{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T10:10:02Z","timestamp":1776247802662,"version":"3.50.1"},"reference-count":32,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2013,9,10]],"date-time":"2013-09-10T00:00:00Z","timestamp":1378771200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["River Research &amp; Apps"],"published-print":{"date-parts":[[2014,11]]},"abstract":"<jats:title>ABSTRACT<\/jats:title><jats:p>In the present study, we tested the potential of combining three machine learning techniques in a bioassessment tool to more accurately predict the pool of expected taxa at a site. This tool, the Hydra, uses the best performing technique from Support Vector Machines (SVM), Multi\u2010layer Perceptron and <jats:italic>K<\/jats:italic>\u2010Nearest Neighbour (KNN), to predict the taxa expected at a stream site, and further evaluates the quality of a site, though a classification system based on observed\/expected values, similar to that used in River Invertebrate Prediction and Classification System (RIVPACS) models. To test the procedure, we used a dataset composed of 137 training sites, 15 validation sites and 174 test sites (potentially disturbed) from Portuguese streams. The combined use of three machine learning techniques was more effective in the prediction of invertebrate taxa at a site than their individual use. The three methods were always tested for all invertebrate taxa, but from the three techniques tested, SVM and KNN were most often the best performing techniques (the most accurate among the three for a higher number of taxa) in the prediction of invertebrate taxa with the present dataset. The combination of all algorithms implemented in Hydra resulted in good models for stream bioassessment (e.g. SD OE<jats:sub>50<\/jats:sub>\u2009&lt;\u20090.2, regression of O vs E: R<jats:sup>2<\/jats:sup>\u2009&gt;\u20090.6, Spearman correlations with global degradation &gt;0.7). We also found no advantage in removing rare taxa from the training dataset, and 50% accuracy is the most adequate accuracy level for calculation of OE ratios through Hydra. Future work should consist of comparing the performance of this technique with others, such as the RIVPACS models, using the same datasets. Considering the flexibility of this technique, self\u2010adjustment and easy implementation through a website (aquaweb.uc.pt), we expect it to be also useful in the prediction of other aquatic elements such as fishes and algae. Copyright \u00a9 2013 John Wiley &amp; Sons, Ltd.<\/jats:p>","DOI":"10.1002\/rra.2707","type":"journal-article","created":{"date-parts":[[2013,9,11]],"date-time":"2013-09-11T09:55:08Z","timestamp":1378893308000},"page":"1157-1165","source":"Crossref","is-referenced-by-count":8,"title":["COMBINING MULTIPLE MACHINE LEARNING ALGORITHMS TO PREDICT TAXA UNDER REFERENCE CONDITIONS FOR STREAMS BIOASSESSMENT"],"prefix":"10.1002","volume":"30","author":[{"given":"M. J.","family":"Feio","sequence":"first","affiliation":[{"name":"Department of Life Sciences Institute of Marine Research\u2014CMA  PO Box\u00a03046 Coimbra Portugal"}]},{"given":"C.","family":"Viana\u2010Ferreira","sequence":"additional","affiliation":[{"name":"University of Aveiro\u2010DETI\/IEETA  Aveiro Portugal"}]},{"given":"C.","family":"Costa","sequence":"additional","affiliation":[{"name":"University of Aveiro\u2010DETI\/IEETA  Aveiro Portugal"}]}],"member":"311","published-online":{"date-parts":[[2013,9,10]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10750-012-1110-4"},{"key":"e_1_2_6_3_1","volume-title":"Introduction to Machine Learning","author":"Alpaydin E","year":"2004"},{"key":"e_1_2_6_4_1","first-page":"217","article-title":"When is \u201cnearest neighbor\u201d meaningful?","volume":"1540","author":"Beyer K","year":"1999","journal-title":"Proceedings of the International Conference on Database Theory"},{"key":"e_1_2_6_5_1","doi-asserted-by":"crossref","unstructured":"CaruanaR Niculescu\u2010MizilA.2006.An empirical comparison of supervised learning algorithms.Proceedings of the 23rd International Conference on Machine LearningC:161\u2013168.","DOI":"10.1145\/1143844.1143865"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14400-4_44"},{"key":"e_1_2_6_7_1","volume-title":"An Introduction to Support Vector Machines and Other Kernel\u2010Based Learning Methods","author":"Cristianini N","year":"2006"},{"key":"e_1_2_6_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1976.5408784"},{"key":"e_1_2_6_9_1","first-page":"1","article-title":"Directive 2000\/60\/EC of the European Parliament and of the Council of 23 October 2000 establishing a framework for Community action in the field of water policy","volume":"327","author":"EC Parliament and Council","year":"2000","journal-title":"Official Journal of the European Communities"},{"key":"e_1_2_6_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolind.2008.09.012"},{"key":"e_1_2_6_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1352-2310(97)00447-0"},{"key":"e_1_2_6_12_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1365-2426.2003.01174.x"},{"key":"e_1_2_6_13_1","doi-asserted-by":"publisher","DOI":"10.1006\/jema.2001.0424"},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.2307\/1468111"},{"key":"e_1_2_6_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/5254.708428"},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3800(01)00306-4"},{"key":"e_1_2_6_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2009.12.001"},{"key":"e_1_2_6_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"e_1_2_6_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(03)00372-2"},{"key":"e_1_2_6_20_1","first-page":"1137","article-title":"A study of cross\u2010validation and bootstrap for accuracy estimation and model selection","volume":"2","author":"Kohavi R","year":"1995","journal-title":"International Joint Conference on Artificial Intelligence"},{"key":"e_1_2_6_21_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2427.2004.01286.x"},{"key":"e_1_2_6_22_1","first-page":"413","article-title":"Comparative exudate classification using support vector machines and neural networks","author":"Osareh A","year":"2002","journal-title":"Medical Image Computing and Computer\u2010Assisted Intervention"},{"key":"e_1_2_6_23_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2664.2005.01126.x"},{"key":"e_1_2_6_24_1","doi-asserted-by":"publisher","DOI":"10.2307\/1468175"},{"key":"e_1_2_6_25_1","first-page":"125","volume-title":"Assessing the Biological Quality of Fresh Waters: RIVPACS and Other Techniques","author":"Simpson JC","year":"2000"},{"key":"e_1_2_6_26_1","volume-title":"Support Vector Machines","author":"Steinwart I","year":"2008"},{"key":"e_1_2_6_27_1","doi-asserted-by":"publisher","DOI":"10.1890\/1051-0761(2006)016[1267:SEFTEC]2.0.CO;2"},{"key":"e_1_2_6_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"e_1_2_6_29_1","doi-asserted-by":"publisher","DOI":"10.1899\/0887-3593(2007)26[319:EORTAP]2.0.CO;2"},{"key":"e_1_2_6_30_1","doi-asserted-by":"publisher","DOI":"10.1139\/f80-017"},{"key":"e_1_2_6_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0043-1354(97)00274-1"},{"key":"e_1_2_6_32_1","volume-title":"Assessing the biological quality of fresh waters: RIVPACS and other techniques","author":"Wright JF","year":"2000"},{"key":"e_1_2_6_33_1","volume-title":"Artificial neural networks","author":"Yegnanarayana B","year":"2004"}],"container-title":["River Research and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Frra.2707","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Frra.2707","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/rra.2707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,3]],"date-time":"2023-10-03T17:35:37Z","timestamp":1696354537000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/rra.2707"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9,10]]},"references-count":32,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2014,11]]}},"alternative-id":["10.1002\/rra.2707"],"URL":"https:\/\/doi.org\/10.1002\/rra.2707","archive":["Portico"],"relation":{},"ISSN":["1535-1459","1535-1467"],"issn-type":[{"value":"1535-1459","type":"print"},{"value":"1535-1467","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9,10]]}}}