An ANN Approach to EEG
Dec 12 , 2001
• EEG – Electroencephalogram
• Measures brain activity.
• Used to diagnose and cure brain
related disorders. EEG is often
contaminated with eye
• These “extra” signals are currently
removed manually during data
• Involves time and money.
• I have used ANN modeled on
Startle blink under noise.
Data Collection & Preprocessing
• Source : Personal Involvement in experiment set up for data collection at The
Psychology Department UW Madison.
• 43 subjects * 21sessions * 10000 = data points for classification.
• DOS Snapshot Stream – Software by the company HEM Data Corp. This
program collects data from channels as per the specified sampling rate and
gain settings of an attached Bio-Electric Amplifier.
• Hardware Contour following Integration of Raw Startle Data.
• The data is streamed to a stimulus file.
• Matlab used to read the stimulus file.
• Scaling of data.
• 60 Hz digital software notch filtering using Matlab Signal Processing ToolBox
• Pattern Classification problem that
distinguishes EEG from Eye Artefact
• MLP with back propagation.
• Program written on the lines of the all
powerful “bp.m” written by Prof .Hu
Results and Future
• I tried out several combinations and trained the
• Attractive classification rate of 90% so far using
learn rate = 0.01 and momentum = 0.4 on a 3
layer MLP with 2 neurons in hidden layer.
• Yet to do cross validation and hopefully Crate