Modeling of Human Physiological Parameters in an E-Laboratory by SOM Neural Networks

Abstract

An approach of interpreting some bioinformatics data using Self-Organizing Map (SOM) type neural networks is described. The ways are proposed constructing intelligent program tools of embedded agents to collect ECG and EEG data for academic usage in a virtual e-laboratory. A SOM-based diagnostic algorithm is proposed interpreting data from Medical databases donated by University of California Machine Learning Page hosts, etc. By applying SOM for EEG data of Colorado State University, methods recognizing some unified mental tasks performed by different subjects are proposed. It is also shown that knowledge discovered by SOM data interpretation can be involved in a process of e-tutoring of students and learners of bioinformatics. Keywords: Ambient Intelligence, Embedded Agents, Machine Learning, Self-Organizing Maps. Ill. 9, bibl. 19 (in English; summaries in English, Russian and Lithuanian).