• Priyanka Chaturvedi

The human’s brain electrical activity changes with the human reactions to the situations, thoughts, sleep stages and different alertness levels. Brain Computer Interface uses different features of brain electrical activity to create a communication pathway. Brain Computer Interface replaces traditional pathway of nervous system and helps in controlling applicationsby patients suffering from severe motor disorders. Efficiency of Brain Computer Interface largely depends on the human alertness level. Large variation in Electroencephalogramsignals due to change in alertness level may cause false interpretation of Electroencephalogram signals. In present work, a methodology is proposed for automatic alertness level detection of human brain using Electroencephalogram signals. In present methodology, the raw data is processed by Multi Scale Principle Component Analysis technique and further Lifting Wavelet Transform based features are extracted from processed signals. For classification or recognition of mental alertness level Support Vector Machine and Radom Forest Tree classifiers are used. The results of the classification illustrate the efficiency of the proposed methodology in automatic detection of alertness level of human brain.

Brain Computer Interface (BCI), Electroencephalogram (EEG), Lifting Wavelet Transform, Support Vector Machine (SVM), Random Forest

"Lifting Wavelet Transform based Mental Alertness Detection for Brain Computer Interface", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.4, Issue 8, page no.20-24, August-2017, Available :http://www.jetir.org/papers/JETIR1708005.pdf

"Lifting Wavelet Transform based Mental Alertness Detection for Brain Computer Interface", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.4, Issue 8, page no. pp20-24, August-2017, Available at : http://www.jetir.org/papers/JETIR1708005.pdf