Related Experiment Video
Updated: Jul 13, 2026
04:54
IntelliSleepScorer, a Software Package with a Graphic User Interface for Mice Automated Sleep Stage Scoring
Published on: November 8, 2024
An efficient method for snore/nonsnore classification of sleep sounds.
M Cavusoglu1, M Kamasak, O Erogul
1Electrical and Electronics Engineering Department, Middle East Technical University, 06530, Ankara, Turkey.
Physiological Measurement
|August 1, 2007
Summary
A novel method effectively detects snoring using sound analysis and principal component analysis. This technique achieves high accuracy in identifying snoring episodes, aiding in the diagnosis of Obstructive Sleep Apnea Syndrome (OSAS).
Area of Science:
- Biomedical Engineering
- Sleep Medicine
- Signal Processing
Background:
- Snoring is a common symptom associated with Obstructive Sleep Apnea Syndrome (OSAS).
- Objective detection of snoring episodes in sleep sound recordings is crucial for clinical diagnosis and treatment.
- Current methods may require complex analysis or invasive procedures.
Purpose of the Study:
- To develop and validate a new, efficient method for detecting snoring episodes in sleep sound recordings.
- To classify sleep sound segments as snores or non-snores using subband energy distributions and dimensionality reduction.
- To assess the accuracy of the proposed method for diagnosing simple snorers and patients with OSAS.
Main Methods:
- Sleep sound recordings from individuals suspected of OSAS were analyzed.
- Sleep sound segments were classified based on subband energy distributions.
- Principal Component Analysis (PCA) was employed to reduce feature vector dimensionality to two dimensions.
- The system was trained and tested using data from 30 subjects (18 simple snorers, 12 OSA patients).
- Performance was evaluated against manual annotations by an ENT specialist.
Main Results:
- The algorithm achieved 97.3% accuracy for simple snorers when trained solely on their data.
- Accuracy dropped to 90.2% when training data included both simple snorers and OSA patients.
- Snore episode detection accuracy for OSA patients was 86.8%.
- All results were obtained using separate training and testing sets.
Conclusions:
- The proposed method demonstrates high accuracy and efficiency in detecting snoring episodes.
- The developed tool provides objective evaluation of sleep sounds for clinical purposes.
- This technique can aid in the diagnosis and treatment of OSAS.
Related Concept Videos
01:21Sleep Apnea
Sleep apnea is a condition where breathing stops intermittently during sleep, often leading to significant health issues. Each episode can last from 10 to 20 seconds or more and is frequently accompanied by a brief arousal from sleep. This disturbance, largely unnoticed by the individual, can lead to severe daytime fatigue. Commonly, individuals seek help after being informed by their partners about loud snoring and noticeable breathing pauses during sleep.
The condition is more prevalent among...
The condition is more prevalent among...
01:30Classification of Signals
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...