Audio-Based Deep Learning Frameworks for Detecting COVID-19

被引:0
|
作者
Ngo, Dat [1 ]
Pham, Lam [2 ]
Hoang, Truong [3 ]
Kolozali, Sefki [1 ]
Jarchi, Delaram [1 ]
机构
[1] Univ Essex, Sch Comp Sci & Elect Engn, Colchester, Essex, England
[2] Austrian Inst Technol, Ctr Digital Safety & Secur, Seibersdorf, Austria
[3] FPT Software Co Ltd Vietnam, Solut Technol Unit Dept, Hanoi, Vietnam
来源
2022 30TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2022) | 2022年
关键词
low-level spectrogram feature; high-level embedding feature; pre-trained model; convolutional neural network; NEURAL-NETWORKS;
D O I
暂无
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
This paper evaluates a wide range of audio-based deep learning frameworks applied to the breathing, cough, and speech sounds for detecting COVID-19. In general, the audio recording inputs are transformed into low-level spectrogram features, then they are fed into pre-trained deep learning models to extract high-level embedding features. Next, the dimension of these high-level embedding features are reduced before finetuning using Light Gradient Boosting Machine (LightGBM) as a back-end classification. Our experiments on the Second DiCOVA Challenge achieved the highest Area Under the Curve (AUC), F1 score, sensitivity score, and specificity score of 89.03%, 64.41%, 63.33%, and 95.13%, respectively. Based on these scores, our method outperforms the state-of-the-art systems, and improves the challenge baseline by 4.33%, 6.00% and 8.33% in terms of AUC, F1 score and sensitivity score, respectively.
引用
收藏
页码:1233 / 1237
页数:5
相关论文
共 50 条
  • [31] Novel deep neural network technique for detecting environmental effect of COVID-19
    Gupta, Rajeev Kumar
    Gupta, Akshay Rameshbhai
    Pathik, Nikhlesh
    Pateriya, R. K.
    Chaurasiya, Prem Kumar
    Rakjak, Upendra
    Verma, Tikendra Nath
    Alosaimi, Abeer M.
    Hussein, Mahmoud Ali.
    ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, 2021, : 8997 - 9015
  • [32] Classification of COVID-19 and Pneumonia Using Deep Transfer Learning
    Mahin, Mainuzzaman
    Tonmoy, Sajid
    Islam, Rufaed
    Tazin, Tahia
    Khan, Mohammad Monirujjaman
    Bourouis, Sami
    JOURNAL OF HEALTHCARE ENGINEERING, 2021, 2021
  • [33] Deep Learning in the Quest for Compound Nomination for Fighting COVID-19
    Mernea, Maria
    Martin, Eliza C.
    Petrescu, Andrei-Jose
    Avram, Speranta
    CURRENT MEDICINAL CHEMISTRY, 2021, 28 (28) : 5699 - 5732
  • [34] A Comparative Study on Deep Learning Models for COVID-19 Forecast
    Guo, Ziyuan
    Lin, Qingyi
    Meng, Xuhui
    HEALTHCARE, 2023, 11 (17)
  • [35] CovMnet–Deep Learning Model for classifying Coronavirus (COVID-19)
    Malathy Jawahar
    Jani Anbarasi L
    Vinayakumar Ravi
    J. Prassanna
    S. Graceline Jasmine
    R. Manikandan
    Rames Sekaran
    Suthendran Kannan
    Health and Technology, 2022, 12 : 1009 - 1024
  • [36] CovFrameNet: An Enhanced Deep Learning Framework for COVID-19 Detection
    Oyelade, Olaide Nathaniel
    Ezugwu, Absalom El-Shamir
    Chiroma, Haruna
    IEEE ACCESS, 2021, 9 : 77905 - 77919
  • [37] COVID-19 diagnosis with Deep Learning: Adjacent-pooling CTScan-COVID-19 Classifier Based on ResNet and CBAM
    Deeb, Ali
    Debow, Ahmad
    Mansour, Saleem
    Shkodyrev, Viacheslav
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 86
  • [38] Deep Learning for COVID-19 Diagnosis from CT Images
    Loddo, Andrea
    Pili, Fabio
    Di Ruberto, Cecilia
    APPLIED SCIENCES-BASEL, 2021, 11 (17):
  • [39] Deep Stacked Ensemble Learning Model for COVID-19 Classification
    Madhu, G.
    Bharadwaj, B. Lalith
    Boddeda, Rohit
    Vardhan, Sai
    Kautish, K. Sandeep
    Alnowibet, Khalid
    Alrasheedi, Adel F.
    Mohamed, Ali Wagdy
    CMC-COMPUTERS MATERIALS & CONTINUA, 2022, 70 (03): : 5467 - 5486
  • [40] A 15-Category Audio Dataset for Drones and an Audio-Based UAV Classification Using Machine Learning
    Wang, Mia Yaqin
    Chu, Zhiwei
    Ku, Ilmun
    Smith, E. Cho
    Matson, Eric T.
    INTERNATIONAL JOURNAL OF SEMANTIC COMPUTING, 2024, 18 (02) : 257 - 272