Dream Classification based on Beta waves in EEG signals

Brain machine interfaces (BMIs) is the interface to understand and decode brain activity to automate external devices by its commands. This research presents the approach of understanding dreams by decoding electroencephalogram (EEG) signals in binary vectors and transferring the results into images using artificial intelligence and machine learning algorithms. During this research EEG signals will be collected from volunteers during the full awakens stage of the human brain with attention state (Beta waves), the testing will be on sleeping volunteers through REM sleep. This research will focus on the beta frequency range with two levels, First level: extracting the signal in the active state of the human brain when the training features will be extracted (beta signals). Second level: results will be during rapid eye movement (REM) sleep which lasts 10-15 minutes during sleeping, the waves in this duration are equal to beta frequency so hypnotically lucid and easy to recall dreams occur at this stage.