The project uses Fourier analysis and spectrograms for classifying respiratory sounds to identify diseases such as asthma, chronic obstructive pulmonary disease (COPD), and pneumonia. Respiratory sounds offer crucial insights into a patient's health, and their classification is vital for accurate diagnosis. The approach involves preprocessing respiratory sound data to remove noise and artifacts, followed by generating spectrograms using the Short-Time Fourier Transform (STFT). These spectrograms highlight time-frequency patterns linked to different respiratory conditions. Machine learning techniques, such as transfer learning with pre-trained models like GoogLeNet, are applied to classify the spectrograms.
The project uses Fourier analysis and spectrograms for classifying respiratory sounds to identify diseases such as asthma, chronic obstructive pulmonary disease (COPD), and pneumonia. Respiratory sounds offer crucial insights into a patient's health, and their classification is vital for accurate diagnosis. The approach involves preprocessing respiratory sound data to remove noise and artifacts, followed by generating spectrograms using the Short-Time Fourier Transform (STFT). These spectrograms highlight time-frequency patterns linked to different respiratory conditions. Machine learning techniques, such as transfer learning with pre-trained models like GoogLeNet, are applied to classify the spectrograms.
Analysis of Respiratory Audio Sound
TEFERI, KALKIDAN SHIMEKIT
2023/2024
Abstract
The project uses Fourier analysis and spectrograms for classifying respiratory sounds to identify diseases such as asthma, chronic obstructive pulmonary disease (COPD), and pneumonia. Respiratory sounds offer crucial insights into a patient's health, and their classification is vital for accurate diagnosis. The approach involves preprocessing respiratory sound data to remove noise and artifacts, followed by generating spectrograms using the Short-Time Fourier Transform (STFT). These spectrograms highlight time-frequency patterns linked to different respiratory conditions. Machine learning techniques, such as transfer learning with pre-trained models like GoogLeNet, are applied to classify the spectrograms.File | Dimensione | Formato | |
---|---|---|---|
Teferi_Kalkidan.pdf
accesso riservato
Dimensione
2.04 MB
Formato
Adobe PDF
|
2.04 MB | Adobe PDF |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/80175