Indian Journal of Science and Technology
DOI: 10.17485/ijst/2015/v8i31/87271
Year: 2015, Volume: 8, Issue: 31, Pages: 1-4
Original Article
K. Venkatesh1 and S. Geetha2*
1 Department of Biomedical Engineering, Jerusalem College of Engineering, Chennai - 600100, Tamil Nadu, India
2 Department of Biomedical Engineering, Bharath University, Chennai - 600073, Tamil Nadu, India; [email protected]
The usual method for sleep stages classification is visual inspection method by sleep specialist. It uses eight EEG channels (O1, O2, T3, T4, C3, C4, Fp1 and Fp2), EOG and also EMG for sleep analysis. This method consumes more time (hours) for sleep stages classification. Some brain disorders like narcolepsy (excessive day time sleepiness) requires real-time monitoring of sleep states which is not possible to using conventional techniques. Hence sleep stages classification is done using Artificial Neural Network (ANN). Feature parameters such as Minimum amplitude, maximum amplitude, mean, standard deviation (SD) and energy were extracted using Discrete Wavelet Transform (DWT). This features for training and also for testing ANN, results obtained with this technique is accurate and also less time consuming as compare to other techniques.
Keywords: Artificial Neural Network (ANN), Discrete Wavelet Transform (DWT), Feed Forward Neural Network (FNN), Electroencephalogram (EEG), Electrooculogram (EOG)
Subscribe now for latest articles and news.