发布求助
文献互助 智能选刊 最新文献

2006 8th Seminar on Neural Network Applications in Electrical Engineering最新文献

筛选
英文 中文
A Two-Stage Algorithm for Post-Nonlinear Blind Source Separation 后非线性盲源分离的两阶段算法
2006 8th Seminar on Neural Network Applications in Electrical Engineering Pub Date : 2006-12-01 DOI: 10.1109/NEUREL.2006.341185
W. Y. Leong, J. Homer, Z. Babic, D. P. Mandic
{"title":"A Two-Stage Algorithm for Post-Nonlinear Blind Source Separation","authors":"W. Y. Leong, J. Homer, Z. Babic, D. P. Mandic","doi":"10.1109/NEUREL.2006.341185","DOIUrl":"https://doi.org/10.1109/NEUREL.2006.341185","url":null,"abstract":"An approach to blind separation of post-nonlinearly mixed sources is presented. The proposed approach consists of two stages, namely the estimation of the inverse of the nonlinearity followed by standard source separation. This approach represents further proving of our previously introduced EKENS algorithm, where the critical stage of the estimation of the inverse of the nonlinearity is revised. The used of the Gram-Charlier series, makes the proposed algorithm capable of dealing with both nonlinear mappings and variations of statistical distributions of the sources. The analysis is supported by a comprehensive set of simulations which justify the proposed approach","PeriodicalId":231606,"journal":{"name":"2006 8th Seminar on Neural Network Applications in Electrical Engineering","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115975248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Gaussian Sum Filters for Recurrent Neural Networks training 用于循环神经网络训练的高斯和滤波器
2006 8th Seminar on Neural Network Applications in Electrical Engineering Pub Date : 2006-09-01 DOI: 10.1109/NEUREL.2006.341175
B. Todorovic, M. Stankovic, C. Moraga
{"title":"Gaussian Sum Filters for Recurrent Neural Networks training","authors":"B. Todorovic, M. Stankovic, C. Moraga","doi":"10.1109/NEUREL.2006.341175","DOIUrl":"https://doi.org/10.1109/NEUREL.2006.341175","url":null,"abstract":"We consider the problem of recurrent neural network training as a Bayesian state estimation. The proposed algorithm uses Gaussian sum filter for nonlinear, non-Gaussian estimation of network outputs and synaptic weights. The performances of the proposed algorithm and other Bayesian filters are compared in noisy chaotic time series long-term prediction","PeriodicalId":231606,"journal":{"name":"2006 8th Seminar on Neural Network Applications in Electrical Engineering","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127437288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Interpolative realization of Boolean algebra frame for consistent treatment of gradation and/or fuzziness 布尔代数框架的插值实现，用于一致处理渐变和/或模糊性
2006 8th Seminar on Neural Network Applications in Electrical Engineering Pub Date : 2006-09-01 DOI: 10.1109/NEUREL.2006.341212
D. Radojevic
{"title":"Interpolative realization of Boolean algebra frame for consistent treatment of gradation and/or fuzziness","authors":"D. Radojevic","doi":"10.1109/NEUREL.2006.341212","DOIUrl":"https://doi.org/10.1109/NEUREL.2006.341212","url":null,"abstract":"The new approach to treating gradation in logic, theory of sets, relations etc., is based on interpolative realization of finite Boolean algebra (IBA). IBA has a crucially different approach to gradation compared to fuzzy approaches. Technically, as any element of finite Boolean algebra can be represent in a canonical disjunctive form it can also be represented in the form of a corresponding generalized Boolean polynomial. A generalized Boolean polynomial can process values from a real unit interval [0, 1]. So, all laws of Boolean algebra are preserved in the case of gradation","PeriodicalId":231606,"journal":{"name":"2006 8th Seminar on Neural Network Applications in Electrical Engineering","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129284753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Neural Network Based Classifier for Acute Meningitis 基于神经网络的急性脑膜炎分类器
2006 8th Seminar on Neural Network Applications in Electrical Engineering Pub Date : 2006-09-01 DOI: 10.1109/NEUREL.2006.341202
K. Revett
{"title":"A Neural Network Based Classifier for Acute Meningitis","authors":"K. Revett","doi":"10.1109/NEUREL.2006.341202","DOIUrl":"https://doi.org/10.1109/NEUREL.2006.341202","url":null,"abstract":"Differentiating bacterial from viral (aseptic) meningitis is still a difficult issue, compounded by factors such as age and time of presentation. Clinicians routinely rely on the results from blood and cerebrospinal fluid (CSF) to discriminate bacterial from viral meningitis. Tests such as the CSF Gram stain performed prior to broad-spectrum antibiotic treatment yield sensitivities between 60 and 92%. In this study, we wished to produce a learning vector quantisation network that could yielded a predictive accuracy approaching that of clinical assessment. The results from this study indicate that we can achieve a classification accuracy of over 97%. In addition, we wished to examine how data discretisation impacts the classification accuracy of the LVQ algorithm","PeriodicalId":231606,"journal":{"name":"2006 8th Seminar on Neural Network Applications in Electrical Engineering","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134620819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Finite State Model of Walking Determined by Adaptive Logic Networks 自适应逻辑网络确定的有限状态行走模型
2006 8th Seminar on Neural Network Applications in Electrical Engineering Pub Date : 2006-09-01 DOI: 10.1109/NEUREL.2006.341194
S. D’souza, P. Kankipati, M. Zubayer-Ul-Karim, D. Popović, W. W. Armstrong
{"title":"Finite State Model of Walking Determined by Adaptive Logic Networks","authors":"S. D’souza, P. Kankipati, M. Zubayer-Ul-Karim, D. Popović, W. W. Armstrong","doi":"10.1109/NEUREL.2006.341194","DOIUrl":"https://doi.org/10.1109/NEUREL.2006.341194","url":null,"abstract":"We developed a method for determining a finite state model of locomotion that is applicable to real-time control of walking in individuals with paralyzed legs. The finite state model represents walking as a set of If-Then rules. An If-Then rule uses coded sensory information as inputs (If) and levels of electrical activities of muscles as outputs (Then). The model incorporates temporal and spatial synergies between muscle groups based on sensory information. The sensory input includes accelerations of leg and body segments, and ground reaction forces at toe and heel zones of the sole. The output of the rules is generated by detecting the onset of muscle activity from the amplified and rectified recordings of EMG signals from the prime movers of the leg. The coding uses a local threshold technique. Adaptive logic networks (ALNs) were used for estimation of If-Then rules. The training consisted of various samples of walking recorded in healthy individuals. The application of ALNs was optimized for low misclassification error and fast training. The overall performance of ALN (correct responses that would lead to correct stepping) when applied on test data, not used for the training, was >82%. We assumed that 80% is the margin for correct stepping for the walking in hemiplegic individuals","PeriodicalId":231606,"journal":{"name":"2006 8th Seminar on Neural Network Applications in Electrical Engineering","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124561558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Influence of Inputs in Modelling by Backpropagation Neural Networks 输入对反向传播神经网络建模的影响
2006 8th Seminar on Neural Network Applications in Electrical Engineering Pub Date : 2006-09-01 DOI: 10.1109/NEUREL.2006.341210
D. Drndarevic
{"title":"Influence of Inputs in Modelling by Backpropagation Neural Networks","authors":"D. Drndarevic","doi":"10.1109/NEUREL.2006.341210","DOIUrl":"https://doi.org/10.1109/NEUREL.2006.341210","url":null,"abstract":"An influence of inputs in modelling processes by multilayer neural networks with backpropagation learning algorithm is given in the paper. Examination of input influence on an output error is performed by comparing the output error of network with and without a given input. Inputs significance, i.e. a measure of inputs influence on outputs, is represented by the final weights value. Influence of the distribution of inputs value on an approximation error is examined by determination of the output error for groups of inputs. The most important results of this analysis are the model optimization and reduction of the model error, which is applicable in practice","PeriodicalId":231606,"journal":{"name":"2006 8th Seminar on Neural Network Applications in Electrical Engineering","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114333709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Using a Fuzzy Modeling in Decision Making for Planning Under Uncertainty with Risk Analysis Paradigm 基于风险分析范式的不确定性规划决策中的模糊建模
2006 8th Seminar on Neural Network Applications in Electrical Engineering Pub Date : 2006-09-01 DOI: 10.1109/NEUREL.2006.341215
G. Svenda, S. Kanjuh, T. Konjic, Vladimiro Miranda
{"title":"Using a Fuzzy Modeling in Decision Making for Planning Under Uncertainty with Risk Analysis Paradigm","authors":"G. Svenda, S. Kanjuh, T. Konjic, Vladimiro Miranda","doi":"10.1109/NEUREL.2006.341215","DOIUrl":"https://doi.org/10.1109/NEUREL.2006.341215","url":null,"abstract":"The text explains that the fuzzy approaches have the objective to bring the decision process in planning closer to the decision maker, by allowing him to understand better the diversity of aspects that must be considered in planning decisions and helping the decision process while keeping as much information as possible, represented in the definition of fuzzy sets. The paper shows that the qualitative aspects of uncertainty, risk and decision making may be adequately modeled with a fuzzy set approach. It could help the decision maker guiding him towards a decision that takes in account uncertainty in the future, the multiple criteria evaluation of plans, as well as hedging policies","PeriodicalId":231606,"journal":{"name":"2006 8th Seminar on Neural Network Applications in Electrical Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129578617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 7
Interpolative realization of Boolean algebra 布尔代数的插值实现
2006 8th Seminar on Neural Network Applications in Electrical Engineering Pub Date : 2006-09-01 DOI: 10.1109/NEUREL.2006.341214
D. Radojevic
{"title":"Interpolative realization of Boolean algebra","authors":"D. Radojevic","doi":"10.1109/NEUREL.2006.341214","DOIUrl":"https://doi.org/10.1109/NEUREL.2006.341214","url":null,"abstract":"Classical (Aristotelian) two-valued realization of Boolean algebra is based on two-elements Boolean algebra as its homomorphism. So, calculus and/or arithmetic for two valued case is Boolean algebra of two-elements. Interpolative Boolean algebra is MV realization of finite Boolean algebra and/or it is consistent generalization of classical two-valued realization. New approach is devoted to treating gradation in logic, theory of sets, and generally relations","PeriodicalId":231606,"journal":{"name":"2006 8th Seminar on Neural Network Applications in Electrical Engineering","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130779488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 12
Coreference Resolution Using Decision Trees 使用决策树的共同参考解决方案
2006 8th Seminar on Neural Network Applications in Electrical Engineering Pub Date : 2006-09-01 DOI: 10.1109/NEUREL.2006.341188
Zoran Dzunic, Svetislav Momcilovic, B. Todorovic, M.S. Stankovic
{"title":"Coreference Resolution Using Decision Trees","authors":"Zoran Dzunic, Svetislav Momcilovic, B. Todorovic, M.S. Stankovic","doi":"10.1109/NEUREL.2006.341188","DOIUrl":"https://doi.org/10.1109/NEUREL.2006.341188","url":null,"abstract":"Coreference resolution is the process of determining whether two expressions in natural language refer to the same entity in the world. We adopt machine learning approach using decision tree to a coreference resolution of general noun phrases in unrestricted text based on well defined features. We also use approximate matching algorithms for a string match feature and databases of American last names and male and female first names for gender agreement and alias feature. For the evaluation we use MUC-6 coreference corpora. We show that pessimistic error pruning method gives better generalization in a coreference resolution task than that reported in W.M. Soon et al. (2001) when weights of positive and negative examples are properly chosen","PeriodicalId":231606,"journal":{"name":"2006 8th Seminar on Neural Network Applications in Electrical Engineering","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123920375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 6
Informative Vector Machines for Text Categorization 用于文本分类的信息向量机
2006 8th Seminar on Neural Network Applications in Electrical Engineering Pub Date : 2006-09-01 DOI: 10.1109/NEUREL.2006.341186
M. Stankovic, S. Stankovic
{"title":"Informative Vector Machines for Text Categorization","authors":"M. Stankovic, S. Stankovic","doi":"10.1109/NEUREL.2006.341186","DOIUrl":"https://doi.org/10.1109/NEUREL.2006.341186","url":null,"abstract":"In this paper an analysis is given of the application of Bayesian Gaussian process statistical learning algorithms to the problem of text categorization. It is demonstrated that the informative vector machine method, as a sparse Bayesian compression scheme, provides results better than those obtained so far with the support vector machine method, with much less computational cost","PeriodicalId":231606,"journal":{"name":"2006 8th Seminar on Neural Network Applications in Electrical Engineering","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122432148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信