Snoring Sound Classification Using 1D-CNN Model Based on Multi-Feature Extraction

다국어 초록 (Multilingual Abstract)

Sound is an essential element of human relationships and communication. The sound recognition process involves three phases: signal preprocessing, feature extraction, and classification. This paper describes research on the classification of snoring data used to determine the importance of sleep health in humans. However, current sound classification methods using deep learning approaches do not yield desirable results for building good models. This is because some of the salient features required to sufficiently discriminate sounds and improve the accuracy of the classification are poorly captured during training. In this study, we propose a new convolutional neural network (CNN) model for sound classification using multi-feature extraction. The extracted features were used to form a new dataset that was used as the input to the CNN. Experiments were conducted on snoring and non-snoring datasets. The accuracy of the proposed model was 99.7% for snoring sounds, demonstrating an almost perfect classification and superior results compared to existing methods.

목차 (Table of Contents)

• Abstract
• 1. Introduction
• 2. Related Work
• 3. Proposed Method
• 4. Experiment Results and Discussion
• 5. Conclusion
• References

참고문헌 (Reference)

1 B. McFee, "librosa: audio and music signal analysis in Python" 2015 : 18-25, 2015

2 M. A. Arasi, "Survey of machine learning techniques in medical imaging" 8 (8): 2107-2116, 2019

3 A. Khamparia, "Sound classification using convolutional neural network and tensor deep stacking network" 7 : 7717-7727, 2019

4 B. Kang, "Snoring and apnea detection based on hybrid neural networks" 2017 : 57-60, 2017

5 S. Amiriparian, "Snore sound classification using image-based deep spectrum features" 2017 : 3512-3516, 2017

6 O. Parra, "Sleep-related breathing disorders: impact on mortality of cerebrovascular disease" 24 (24): 267-272, 2004

7 S. Yu, "STFT-like time frequency representations of nonstationary signal with arbitrary sampling schemes" 204 : 211-221, 2016

8 B. Arsenali, "Recurrent neural network for classification of snoring and non-snoring sound events" 2018 : 328-331, 2018

9 X. Zhang, "Performance of a snoring noise control system based on an active partition" 116 : 283-290, 2017

10 F. Demir, "Low level texture features for snore sound discrimination" 2018 : 2018-2413, 2018

11 "Librosa: spectral feature"

12 K. Okuno, "Japanese cross-sectional multicenter survey (JAMS) of oral appliance therapy in the management of obstructive sleep apnea" 16 (16): 3288-, 2019

13 N. Dalal, "Histograms of oriented gradients for human detection" 2005 : 886-893, 2005

14 Yagya Raj Pandeya ; Joonwhoan Lee, "Domestic Cat Sound Classification Using Transfer Learning" 한국지능시스템학회 18 (18): 154-160, 2018

15 F. F. Li, "Digital Signal Processing in Audio and Acoustical Engineering" CRC Press 2019

16 S. J. Lim, "Classification of snoring sound based on a recurrent neural network" 123 : 237-245, 2019

17 J. Huang, "An improved kNN based on class contribution and feature weighting" 2018 : 313-316, 2018

18 S. A. Tuncer, "A deep learning-based decision support system for diagnosis of OSAS using PTT signals" 127 : 15-22, 2019

19 T. Khan, "A deep learning model for snoring detection and vibration notification using a smart wearable gadget" 8 (8): 987-, 2019

20 T. A. Adesuyi, "A brief on snoring data and classification methods" 9 (9): 426-432, 2020

21 T. A. Adesuyi, "A Convolutional Neural Network Model for Sound Classification Based on Multi-Feature Extraction" Kumoh National University of Technology 2020

22 J. Wang, "A CNNGRU approach to capture time-frequency pattern interdependence for snore sound classification" 2018 : 997-1001, 2018

23 S. Kiranyaz, "1D convolutional neural networks and applications: a survey"

24 JalFaizy, "10 Advanced deep learning architectures data scientists should know!"