Self-organizing map based feature learning in bio-signal processing

Abstract

Feature extraction is playing a significant role in bio-signal processing. Feature identification and selection has two approaches. The standard method is engineering handcraft which is based on user experience and application area. While the other approach is feature learning that based on making the system identify and select the best features suit the application. The idea behind feature learning is to avoid dealing with any feature extraction or reduction algorithms and to train the suggested model on learning features from input bio-signal by itself. In this paper, Self-Organizing Map (SOM) will be implemented as a feature learning technique to learn the model extract the features from the input data. Deep learning approach will be proposed by deploying SOM to learn features. In the proposed model, the raw data will be read then represented by using different signal representation as Spectrogram, Wavelet and Wavelet Packet. The newly represented data will be fed to self-organizing map layer to generate features, and finally, the performance of the suggested scheme will be evaluated by applying different classifiers such as Support Vector Machine, Extreme Learning Machine, Evolutionally Extreme Learning Machine and Discriminate Analysis Classification. Analysis of Variance (ANOVA) and confidence interval for different classifiers will be calculated. As an improving step for the results, classifier fusion layer will be implemented to select the most accurate result for both training and testing set. Classifier fusion layer led to a promising training and testing accuracies.