Abstract-Meditation refers to a family of selfregulation practices that focus on training attention and awareness in order to bring mental processes under greater voluntary control. The aim of this study is to evaluate the efficiency of two different classifiers, kNearest Neighbor (k-NN) and Radial Basis Function (RBF), on the heart rate signals in a specific psychological state. For this purpose, two types of heart rate time series (before, and during meditation) of 25 healthy women are collected in the meditation clinic in Mashhad. The spectral parameters are used to gain insight into the autonomic nervous system (ANS) response induced by meditation. Therefore, very low frequency, low frequency, high frequency, the LF/HF ratio and frequency of the highest spectral peak of heart rate signals are extracted and used as inputs of the classifiers. To evaluate performance of the classifiers, the classification accuracies and mean square error (MSE) of the classifiers were examined. The classification results of this study denote that the RBF classifier trained on spectral features obtains higher accuracy than that of k-NN classifier. The total classification accuracy of the RBF classifier is 92.3% with 0.026 classification error. However, k-Nearest Neighbor classifier gives encouraging results (86.5%). Experimental results verify that radial basis function is an efficient classifier for classifying heart rate signals in a specific psychological state.