DETECTION OF CRACKLES AND WHEEZES IN LUNG SOUND USING TRANSFER LEARNING

In recent years, deep learning models have improved how well various diseases, particularly respiratory ailments, can be diagnosed. In order to assist in offering a diagnosis of respiratory pathologies in digitally recorded respiratory sounds, this research will provide an evaluation of the effectiveness of several deep learning models connected with the raw lung auscultation sounds in detecting respiratory pathologies. We will also determine which deep learning model is most appropriate for this purpose. With the development of computer -systems that can collect and analyze enormous volumes of data, the medical profession is establishing several non-invasive tools. This work attempts to develop a non-invasive technique for identifying respiratory sounds acquired by a stethoscope and voice recording software via machine learning techniques. This study suggests a trained and proven CNN-based approach for categorizing respiratory sounds. A visual representation of each audio sample is constructed, allowing resource identification for classification using methods like those used to effectively describe visuals. We used a technique called Mel Frequency Cepstral Coefficients (MFCCs). Here, features are retrieved and categorized via VGG16 (transfer learning) and prediction is accomplished using 5-fold cross-validation. Employing various data splitting techniques, Respiratory Sound Database obtained cutting-edge results, including accuracy of 95%, precision of 88%, recall score of 86%, and F1 score of 81 %. We trained and tested the model using a sound database made by the International Conference on Biomedical and Health Informatics (ICBHI) in 2017 and annotated by experts with a classification of the lung sound.