MétaCan
Menu
Back to cohort
Record W4407066574 · doi:10.48084/etasr.9154

Optimal CNN Model for Obstructive Sleep Apnea Detection using Particle Swarm Optimization

2025· article· en· W4407066574 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueEngineering Technology & Applied Science Research · 2025
Typearticle
Languageen
FieldMedicine
TopicObstructive Sleep Apnea Research
Canadian institutionsÉcole de Technologie Supérieure
Fundersnot available
KeywordsParticle swarm optimizationObstructive sleep apneaSleep (system call)Computer scienceParticle (ecology)Sleep apneaArtificial intelligenceMedicineMachine learningAnesthesiaBiologyEcology

Abstract

fetched live from OpenAlex

Obstructive Sleep Apnea (OSA) is a prevalent sleep disorder with significant health risks. It is characterized by the narrowing of the upper airway during sleep, leading to vibrations in the airway structures and the production of snoring sounds. Recently, Convolutional Neural Networks (CNNs) have been leveraged to extract meaningful features from snoring sound data, enabling early and accurate detection of OSA. The effectiveness of these neural network optimizations depends on the starting values of the model, the gradient algorithm used, and the complexity of the problem. This study introduces an improved Particle Swarm Optimization (PSO) strategy that linearly adjusts the learning rate coefficient to enhance accuracy and convergence speed. Our approach was evaluated on a collected and pre-processed dataset based on the PSG-Audio database. Experimental results demonstrate that our method significantly outperforms the conventional optimization algorithm and existing PSO techniques, achieving a remarkable accuracy of 99.1%. These findings confirm the potential of our optimized model for OSA detection.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.388
Threshold uncertainty score0.823

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0020.006
Science and technology studies0.0010.001
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.036
GPT teacher head0.354
Teacher spread0.317 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it