Eliminating ECG noise from electroencephalogram for efficient brain tumor detection

The Electroencephalogram signal which is picked up by electrodes from the skull of the patient´s body is effected severely by noise of power line, noise of human body muscles,noise of human lungs and noise of the baseline. The baseline noises arise even because of patients body movements and breathing, the sensors are loosely connected and eye movements. Researchers have applied many algorithms for removal of these noises. The basic important algorithms used are Kalman filter, Moving average and Cubic spline. The Electroencephalogram signals are highly contaminated with various artifacts both from subject and from equipment interferences. For efficient detection of tumor artifacts exist in the electroencephalogram signal are removed using analogue filtering. In this research Fast Independent Component Analysis algorithm is used to separate the noise and get the features which are buried in the extended band of noise. For problem solution a unique Fast Independent Component Analysis filter is being proposed in this research.