A NOVEL SLEEP STAGE CLASSIFICATION METHOD FOR ELDERLY PEOPLE USING THE SLEEP EEG SIGNAL AND SENET MODELS

First, research on sleep stage staging in older individuals is highly valuable because it helps to obtain insights into sleep quality and structure changes that occur in older persons. This approach was used to better understand the correlations with cognitive functioning, the immune system, and mental health, among other factors. Second, identifying the features of older persons in various stages of sleep could lead to more specific guidance for managing and treating personalized sleep to significantly improve the quality of life of these individuals. Finally, in-depth research on sleep in older persons can assist in the development of preventative and intervention measures for older adults, which can help to reduce the negative consequences that age-related sleep issues have on general health. Categorizing sleep EEG data is the focus of this research to present an improved squeeze-and-excitation network (SENet) for application in the classification process. For the purpose of this study, electroencephalogram (EEG) features were extracted using continuous wavelet transform. Subsequently, the lightweight context transform (LCT), which is a combination of normalization, linear transformation, and SENet, is carried out to achieve sleep EEG classification. Extraction using the continuous wavelet transform has the potential to more accurately depict the changes and characteristics of sleep stages. As a result of incorporating LCT, the computational cost of the model is reduced, and the model becomes more applicable to real-world situations. Experiments conducted on two public datasets, Sleep-EDF-20 and Sleep-EDF-78, demonstrated that the strategy presented in this study can achieve the requisite classification performance and the model converges faster.