Title :
Estimation of Action Potential of the Cellular Membrane using Support Vectors Machines
Author :
Seijas, Cesar ; Caralli, Antonino ; Villazana, Sergio
Author_Institution :
Fac. de Ingenieria, Univ. de Carabobo, Valencia
fDate :
Aug. 30 2006-Sept. 3 2006
Abstract :
In this article an application of the support vectors machines (SVM) is presented in the problem of the estimate of the action potential of the cellular membrane V, which is, a temporary function, highly non-linear, of the ionic concentrations of sodium and potassium. A model, for the estimate of V, is the Hodgkin-Huxley (HH) model that describes the dynamics of V similar to an electric circuit with passive elements representing the biochemical variables involved in the process. SVM are algorithms of emergent computation that have demonstrated an excellent performance in classification and regression applications; in this article they are used for the estimate of V and the result is compared with that obtained using HH, demonstrating that SVM are a promising alternative in modelling problem of biological processes
Keywords :
bioelectric potentials; biological techniques; biology computing; biomembrane transport; pattern classification; support vector machines; Hodgkin-Huxley model; SVM; action potential estimation; biological processes; cellular membrane; classification application; potassium ion concentration; regression application; sodium ion concentration; support vectors machines; Artificial neural networks; Biological processes; Biological system modeling; Biomembranes; Capacitance; Cities and towns; Equivalent circuits; Risk management; Support vector machine classification; Support vector machines;
Conference_Titel :
Engineering in Medicine and Biology Society, 2006. EMBS '06. 28th Annual International Conference of the IEEE
Conference_Location :
New York, NY
Print_ISBN :
1-4244-0032-5
Electronic_ISBN :
1557-170X
DOI :
10.1109/IEMBS.2006.260149
