@article{
 title = {ECG analysis using nonlinear PCA neural networks for ischemia detection},
 type = {article},
 year = {1998},
 identifiers = {[object Object]},
 keywords = {Biom??dical signal processing,Ischemia detection,Neural networks,Principal component analysis,Radial basis function},
 pages = {3030-3044},
 volume = {46},
 id = {d3e8041b-2097-394a-b5fa-a300055533c0},
 created = {2015-04-30T11:14:17.000Z},
 file_attached = {true},
 profile_id = {5e73f9af-1f10-3a70-a285-d3fbb699efe2},
 group_id = {e134fb94-8118-3ebe-b82d-bfbf0a8ae633},
 last_modified = {2015-04-30T12:04:49.000Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 abstract = {The detection of ischemic cardiac beats from a patient's
electrocardiogram (EGG) signal is based on the characteristics of a
specific part of the beat called the ST segment. The correct
classification of the beats relies heavily on the efficient and accurate
extraction of the ST segment features. An algorithm is developed for
this feature extraction based on nonlinear principal component analysis
(NLPCA). NLPCA is a method for nonlinear feature extraction that is
usually implemented by a multilayer neural network. It has been observed
to have better performance, compared with linear principal component
analysis (PCA), in complex problems where the relationships between the
variables are not linear. In this paper, the NLPCA techniques are used
to classify each segment into one of two classes: normal and abnormal
(ST+, ST-, or artifact). During the algorithm training phase, only
normal patterns are used, and for classification purposes, we use only
two nonlinear features for each ST segment. The distribution of these
features is modeled using a radial basis function network (RBFN). Test
results using the European ST-T database show that using only two
nonlinear components and a training set of 1000 normal samples from each
file produce a correct classification rate of approximately 80% for the
normal beats and higher than 90% for the ischemic beats},
 bibtype = {article},
 author = {Stamkopoulos, Telemachos and Diamantaras, Konstantinos and Maglaveras, Nicos and Strintzis, Michael},
 journal = {IEEE Transactions on Signal Processing},
 number = {11}
}

{"_id":"LdkC6jPwZEucJGWQX","bibbaseid":"stamkopoulos-diamantaras-maglaveras-strintzis-ecganalysisusingnonlinearpcaneuralnetworksforischemiadetection-1998","downloads":0,"creationDate":"2016-05-08T13:37:38.789Z","title":"ECG analysis using nonlinear PCA neural networks for ischemia detection","author_short":["Stamkopoulos, T.","Diamantaras, K.","Maglaveras, N.","Strintzis, M."],"year":1998,"bibtype":"article","biburl":null,"bibdata":{"title":"ECG analysis using nonlinear PCA neural networks for ischemia detection","type":"article","year":"1998","identifiers":"[object Object]","keywords":"Biom??dical signal processing,Ischemia detection,Neural networks,Principal component analysis,Radial basis function","pages":"3030-3044","volume":"46","id":"d3e8041b-2097-394a-b5fa-a300055533c0","created":"2015-04-30T11:14:17.000Z","file_attached":"true","profile_id":"5e73f9af-1f10-3a70-a285-d3fbb699efe2","group_id":"e134fb94-8118-3ebe-b82d-bfbf0a8ae633","last_modified":"2015-04-30T12:04:49.000Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"abstract":"The detection of ischemic cardiac beats from a patient's\nelectrocardiogram (EGG) signal is based on the characteristics of a\nspecific part of the beat called the ST segment. The correct\nclassification of the beats relies heavily on the efficient and accurate\nextraction of the ST segment features. An algorithm is developed for\nthis feature extraction based on nonlinear principal component analysis\n(NLPCA). NLPCA is a method for nonlinear feature extraction that is\nusually implemented by a multilayer neural network. It has been observed\nto have better performance, compared with linear principal component\nanalysis (PCA), in complex problems where the relationships between the\nvariables are not linear. In this paper, the NLPCA techniques are used\nto classify each segment into one of two classes: normal and abnormal\n(ST+, ST-, or artifact). During the algorithm training phase, only\nnormal patterns are used, and for classification purposes, we use only\ntwo nonlinear features for each ST segment. The distribution of these\nfeatures is modeled using a radial basis function network (RBFN). Test\nresults using the European ST-T database show that using only two\nnonlinear components and a training set of 1000 normal samples from each\nfile produce a correct classification rate of approximately 80% for the\nnormal beats and higher than 90% for the ischemic beats","bibtype":"article","author":"Stamkopoulos, Telemachos and Diamantaras, Konstantinos and Maglaveras, Nicos and Strintzis, Michael","journal":"IEEE Transactions on Signal Processing","number":"11","bibtex":"@article{\n title = {ECG analysis using nonlinear PCA neural networks for ischemia detection},\n type = {article},\n year = {1998},\n identifiers = {[object Object]},\n keywords = {Biom??dical signal processing,Ischemia detection,Neural networks,Principal component analysis,Radial basis function},\n pages = {3030-3044},\n volume = {46},\n id = {d3e8041b-2097-394a-b5fa-a300055533c0},\n created = {2015-04-30T11:14:17.000Z},\n file_attached = {true},\n profile_id = {5e73f9af-1f10-3a70-a285-d3fbb699efe2},\n group_id = {e134fb94-8118-3ebe-b82d-bfbf0a8ae633},\n last_modified = {2015-04-30T12:04:49.000Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n abstract = {The detection of ischemic cardiac beats from a patient's\nelectrocardiogram (EGG) signal is based on the characteristics of a\nspecific part of the beat called the ST segment. The correct\nclassification of the beats relies heavily on the efficient and accurate\nextraction of the ST segment features. An algorithm is developed for\nthis feature extraction based on nonlinear principal component analysis\n(NLPCA). NLPCA is a method for nonlinear feature extraction that is\nusually implemented by a multilayer neural network. It has been observed\nto have better performance, compared with linear principal component\nanalysis (PCA), in complex problems where the relationships between the\nvariables are not linear. In this paper, the NLPCA techniques are used\nto classify each segment into one of two classes: normal and abnormal\n(ST+, ST-, or artifact). During the algorithm training phase, only\nnormal patterns are used, and for classification purposes, we use only\ntwo nonlinear features for each ST segment. The distribution of these\nfeatures is modeled using a radial basis function network (RBFN). Test\nresults using the European ST-T database show that using only two\nnonlinear components and a training set of 1000 normal samples from each\nfile produce a correct classification rate of approximately 80% for the\nnormal beats and higher than 90% for the ischemic beats},\n bibtype = {article},\n author = {Stamkopoulos, Telemachos and Diamantaras, Konstantinos and Maglaveras, Nicos and Strintzis, Michael},\n journal = {IEEE Transactions on Signal Processing},\n number = {11}\n}","author_short":["Stamkopoulos, T.","Diamantaras, K.","Maglaveras, N.","Strintzis, M."],"urls":{"Paper":"http://bibbase.org/service/mendeley/5e73f9af-1f10-3a70-a285-d3fbb699efe2/file/3bab1297-4cdb-df63-5d81-5eef5289ed12/1998-ECG_analysis_using_nonlinear_PCA_neural_networks_for_ischemia_detection.pdf.pdf"},"bibbaseid":"stamkopoulos-diamantaras-maglaveras-strintzis-ecganalysisusingnonlinearpcaneuralnetworksforischemiadetection-1998","role":"author","keyword":["Biom??dical signal processing","Ischemia detection","Neural networks","Principal component analysis","Radial basis function"],"downloads":0},"search_terms":["ecg","analysis","using","nonlinear","pca","neural","networks","ischemia","detection","stamkopoulos","diamantaras","maglaveras","strintzis"],"keywords":["biom??dical signal processing","ischemia detection","neural networks","principal component analysis","radial basis function"],"authorIDs":[]}