{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T03:55:06Z","timestamp":1648526106984},"reference-count":20,"publisher":"World Scientific Pub Co Pte Lt","issue":"05","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2004,8]]},"abstract":"<jats:p> Brownboost is an adaptive, continuous time boosting algorithm based on the Boost-by-Majority (BBM) algorithm. Though it has been little studied at the time of writing, it is believed that it should prove especially robust with respect to noisy data sets. This would make it a very useful boosting algorithm for real-world applications. More familiar algorithms such as Adaboost, or its successor Logitboost, are known to be especially susceptible to overfitting the training data examples. This can lead to a poor generalization error in the presence of class noise, since weak hypotheses induced at later iterations to fit the noisy examples will tend to be given undue influence in the final combined hypothesis. Brownboost allows us to specify an expected base-line error rate in advance, corresponding to our prior beliefs about the proportion of noise in the training data, and thus avoid overfitting. The original derivation of Brownboost is restricted to binary classification problems. In this paper we propose a natural multiclass extension to the basic algorithm, incorporating error-correcting output codes and a multiclass gain measure. We test two-class and multiclass versions of the algorithm on a number of real and simulated data sets with artificial class noise, and show that Brownboost consistently outperforms Adaboost in these situations. <\/jats:p>","DOI":"10.1142\/s0218001404003472","type":"journal-article","created":{"date-parts":[[2004,8,19]],"date-time":"2004-08-19T07:33:59Z","timestamp":1092900839000},"page":"905-931","source":"Crossref","is-referenced-by-count":2,"title":["A MULTICLASS EXTENSION TO THE BROWNBOOST ALGORITHM"],"prefix":"10.1142","volume":"18","author":[{"given":"ROSS A.","family":"MCDONALD","sequence":"first","affiliation":[{"name":"Department of Mathematics, Imperial College London, 180 Queen's Gate, London SW7 2BZ, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"DAVID J.","family":"HAND","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Imperial College London, 180 Queen's Gate, London SW7 2BZ, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"IDRIS A.","family":"ECKLEY","sequence":"additional","affiliation":[{"name":"Shell Global Solutions (UK), Cheshire Innovation Park, P. O. Box 1, Chester CH1 3SH, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2011,11,21]]},"reference":[{"key":"rf2","first-page":"113","volume":"1","author":"Allwein E. L.","journal-title":"J. Mach. Learn. Res."},{"key":"rf3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007515423169"},{"key":"rf4","volume-title":"Classification and Regression Trees","author":"Breiman L.","year":"1984"},{"key":"rf5","first-page":"97","volume":"18","author":"Dietterich T. G.","journal-title":"AI Mag."},{"key":"rf6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.105"},{"key":"rf8","volume":"121","author":"Freund Y.","journal-title":"Inform. Comput."},{"key":"rf9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010852229904"},{"key":"rf11","first-page":"771","volume":"14","author":"Freund Y.","journal-title":"J. Japanese Soc. Artif. Intell."},{"key":"rf12","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1016218223"},{"key":"rf13","volume-title":"Construction and Assessment of Classification Rules","author":"Hand D. J.","year":"1997"},{"key":"rf14","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-985X.1997.00078.x"},{"key":"rf15","volume-title":"A First Course in Coding Theory","author":"Hill R.","year":"1986"},{"key":"rf17","first-page":"1","volume":"23","author":"Mangasarian O. L.","journal-title":"SIAM News"},{"key":"rf18","volume-title":"Credit Risk Modeling, Design and Application","author":"Mays E.","year":"1998"},{"key":"rf19","volume-title":"Machine Learning: An Artificial Intelligence Approach","volume":"2","author":"Quinlan J. R.","year":"1986"},{"key":"rf20","volume-title":"C4.5: Programs for Machine Learning","author":"Quinlan J. R.","year":"1993"},{"key":"rf22","first-page":"197","volume":"5","author":"Schapire R. E.","journal-title":"Mach. Learn."},{"key":"rf23","first-page":"1651","volume":"26","author":"Schapire R. E.","journal-title":"Ann. Statist."},{"key":"rf24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007614523901"},{"key":"rf25","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-2070(00)00034-0"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001404003472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T22:21:58Z","timestamp":1565130118000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0218001404003472"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004,8]]},"references-count":20,"journal-issue":{"issue":"05","published-online":{"date-parts":[[2011,11,21]]},"published-print":{"date-parts":[[2004,8]]}},"alternative-id":["10.1142\/S0218001404003472"],"URL":"https:\/\/doi.org\/10.1142\/s0218001404003472","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"value":"0218-0014","type":"print"},{"value":"1793-6381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2004,8]]}}}