|NITAAI-Veda.nyf > Soul Science God Philosophy > Science and Spiritual Quest > Section 4 Towards a New Biology > MATHEMATICAL TECHNIQUES FOR STUDY OF EEG > 5. Conclusions|
The attractor dimension curves presented in this study may have potential as means of understanding the transitional process of the chaotic dynamics involving large-scale neuronal behavior of brain during meditation. We have presented CSA, running fractal and attractor dimension curves of time record of the meditation EEG. The transitions in the meditation can be clearly discerned in the fractal and attractor dimension plots which corresponds to the changes seen in the CSA. The results indicate that the attractor dimension estimation is effective in depicting the dynamics of the brain in a highly complex state. The brain evolves gradually from a basal level of low dimensional complexity in keeping with waking state into a hyper chaotic state during meditation. The neural system may relax into a less complex level in some stages of meditation.We have also presented the efficacy of neural networks in differentiating various levels of consciousness using electroencephalogram (EEG) signals. We compared conventional KNNC method with three kinds of neural networks (MLP, RBF and SVM). The obtained accuracies for the back propagation network, RBF network units and support vector machine with RBF kernel are higher than for k-neighbors. Among neural network methods, SVM gives better performance than MLP and RBF networks. RBF network, in general, gives better performance than MLP network.We are able to attain very high accuracy of 99.6% with SVM in case of two-category problem (Meditation and Pre-meditation), 99.6% with SVM in case of three-category problem (Meditation, Pre-meditation and Post meditation) and 99.38% with SVM in case of four-category problem (Meditation, Deep meditation, Pre-meditation and Post meditation). Thus the efficacy of neural networks in differentiating various levels of consciousness using EEG data is shown.