A method for feature extraction of the capnogram for asthma classification is proposed based on wavelet decomposition.The method requires low computational cost and shows adequate performance for a real time classification of asthma severity.The experiments include testing 23 capnograms collected from an Asthma Camp in Cuba on a personal computer architecture running Matlab.An estimation of the execution time for a physiological multiparameter monitor is obtained,showing an average of 8 sec to determine the suitable features.The proposal aims to be a part in the decision support system for asthma classification that is under development by research group of TITECH and TMDU.