TY - JOUR
T1 - Ischemia detection with a self-organizing map supplemented by supervised learning
AU - Papadimitriou, Stergios
AU - Mavroudi, Seferina
AU - Vladutu, Liviu
AU - Bezerianos, Anastasios
N1 - Funding Information:
Manuscript received December 10, 1999; revised November 8, 2000. This work was supported in part by the Greek State Scholarship Foundation (SSF) and the General Secretariat for Research and Technology (GSRT) of Greece Contract PENED (ED 146). Reprints and the software implementation of the presented sNetSOM neural model are available upon request from stergios@heart.med.upatras.gr.
PY - 2001/5
Y1 - 2001/5
N2 - 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 self-organizing map (sNet-SOM) model is to exploit this fact for designing computationally effective solutions both for the particular ischemic detection problem and for other applications that share similar characteristics. Specifically, the sNet-SOM 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 self-organizing 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 (and therefore with ambiguous classification) reduces to a size manageable numerically with a capable supervised 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 sNet-SOM with supervised learning based on the 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 machine allows designing the proper model for the number of patterns transferred to the supervised expert.
AB - 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 self-organizing map (sNet-SOM) model is to exploit this fact for designing computationally effective solutions both for the particular ischemic detection problem and for other applications that share similar characteristics. Specifically, the sNet-SOM 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 self-organizing 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 (and therefore with ambiguous classification) reduces to a size manageable numerically with a capable supervised 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 sNet-SOM with supervised learning based on the 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 machine allows designing the proper model for the number of patterns transferred to the supervised expert.
KW - Computational complexity
KW - Divide and conquer algorithms
KW - Entropy
KW - Ischemia
KW - Principal component analysis
KW - Radial basis functions
KW - Self-organizing maps
KW - Support vector machines
KW - Vapnik-Chervonenkis dimension
UR - http://www.scopus.com/inward/record.url?scp=0035330547&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0035330547&partnerID=8YFLogxK
U2 - 10.1109/72.925554
DO - 10.1109/72.925554
M3 - Article
C2 - 18249884
AN - SCOPUS:0035330547
SN - 1045-9227
VL - 12
SP - 503
EP - 515
JO - IEEE Transactions on Neural Networks
JF - IEEE Transactions on Neural Networks
IS - 3
ER -