%0 Journal Article
%@holdercode {isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}
%@nexthigherunit 8JMKD3MGPCW/3ESGTTP
%@resumeid
%@resumeid 8JMKD3MGP5W/3C9JHH2
%X In this paper, we report results obtained with a Madaline neural network trained to classify inductive signatures of two vehicles classes: trucks with one rear axle and trucks with double rear axle. In order to train the Madaline, the inductive signatures were pre-processed and both classes, named C2 and C3, were subdivided into four subclasses. Thus, the initial classification task was split into four smaller tasks (theoretically) easier to be performed. The heuristic adopted in the training attempts to minimize the effects of the input space non-linearity on the classifier performance by uncoupling the learning of the classes and, for this, we induce output Adalines to specialize in learning one of the classes. The percentages of correct classifications presented concern patterns which were not submitted to the neural network in the training process, and, therefore, they indicate the neural network generalization ability. The results are good and stimulate the maintenance of this research on the use of Madaline networks in vehicle classification tasks using not linearly separable inductive signatures.
%@mirrorrepository sid.inpe.br/mtc-m19@80/2009/08.21.17.02.53
%8 Sept.
%N 3
%T Vehicle inductive signatures recognition using a Madaline neural network
%@secondarytype PRE PI
%K Vehicle inductive signatures - Vehicle classification - Madaline neural network.
%@archivingpolicy denypublisher denyfinaldraft12
%@usergroup administrator
%@usergroup simone
%@group
%@group LAC-CTE-INPE-MCT-BR
%3 vehicle indutive.pdf
%@secondarykey INPE--PRE/
%@secondarymark B2_CIÊNCIA_DA_COMPUTAÇÃO A2_ENGENHARIAS_IV B1_INTERDISCIPLINAR
%@issn 0941-0643
%2 sid.inpe.br/mtc-m19@80/2009/12.10.17.47.53
%@affiliation Instituto Tecnológico de Aeronáutica-ITA
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Tecnológico de Aeronáutica-ITA
%B Neural Computing and Applications
%@versiontype publisher
%P 421 436
%4 sid.inpe.br/mtc-m19@80/2009/12.10.17.47
%@documentstage not transferred
%D 2010
%V 19
%@doi 10.1007/s00521-009-0298-3
%A Lima, Glauston R. Teixeira,
%A Silva, José Demísio Simões da,
%A Saotome, Osamu,
%@dissemination WEBSCI; PORTALCAPES.
%@area COMP