Multi-stage nonlinear classification of respiratory sounds

The three-class recognition problem of respiratory sounds based on multi-stage decisions is addressed. The method consists of dividing respiratory cycles of patients into phases, and classifying each phase with a separate multilayer perceptron, called the “phase expert”. Each phase information consists of several time segments and their parametric representation. Expert decisions on phase segments are then combined by a decision fusion scheme, simulating a consultation session. Thus in the first stage of hierarchy one uses signal features to reach segment decisions, while in the second stage one uses decision votes themselves as features inputted into a second classifier. Furthermore a new regularization scheme is applied to the data to stabilize training and consultation.