VI. CONCLUSION
In this paper, two database have been used, one with 128Hz and another is with 1024Hz. Feature extraction was done using DWT method and statistical parameter were calculated on wavelet coefficients. For classification purposes, three different sets have been considered. Considering all the bands at once, considering only three bands at a time and finally considering the individual band. From the Table I, II conclude that for the sampling rate of 1024 Hz results are more accurate. This paper also concludes that the accuracy is less when sampling rate is less. But when sampling rate is increased decomposition level increases which in turn increases the processing time.
