Multilevel Feature Fusion-based Convolutional Neural Network for Anomaly Classification of Respiratory Sound

Ida Ayu Putu Ari Crisdayanti; Seong Eun Kim

doi:10.1109/ICCE-Asia57006.2022.9954716

Multilevel Feature Fusion-based Convolutional Neural Network for Anomaly Classification of Respiratory Sound

Ida Ayu Putu Ari Crisdayanti
, Seong Eun Kim

Dept. of Applied Artificial Intelligence

Seoul National University of Science and Technology (SNUST)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Respiratory sound classification has been extensively studied to early detect heart and lung diseases using digital stethoscope. Previous works mainly leveraged convolutional neural network (CNN)-based deep learning methods by transforming sound signals into spectrogram images. The fine-tuned model based on pretrained ResNet (RespireNet) has been proposed and achieved high performance. However, ResNet has a very large network size, which is not suitable for mobile applications. In this paper, we proposed a lightweight deep learning approach based on a CNN architecture by incorporating self-attention and multilevel feature extraction. With considerably fewer number of parameters, we achieved a competitive performance compared to the state-of-the-art model, RespireNet, on the ICBHI dataset for normal-abnormal respiratory sound classification. The smaller model size can give an advantage in the development of internet of things (IoT) applications for automatic respiratory sound classification.

Original language	English
Title of host publication	2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665464345
DOIs	https://doi.org/10.1109/ICCE-Asia57006.2022.9954716
State	Published - 2022
Event	2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022 - Yeosu, Korea, Republic of Duration: 26 Oct 2022 → 28 Oct 2022

Publication series

Name	2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022

Conference

Conference	2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022
Country/Territory	Korea, Republic of
City	Yeosu
Period	26/10/22 → 28/10/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

CNN
Multilevel Feature
Respiratory Sound
Self-Attention

Access to Document

10.1109/ICCE-Asia57006.2022.9954716

Cite this

Crisdayanti, I. A. P. A., & Kim, S. E. (2022). Multilevel Feature Fusion-based Convolutional Neural Network for Anomaly Classification of Respiratory Sound. In 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022 (2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-Asia57006.2022.9954716

Crisdayanti, Ida Ayu Putu Ari ; Kim, Seong Eun. / Multilevel Feature Fusion-based Convolutional Neural Network for Anomaly Classification of Respiratory Sound. 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022).

@inproceedings{1182ddc00fff4da2a5887b2f17e3dc44,

title = "Multilevel Feature Fusion-based Convolutional Neural Network for Anomaly Classification of Respiratory Sound",

abstract = "Respiratory sound classification has been extensively studied to early detect heart and lung diseases using digital stethoscope. Previous works mainly leveraged convolutional neural network (CNN)-based deep learning methods by transforming sound signals into spectrogram images. The fine-tuned model based on pretrained ResNet (RespireNet) has been proposed and achieved high performance. However, ResNet has a very large network size, which is not suitable for mobile applications. In this paper, we proposed a lightweight deep learning approach based on a CNN architecture by incorporating self-attention and multilevel feature extraction. With considerably fewer number of parameters, we achieved a competitive performance compared to the state-of-the-art model, RespireNet, on the ICBHI dataset for normal-abnormal respiratory sound classification. The smaller model size can give an advantage in the development of internet of things (IoT) applications for automatic respiratory sound classification.",

keywords = "CNN, Multilevel Feature, Respiratory Sound, Self-Attention",

author = "Crisdayanti, \{Ida Ayu Putu Ari\} and Kim, \{Seong Eun\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022 ; Conference date: 26-10-2022 Through 28-10-2022",

year = "2022",

doi = "10.1109/ICCE-Asia57006.2022.9954716",

language = "English",

series = "2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022",

}

Crisdayanti, IAPA & Kim, SE 2022, Multilevel Feature Fusion-based Convolutional Neural Network for Anomaly Classification of Respiratory Sound. in 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022. 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022, Institute of Electrical and Electronics Engineers Inc., 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022, Yeosu, Korea, Republic of, 26/10/22. https://doi.org/10.1109/ICCE-Asia57006.2022.9954716

Multilevel Feature Fusion-based Convolutional Neural Network for Anomaly Classification of Respiratory Sound. / Crisdayanti, Ida Ayu Putu Ari; Kim, Seong Eun.
2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multilevel Feature Fusion-based Convolutional Neural Network for Anomaly Classification of Respiratory Sound

AU - Crisdayanti, Ida Ayu Putu Ari

AU - Kim, Seong Eun

PY - 2022

Y1 - 2022

N2 - Respiratory sound classification has been extensively studied to early detect heart and lung diseases using digital stethoscope. Previous works mainly leveraged convolutional neural network (CNN)-based deep learning methods by transforming sound signals into spectrogram images. The fine-tuned model based on pretrained ResNet (RespireNet) has been proposed and achieved high performance. However, ResNet has a very large network size, which is not suitable for mobile applications. In this paper, we proposed a lightweight deep learning approach based on a CNN architecture by incorporating self-attention and multilevel feature extraction. With considerably fewer number of parameters, we achieved a competitive performance compared to the state-of-the-art model, RespireNet, on the ICBHI dataset for normal-abnormal respiratory sound classification. The smaller model size can give an advantage in the development of internet of things (IoT) applications for automatic respiratory sound classification.

AB - Respiratory sound classification has been extensively studied to early detect heart and lung diseases using digital stethoscope. Previous works mainly leveraged convolutional neural network (CNN)-based deep learning methods by transforming sound signals into spectrogram images. The fine-tuned model based on pretrained ResNet (RespireNet) has been proposed and achieved high performance. However, ResNet has a very large network size, which is not suitable for mobile applications. In this paper, we proposed a lightweight deep learning approach based on a CNN architecture by incorporating self-attention and multilevel feature extraction. With considerably fewer number of parameters, we achieved a competitive performance compared to the state-of-the-art model, RespireNet, on the ICBHI dataset for normal-abnormal respiratory sound classification. The smaller model size can give an advantage in the development of internet of things (IoT) applications for automatic respiratory sound classification.

KW - CNN

KW - Multilevel Feature

KW - Respiratory Sound

KW - Self-Attention

UR - https://www.scopus.com/pages/publications/85143824395

U2 - 10.1109/ICCE-Asia57006.2022.9954716

DO - 10.1109/ICCE-Asia57006.2022.9954716

M3 - Conference contribution

AN - SCOPUS:85143824395

T3 - 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022

BT - 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022

Y2 - 26 October 2022 through 28 October 2022

ER -

Crisdayanti IAPA, Kim SE. Multilevel Feature Fusion-based Convolutional Neural Network for Anomaly Classification of Respiratory Sound. In 2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022). doi: 10.1109/ICCE-Asia57006.2022.9954716

Multilevel Feature Fusion-based Convolutional Neural Network for Anomaly Classification of Respiratory Sound

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this