Evolvable Block-based Neural Networks for Heart Monitoring

Seong Gon Kong: Department of Electrical and Computer Engineering, The University of Tennessee, Knoxville, TN 37996, USA. (TEL) (865)974-3861 (FAX) (865)974-5483 (E-Mail) skong@utk.edu (URL) http://www.ece.utk.edu/~skong

Abstract

This paper presents evolvable block-based neural networks (BbNNs) for heart condition monitoring. A BbNN consists of a two-dimensional (2-D) array of modular basic blocks that can be easily implemented using reconfigurable digital hardware. BbNNs are evolved for each patient in order to provide personalized health monitoring. A genetic algorithm evolves the internal structure and associated weights of a BbNN using training patterns that consist of morphological and temporal features extracted from the ECG signal of a patient. The remaining part of the ECG record serves as the test signal. The BbNN was tested for ECG signals collected from different patients provided by the MIT-BIH Arrhythmia database.

Short Biography

Seong Gon Kong: Seong Gon Kong is an Associate Professor in Department of Electrical and Computer Engineering at the University of Tennessee, Knoxville, Tennessee. His current research interests are intelligent systems, pattern recognition, and image processing.

Before he joined the faculty of the University of Tennessee in 2002, he was an Associate Professor in the Department of Electrical Engineering at Soongsil University from 1992 to 2001 and a visiting scholar at Purdue University, West Lafayette, Indiana from 2000 to 2001. He received the BS and the MS degrees from Seoul National University, in 1982 and 1987, and the Ph.D. degree from the University of Southern California, Los Angeles, California in 1991, all in Electrical Engineering. Dr. Kong is a Senior Member of IEEE, an Associate Editor of IEEE Transactions on Neural Networks, and members of Technical and Standards Committees of IEEE Computational Intelligence Society. He served as a president of Tennessee Chapter of KSEA from 2003 to 2004.