Reckoning respiratory signals to affectively decipher mental state.

Recognizing mental states from physiological signal is a concern not only for medical diagnostics, but also for cognitive science, behavioral studies as well as brain machine interfaces. This study employs an unique approach of solely utilizing the respiration signals in order to decipher mental states. A public dataset, Affective Pacman, is considered for this study, where the various physiological signals are acquired during normal and frustrated mental states. An efficient way to remove the non-linear baseline drifts in the signal is implemented to extract the respiratory features in most effective way. Another major adversity is the presence of class imbalance, which is effectively rectified using Synthetic Minority Oversampling TEchnique (SMOTE). Application of SMOTE algorithm to resolve class imbalance problem, not only increased the classification accuracy, but also reduced the classifier bias towards the majority class, which in turn exceedingly enhanced the classifier sensitivity. The multilayer perceptron classifier performed best with SMOTE generated feature set, with classification accuracy (CA), true positive rate (TPR) and true negative rate (TNR) of 97.9%, 92.6% and 99.3% respectively. The current approach is found to perform better compared to relevant literature.