Existing Methodologies, Evaluation Metrics, Research Gaps, and Future Research Trends: A Sleep Stage Classification Framework

The quality of life of the patients is degraded when the person is affected with sleep-related disorders that include narcolepsy, insomnia, and sleep apnea. The sleep stage classification under manual scoring is required expert knowledge, and the standard guidelines, as well as the manual progressio...

Full description

Saved in:
Bibliographic Details
Main Authors: Ravi Raja, A, Polasi, Phani Kumar
Format: Conference Proceeding
Language:English
Subjects:
Dataset Consideration
Evaluation Metrics
Existing Methodologies
Machine learning algorithms
Manuals
Measurement
Research Gaps and Future Research Trends
Sleep
Sleep Stage Classification Framework
Surveys
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The quality of life of the patients is degraded when the person is affected with sleep-related disorders that include narcolepsy, insomnia, and sleep apnea. The sleep stage classification under manual scoring is required expert knowledge, and the standard guidelines, as well as the manual progression, are also needed for the classification of sleep stages. The unusual patterns from various nerve-related signals are carefully inspected for monitoring sleep stages. But, the visual inspection of an Electroencephalogram (EEG) with long-term EEG recording is very complex, and it requires more time to complete the process. Various approaches are developed to classify the sleep stages with high accuracy automatically. Moreover, machine learning algorithms and several signal processing methodologies are adopted to extract the relevant information from the original biological signals. Hence, this paper focuses on the literature review of existing methodologies of classifying sleep stages using EEG signals. It also explores the machine structure and deep structure network models for detecting sleep disorders. The challenging issues are discussed, which is helpful to direct future development. Consequently, the survey section is given, and its chronological order is analyzed of traditional sleep stage classification. It is then followed by dataset consideration, techniques used, results, and its performance metrics and implementation tool. Lastly, the research gaps motivate to develop the new efficient classification model for sleep disorders.
ISSN:2768-5330
DOI:10.1109/ICICCS56967.2023.10142691