Feature extraction and selection algorithms in biomedical data classifiers based on time-frequency and principle component analysis

Proposed methods for feature extraction and selection stages of biomedical pattern recognition system are presented. Time-Frequency signal analysis based on adaptive wavelet transform and Principle Component Algorithm (PCA) algorithm is used for extracting and selecting from original data the input features that are most predictive for a given outcome. From the discrete fast wavelet transform coefficients optimal feature set based on energy and entropy of wavelet components is created. Then PCA is used to shrink this feature group by creating the most representative parameter subset for given problem, which is the input for last neural classifier stage. System was positively verified on the set of clinically classified ECG signals for control and atrial fibrillation (AF) disease patients taken from MITBIH data base. The measures of specificity and sensitivity computed for the set of 20 AF and 20 patients from control group divided into learning and verifying subsets were used to evaluate presented pattern recognition structure. Different types of wavelet basic function for feature extraction stage as well as supervised (Multilayer Perceptron) and unsupervised (Self Organizating Maps) neural net-work classification units were tested to find the best system structure.