Catalogo Articoli (Spogli Riviste)
OPAC HELP
Titolo: Ischemia detection with a selforganizing map supplemented by supervised learning
Autore: Papadimitriou, S; Mavroudi, S; Vladutu, L; Bezerianos, A;
 Indirizzi:
 Univ Patras, Sch Med, Dept Med Phys, GR26110 Patras, Greece Univ Patras Patras Greece GR26110 ept Med Phys, GR26110 Patras, Greece
 Titolo Testata:
 IEEE TRANSACTIONS ON NEURAL NETWORKS
fascicolo: 3,
volume: 12,
anno: 2001,
pagine: 503  515
 SICI:
 10459227(200105)12:3<503:IDWASM>2.0.ZU;2D
 Fonte:
 ISI
 Lingua:
 ENG
 Soggetto:
 WAVELET TRANSFORM; NEURAL NETWORKS; ECG ANALYSIS; ALGORITHMS;
 Keywords:
 computational complexity; divide and conquer algorithms; entropy; ischemia; principal component analysis; radial basis functions; selforganizing maps; support vector machines; VapnikChervonenkis dimension;
 Tipo documento:
 Article
 Natura:
 Periodico
 Settore Disciplinare:
 Engineering, Computing & Technology
 Citazioni:
 40
 Recensione:
 Indirizzi per estratti:
 Indirizzo: Papadimitriou, S Univ Patras, Sch Med, Dept Med Phys, GR26110 Patras, Greece Univ Patras Patras Greece GR26110 26110 Patras, Greece



 Citazione:
 S. Papadimitriou et al., "Ischemia detection with a selforganizing map supplemented by supervised learning", IEEE NEURAL, 12(3), 2001, pp. 503515
Abstract
The problem of maximizing the performance of the detection of ischemia episodes is a difficult pattern classification problem. The state space for this problem consists of regions that lie near class separation boundaries and require the construction of complex discriminants while for the rest regions the classification task is significantly simpler. The motivation for developing the supervising network selforganizing map (sNetSOM) model is toexploit this fact for designing computationally effective solutions both for the particular ischemic detection problem and for other applications that share similar characteristics. Specifically( the sNetSOM utilizes unsupervised learning for the "simple" regions and supervised for the "difficult"ones in a two stage learning process. The unsupervised learning approach extends and adapts the selforganizing map (SOM) algorithm of Kohonen, The basic SOM is modified with a dynamic expansion process controlled with an entropy based criterion that allows the adaptive formation of the proper SOM structure. This extension proceeds until the total number of training patterns that are mapped to neurons with high entropy land therefore with ambiguous classification) reduces to a size manageable numerically with a capablesupervised model, The second learning phase (the supervised training) has the objective of constructing better decision boundaries at the ambiguous regions. At this phase, a special supervised network is trained for the computationally reduced task of performing the classification at the ambiguous regions only. The utilization of sNetSOM with supervised learning based onthe radial basis functions and support vector machines has resulted in an improved accuracy of ischemia detection especially in the last case. The highly disciplined design of the generalization performance of the support vector mai chine allows designing the proper model for the number of patternstransferred to the supervised expert.
ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 14/07/20 alle ore 19:41:40