Exploring an optimal vector autoregressive model for multi-channel pulmonary sound data

The purpose of this study is to find a useful mathematical model for multi-channel pulmonary sound data. Vector auto-regressive (VAR) model schema is adopted and the best set of arguments, namely, the order and sample size of the model and the sampling rate of the data, is aimed to be determined. Both conventional prediction error criteria and a set of three new criteria which are derived specifically for pulmonary sound signals are used to evaluate the success of the model. In terms of these criteria, the second order 250-point model is selected to be the most descriptive VAR model for 14-channel pulmonary sound data. The preferred sampling rate is the original data acquisition rate, which is 9600 samples per second. The effect of normalization of the data with respect to the air flow is also examined. Six normalization schemes are implemented on the data prior to the model fit, and the resulting model parameters are examined in terms of the proposed criterion measures. It is concluded that normalization with respect to flow is not necessary prior to the VAR modeling of pulmonary sound data.