{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T04:10:01Z","timestamp":1736568601091,"version":"3.32.0"},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540464846"},{"type":"electronic","value":"9783540464853"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11893295_3","type":"book-chapter","created":{"date-parts":[[2006,10,2]],"date-time":"2006-10-02T16:23:21Z","timestamp":1159806201000},"page":"21-29","source":"Crossref","is-referenced-by-count":5,"title":["An Empirical Analysis of Under-Sampling Techniques to Balance a Protein Structural Class Dataset"],"prefix":"10.1007","author":[{"given":"Marcilio C. P.","family":"de Souto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valnaide G.","family":"Bittencourt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose A. F.","family":"Costa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"3_CR1","unstructured":"Japkowicz, N.: Learning from imbalanced data sets: A comparison of various strategies. In: Proc. of the AAAI Worrkshop on Learning from Imbalanced Data Sets, pp. 10\u201315 (2000)"},{"key":"3_CR2","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1023\/A:1009700419189","volume":"1","author":"T. Fawcett","year":"1997","unstructured":"Fawcett, T., Provost, J.: Adaptive fraud detection. Data Mining and Knowledge Discovery\u00a01, 291\u2013316 (1997)","journal-title":"Data Mining and Knowledge Discovery"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1023\/A:1007452223027","volume":"30","author":"M. Kubat","year":"1998","unstructured":"Kubat, M., Holte, R., Matwin, S.: Machine learning for the detection of oil spills in satellite radar images. Machine Learning\u00a030, 195\u2013215 (1998)","journal-title":"Machine Learning"},{"key":"3_CR4","doi-asserted-by":"crossref","first-page":"429","DOI":"10.3233\/IDA-2002-6504","volume":"6","author":"N. Japkowicz","year":"2002","unstructured":"Japkowicz, N., Stephen, S.: The class imbalance problem: A systematic study. Intelligent data Analyis\u00a06, 429\u2013449 (2002)","journal-title":"Intelligent data Analyis"},{"key":"3_CR5","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1145\/1007730.1007735","volume":"6","author":"G.E.A.P.A. Batista","year":"2004","unstructured":"Batista, G.E.A.P.A., Prati, R.C., Monard, M.C.: A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explorations\u00a06, 20\u201329 (2004)","journal-title":"SIGKDD Explorations"},{"key":"3_CR6","volume-title":"Bioinformatics: the Machine Learning approach","author":"P. Baldi","year":"2001","unstructured":"Baldi, P., Brunak, S.: Bioinformatics: the Machine Learning approach, 2nd edn. MIT Press, Cambridge (2001)","edition":"2"},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1093\/bioinformatics\/17.4.349","volume":"17","author":"C. Ding","year":"2001","unstructured":"Ding, C., Dubchak, I.: Multi-class protein fold recognition using support vector machines and neural networks. Bioinformatics\u00a017, 349\u2013358 (2001)","journal-title":"Bioinformatics"},{"key":"3_CR8","first-page":"206","volume":"14","author":"A. Tan","year":"2003","unstructured":"Tan, A., Gilbert, D., Deville, Y.: Multi-class protein fold classification using a new ensemble machine learning approach. Genome Informatics\u00a014, 206\u2013217 (2003)","journal-title":"Genome Informatics"},{"key":"3_CR9","unstructured":"Craven, M.W., Mural, R.J., Hauser, L.J., Uberbacher, E.C.: Predicting protein folding classes without overly relying on homology. In: Proc. of ISBM, pp. 98\u2013106 (1995)"},{"key":"3_CR10","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1093\/nar\/28.1.257","volume":"28","author":"L. Lo Conte","year":"2000","unstructured":"Lo Conte, L., Ailey, B., Hubbard, T., Brenner, S., Murzin, A., Chotia, C.: SCOP: a structural classification of proteins database. Nucleic Acids Research\u00a028, 257\u2013259 (2000)","journal-title":"Nucleic Acids Research"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Chinnasamy, A., Sung, W., Mittal, A.: Protein structure and fold prediction using tree-augmented nave bayesian classifier. In: Proc. of the Pacific Symposium on Biocomputing, vol.\u00a09, pp. 387\u2013398 (2004)","DOI":"10.1142\/9789812704856_0037"},{"key":"3_CR12","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TSMC.1976.4309452","volume":"6","author":"I. Tomek","year":"1976","unstructured":"Tomek, I.: Two modifications of CNN. IEEE Transactions on Systems, Man, and Communications\u00a06, 769\u2013772 (1976)","journal-title":"IEEE Transactions on Systems, Man, and Communications"},{"key":"3_CR13","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1109\/TIT.1968.1054155","volume":"14","author":"P. Hart","year":"1968","unstructured":"Hart, P.: The condensed nearest neighbor rule. IEEE Transactions on Information Theory\u00a014, 515\u2013516 (1968)","journal-title":"IEEE Transactions on Information Theory"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Batista, G.E.A.P.A., Carvalho, A.C.P.L.F., Monard, M.C.: Applying one-sided selection to unbalanced datasets. In: Proc. of the Mexican International Conference on Artificial Intelligence, pp. 315\u2013325 (2000)","DOI":"10.1007\/10720076_29"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Laurikkala, J.: Improving identification of dificult small classes by balancing class distribution. A-2001-2, University of Tampere (2001)","DOI":"10.1007\/3-540-48229-6_9"},{"key":"3_CR16","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1109\/TSMC.1972.4309137","volume":"2","author":"D. Wilson","year":"1972","unstructured":"Wilson, D.: Asymptotic properties of nearest neighbor rules using edited data. IEEE Transactions on Systems, Man, and Communications\u00a02, 408\u2013421 (1972)","journal-title":"IEEE Transactions on Systems, Man, and Communications"},{"key":"3_CR17","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1002\/pro.5560030317","volume":"3","author":"U. Hobohm","year":"1994","unstructured":"Hobohm, U., Sander, C.: Enlarged representative set of proteins. Protein Science\u00a03, 522\u2013524 (1994)","journal-title":"Protein Science"},{"key":"3_CR18","unstructured":"Dubchak, I., Muchnik, I., Kim, S.: Protein folding class predictor for SCOP: Approach based on global descriptors. In: Proc. of the Intelligent Systems for Molecular Biology, pp. 104\u2013107 (1997)"},{"key":"3_CR19","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1093\/nar\/30.1.260","volume":"30","author":"J.M. Chandonia","year":"2002","unstructured":"Chandonia, J.M., Walker, N., Lo Conte, L., Koehl, P., Levitt, M., Brenner, S.: Astral compendium enhancements. Nucleic Acids Research\u00a030, 260\u2013263 (2002)","journal-title":"Nucleic Acids Research"},{"key":"3_CR20","volume-title":"Machine Learning","author":"T. Mitchell","year":"1997","unstructured":"Mitchell, T.: Machine Learning. McGraw-Hill, New York (1997)"},{"key":"3_CR21","volume-title":"Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations","author":"I. Witten","year":"2005","unstructured":"Witten, I., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann, San Francisco (2005)"},{"key":"3_CR22","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1162\/089976698300017197","volume":"10","author":"T. Dietterich","year":"1998","unstructured":"Dietterich, T.: Approximate statistical test for comparing supervised classification learning algorithms. Neural Computation\u00a010, 1895\u20131923 (1998)","journal-title":"Neural Computation"},{"key":"3_CR23","unstructured":"Batista, G.E.A.P.A.: Pre-processamento de dados em Aprendizado de Mquina Supervisionado. PhD thesis, Universidade de So Paulo, Instituto de Cincias Matemticas e de Computao (2003)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11893295_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T02:46:09Z","timestamp":1736563569000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11893295_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540464846","9783540464853"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/11893295_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}