Automated phase classification in cyclic alternating patterns in sleep stages using Wigner-Ville Distribution based...

Area of Science:

• Neuroscience
• Signal Processing
• Biomedical Engineering

Background:

• Sleep quality analysis is crucial for diagnosing various neurological disorders.
• Cyclic Alternating Patterns (CAP) are key indicators of sleep quality and stability.
• Manual CAP phase classification is labor-intensive and prone to errors.

Purpose of the Study:

• To develop an automated and simplified method for classifying CAP phases (A and B).
• To improve the accuracy and efficiency of sleep disorder diagnosis.

Main Methods:

• Utilized Wigner-Ville Distribution (WVD) for high-resolution time-frequency analysis.
• Employed Rényi entropy (RE) to minimize time-frequency uncertainty with WVD.
• Implemented a Support Vector Machine (SVM) with a medium Gaussian kernel and 10-fold cross-validation.

Main Results:

• Achieved an average classification accuracy of 72.35% for balanced datasets.
• Achieved an average classification accuracy of 87.45% for unbalanced datasets.
• The method requires no pre-processing or post-processing, enhancing simplicity.

Conclusions:

• The proposed automated approach offers a simple yet effective tool for CAP phase classification.
• This method can assist medical experts in assessing cerebral stability and sleep quality.
• Potential to improve diagnostic accuracy for sleep-related disorders.