A contextual method for electroencephalogram recognition

The contextual method is used to classify electroencephalogram data. The experimental results show that this method has an advantage in recognition rate over conventional statistical methods and the fuzzy method. By experience, five important testing markers are extracted from an electroencephalogram, and each marker is divided into several quantization levels. The five markers are tested at four positions on the patient´s head. Each marker is represented by its upper and lower bounds. Thus 76 test results can be obtained, then converted into a 136-dimensional eigenvector according to discretization in quantization levels