http://www.bibsonomy.org/burst/concept/tag/BayesBibSonomy BuRST Feed for /concept/tag/Bayes2008-07-21T00:38:52+02:00http://www.bibsonomy.org/bibtex/2c66fa858b58398f469558c5d85cf8a7a/cschenkcschenk2008-06-21T18:52:26+02:00winnow categorization benchmark folders automatic read:2008 svm retrieval classification sri email enron ir algorithms information paper bayes <span style="color:#555555;">R. <a href="http://www.bibsonomy.org/author/Bekkerman">Bekkerman</a> and A. <a href="http://www.bibsonomy.org/author/McCallum">McCallum</a> and G. <a href="http://www.bibsonomy.org/author/Huang">Huang</a> </span><em>Center for Intelligent Information Retrieval, Technical Report IR</em>(<em>2004</em>)Sat Jun 21 18:52:26 CEST 2008Center for Intelligent Information Retrieval, Technical Report IRAutomatic Categorization of Email into Folders: Benchmark Experiments on Enron and SRI Corpora4182004winnow categorization benchmark folders automatic read:2008 svm retrieval classification sri email enron ir algorithms information paper bayes Office workers everywhere are drowning in email—not only spam, but also large quantities of legitimate email to be read and organized for browsing. Although there have been extensive investigations of automatic document categorization, email gives rise to a number of unique challenges, and there has been relatively little study of classifying email into folders. This paper presents an extensive benchmark study of email foldering using two large corpora of real-world email messages and foldering schemes: one from former Enron employees, another from participants in an SRI research pro ject. We discuss the challenges that arise from differences between email foldering and traditional document classification. We show experimental results from an array of automated classification methods and evaluation methodologies, including a new evaluation method of foldering results based on the email timeline, and including enhancements to the exponential gradient method Winnow, providing top-tier accuracy with a fraction the training time of alternative methods. We also establish that classification accuracy in many cases is relatively low, confirming the challenges of email data, and pointing toward email foldering as an important area for further research.http://www.bibsonomy.org/bibtex/2797af734fa2ebc20d8ad574c5a7eeddd/brazovayeyebrazovayeye2008-06-19T17:46:40+02:00Bayesian feature-learning genetic identification, composite algorithms, operations methods, primitive learning feature visual image classification algorithm, (artificial NIST-4 extraction, classification, programming, databases classifier, Bayes intelligence), discovery, processing fingerprint operator method, database, <span style="color:#555555;">Xuejun <a href="http://www.bibsonomy.org/author/Tan">Tan</a> and B. <a href="http://www.bibsonomy.org/author/Bhanu">Bhanu</a> and Yingqiang <a href="http://www.bibsonomy.org/author/Lin">Lin</a> </span><em>IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews</em><em>35(3):287--300</em>(<em>Aug</em>)Thu Jun 19 17:46:40 CEST 2008IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews3287--300Fingerprint classification based on learned features35AugBayesian feature-learning genetic identification, composite algorithms, operations methods, primitive learning feature visual image classification algorithm, (artificial NIST-4 extraction, classification, programming, databases classifier, Bayes intelligence), discovery, processing fingerprint operator method, database, In this paper, we present a fingerprint classification approach based on a novel feature-learning algorithm. Unlike current research for fingerprint classification that generally uses well defined meaningful features, our approach is based on Genetic Programming (GP), which learns to discover composite operators and features that are evolved from combinations of primitive image processing operations. Our experimental results show that our approach can find good composite operators to effectively extract useful features. Using a Bayesian classifier, without rejecting any fingerprints from the NIST-4 database, the correct rates for 4- and 5-class classification are 93.3percent and 91.6percent, respectively, which compare favourably with other published research and are one of the best results published to date.http://www.bibsonomy.org/bibtex/2438f2f5eb462703657a8ff44c7121d72/brazovayeyebrazovayeye2008-06-19T17:35:00+02:00boosting, algorithms, naive programming, genetic RSS, DSS, C4.5, Bayes <span style="color:#555555;">Peter <a href="http://www.bibsonomy.org/author/Lichodzijewski">Lichodzijewski</a> and Malcolm I. <a href="http://www.bibsonomy.org/author/Heywood">Heywood</a> and A. <a href="http://www.bibsonomy.org/author/Nur Zincir-Heywood">Nur Zincir-Heywood</a> </span><em>Proceedings of the 2005 IEEE Congress on Evolutionary Computation, </em><em>2, </em><em>page1180--1187. </em><em>Edinburgh, UK, </em><em>IEEE Press, </em><em>2-5 September2005. </em>Thu Jun 19 17:35:00 CEST 2008Edinburgh, UKProceedings of the 2005 IEEE Congress on Evolutionary Computation2-5 September1180--1187Cas{GP}: Building Cascaded Hierarchical Models Using Niching22005boosting, algorithms, naive programming, genetic RSS, DSS, C4.5, Bayes A Cascaded model is introduced for mining large datasets using Genetic Programming without recourse to specialist hardware. Such an algorithm satisfies the seeming conflicting requirements of scalability and accuracy on large datasets by incrementally building GP classifiers through the use of a hierarchical Dynamic Subset Selection algorithm. Models are built incrementally with each layer of the cascade receiving as input the original feature vector, plus the output from the previous layer(s). In order to encourage each layer to explicitly solve new aspects of the problem a combination of Sum Square Error and Niching is used. Thus, previous layers of the model are considered a niche, and the cost function is a shared error metric.http://www.bibsonomy.org/bibtex/2115bc7a60bc5ec8fa422ddda1f5c666d/phbaerphbaer2008-06-11T11:59:45+02:00inference shafer bayes dempster <span style="color:#555555;">A. P. <a href="http://www.bibsonomy.org/author/Dempster">Dempster</a> </span><em>Journal of the Royal Statistical Society</em><em>30(B):205--247</em>(<em>1968</em>)Wed Jun 11 11:59:45 CEST 2008Journal of the Royal Statistical SocietyB205--247A generalization of Bayesian inference301968inference shafer bayes dempster http://www.bibsonomy.org/bibtex/2d9f0db05cf0f8f8d66093bd3813cca58/sb3000sb30002008-05-16T13:42:13+02:00srl bayes <span style="color:#555555;">J. <a href="http://www.bibsonomy.org/author/Neville">Neville</a> and D. <a href="http://www.bibsonomy.org/author/Jensen">Jensen</a> and B. <a href="http://www.bibsonomy.org/author/Gallagher">Gallagher</a> </span><em>Proceedings of the 3rd IEEE International Conference on Data Mining (ICDM 2003), December 19-22, 2003, Melbourne, Florida, USA, </em><em>page609--612. </em><em>IEEE Computer Society, Washington, DC, USA, </em>(<em>2003</em>)Fri May 16 13:42:13 CEST 2008Proceedings of the 3rd IEEE International Conference on Data Mining (ICDM 2003), December 19-22, 2003, Melbourne, Florida, USA609--612Simple estimators for relational Bayesian classifiers2003srl bayes http://www.bibsonomy.org/bibtex/2690d9e63f68ff0a0f9ad2a964afcbd36/jgomezdansjgomezdans2008-05-15T11:40:15+02:00uncertainty tutorial model bayes statistics assimilation <span style="color:#555555;">Christopher K. <a href="http://www.bibsonomy.org/author/Wikle">Wikle</a> and Mark L. <a href="http://www.bibsonomy.org/author/Berliner">Berliner</a> </span><em>Physica D: Nonlinear Phenomena</em><em>230(1-2):1--16</em><em>June2007. </em>Thu May 15 11:40:15 CEST 2008Data AssimilationPhysica D: Nonlinear PhenomenaJune1-21--16A Bayesian tutorial for data assimilation2302007uncertainty tutorial model bayes statistics assimilation Data assimilation is the process by which observational data are fused with scientific information. The Bayesian paradigm provides a coherent probabilistic approach for combining information, and thus is an appropriate framework for data assimilation. Viewing data assimilation as a problem in Bayesian statistics is not new. However, the field of Bayesian statistics is rapidly evolving and new approaches for model construction and sampling have been utilized recently in a wide variety of disciplines to combine information. This article includes a brief introduction to Bayesian methods. Paying particular attention to data assimilation, we review linkages to optimal interpolation, kriging, Kalman filtering, smoothing, and variational analysis. Discussion is provided concerning Monte Carlo methods for implementing Bayesian analysis, including importance sampling, particle filtering, ensemble Kalman filtering, and Markov chain Monte Carlo sampling. Finally, hierarchical Bayesian modeling is reviewed. We indicate how this approach can be used to incorporate significant physically based prior information into statistical models, thereby accounting for uncertainty. The approach is illustrated in a simplified advection-diffusion model.http://www.bibsonomy.org/bibtex/2bfd11cc0720b5c13ca82c4ccb146a95b/marcoalvarezmarcoalvarez2008-05-14T11:33:59+02:00Classification Bayes <span style="color:#555555;">A. <a href="http://www.bibsonomy.org/author/McCallum">McCallum</a> and K. <a href="http://www.bibsonomy.org/author/Nigam">Nigam</a> </span><em>AAAI Workshop on Learning for Text Categorization, </em><em>page41--48. </em>(<em>1998</em>)Wed May 14 11:33:59 CEST 2008AAAI Workshop on Learning for Text Categorization41--48A comparison of event models for naive bayes text classification1998Classification Bayes Recent approaches to text classification have used two different first-order probabilistic models for classification, both of which make the naive Bayes assumption. Some use a multi-variate Bernoulli model, that is, a Bayesian Network with no dependencies between words and binary word features (e.g. Larkey and Croft 1996; Koller and Sahami 1997). Others use a multinomial model, that is, a uni-gram language model with integer word counts (e.g. Lewis and Gale 1994; Mitchell 1997). This paper aims to clarify the confusion by describing the differences and details of these two models, and by empirically comparing their classification performance on five text corpora. We find that the multi-variate Bernoulli performs well with small vocabulary sizes, but that the multinomial performs usually performs even better at larger vocabulary sizes|providing on average a 27\% reduction in error over the multi-variate Bernoulli model at any vocabulary size.http://www.bibsonomy.org/bibtex/292289e141d65e1d6e56c5abcd159a155/marcoalvarezmarcoalvarez2008-05-14T11:33:59+02:00Bayes IR <span style="color:#555555;">David D. <a href="http://www.bibsonomy.org/author/Lewis">Lewis</a> </span><em>European Conference on Machine Learning, </em><em>page4--15. </em>(<em>1998</em>)Wed May 14 11:33:59 CEST 2008European Conference on Machine Learning4--15Naive (bayes) at forty: the independence assumption in information retrieval1998Bayes IR The naive Bayes classifier, currently experiencing a renaissance in machine learning, has long been a core technique in information retrieval. We review some of the variations of naive Bayes models used for text retrieval and classification, focusing on the distributional assumptions made about word occurrences in documents.http://www.bibsonomy.org/bibtex/2d8b8b8894c969cf73448958414c916d5/marcoalvarezmarcoalvarez2008-05-14T11:33:59+02:00RVM Bayes <span style="color:#555555;">Michael E. <a href="http://www.bibsonomy.org/author/Tipping">Tipping</a> </span><em>Journal of Machine Learning Research</em>(<em>2001</em>)Wed May 14 11:33:59 CEST 2008Journal of Machine Learning Research211--244Sparse bayesian learning and the relevance vector machine12001RVM Bayes This paper introduces a general Bayesian framework for obtaining sparse solutions to regression and classification tasks utilising models linear in the parameters. Although this framework is fully general, we illustrate our approach with a particular specialisation that we denote the 'relevance vector machine' (RVM), a model of identical functional form to the popular and state-of-the-art 'support vector machine' (SVM). We demonstrate that by exploiting a probabilistic Bayesian learning framework, we can derive accurate prediction models which typically utilise dramatically fewer basis functions than a comparable SVM while offering a number of additional advantages. These include the benefits of probabilistic predictions, automatic estimation of 'nuisance' parameters, and the facility to utilise arbitrary basis functions (e.g. non-'Mercer' kernels). We detail the Bayesian framework and associated learning algorithm for the RVM, and give some illustrative examples of its application along with some comparative benchmarks. We offer some explanation for the exceptional degree of sparsity obtained, and discuss and demonstrate some of the advantageous features, and potential extensions, of Bayesian relevance learning.http://www.bibsonomy.org/bibtex/2222f0596bf27e308295af87c98d90af6/marcoalvarezmarcoalvarez2008-05-14T11:33:59+02:00Bayes SubCellLoc <span style="color:#555555;">Alla <a href="http://www.bibsonomy.org/author/Bulashevska">Bulashevska</a> and Roland <a href="http://www.bibsonomy.org/author/Eils">Eils</a> </span><em>BMC Bioinformatics</em><em>7(1):298</em><em>June2006. </em>Wed May 14 11:33:59 CEST 2008BMC BioinformaticsJune1298Predicting protein subcellular locations using hierarchical ensemble of bayesian classifiers based on markov chains72006Bayes SubCellLoc Background: The subcellular location of a protein is closely related to its function. It would be worthwhile to develop a method to predict the subcellular location for a given protein when only the amino acid sequence of the protein is known. Although many efforts have been made to predict subcellular location from sequence information only, there is the need for further research to improve the accuracy of prediction. Results: A novel method called HensBC is introduced to predict protein subcellular location. HensBC is a recursive algorithm which constructs a hierarchical ensemble of classifiers. The classifiers used are Bayesian classifiers based on Markov chain models. We tested our method on six various datasets; among them are Gram-negative bacteria dataset, data for discriminating outer membrane proteins and apoptosis proteins dataset. We observed that our method can predict the subcellular location with high accuracy. Another advantage of the proposed method is that it can improve the accuracy of the prediction of some classes with few sequences in training and is therefore useful for datasets with imbalanced distribution of classes. Conclusion: This study introduces an algorithm which uses only the primary sequence of a protein to predict its subcellular location. The proposed recursive scheme represents an interesting methodology for learning and combining classifiers. The method is computationally efficient and competitive with the previously reported approaches in terms of prediction accuracies as empirical results indicate. The code for the software is available upon request.http://www.bibsonomy.org/bibtex/2d720a6acf4dbb0067004e7452c96c0cf/marcoalvarezmarcoalvarez2008-05-14T11:33:59+02:00Bayes ObjectDetection <span style="color:#555555;">J. <a href="http://www.bibsonomy.org/author/Ross Beveridge">Ross Beveridge</a> and Jilmil <a href="http://www.bibsonomy.org/author/Saraf">Saraf</a> and Ben <a href="http://www.bibsonomy.org/author/Randall">Randall</a> </span><em>International Conference on Pattern Recognition, </em><em>page1175--1178. </em>(<em>2006</em>)Wed May 14 11:33:59 CEST 2008International Conference on Pattern Recognition1175--1178A comparison of pixel, edge and wavelet features for face detection using a semi-naive bayesian classifier2006Bayes ObjectDetection Henry Schneiderman at Carnegie Mellon University developed a face detection algorithm based upon a semi-naive Bayesian classifier and 5/3 linear phase wavelets. This paper explores the relative value of these wavelet features compared to simpler pixel and edge features. Experiments suggest edge features are superior for highly controlled lighting, while pixel features are better and more stable for uncontrolled lighting. Tests use the Notre Dame face data collected in Fall 2003 and Spring 2004 and use over 400,000 face and non-face test image chips.http://www.bibsonomy.org/bibtex/2dfa99d567392038673882c932153053c/jiljil2008-05-08T19:46:13+02:00bayes probabilistic rocchio estimator tfidf laplace <span style="color:#555555;">Thorsten <a href="http://www.bibsonomy.org/author/Joachims">Joachims</a> </span><em>ICML, </em><em>page143-151. </em><em>Morgan Kaufmann, </em>(<em>1997</em>)Thu May 08 19:46:13 CEST 2008ICMLconf/icml/1997143-151A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Categorization.1997bayes probabilistic rocchio estimator tfidf laplace http://www.bibsonomy.org/bibtex/2b8f819dc681e76ee9723c72a859dff3c/jiljil2008-05-06T02:13:03+02:00multinomial machine normalization learning bayes length naive <span style="color:#555555;">S. <a href="http://www.bibsonomy.org/author/Kim">Kim</a> and H. <a href="http://www.bibsonomy.org/author/Rim">Rim</a> and D. <a href="http://www.bibsonomy.org/author/Yook">Yook</a> and H. <a href="http://www.bibsonomy.org/author/Lim">Lim</a> </span>(<em>2002</em>)Tue May 06 02:13:03 CEST 2008Effective methods for improving Naive Bayes text classifiers2002multinomial machine normalization learning bayes length naive http://www.bibsonomy.org/bibtex/22896eb9538a6ee34f8e6c6757bdcf99e/jiljil2008-05-05T19:34:57+02:00thesis estimation multinomial bayes komplett naive exhaustive herleitung map likelihood mle prior deduction maximum <span style="color:#555555;">Jason D. M. <a href="http://www.bibsonomy.org/author/Rennie">Rennie</a> </span>(<em>2001</em>)Mon May 05 19:34:57 CEST 2008Improving Multi-class Text Classification with Naive Bayes2001thesis estimation multinomial bayes komplett naive exhaustive herleitung map likelihood mle prior deduction maximum There are numerous text documents available in electronic form. More and more are becoming available every day. Such documents represent a massive amount of information that is easily accessible. Seeking value in this huge collection requires organization; much of the work of organizing documents can be automated through text classification. The accuracy and our understanding of such systems greatly influences their usefulness. In this paper, we seek 1) to advance the understanding of commonly used text classification techniques, and 2) through that understanding, improve the tools that are available for text classification. We begin by clarifying the assumptions made in the derivation of Naive Bayes, noting basic properties and proposing ways for its extension and improvement. Next, we investigate the quality of Naive Bayes parameter estimates and their impact on classification. Our analysis leads to a theorem which gives an explanation for the improvements that can be found in multiclass classification with Naive Bayes using Error-Correcting Output Codes. We use experimental evidence on two commonly-used data sets to exhibit an application of the theorem. Finally, we show fundamental flaws in a commonly-used feature selection algorithm and develop a statistics-based framework for text feature selection. Greater understanding of Naive Bayes and the properties of text allows us to make better use of it in text classification.http://www.bibsonomy.org/bibtex/2fa46d1cc0dd56ab40a7f722e569a1fd3/jiljil2008-05-05T19:02:36+02:00text vergleich multinomial model event classification bayes bernoulli naive ereignis <span style="color:#555555;">Andrew <a href="http://www.bibsonomy.org/author/McCallum">McCallum</a> and Kamal <a href="http://www.bibsonomy.org/author/Nigam">Nigam</a> </span><em>Learning for Text Categorization: Papers from the 1998 AAAI Workshop, </em><em>page41--48. </em>(<em>1998</em>)Mon May 05 19:02:36 CEST 2008Learning for Text Categorization: Papers from the 1998 {AAAI} Workshop 41--48A Comparison of Event Models for Naive {B}ayes Text Classification1998text vergleich multinomial model event classification bayes bernoulli naive ereignis http://www.bibsonomy.org/bibtex/2e290abb350b7aa09a412c1dddac55cd6/jiljil2008-05-05T18:53:49+02:00text naive representation ir bayes forty overview <span style="color:#555555;">David D. <a href="http://www.bibsonomy.org/author/Lewis">Lewis</a> </span><em>Proceedings of ECML-98, 10th European Conference on Machine Learning, </em><em>1398, </em><em>page4--15. </em><em>Chemnitz, DE, </em><em>Springer Verlag, Heidelberg, DE, </em>(<em>1998</em>)Mon May 05 18:53:49 CEST 2008Chemnitz, DEProceedings of {ECML}-98, 10th European Conference on Machine Learning13984--15Naive ({B}ayes) at forty: The independence assumption in information retrieval.1998text naive representation ir bayes forty overview http://www.bibsonomy.org/bibtex/2b4e1a9d4635a9fb1f11a947f1ab3618a/jiljil2008-05-05T18:50:15+02:00naive spam multinomial multivariate metsis bayes <span style="color:#555555;">Vangelis <a href="http://www.bibsonomy.org/author/Metsis">Metsis</a> and Ion <a href="http://www.bibsonomy.org/author/Androutsopoulos">Androutsopoulos</a> and Georgios <a href="http://www.bibsonomy.org/author/Paliouras">Paliouras</a> </span>(<em>2006</em>)Mon May 05 18:50:15 CEST 2008Spam Filtering with Naive Bayes -- Which Naive Bayes?2006naive spam multinomial multivariate metsis bayes http://www.bibsonomy.org/bibtex/2d3156d6e88054cdf48358f96a42b5c9a/smichasmicha2008-04-23T22:05:04+02:00Bayes prediction <span style="color:#555555;">Essam K. <a href="http://www.bibsonomy.org/author/AL-Hussaini">AL-Hussaini</a> </span><em>Journal of Statistical Planning and Inference</em><em>79(1):79--91</em><em>Jun1999. </em>Wed Apr 23 22:05:04 CEST 2008Journal of Statistical Planning and InferenceJun179--91Predicting observables from a general class of distributions791999Bayes prediction http://www.bibsonomy.org/bibtex/2eadff641071e1496f91635632b3fe3a6/smichasmicha2008-04-23T22:05:04+02:00Empirical Bayes Procedures <span style="color:#555555;">Enrique de <a href="http://www.bibsonomy.org/author/Alba">Alba</a> and John Van <a href="http://www.bibsonomy.org/author/Ryzin">Ryzin</a> </span><em>Journal of Statistical Planning and Inference</em><em>4(3):217--236</em>(<em>1980</em>)Wed Apr 23 22:05:04 CEST 2008Journal of Statistical Planning and Inference3217--236An empirical Bayes approach to outliers41980Empirical Bayes Procedures http://www.bibsonomy.org/bibtex/22d410a6e70976e8e629adf17c3043889/smichasmicha2008-04-23T22:05:04+02:00Empirical Bayes <span style="color:#555555;">Jeremy <a href="http://www.bibsonomy.org/author/Aldworth">Aldworth</a> and Noel <a href="http://www.bibsonomy.org/author/Cressie">Cressie</a> </span><em>Journal of Statistical Planning and Inference</em><em>112(1-2):3--41</em><em>Mar2003. </em>Wed Apr 23 22:05:04 CEST 2008Journal of Statistical Planning and InferenceMar1-23--41Prediction of nonlinear spatial functionals1122003Empirical Bayes 01