Sleep apnea syndrome recognition using the GreyART network

This study employs relational analysis and the GreyART network to identify the characteristics of electroencephalogram signals of sleep apnea syndrome (SAS). Seventeen raw electroencephalogram data from the sleep database compiled by Massachusetts Institute of Technology (MIT) and Beth Israel Hospital (BIH) were used in conjunction with four wavelet decomposition steps to obtain the cD4 wavelet coefficient as input for the GreyART network (Grey relational analysis and Adaptive resonant theory network). The GreyART network was then used for simulation training and testing in order to achieve the best recognition results. This study achieved an average recognition rate of 93.33% for electroencephalogram data slp01b, and recognition rates during the training and testing stage for this record were 95.80% and 92.12% respectively. This was the best recognition result for any of the 17 records. The overall average recognition rate for all 17 records was 78.10%. In comparison with past literature, this study´s use of the GreyART network to recognize electroencephalogram signal characteristics of SAS possesses excellent reference value.