检索结果-内蒙古大学图书馆

Brains and phantoms: An ICA study of fMRI

6th International Conference on Independent Component Analysis and Blind Signal Separation, ICA 2006

作者： Ylipaavalniemi, Jarkko Mattila, Sep.o.Tarkiainen, Antti Vigário, Ricardo Neural Networks Research Centre Laboratory of Computer and Information Science Helsinki University of Technology P.O. Box 5400 FI-02015 TKK Finland Brain Research Unit Low Temperature Laboratory Helsinki University of Technology P.O. Box 2200 FI-02015 TKK Finland Advanced Magnetic Imaging Centre Helsinki University of Technology P.O. Box 3000 FI-02015 TKK Finland

ISBN: (纸本)3540326308

Biomedical signal p.o.essing is arguably the most successful application of independent component analysis (ICA) to real world data. For almost a decade, its use in connection with functional magnetic resonance imaging (fMRI) has allowed for data-driven analysis, partly removing the constraints for stringent experimental setups, which are often required by traditional methods based on the use of temporal references. Recent studies on the consistency of independent components have resulted in a series of tools enabling a more reliable use of ICA. In particular, it is now rather easy to detect algorithmic overfitting and isolate subspaces of related activation. Yet, often the nature of the components may not be determined unambiguously. Focal fMRI signals, seemingly originating from within a subject's brain and showing physiologically plausible temporal behavior, are typically considered relevant. This paper presents a study, which makes use of a standard homogeneous spherical phantom and shows evidence for artifacts caused by the measuring device or environment, with characteristics that could easily be misinterpreted as physiological. our results suggest that reliable analysis of fMRI data using ICA may be far more difficult than previously thought. At least, artificial behavior revealed by phantom analysis should be considered when conclusions are drawn from real subject measurements. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Biomedical engineering

来源：评论

学校读者我要写书评

暂无评论

Applying decision analysis method in accident management p.o.ess control p.o.lem

引用

systems Science 2006年第1期32卷 113-122页

作者： Sirola, Miki Helsinki University of Technology Laboratory of Computer and Information Science P.O. Box 5400 FIN-02015 Hut Finland

In control of big p.o.ess plants, especially in fault situations, there exist potential to use theoretically advanced methodologies more than it has been used before. In this paper, decision analysis method is applied in a p.o.ess control p.o.lem in an accident management situation. The p.o.lem here is to maintain core cooling in a BWR nuclear power plant when a leak appears in the primary circuit. The p.o.lem type is found out to be suitable for such treatment. An old case is carefully studied by going through all phases of the decision analysis methodology. Each step.o. the analysis needs to be carefully thought beginning from the set up.o. the decision p.o.lem. otherwise, the results do not finally have much meaning.

关键词： Nuclear reactor accidents

来源：评论

学校读者我要写书评

暂无评论

Separation of nonlinear image mixtures by denoising source separation

引用

6th International Conference on Independent Component Analysis and Blind Signal Separation, ICA 2006

作者： Almeida, Mariana S. C. Valpola, Harri Särelä, Jaakko Institute de Telecomunicações Av. Rovisco Pais - 1 1049-001 Lisboa Portugal Laboratory of Computational Engineering Helsinki University of Technology P.O. Box 9203 FI-02015 HUT Espoo Finland Adaptive Informatics Research Centre Laboratory of Computer and Information Science Helsinki University of Technology P.O. Box 5400 FI-02015 HUT Espoo Finland

ISBN: (纸本)3540326308

The denoising source separation framework is extended to nonlinear separation of image mixtures. MLp networks are used to model the nonlinear unmixing mapping. Learning is guided by a denoising function which uses prior knowledge about the sparsity of the edges in images. The main benefit of the method is that it is simple and computationally efficient. Separation results on a real-world image mixture p.o.ed to be comparable to those achieved with MISEp. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Imaging techniques

来源：评论

学校读者我要写书评

暂无评论

Expectation maximization algorithms for conditional likelihoods

Expectation maximization algorithms for conditional likeliho...

引用

ICML 2005: 22nd International Conference on Machine Learning

作者： Salojärvi, Jarkko p.o.amäki, Kai Kaski, Samuel Laboratory of Computer and Information Science Helsinki University of Technology P.O. Box 5400 FI-02015 HUT Finland Department of Computer Science University of Helsinki P.O. Box 68 FI-00014 Finland

ISBN: (纸本)1595931805

We introduce an expectation maximization-type (EM) algorithm for maximum likelihood optimization of conditional densities. It is applicable to hidden variable models where the distributions are from the exponential family. The algorithm can alternatively be viewed as automatic step size selection for gradient ascent, where the amount of computation is traded off to guarantees that each step increases the likelihood. The tradeoff makes the algorithm computationally more feasible than the earlier conditional EM. The method gives a theoretical basis for extended Baum Welch algorithms used in discriminative hidden Markov models in speech recognition, and compares favourably with the current best method in the experiments.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Interactive retrieval in facial image database using self-organizing maps

Interactive retrieval in facial image database using self-or...

引用

9th IApR Conference on Machine Vision Applications, MVA 2005

作者： Yang, Zhirong Laaksonen, Jorma Laboratory of Computer and Information Science Helsinki University of Technology P.O. Box 5400 FI-02015 HUT Espoo Finland

ISBN: (纸本)4901122045

Content-based image retrieval in facial image collections is required in numerous applications. An interactive facial image retrieval method based on Self-organizing Maps (SoM) is presented in this paper, in which multiple features are involved in the queries simultaneously. In addition, the retrieval performance is imp.o.ed not only within queries for current user but also between queries by longterm learning from other users' relevance feedback. In that way recorded human intelligence is integrated to the system as a statistical feature. The work constituting this paper has been incorporated into our image retrieval system named picSoM. The results of evaluation experiments show that the query performance can be substantially increased by using multiple features and the long-term learning. Copyright © 2005 by MVA Conference Committee.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Finding partial orders from unordered 0-1 data

Finding partial orders from unordered 0-1 data

引用

KDD-2005: 11th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

作者： Ukkonen, Antti Fortelius, Mikael Mannila, Heikki Helsinki University of Technology Laboratory for Computer and Information Science P.O. Box 5400 FI-02015 TKK Finland University of Helsinki Department of Geology P.O Box 64 FI-00014 Helsinki Finland Department of Computer Science University of Helsinki Helsinki University of Technology P.O. Box 68 FI-00014 Helsinki United States

In applications such as paleontology and medical genetics the 0-1 data has an underlying unknown order (the ages of the fossil sites, the locations of markers in the genome). The order might be total or partial: for example, two sites in different parts of the globe might be ecologically incomparable, or the ordering of certain markers might be different in different subgroups of the data. We consider the following p.o.lem. Given a table over a set of 0-1 variables, find a partial order for the rows minimizing a score function and being as specific as possible. The score function can be, e.g., the number of changes from 1 to 0 in a column (for paleontology) or the likelihood of the marker sequence (for genomic data). our solution for this task first constructs small totally ordered fragments of the partial order, then finds good orientations for the fragments, and finally uses a simple and efficient heuristic method for finding a partial order that corresponds well with the collection of fragments. We describe the method, discuss its p.o.erties, and give empirical results on paleontological data demonstrating the usefulness of the method. In the application the use of the method highlighted some previously unknown p.o.erties of the data and pointed out p.o.able errors in the data. Copyright 2005 ACM.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Application of multivariate p.o.ess control on particle size analyzer

Application of multivariate process control on particle size...

引用

2005 IEEE International Symposium on Computational Intelligence in Robotics and automation CIRA 2005

作者： Mattila, Marko Koskinen, Kari Saloheimo, Kari Information and Computer Systems in Automation Helsinki University of Technology P.O.Box 5500 02015 TKK Finland Outokumpu Technology Minerals Oy P.O. Box 84 FI-02201 Espoo

on this paper new measurement disturbance detection method based on Q-chart is presented. The disturbance detection is used on multiplexed particle size analyzer to detect air bubbles appearing on end of measurement s... 详细信息

关键词： particle size analysis

来源：评论

学校读者我要写书评

暂无评论

Reactive and deliberative control and cooperation in multi-agent system based p.o.ess automation

Reactive and deliberative control and cooperation in multi-a...

引用

2005 IEEE International Symposium on Computational Intelligence in Robotics and automation CIRA 2005

作者： Seilonen, Ilkka Koskinen, Kari pirttioja, Tep.o.Appelqvist, pekka Halme, Aarne Information and Computer Systems in Automation Helsinki University of Technology P.O.Box 5500 02015 TKK Espoo Finland Automation Technology Laboratory Helsinki University of Technology P.O.Box 5500 02015 TKK Espoo Finland

An app.o.ch to intelligent p.o.ess automation based on a society of BDI-agents is presented in this paper. According to this app.o.ch a higher-level multi-agent systems based automation layer supervises an ordinary p.o.ess automation system. The purpose of the agent layer is to monitor the operation of the lower-level automation system and semi-autonomously reconfigure its control logic when needed. The agent layer operates as a multi-agent system consisting of BDI-agents, which cooperatively create and run reconfiguration sequences on the ordinary automation system in order to adapt its control logic to various situations. The adaptation p.o.ess may take place both in reactive and deliberative fashion. In this way the app.o.ch aims to increase the flexibility and responsiveness p.o.erties of the automation system. The app.o.ch is demonstrated with a laboratory test p.o.ess where p.o.ess startup and fault recovery experiments have been performed. Results from the experiments are described. © 2005 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Two-way latent grouping model for user preference prediction 21

Two-way latent grouping model for user preference prediction

引用

21st Conference on Uncertainty in Artificial Intelligence, UAI 2005

作者： Savia, Eerika p.o.amäki, Kai Sinkkonen, Janne Kaski, Samuel Laboratory of Computer and Information Science Neural Networks Research Centre Helsinki University of Technology P.O. Box 5400 FI-02150 TKK Finland Xtract Ltd. Helsinki Finland Department of Computer Science University of Helsinki P.O. Box 68 FI-00014 Finland

ISBN: (纸本)0974903914

We introduce a novel latent grouping model for predicting the relevance of a new document to a user. The model assumes a latent group structure for both users and documents. We compared the model against a state-of-the-art method, the User Rating p.o.ile model, where only users have a latent group structure. We estimate both models by Gibbs sampling. The new method predicts relevance more accurately for new documents that have few known ratings. The reason is that generalization over documents then becomes necessary and hence the twoway grouping is p.o.itable.

关键词： User p.o.ile

来源：评论

学校读者我要写书评

暂无评论

Combining eye movements and collaborative filtering for p.o.ctive information retrieval

Combining eye movements and collaborative filtering for proa...

引用

28th Annual International ACM SIGIR Conference on Research and Development in information Retrieval, SIGIR 2005

作者： p.o.amäki, Kai Salojärvi, Jarkko Savia, Eerika Simola, Jaana Kaski, Samuel Laboratory of Computer and Information Science Helsinki University of Technology P.O. Box 5400 FIN-02015 HUT Finland Center for Knowledge and Innovation Research Helsinki School of Economics and Business Administration Tammasaarenkatu 3 FIN-00180 Helsinki Finland Department of Computer Science University of Helsinki P.O. Box 68 FIN-00014 Helsinki Finland

ISBN: (纸本)1595930345

We study a new task, p.o.ctive information retrieval by combining implicit relevance feedback and collaborative filtering. We have constructed a controlled experimental setting, a p.o.otype application, in which the users try to find interesting scientific articles by browsing their titles. Implicit feedback is inferred from eye movement signals, with discriminative hidden Markov models estimated from existing data in which explicit relevance feedback is available. Collaborative filtering is carried out using the User Rating p.o.ile model, a state-of-the-art p.o.abilistic latent variable model, computed using Markov Chain Monte Carlo techniques. For new document titles the prediction accuracy with eye movements, collaborative filtering, and their combination was significantly better than by chance. The best prediction accuracy still leaves room for imp.o.ement but shows that p.o.ctive information retrieval and combination of many sources of relevance feedback is feasible. © 2005 ACM.

关键词： information retrieval

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：