute Advanced Technologies in Engineering Maslak/Istanbul Turkey Istanbul Technical University Informatics Institute Satellite Communication and Remote Sensing Program Maslak/Istanbul Turkey Istanbul Technical University Faculty of Electrical and Electronic Engineering Electronics and Communication Department Maslak/Istanbul Turkey Istanbul Technical University Faculty of Electrical and Electronic Engineering Computer Engineering Department Maslak/Istanbul Turkey Purdue University School of Electrical and Computer Engineering West Lafayette IN United States

ISBN: (纸本)0780389778

In this paper, we discuss edge detection by first using a clustering algorithm followed by a known edge detection filter such as Canny or Generalized Edge Detector (GED). We developed a new clustering method called Self-Organizing Global Ranking (SOGR). Comparative results with multispectral satellite images including SOGR, SOM and K-Means clustering methods are discussed. The results show that the two-stage algorithms are better than single stage edge detector algorithms. © 2005 IEEE.

关键词： Edge detection

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：