A Methodological Review on EEG Data Reduction in Edge/Fog computing-based IoMT networks

This paper presents a methodological review of electroencephalography (EEG) data reduction in edge/fog computing-based IoMT networks. The review focuses on the existing EEG-based signal reduction methods. The EEG components and their framework for capturing the signal generated by the EEG and the signal analysis process are explained. In addition, the public EEG datasets and their characteristics are illustrated. Various signal processing algorithms, including data reduction, compression, and feature extraction, which are used to reduce the size of the captured data, are investigated. The feature-based machine learning techniques are proposed to achieve two goals: reducing the size of the data and extracting a meaningful representation for signal classification. This work can serve as a fundamental plan and a road map for scholars interested in EEG data reduction on edge/fog computing based on INTERNET OF MEDICAL THINGS (IOMT) networks.