NITAAI-Veda.nyf > Soul Science God Philosophy > Science and Spiritual Quest > Section 4 Towards a New Biology > MATHEMATICAL TECHNIQUES FOR STUDY OF EEG > 2. Methods > 2.3 Features considered |

**2.3 Features considered**

This section describes the features considered for classifying EEG
data.

Fractal Dimension: Katz's approach is used to calculate the FD of
a waveform.

Complexity measure: Lempel-Ziv complexity measure C (n) (Zhang XS,
Roy RJ and Jension EW, 2001) is used in our work, since it is extremely suited
for characterizing the development of spatio-temporal activity patterns in
high-dimensionality nonlinear systems.The other features considered are mean,
variance and powers in alpha, beta, theta and delta waves.

Data handled: The EEG data consists of recordings made from a
subject performing meditation. This data was collected during a meditation
session where the subject was asked to simply sit without meditation for some
time and then asked to start meditation.

Features Considered KNNC MLP RBF SVM

Mean, Variance 84.47 87.58 88.47 89.31

Ractal Dimension (FD), Complexity Measure (CM) 90.54 94.65 97.79 98.18

Mean, Variance, FD, CM 89.74 98.38 98.29 98.81

Frequency Domain Features 87.28 96.25 96.43 98.29

Mean, Variance, FD, CM
& Frequency domain features 89.44 98.81 98.81 99.60

Table 1: Testing Accuracy Table for EEG Data (Two-category case)

After the end of meditation, recording was continued and post
meditation data was collected. We considered 60 segments of premeditation data,
140 segments of meditation data, 140 segments of deep meditation data and 60
segments of post meditation data.

Features Considered KNNC MLP RBF SVM

Mean, Variance 84.47 87.58 88.47 89.31

Fractal Dimension (FD), Complexity Measure (CM) 90.54 94.65 97.79 98.18

Mean, Variance, FD, CM 89.74 98.38 98.29 98.81

Frequency Domain Features 87.28 96.25 96.43 98.29

Mean, Variance, FD, CM
& Frequency domain features 89.44 98.81 98.81 99.60

Features Considered KNNC MLP RBF SVM

Mean, Variance 74.40 81.57 86.44 87.30

Fractal Dimension (FD), Complexity Measure (CM) 80.55 92.56 97.27 97.65

Mean, Variance, FD, CM 78.50 98.29 97.95 98.81

Frequency Domain Features 77.82 96.25 96.43 97.95

Mean, Variance, FD, CM
& Frequency domain features 80.20 98.63 98.29 99.60

Table 2: Testing Accuracy Table for EEG Data (Three-category
case).