Abstract
In this study, a new feature selection algorithm, the neighborhood-relationship feature selection (NRFS) algorithm, is proposed for identifying rat electroencephalogram signals and recognizing Chinese characters. In these two applications, dependent relationships exist among the feature vectors and their neighboring feature vectors. Therefore, the proposed NRFS algorithm was designed for solving this problem. By applying the NRFS algorithm, unselected feature vectors have a high priority of being added into the feature subset if the neighboring feature vectors have been selected. In addition, selected feature vectors have a high priority of being eliminated if the neighboring feature vectors are not selected. In the experiments conducted in this study, the NRFS algorithm was compared with two feature algorithms. The experimental results indicated that the NRFS algorithm can extract the crucial frequency bands for identifying rat vigilance states and identifying crucial character regions for recognizing Chinese characters.
Highlights
Sleep is a physiological state comprising multiple stages
Experimental simulations were conducted in this study to compare four feature-selection methods: methods: the Information Gain (IG) [12], sequential floating search (SFS) [23], sequential forward floating search (SFFS) [23], and neighborhood-relationship feature selection (NRFS) algorithms
This study proposes using the NRFS algorithm to identify crucial frequency bands for classifying the vigilance states of rats, and for locating crucial areas in a character image for recognizing Chinese characters
Summary
Electroencephalogram (EEG) analysis has indicated that typical patterns of activity are correlated with various stages of sleep, wakefulness, and certain pathophysiological processes, such as seizures. Sleep stages can be identified by combining EEG, electromyography (EMG), electrooculography (EOG), and visual behavioral monitoring. Scoring these vigilance states manually is a time-consuming task, even when the analyzer is an expert. During the AW state, the rats produced high-frequency EEG results. The SWS state, which is defined by a high-amplitude and low-frequency EEG, begins with a sleep spindle and is dominated by a delta (0.5–4 Hz) wave. In the REM state, the rats produced high-frequency EEG results, which were similar to those produced in the AW state. The rats were atonic and demonstrated flat EMG activity
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have