Abstract :
A hybrid system for automated EEG sleep staging is presented in this article. By combining a self-organizing feature map (SOFM) with a fuzzy reasoning-based classifier (FRBC) and utilizing both temporal and spectrum features of the EEG signal, the system provides a reliable tool for automatic EEG sleep staging. Conceptually, the system is divided into four passes: artifact detection, rough staging, stage refinement and post processing. The artifact detection module is firstly employed to exclude stage movement from other stages. Then, the SOFM with features as its inputs derived from the power spectrum divides sleep into three "extreme" stages: wake, light/REM and deep stage. In stage refinement pass, the FRBC, which takes characteristic waveforms\´ activities as inputs, subdivides the extreme stages into the exact stages (i.e., stage 1, stage 2) defined by R&K standard. At last, in post processing pass, a stage-smoothing method that mainly utilizes the temporal context information is used to correct unexpected stage transitions, thus to improve the system\´s performance. The system was tested with eight whole night sleep records with an average man-machine agreement of 85.3%. Compared with the high inter-scorer disagreement, the performance is desirable
Keywords :
electroencephalography; fuzzy set theory; medical signal processing; self-organising feature maps; sleep; smoothing methods; artifact detection; automated EEG sleep staging; deep stage; fuzzy reasoning-based classifier; fuzzy rule-based reasoning; hybrid system; light/REM; man-machine agreement; neural network; post processing; rough staging; self-organizing feature map; stage refinement; stage refinement pass; stage-smoothing method; temporal context information; wake; Electroencephalography; Fuzzy neural networks; Fuzzy reasoning; Fuzzy systems; Man machine systems; Neural networks; Power system reliability; Sleep; System performance; System testing; EEG; SOFM; fuzzy reasoning-based classifier; neural network; sleep staging;
