TY - GEN
T1 - Classification of Respiratory Diseases with Respiratory Sounds with Deep Learning Algorithm
AU - Majumdar, Nayan Kanti
AU - Christa, Sharon
AU - Manek, Asha S.
AU - Sajeev, Shelda
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - It is crucial to improve access to quality healthcare for the economically underprivileged community in order to ensure that imperative illnesses may be treated quickly. In situations where medical personnel are severely lacking, a simple categorization of respiratory tones using a computerized instrument can be performed to provide a rapid diagnosis for respiratory-related disorders such as Respiratory function. In this paper, it presents Respiratory Specification, an upgraded bi-ResNet deep learning architecture that employs STFT and wavelet extraction of features approaches to boost performance over previous work. The authorized data compared to the global and the "train-and-test"datasets splitting procedure from the ICBHI 2017 challenge to create a fair assessment. As an outcome, able to obtain a productivity of 51.17 percent, which would be the best prediction consequence among all ICBHI 2017 teams participating.
AB - It is crucial to improve access to quality healthcare for the economically underprivileged community in order to ensure that imperative illnesses may be treated quickly. In situations where medical personnel are severely lacking, a simple categorization of respiratory tones using a computerized instrument can be performed to provide a rapid diagnosis for respiratory-related disorders such as Respiratory function. In this paper, it presents Respiratory Specification, an upgraded bi-ResNet deep learning architecture that employs STFT and wavelet extraction of features approaches to boost performance over previous work. The authorized data compared to the global and the "train-and-test"datasets splitting procedure from the ICBHI 2017 challenge to create a fair assessment. As an outcome, able to obtain a productivity of 51.17 percent, which would be the best prediction consequence among all ICBHI 2017 teams participating.
KW - Deep Learning
KW - Respiratory Sound Classification
KW - STFT
KW - Support Vector Method
KW - Wavelet Evaluation
UR - http://www.scopus.com/inward/record.url?scp=85166466126&partnerID=8YFLogxK
U2 - 10.1109/ICWITE57052.2022.10176205
DO - 10.1109/ICWITE57052.2022.10176205
M3 - Conference contribution
AN - SCOPUS:85166466126
T3 - 2022 IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2022 - Proceedings
BT - 2022 IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2022
Y2 - 1 December 2022 through 3 December 2022
ER -