Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63668
Volume:
10 |
5 |
May 2026
Pages:
1-10
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Computer Science and Engineering
Government College of Technology

Computer Science and Engineering
Government College of Technology
Cognitive, physiological and human health effects are the main consequences of sleep instability and neurological sleep disorders. The Cyclic Alternating Pattern (CAP) has been identified as a valuable biomarker in assessing the sleep instability during the Non-Rapid Eye Movement (NREM) sequence. This research formulates an automated CAP phase classification framework based on Continuous Wavelet Transform (CWT) and Lightweight Convolutional Neural Network (CNN). Pre-processing of raw EEG recordings obtained from the CAP Sleep Database is conducted through band-pass filtering to eliminate noise and unwanted artifacts. In a bid to extract transient CAP-related features, the preprocessed EEG data segments are converted into time-frequency representations by Continuous Wavelet Transform (CWT), with each EEG segment being transformed into a two-dimensional scalogram plot/image. These scalogram representations are then fed into the Lightweight CNN model for automated classification of the CAP subtypes. The proposed framework integrates the time-frequency signal analysis with feature extraction using deep learning methods to enhance the CAP phase recognition results. For the experimental evaluation, Accuracy, Precision, Recall, F1-Score and the Confusion Matrix analysis were used. However, the proposed system attained a classification accuracy of 93.8% while preserving a computationally frugal architectural form that can be employed for pragmatic clinical analyses. Therefore, the development framework indicates automation of sleep microstructure assessment and ascertain a probable approach of EEG based sleep instability detection.
KEYWORDS
This paper proposed an automatic CAP phases classification system which combines CWT and Light Weight CNN for efficient analysis of sleep instability based on EEG signals. The proposed framework successfully convert non-stationary EEG signals into informative time-frequency scalogram features to differentiate among different CAP subclasses such as A1, A2, A3 phase. From the experimental results, the proposed system achieved significant improvements of Accuracy, Precision, Recall, F1-Score but has decreased complexity. Analysis from the confusion matrix and training analysis indicates that the framework can efficiently classify and have excellent generalization. The lightweight CNN based model is adaptable for on-line clinical diagnosis systems and medical devices that face memory constraint issues. In future, we can investigate the possibility of integrating transformer networks and multimodal PSG signal features into the developed framework and also apply this system for real-time sleep monitoring.
[1] Terzano, M. G., Parrino, L., Sherieri, A., et al. (2001). "Atlas, rules, and recording techniques for the scoring of cyclic alternating pattern (CAP) in human sleep." Sleep Medicine, 2(6), 537-553. [2] Parrino, L., Ferri, R., Bruni, O., & Terzano, M. G. (2012). "Cyclic alternating pattern (CAP): The marker of sleep instability." Sleep Medicine Reviews, 16(1), 27-45. [3] Terzano, M. G., & Parrino, L. (2000). "Origin and significance of the cyclic alternating pattern (CAP)." Sleep Medicine Reviews, 4(1), 101-123. [4] Ferri, R., Bruni, O., Miano, S., & Terzano, M. G. (2005). "Topographic mapping of the spectral components of the cyclic alternating pattern (CAP)." Sleep Medicine, 6(1), 29-36. [5] Halász, P., Terzano, M., Parrino, L., & Bodizs, R. (2004). "The nature of arousal in sleep." Journal of Sleep Research, 13(1), 1-23. [6] Smerieri, A., del Felice, A., et al. (2007). "Cyclic alternating pattern (CAP) in healthy and pathological sleep." Clinical Neurophysiology, 118(9). [7] Berry, R. B., et al. (2012). "The AASM Manual for the Scoring of Sleep and Associated Events." American Academy of Sleep Medicine. [8] Chokroverty, S. (2009). "Sleep Disorders Medicine: Basic Science, Technical Considerations, and Clinical Aspects." Elsevier Health Sciences. [9] Dridi, H., et al. (2021). "The Role of CAP in Sleep Disorders: A Comprehensive Review." Sleep Science. [10] Rosa, A. C., et al. (1999). "Automatic detection of the cyclic alternating pattern (CAP) sequences in sleep EEG." Proceedings of the 21st Annual IEEE-EMBS.
Publication Date
5/22/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...